Akshitab's group workspace
Group: OLMo-7B-Twin-2T
Name
24 visualized
State
Notes
User
Tags
Created
Runtime
Sweep
activation_checkpointing
canceled_check_interval
compile.backend
compile.fullgraph
console_log_interval
data.drop_last
data.generate_attention_mask
data.num_workers
data.pad_direction
data.paths
data.persistent_workers
data.pin_memory
data.prefetch_factor
data.timeout
device_eval_batch_size
device_train_batch_size
device_train_grad_accum
device_train_microbatch_size
dry_run
epoch
eval_interval
eval_on_load
eval_subset_num_batches
evaluators
extra_steps_after_cancel
force_save_unsharded
fsdp.precision
fsdp.sharding_strategy
fsdp.use_orig_params
fsdp.wrapping_strategy
fused_loss
gen1_gc_interval
global_train_batch_size
load_path
max_duration
max_grad_norm
model.activation_type
model.alibi
model.alibi_bias_max
model.attention_dropout
model.attention_layer_norm
model.attention_layer_norm_with_affine
model.bias_for_layer_norm
model.block_group_size
Finished
-
epwalsh
mosaicml-7b-v1
20m 27s
-
fine_grained
50
-
-
1
true
-
0
right
["/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-000-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-000-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-001-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-001-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-002-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-002-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-003-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-003-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-004-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-004-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-005-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-005-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-006-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-006-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-006-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-007-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-007-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-008-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-008-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-008-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-009-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-009-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-010-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-010-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-010-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-011-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-011-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-012-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-012-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-013-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-013-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-013-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-014-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-014-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-014-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-015-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-015-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-016-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-016-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-017-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-017-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-018-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-018-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-019-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-019-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-020-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-020-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-021-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-021-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-022-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-022-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-023-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-023-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-024-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-024-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-025-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-025-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-025-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-026-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-026-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-027-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-027-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-027-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-028-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-028-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-028-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-029-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-029-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-030-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-030-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-031-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-031-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-032-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-032-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-033-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-033-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-033-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-034-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-034-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-034-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-035-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-035-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-036-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-036-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-037-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-037-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-038-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-038-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-039-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-039-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-040-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-040-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-041-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-041-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-042-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-042-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-042-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-043-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-043-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-043-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-044-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-044-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-044-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-045-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-045-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-046-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-046-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-046-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-046-00003.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-047-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-047-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-048-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-048-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-049-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-049-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-050-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-050-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-051-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-051-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-052-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-052-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-052-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-053-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-053-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-053-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-054-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-054-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-055-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-055-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-055-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-056-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-056-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-056-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-057-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-057-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-057-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-058-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-058-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-059-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-059-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-060-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-060-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-061-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-061-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-062-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-062-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-062-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-063-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-063-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-063-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-064-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-064-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-064-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-065-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-065-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-065-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-066-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-066-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-067-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-067-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-068-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-068-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-069-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-069-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-070-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-070-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-071-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-071-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-072-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-072-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-073-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-073-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-074-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-074-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-075-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-075-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-076-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-076-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-077-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-077-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-078-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-078-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-079-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-079-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-080-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-080-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-081-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-081-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-082-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-082-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-083-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-083-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-084-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-084-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-085-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-085-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-086-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-086-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-087-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-087-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-088-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-088-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-089-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-089-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-089-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-090-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-090-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-091-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-091-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-091-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-092-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-092-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-093-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-093-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-093-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-094-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-094-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-094-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-095-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-095-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-096-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-096-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-097-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-097-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-097-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-098-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-098-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-099-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-099-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-100-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-100-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-100-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-101-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-101-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-102-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-102-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-103-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-103-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-104-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-104-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-105-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-105-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-106-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-106-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-106-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-107-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-107-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-108-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-108-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-109-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-109-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-109-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-110-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-110-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-110-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-111-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-111-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-112-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-112-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-113-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-113-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-114-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-114-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-114-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-115-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-115-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-116-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-116-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-117-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-117-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-118-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-118-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-119-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-119-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-120-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-120-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-120-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-121-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-121-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-122-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-122-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-122-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-123-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-123-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-123-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-124-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-124-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-125-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-125-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-126-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-126-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-127-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-127-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-127-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-128-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-128-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-129-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-129-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-129-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-130-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-130-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-131-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-131-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-132-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-132-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-133-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-133-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-133-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-134-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-134-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-134-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-135-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-135-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-135-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-136-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-136-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-137-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-137-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-137-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-138-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-138-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-139-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-139-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-140-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-140-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-141-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-141-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-141-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-142-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-142-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-142-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-143-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-143-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-144-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-144-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-144-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-145-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-145-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-145-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-146-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-146-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-146-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-147-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-147-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-147-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-148-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-148-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-149-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-149-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-149-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-150-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-150-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-150-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-150-00003.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-151-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-151-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-152-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-152-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-153-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-153-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-154-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-154-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-155-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-155-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-155-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-156-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-156-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-157-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-157-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-157-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-158-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-158-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-159-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-159-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-160-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-160-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-161-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-161-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-161-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-162-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-162-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-163-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-163-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-164-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-164-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-165-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-165-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-165-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-166-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-166-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-166-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-167-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-167-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-167-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-168-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-168-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-169-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-169-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-170-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-170-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-171-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-171-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-172-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-172-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-173-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-173-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-173-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-174-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-174-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-174-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-175-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-175-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-175-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-176-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-176-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-176-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-177-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-177-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-178-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-178-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-179-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-179-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-180-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-180-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-181-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-181-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-182-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-182-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-182-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-183-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-183-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-183-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-184-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-184-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-185-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-185-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-185-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-186-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-186-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-186-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-187-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-187-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-187-00002.npy"]
true
true
16
0
2
2
1
2
false
0
10000
false
-1
[{"data":{"drop_last":true,"pad_direction":"right","persistent_workers":false,"prefetch_factor":null,"timeout":0,"datasets":{"gab-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/gab/val.npy"],"ice-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/ice/val.npy"],"m2d2_s2orc-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/m2d2_s2orc/val.npy"],"pile-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/pile/val.npy"],"twitterAEE-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/twitterAEE/val.npy"],"wikitext_103-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/wikitext_103/val.npy"],"c4_en-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/c4_en/val.npy"],"m2d2_wiki-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/m2d2_wiki/val.npy"],"manosphere-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/manosphere/val.npy"],"mc4_en-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/mc4_en/val.npy"],"ptb-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/ptb/val.npy"],"4chan-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/4chan/val.npy"],"c4_100_domains-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/c4_100_domains/val.npy"]},"num_workers":0,"paths":null,"pin_memory":false},"device_eval_batch_size":null,"label":"all-small-ppl-validation","subset_num_batches":null,"type":"lm"},{"subset_num_batches":null,"type":"downstream","data":{"timeout":0,"datasets":null,"pad_direction":"right","persistent_workers":false,"pin_memory":false,"drop_last":false,"num_workers":0,"paths":null,"prefetch_factor":null},"device_eval_batch_size":null,"label":"piqa"},{"label":"hellaswag","subset_num_batches":null,"type":"downstream","data":{"drop_last":false,"paths":null,"persistent_workers":false,"pin_memory":false,"timeout":0,"datasets":null,"num_workers":0,"pad_direction":"right","prefetch_factor":null},"device_eval_batch_size":null},{"data":{"prefetch_factor":null,"timeout":0,"datasets":null,"num_workers":0,"persistent_workers":false,"pin_memory":false,"drop_last":false,"pad_direction":"right","paths":null},"device_eval_batch_size":null,"label":"winogrande","subset_num_batches":null,"type":"downstream"},{"device_eval_batch_size":null,"label":"openbook_qa","subset_num_batches":null,"type":"downstream","data":{"datasets":null,"num_workers":0,"pad_direction":"right","persistent_workers":false,"pin_memory":false,"drop_last":false,"paths":null,"prefetch_factor":null,"timeout":0}},{"data":{"datasets":null,"num_workers":0,"pin_memory":false,"prefetch_factor":null,"drop_last":false,"pad_direction":"right","paths":null,"persistent_workers":false,"timeout":0},"device_eval_batch_size":null,"label":"sciq","subset_num_batches":null,"type":"downstream"},{"data":{"pin_memory":false,"prefetch_factor":null,"timeout":0,"drop_last":false,"num_workers":0,"pad_direction":"right","persistent_workers":false,"datasets":null,"paths":null},"device_eval_batch_size":null,"label":"arc_easy","subset_num_batches":null,"type":"downstream"},{"type":"downstream","data":{"datasets":null,"drop_last":false,"num_workers":0,"pad_direction":"right","paths":null,"persistent_workers":false,"pin_memory":false,"prefetch_factor":null,"timeout":0},"device_eval_batch_size":null,"label":"copa","subset_num_batches":null},{"data":{"persistent_workers":false,"pin_memory":false,"drop_last":false,"num_workers":0,"pad_direction":"right","prefetch_factor":null,"timeout":0,"datasets":null,"paths":null},"device_eval_batch_size":null,"label":"rte","subset_num_batches":null,"type":"downstream"},{"device_eval_batch_size":null,"label":"commitment_bank","subset_num_batches":null,"type":"downstream","data":{"prefetch_factor":null,"timeout":0,"drop_last":false,"num_workers":0,"paths":null,"persistent_workers":false,"pin_memory":false,"datasets":null,"pad_direction":"right"}},{"data":{"num_workers":0,"paths":null,"pin_memory":false,"prefetch_factor":null,"timeout":0,"datasets":null,"drop_last":false,"pad_direction":"right","persistent_workers":false},"device_eval_batch_size":null,"label":"mrpc","subset_num_batches":null,"type":"downstream"},{"subset_num_batches":null,"type":"downstream","data":{"datasets":null,"paths":null,"prefetch_factor":null,"timeout":0,"drop_last":false,"num_workers":0,"pad_direction":"right","persistent_workers":false,"pin_memory":false},"device_eval_batch_size":null,"label":"sst2"}]
-
false
mixed
ShardingStrategy.FULL_SHARD
true
one_in_four
-
-
2048
/scratch/project_462000229/checkpoints/5307103/latest
2e12T
1
swiglu
false
8
0
false
false
false
1
Finished
-
epwalsh
mosaicml-7b-v1
5m 58s
-
fine_grained
50
-
-
1
true
-
0
right
["/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-000-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-000-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-001-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-001-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-002-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-002-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-003-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-003-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-004-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-004-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-005-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-005-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-006-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-006-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-006-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-007-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-007-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-008-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-008-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-008-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-009-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-009-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-010-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-010-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-010-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-011-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-011-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-012-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-012-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-013-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-013-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-013-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-014-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-014-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-014-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-015-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-015-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-016-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-016-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-017-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-017-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-018-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-018-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-019-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-019-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-020-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-020-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-021-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-021-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-022-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-022-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-023-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-023-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-024-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-024-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-025-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-025-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-025-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-026-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-026-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-027-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-027-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-027-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-028-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-028-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-028-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-029-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-029-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-030-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-030-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-031-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-031-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-032-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-032-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-033-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-033-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-033-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-034-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-034-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-034-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-035-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-035-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-036-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-036-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-037-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-037-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-038-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-038-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-039-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-039-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-040-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-040-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-041-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-041-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-042-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-042-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-042-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-043-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-043-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-043-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-044-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-044-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-044-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-045-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-045-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-046-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-046-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-046-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-046-00003.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-047-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-047-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-048-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-048-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-049-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-049-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-050-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-050-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-051-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-051-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-052-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-052-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-052-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-053-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-053-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-053-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-054-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-054-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-055-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-055-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-055-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-056-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-056-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-056-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-057-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-057-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-057-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-058-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-058-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-059-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-059-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-060-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-060-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-061-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-061-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-062-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-062-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-062-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-063-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-063-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-063-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-064-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-064-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-064-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-065-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-065-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-065-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-066-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-066-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-067-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-067-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-068-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-068-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-069-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-069-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-070-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-070-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-071-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-071-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-072-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-072-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-073-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-073-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-074-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-074-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-075-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-075-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-076-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-076-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-077-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-077-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-078-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-078-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-079-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-079-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-080-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-080-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-081-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-081-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-082-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-082-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-083-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-083-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-084-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-084-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-085-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-085-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-086-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-086-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-087-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-087-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-088-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-088-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-089-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-089-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-089-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-090-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-090-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-091-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-091-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-091-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-092-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-092-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-093-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-093-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-093-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-094-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-094-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-094-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-095-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-095-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-096-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-096-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-097-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-097-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-097-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-098-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-098-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-099-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-099-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-100-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-100-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-100-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-101-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-101-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-102-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-102-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-103-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-103-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-104-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-104-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-105-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-105-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-106-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-106-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-106-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-107-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-107-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-108-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-108-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-109-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-109-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-109-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-110-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-110-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-110-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-111-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-111-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-112-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-112-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-113-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-113-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-114-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-114-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-114-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-115-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-115-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-116-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-116-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-117-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-117-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-118-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-118-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-119-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-119-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-120-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-120-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-120-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-121-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-121-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-122-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-122-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-122-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-123-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-123-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-123-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-124-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-124-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-125-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-125-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-126-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-126-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-127-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-127-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-127-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-128-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-128-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-129-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-129-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-129-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-130-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-130-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-131-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-131-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-132-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-132-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-133-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-133-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-133-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-134-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-134-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-134-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-135-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-135-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-135-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-136-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-136-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-137-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-137-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-137-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-138-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-138-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-139-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-139-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-140-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-140-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-141-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-141-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-141-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-142-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-142-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-142-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-143-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-143-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-144-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-144-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-144-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-145-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-145-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-145-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-146-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-146-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-146-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-147-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-147-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-147-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-148-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-148-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-149-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-149-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-149-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-150-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-150-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-150-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-150-00003.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-151-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-151-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-152-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-152-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-153-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-153-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-154-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-154-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-155-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-155-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-155-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-156-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-156-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-157-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-157-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-157-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-158-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-158-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-159-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-159-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-160-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-160-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-161-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-161-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-161-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-162-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-162-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-163-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-163-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-164-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-164-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-165-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-165-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-165-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-166-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-166-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-166-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-167-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-167-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-167-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-168-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-168-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-169-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-169-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-170-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-170-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-171-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-171-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-172-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-172-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-173-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-173-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-173-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-174-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-174-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-174-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-175-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-175-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-175-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-176-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-176-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-176-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-177-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-177-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-178-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-178-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-179-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-179-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-180-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-180-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-181-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-181-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-182-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-182-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-182-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-183-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-183-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-183-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-184-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-184-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-185-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-185-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-185-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-186-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-186-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-186-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-187-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-187-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-187-00002.npy"]
true
true
16
0
2
2
1
2
false
0
10000
false
-1
[{"type":"lm","data":{"datasets":{"ice-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/ice/val.npy"],"pile-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/pile/val.npy"],"wikitext_103-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/wikitext_103/val.npy"],"c4_100_domains-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/c4_100_domains/val.npy"],"gab-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/gab/val.npy"],"m2d2_s2orc-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/m2d2_s2orc/val.npy"],"m2d2_wiki-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/m2d2_wiki/val.npy"],"manosphere-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/manosphere/val.npy"],"mc4_en-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/mc4_en/val.npy"],"ptb-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/ptb/val.npy"],"twitterAEE-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/twitterAEE/val.npy"],"4chan-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/4chan/val.npy"],"c4_en-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/c4_en/val.npy"]},"drop_last":true,"num_workers":0,"pad_direction":"right","persistent_workers":false,"pin_memory":false,"prefetch_factor":null,"timeout":0,"paths":null},"device_eval_batch_size":null,"label":"all-small-ppl-validation","subset_num_batches":null},{"data":{"persistent_workers":false,"pin_memory":false,"timeout":0,"datasets":null,"drop_last":false,"num_workers":0,"paths":null,"prefetch_factor":null,"pad_direction":"right"},"device_eval_batch_size":null,"label":"piqa","subset_num_batches":null,"type":"downstream"},{"data":{"drop_last":false,"pad_direction":"right","paths":null,"persistent_workers":false,"prefetch_factor":null,"datasets":null,"num_workers":0,"pin_memory":false,"timeout":0},"device_eval_batch_size":null,"label":"hellaswag","subset_num_batches":null,"type":"downstream"},{"device_eval_batch_size":null,"label":"winogrande","subset_num_batches":null,"type":"downstream","data":{"persistent_workers":false,"pin_memory":false,"drop_last":false,"num_workers":0,"pad_direction":"right","paths":null,"prefetch_factor":null,"timeout":0,"datasets":null}},{"data":{"datasets":null,"drop_last":false,"num_workers":0,"pad_direction":"right","paths":null,"pin_memory":false,"persistent_workers":false,"prefetch_factor":null,"timeout":0},"device_eval_batch_size":null,"label":"openbook_qa","subset_num_batches":null,"type":"downstream"},{"label":"sciq","subset_num_batches":null,"type":"downstream","data":{"datasets":null,"drop_last":false,"num_workers":0,"pad_direction":"right","paths":null,"persistent_workers":false,"pin_memory":false,"prefetch_factor":null,"timeout":0},"device_eval_batch_size":null},{"label":"arc_easy","subset_num_batches":null,"type":"downstream","data":{"datasets":null,"num_workers":0,"pad_direction":"right","prefetch_factor":null,"drop_last":false,"paths":null,"persistent_workers":false,"pin_memory":false,"timeout":0},"device_eval_batch_size":null},{"label":"copa","subset_num_batches":null,"type":"downstream","data":{"pad_direction":"right","paths":null,"pin_memory":false,"datasets":null,"num_workers":0,"persistent_workers":false,"prefetch_factor":null,"timeout":0,"drop_last":false},"device_eval_batch_size":null},{"data":{"datasets":null,"drop_last":false,"pad_direction":"right","timeout":0,"num_workers":0,"paths":null,"persistent_workers":false,"pin_memory":false,"prefetch_factor":null},"device_eval_batch_size":null,"label":"rte","subset_num_batches":null,"type":"downstream"},{"data":{"prefetch_factor":null,"timeout":0,"drop_last":false,"pad_direction":"right","persistent_workers":false,"datasets":null,"num_workers":0,"paths":null,"pin_memory":false},"device_eval_batch_size":null,"label":"commitment_bank","subset_num_batches":null,"type":"downstream"},{"label":"mrpc","subset_num_batches":null,"type":"downstream","data":{"pin_memory":false,"prefetch_factor":null,"timeout":0,"datasets":null,"drop_last":false,"num_workers":0,"paths":null,"pad_direction":"right","persistent_workers":false},"device_eval_batch_size":null},{"data":{"datasets":null,"num_workers":0,"paths":null,"persistent_workers":false,"pin_memory":false,"timeout":0,"drop_last":false,"pad_direction":"right","prefetch_factor":null},"device_eval_batch_size":null,"label":"sst2","subset_num_batches":null,"type":"downstream"}]
-
false
mixed
ShardingStrategy.FULL_SHARD
true
one_in_four
-
-
2048
/scratch/project_462000229/checkpoints/5307103/latest
2e12T
1
swiglu
false
8
0
false
false
false
1
Finished
-
epwalsh
mosaicml-7b-v1
19m 1s
-
fine_grained
50
-
-
1
true
-
0
right
["/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-000-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-000-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-001-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-001-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-002-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-002-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-003-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-003-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-004-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-004-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-005-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-005-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-006-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-006-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-006-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-007-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-007-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-008-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-008-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-008-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-009-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-009-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-010-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-010-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-010-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-011-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-011-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-012-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-012-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-013-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-013-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-013-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-014-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-014-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-014-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-015-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-015-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-016-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-016-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-017-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-017-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-018-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-018-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-019-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-019-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-020-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-020-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-021-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-021-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-022-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-022-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-023-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-023-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-024-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-024-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-025-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-025-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-025-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-026-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-026-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-027-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-027-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-027-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-028-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-028-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-028-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-029-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-029-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-030-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-030-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-031-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-031-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-032-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-032-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-033-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-033-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-033-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-034-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-034-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-034-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-035-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-035-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-036-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-036-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-037-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-037-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-038-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-038-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-039-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-039-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-040-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-040-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-041-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-041-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-042-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-042-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-042-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-043-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-043-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-043-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-044-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-044-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-044-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-045-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-045-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-046-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-046-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-046-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-046-00003.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-047-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-047-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-048-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-048-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-049-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-049-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-050-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-050-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-051-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-051-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-052-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-052-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-052-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-053-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-053-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-053-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-054-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-054-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-055-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-055-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-055-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-056-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-056-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-056-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-057-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-057-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-057-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-058-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-058-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-059-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-059-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-060-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-060-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-061-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-061-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-062-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-062-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-062-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-063-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-063-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-063-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-064-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-064-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-064-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-065-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-065-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-065-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-066-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-066-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-067-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-067-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-068-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-068-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-069-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-069-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-070-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-070-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-071-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-071-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-072-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-072-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-073-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-073-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-074-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-074-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-075-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-075-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-076-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-076-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-077-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-077-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-078-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-078-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-079-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-079-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-080-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-080-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-081-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-081-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-082-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-082-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-083-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-083-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-084-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-084-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-085-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-085-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-086-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-086-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-087-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-087-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-088-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-088-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-089-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-089-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-089-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-090-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-090-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-091-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-091-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-091-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-092-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-092-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-093-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-093-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-093-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-094-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-094-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-094-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-095-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-095-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-096-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-096-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-097-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-097-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-097-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-098-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-098-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-099-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-099-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-100-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-100-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-100-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-101-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-101-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-102-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-102-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-103-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-103-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-104-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-104-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-105-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-105-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-106-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-106-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-106-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-107-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-107-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-108-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-108-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-109-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-109-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-109-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-110-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-110-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-110-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-111-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-111-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-112-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-112-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-113-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-113-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-114-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-114-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-114-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-115-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-115-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-116-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-116-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-117-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-117-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-118-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-118-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-119-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-119-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-120-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-120-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-120-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-121-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-121-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-122-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-122-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-122-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-123-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-123-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-123-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-124-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-124-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-125-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-125-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-126-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-126-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-127-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-127-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-127-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-128-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-128-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-129-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-129-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-129-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-130-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-130-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-131-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-131-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-132-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-132-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-133-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-133-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-133-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-134-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-134-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-134-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-135-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-135-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-135-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-136-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-136-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-137-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-137-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-137-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-138-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-138-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-139-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-139-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-140-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-140-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-141-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-141-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-141-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-142-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-142-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-142-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-143-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-143-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-144-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-144-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-144-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-145-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-145-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-145-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-146-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-146-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-146-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-147-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-147-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-147-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-148-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-148-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-149-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-149-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-149-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-150-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-150-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-150-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-150-00003.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-151-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-151-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-152-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-152-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-153-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-153-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-154-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-154-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-155-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-155-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-155-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-156-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-156-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-157-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-157-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-157-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-158-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-158-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-159-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-159-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-160-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-160-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-161-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-161-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-161-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-162-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-162-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-163-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-163-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-164-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-164-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-165-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-165-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-165-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-166-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-166-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-166-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-167-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-167-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-167-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-168-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-168-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-169-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-169-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-170-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-170-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-171-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-171-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-172-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-172-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-173-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-173-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-173-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-174-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-174-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-174-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-175-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-175-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-175-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-176-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-176-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-176-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-177-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-177-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-178-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-178-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-179-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-179-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-180-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-180-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-181-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-181-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-182-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-182-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-182-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-183-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-183-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-183-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-184-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-184-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-185-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-185-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-185-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-186-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-186-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-186-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-187-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-187-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-187-00002.npy"]
true
true
16
0
2
2
1
2
false
0
1000
false
-1
[{"data":{"datasets":{"c4_en-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/c4_en/val.npy"],"gab-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/gab/val.npy"],"ice-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/ice/val.npy"],"m2d2_s2orc-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/m2d2_s2orc/val.npy"],"manosphere-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/manosphere/val.npy"],"m2d2_wiki-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/m2d2_wiki/val.npy"],"mc4_en-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/mc4_en/val.npy"],"pile-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/pile/val.npy"],"ptb-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/ptb/val.npy"],"twitterAEE-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/twitterAEE/val.npy"],"wikitext_103-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/wikitext_103/val.npy"],"4chan-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/4chan/val.npy"],"c4_100_domains-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/c4_100_domains/val.npy"]},"paths":null,"persistent_workers":false,"pin_memory":false,"drop_last":true,"num_workers":0,"pad_direction":"right","prefetch_factor":null,"timeout":0},"device_eval_batch_size":null,"label":"all-small-ppl-validation","subset_num_batches":null,"type":"lm"},{"type":"downstream","data":{"drop_last":false,"num_workers":0,"pad_direction":"right","persistent_workers":false,"prefetch_factor":null,"timeout":0,"datasets":null,"paths":null,"pin_memory":false},"device_eval_batch_size":null,"label":"piqa","subset_num_batches":null},{"data":{"datasets":null,"drop_last":false,"num_workers":0,"pad_direction":"right","pin_memory":false,"timeout":0,"paths":null,"persistent_workers":false,"prefetch_factor":null},"device_eval_batch_size":null,"label":"hellaswag","subset_num_batches":null,"type":"downstream"},{"data":{"pin_memory":false,"datasets":null,"drop_last":false,"pad_direction":"right","paths":null,"persistent_workers":false,"prefetch_factor":null,"timeout":0,"num_workers":0},"device_eval_batch_size":null,"label":"winogrande","subset_num_batches":null,"type":"downstream"},{"type":"downstream","data":{"paths":null,"persistent_workers":false,"pin_memory":false,"timeout":0,"datasets":null,"drop_last":false,"num_workers":0,"pad_direction":"right","prefetch_factor":null},"device_eval_batch_size":null,"label":"openbook_qa","subset_num_batches":null},{"type":"downstream","data":{"pin_memory":false,"prefetch_factor":null,"timeout":0,"drop_last":false,"num_workers":0,"pad_direction":"right","paths":null,"datasets":null,"persistent_workers":false},"device_eval_batch_size":null,"label":"sciq","subset_num_batches":null},{"data":{"datasets":null,"num_workers":0,"pad_direction":"right","persistent_workers":false,"prefetch_factor":null,"timeout":0,"drop_last":false,"paths":null,"pin_memory":false},"device_eval_batch_size":null,"label":"arc_easy","subset_num_batches":null,"type":"downstream"},{"data":{"datasets":null,"pad_direction":"right","persistent_workers":false,"pin_memory":false,"prefetch_factor":null,"drop_last":false,"num_workers":0,"paths":null,"timeout":0},"device_eval_batch_size":null,"label":"copa","subset_num_batches":null,"type":"downstream"},{"data":{"datasets":null,"num_workers":0,"persistent_workers":false,"prefetch_factor":null,"drop_last":false,"pad_direction":"right","paths":null,"pin_memory":false,"timeout":0},"device_eval_batch_size":null,"label":"rte","subset_num_batches":null,"type":"downstream"},{"data":{"datasets":null,"drop_last":false,"paths":null,"pin_memory":false,"prefetch_factor":null,"num_workers":0,"pad_direction":"right","persistent_workers":false,"timeout":0},"device_eval_batch_size":null,"label":"commitment_bank","subset_num_batches":null,"type":"downstream"},{"subset_num_batches":null,"type":"downstream","data":{"datasets":null,"drop_last":false,"num_workers":0,"paths":null,"persistent_workers":false,"prefetch_factor":null,"timeout":0,"pad_direction":"right","pin_memory":false},"device_eval_batch_size":null,"label":"mrpc"},{"data":{"drop_last":false,"num_workers":0,"pad_direction":"right","paths":null,"pin_memory":false,"prefetch_factor":null,"timeout":0,"datasets":null,"persistent_workers":false},"device_eval_batch_size":null,"label":"sst2","subset_num_batches":null,"type":"downstream"}]
-
false
mixed
ShardingStrategy.FULL_SHARD
true
one_in_four
-
-
2048
/scratch/project_462000229/checkpoints/5235002/latest
2e12T
1
swiglu
false
8
0
false
false
false
1
Finished
-
epwalsh
mosaicml-7b-v1
23m 35s
-
fine_grained
50
-
-
1
true
-
0
right
["/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-000-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-000-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-001-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-001-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-002-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-002-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-003-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-003-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-004-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-004-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-005-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-005-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-006-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-006-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-006-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-007-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-007-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-008-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-008-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-008-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-009-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-009-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-010-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-010-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-010-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-011-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-011-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-012-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-012-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-013-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-013-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-013-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-014-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-014-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-014-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-015-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-015-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-016-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-016-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-017-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-017-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-018-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-018-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-019-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-019-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-020-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-020-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-021-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-021-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-022-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-022-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-023-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-023-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-024-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-024-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-025-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-025-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-025-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-026-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-026-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-027-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-027-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-027-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-028-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-028-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-028-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-029-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-029-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-030-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-030-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-031-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-031-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-032-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-032-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-033-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-033-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-033-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-034-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-034-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-034-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-035-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-035-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-036-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-036-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-037-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-037-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-038-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-038-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-039-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-039-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-040-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-040-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-041-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-041-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-042-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-042-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-042-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-043-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-043-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-043-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-044-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-044-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-044-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-045-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-045-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-046-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-046-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-046-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-046-00003.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-047-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-047-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-048-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-048-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-049-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-049-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-050-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-050-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-051-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-051-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-052-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-052-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-052-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-053-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-053-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-053-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-054-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-054-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-055-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-055-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-055-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-056-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-056-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-056-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-057-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-057-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-057-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-058-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-058-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-059-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-059-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-060-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-060-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-061-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-061-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-062-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-062-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-062-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-063-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-063-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-063-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-064-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-064-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-064-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-065-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-065-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-065-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-066-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-066-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-067-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-067-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-068-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-068-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-069-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-069-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-070-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-070-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-071-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-071-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-072-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-072-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-073-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-073-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-074-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-074-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-075-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-075-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-076-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-076-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-077-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-077-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-078-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-078-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-079-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-079-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-080-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-080-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-081-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-081-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-082-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-082-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-083-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-083-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-084-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-084-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-085-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-085-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-086-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-086-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-087-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-087-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-088-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-088-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-089-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-089-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-089-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-090-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-090-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-091-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-091-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-091-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-092-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-092-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-093-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-093-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-093-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-094-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-094-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-094-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-095-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-095-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-096-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-096-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-097-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-097-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-097-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-098-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-098-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-099-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-099-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-100-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-100-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-100-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-101-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-101-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-102-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-102-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-103-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-103-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-104-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-104-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-105-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-105-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-106-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-106-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-106-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-107-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-107-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-108-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-108-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-109-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-109-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-109-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-110-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-110-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-110-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-111-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-111-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-112-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-112-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-113-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-113-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-114-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-114-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-114-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-115-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-115-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-116-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-116-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-117-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-117-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-118-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-118-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-119-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-119-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-120-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-120-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-120-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-121-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-121-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-122-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-122-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-122-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-123-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-123-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-123-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-124-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-124-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-125-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-125-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-126-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-126-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-127-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-127-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-127-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-128-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-128-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-129-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-129-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-129-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-130-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-130-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-131-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-131-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-132-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-132-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-133-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-133-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-133-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-134-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-134-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-134-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-135-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-135-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-135-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-136-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-136-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-137-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-137-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-137-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-138-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-138-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-139-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-139-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-140-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-140-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-141-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-141-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-141-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-142-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-142-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-142-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-143-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-143-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-144-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-144-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-144-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-145-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-145-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-145-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-146-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-146-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-146-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-147-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-147-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-147-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-148-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-148-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-149-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-149-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-149-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-150-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-150-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-150-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-150-00003.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-151-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-151-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-152-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-152-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-153-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-153-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-154-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-154-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-155-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-155-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-155-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-156-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-156-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-157-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-157-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-157-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-158-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-158-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-159-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-159-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-160-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-160-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-161-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-161-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-161-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-162-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-162-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-163-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-163-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-164-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-164-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-165-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-165-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-165-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-166-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-166-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-166-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-167-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-167-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-167-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-168-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-168-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-169-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-169-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-170-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-170-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-171-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-171-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-172-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-172-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-173-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-173-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-173-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-174-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-174-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-174-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-175-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-175-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-175-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-176-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-176-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-176-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-177-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-177-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-178-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-178-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-179-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-179-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-180-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-180-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-181-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-181-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-182-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-182-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-182-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-183-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-183-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-183-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-184-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-184-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-185-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-185-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-185-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-186-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-186-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-186-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-187-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-187-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-187-00002.npy"]
true
true
16
0
2
2
1
2
false
0
1000
false
-1
[{"subset_num_batches":null,"type":"lm","data":{"persistent_workers":false,"pin_memory":false,"prefetch_factor":null,"timeout":0,"pad_direction":"right","paths":null,"datasets":{"m2d2_s2orc-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/m2d2_s2orc/val.npy"],"m2d2_wiki-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/m2d2_wiki/val.npy"],"mc4_en-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/mc4_en/val.npy"],"twitterAEE-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/twitterAEE/val.npy"],"4chan-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/4chan/val.npy"],"gab-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/gab/val.npy"],"ice-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/ice/val.npy"],"manosphere-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/manosphere/val.npy"],"pile-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/pile/val.npy"],"ptb-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/ptb/val.npy"],"wikitext_103-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/wikitext_103/val.npy"],"c4_100_domains-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/c4_100_domains/val.npy"],"c4_en-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/c4_en/val.npy"]},"drop_last":true,"num_workers":0},"device_eval_batch_size":null,"label":"all-small-ppl-validation"},{"device_eval_batch_size":null,"label":"piqa","subset_num_batches":null,"type":"downstream","data":{"persistent_workers":false,"pin_memory":false,"datasets":null,"drop_last":false,"pad_direction":"right","prefetch_factor":null,"timeout":0,"num_workers":0,"paths":null}},{"data":{"pad_direction":"right","paths":null,"prefetch_factor":null,"datasets":null,"num_workers":0,"persistent_workers":false,"pin_memory":false,"timeout":0,"drop_last":false},"device_eval_batch_size":null,"label":"hellaswag","subset_num_batches":null,"type":"downstream"},{"device_eval_batch_size":null,"label":"winogrande","subset_num_batches":null,"type":"downstream","data":{"datasets":null,"num_workers":0,"pad_direction":"right","paths":null,"persistent_workers":false,"pin_memory":false,"prefetch_factor":null,"drop_last":false,"timeout":0}},{"data":{"drop_last":false,"num_workers":0,"pad_direction":"right","prefetch_factor":null,"datasets":null,"paths":null,"persistent_workers":false,"pin_memory":false,"timeout":0},"device_eval_batch_size":null,"label":"openbook_qa","subset_num_batches":null,"type":"downstream"},{"data":{"datasets":null,"num_workers":0,"paths":null,"persistent_workers":false,"pin_memory":false,"drop_last":false,"pad_direction":"right","prefetch_factor":null,"timeout":0},"device_eval_batch_size":null,"label":"sciq","subset_num_batches":null,"type":"downstream"},{"data":{"timeout":0,"datasets":null,"drop_last":false,"num_workers":0,"pad_direction":"right","pin_memory":false,"prefetch_factor":null,"paths":null,"persistent_workers":false},"device_eval_batch_size":null,"label":"arc_easy","subset_num_batches":null,"type":"downstream"},{"type":"downstream","data":{"datasets":null,"drop_last":false,"pad_direction":"right","paths":null,"persistent_workers":false,"pin_memory":false,"timeout":0,"num_workers":0,"prefetch_factor":null},"device_eval_batch_size":null,"label":"copa","subset_num_batches":null},{"subset_num_batches":null,"type":"downstream","data":{"pin_memory":false,"prefetch_factor":null,"timeout":0,"drop_last":false,"num_workers":0,"pad_direction":"right","datasets":null,"paths":null,"persistent_workers":false},"device_eval_batch_size":null,"label":"rte"},{"label":"commitment_bank","subset_num_batches":null,"type":"downstream","data":{"pad_direction":"right","persistent_workers":false,"timeout":0,"paths":null,"pin_memory":false,"prefetch_factor":null,"datasets":null,"drop_last":false,"num_workers":0},"device_eval_batch_size":null},{"device_eval_batch_size":null,"label":"mrpc","subset_num_batches":null,"type":"downstream","data":{"datasets":null,"drop_last":false,"pad_direction":"right","persistent_workers":false,"timeout":0,"num_workers":0,"paths":null,"pin_memory":false,"prefetch_factor":null}},{"data":{"num_workers":0,"paths":null,"persistent_workers":false,"pin_memory":false,"prefetch_factor":null,"timeout":0,"datasets":null,"drop_last":false,"pad_direction":"right"},"device_eval_batch_size":null,"label":"sst2","subset_num_batches":null,"type":"downstream"}]
-
false
mixed
ShardingStrategy.FULL_SHARD
true
one_in_four
-
-
2048
/scratch/project_462000229/checkpoints/5211152/latest
2e12T
1
swiglu
false
8
0
false
false
false
1
Finished
-
epwalsh
mosaicml-7b-v1
40m 6s
-
fine_grained
50
-
-
1
true
-
0
right
["/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-000-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-000-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-001-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-001-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-002-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-002-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-003-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-003-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-004-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-004-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-005-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-005-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-006-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-006-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-006-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-007-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-007-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-008-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-008-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-008-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-009-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-009-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-010-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-010-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-010-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-011-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-011-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-012-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-012-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-013-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-013-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-013-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-014-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-014-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-014-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-015-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-015-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-016-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-016-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-017-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-017-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-018-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-018-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-019-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-019-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-020-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-020-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-021-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-021-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-022-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-022-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-023-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-023-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-024-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-024-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-025-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-025-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-025-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-026-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-026-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-027-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-027-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-027-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-028-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-028-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-028-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-029-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-029-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-030-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-030-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-031-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-031-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-032-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-032-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-033-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-033-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-033-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-034-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-034-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-034-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-035-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-035-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-036-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-036-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-037-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-037-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-038-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-038-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-039-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-039-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-040-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-040-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-041-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-041-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-042-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-042-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-042-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-043-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-043-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-043-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-044-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-044-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-044-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-045-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-045-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-046-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-046-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-046-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-046-00003.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-047-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-047-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-048-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-048-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-049-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-049-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-050-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-050-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-051-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-051-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-052-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-052-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-052-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-053-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-053-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-053-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-054-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-054-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-055-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-055-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-055-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-056-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-056-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-056-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-057-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-057-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-057-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-058-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-058-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-059-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-059-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-060-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-060-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-061-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-061-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-062-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-062-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-062-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-063-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-063-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-063-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-064-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-064-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-064-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-065-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-065-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-065-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-066-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-066-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-067-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-067-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-068-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-068-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-069-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-069-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-070-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-070-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-071-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-071-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-072-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-072-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-073-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-073-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-074-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-074-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-075-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-075-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-076-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-076-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-077-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-077-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-078-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-078-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-079-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-079-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-080-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-080-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-081-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-081-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-082-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-082-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-083-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-083-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-084-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-084-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-085-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-085-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-086-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-086-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-087-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-087-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-088-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-088-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-089-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-089-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-089-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-090-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-090-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-091-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-091-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-091-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-092-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-092-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-093-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-093-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-093-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-094-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-094-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-094-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-095-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-095-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-096-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-096-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-097-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-097-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-097-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-098-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-098-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-099-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-099-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-100-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-100-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-100-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-101-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-101-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-102-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-102-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-103-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-103-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-104-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-104-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-105-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-105-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-106-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-106-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-106-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-107-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-107-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-108-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-108-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-109-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-109-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-109-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-110-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-110-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-110-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-111-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-111-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-112-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-112-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-113-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-113-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-114-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-114-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-114-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-115-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-115-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-116-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-116-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-117-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-117-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-118-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-118-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-119-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-119-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-120-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-120-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-120-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-121-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-121-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-122-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-122-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-122-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-123-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-123-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-123-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-124-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-124-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-125-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-125-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-126-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-126-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-127-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-127-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-127-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-128-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-128-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-129-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-129-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-129-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-130-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-130-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-131-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-131-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-132-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-132-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-133-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-133-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-133-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-134-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-134-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-134-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-135-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-135-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-135-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-136-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-136-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-137-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-137-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-137-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-138-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-138-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-139-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-139-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-140-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-140-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-141-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-141-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-141-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-142-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-142-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-142-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-143-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-143-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-144-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-144-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-144-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-145-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-145-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-145-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-146-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-146-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-146-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-147-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-147-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-147-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-148-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-148-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-149-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-149-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-149-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-150-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-150-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-150-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-150-00003.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-151-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-151-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-152-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-152-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-153-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-153-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-154-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-154-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-155-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-155-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-155-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-156-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-156-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-157-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-157-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-157-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-158-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-158-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-159-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-159-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-160-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-160-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-161-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-161-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-161-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-162-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-162-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-163-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-163-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-164-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-164-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-165-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-165-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-165-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-166-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-166-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-166-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-167-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-167-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-167-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-168-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-168-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-169-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-169-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-170-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-170-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-171-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-171-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-172-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-172-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-173-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-173-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-173-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-174-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-174-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-174-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-175-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-175-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-175-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-176-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-176-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-176-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-177-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-177-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-178-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-178-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-179-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-179-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-180-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-180-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-181-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-181-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-182-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-182-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-182-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-183-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-183-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-183-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-184-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-184-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-185-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-185-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-185-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-186-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-186-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-186-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-187-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-187-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-187-00002.npy"]
true
true
16
0
2
2
1
2
false
0
1000
false
-1
[{"type":"lm","data":{"paths":null,"persistent_workers":false,"pin_memory":false,"prefetch_factor":null,"timeout":0,"datasets":{"manosphere-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/manosphere/val.npy"],"pile-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/pile/val.npy"],"twitterAEE-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/twitterAEE/val.npy"],"4chan-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/4chan/val.npy"],"c4_en-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/c4_en/val.npy"],"gab-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/gab/val.npy"],"ice-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/ice/val.npy"],"m2d2_wiki-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/m2d2_wiki/val.npy"],"mc4_en-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/mc4_en/val.npy"],"ptb-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/ptb/val.npy"],"wikitext_103-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/wikitext_103/val.npy"],"c4_100_domains-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/c4_100_domains/val.npy"],"m2d2_s2orc-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/m2d2_s2orc/val.npy"]},"drop_last":true,"num_workers":0,"pad_direction":"right"},"device_eval_batch_size":null,"label":"all-small-ppl-validation","subset_num_batches":null},{"type":"downstream","data":{"num_workers":0,"persistent_workers":false,"pin_memory":false,"drop_last":false,"pad_direction":"right","paths":null,"prefetch_factor":null,"timeout":0,"datasets":null},"device_eval_batch_size":null,"label":"piqa","subset_num_batches":null},{"data":{"timeout":0,"datasets":null,"drop_last":false,"num_workers":0,"paths":null,"pin_memory":false,"prefetch_factor":null,"pad_direction":"right","persistent_workers":false},"device_eval_batch_size":null,"label":"hellaswag","subset_num_batches":null,"type":"downstream"},{"data":{"persistent_workers":false,"pin_memory":false,"num_workers":0,"pad_direction":"right","paths":null,"prefetch_factor":null,"timeout":0,"datasets":null,"drop_last":false},"device_eval_batch_size":null,"label":"winogrande","subset_num_batches":null,"type":"downstream"},{"subset_num_batches":null,"type":"downstream","data":{"drop_last":false,"num_workers":0,"paths":null,"persistent_workers":false,"pin_memory":false,"datasets":null,"pad_direction":"right","prefetch_factor":null,"timeout":0},"device_eval_batch_size":null,"label":"openbook_qa"},{"data":{"datasets":null,"num_workers":0,"pad_direction":"right","paths":null,"drop_last":false,"persistent_workers":false,"pin_memory":false,"prefetch_factor":null,"timeout":0},"device_eval_batch_size":null,"label":"sciq","subset_num_batches":null,"type":"downstream"},{"subset_num_batches":null,"type":"downstream","data":{"datasets":null,"num_workers":0,"paths":null,"persistent_workers":false,"prefetch_factor":null,"timeout":0,"drop_last":false,"pad_direction":"right","pin_memory":false},"device_eval_batch_size":null,"label":"arc_easy"},{"type":"downstream","data":{"datasets":null,"drop_last":false,"prefetch_factor":null,"timeout":0,"num_workers":0,"pad_direction":"right","paths":null,"persistent_workers":false,"pin_memory":false},"device_eval_batch_size":null,"label":"copa","subset_num_batches":null},{"data":{"datasets":null,"pad_direction":"right","persistent_workers":false,"pin_memory":false,"timeout":0,"drop_last":false,"num_workers":0,"paths":null,"prefetch_factor":null},"device_eval_batch_size":null,"label":"rte","subset_num_batches":null,"type":"downstream"},{"type":"downstream","data":{"drop_last":false,"pad_direction":"right","paths":null,"persistent_workers":false,"timeout":0,"datasets":null,"num_workers":0,"pin_memory":false,"prefetch_factor":null},"device_eval_batch_size":null,"label":"commitment_bank","subset_num_batches":null},{"data":{"drop_last":false,"num_workers":0,"pad_direction":"right","paths":null,"persistent_workers":false,"pin_memory":false,"prefetch_factor":null,"timeout":0,"datasets":null},"device_eval_batch_size":null,"label":"mrpc","subset_num_batches":null,"type":"downstream"},{"data":{"drop_last":false,"paths":null,"timeout":0,"datasets":null,"num_workers":0,"pad_direction":"right","persistent_workers":false,"pin_memory":false,"prefetch_factor":null},"device_eval_batch_size":null,"label":"sst2","subset_num_batches":null,"type":"downstream"}]
-
false
mixed
ShardingStrategy.FULL_SHARD
true
one_in_four
-
-
2048
/scratch/project_462000229/checkpoints/5139412/latest
2e12T
1
swiglu
false
8
0
false
false
false
1
Finished
-
epwalsh
mosaicml-7b-v1
39m 1s
-
fine_grained
50
-
-
1
true
-
0
right
["/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-000-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-000-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-001-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-001-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-002-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-002-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-003-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-003-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-004-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-004-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-005-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-005-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-006-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-006-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-006-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-007-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-007-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-008-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-008-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-008-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-009-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-009-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-010-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-010-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-010-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-011-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-011-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-012-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-012-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-013-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-013-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-013-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-014-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-014-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-014-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-015-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-015-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-016-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-016-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-017-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-017-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-018-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-018-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-019-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-019-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-020-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-020-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-021-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-021-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-022-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-022-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-023-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-023-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-024-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-024-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-025-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-025-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-025-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-026-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-026-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-027-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-027-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-027-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-028-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-028-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-028-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-029-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-029-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-030-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-030-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-031-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-031-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-032-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-032-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-033-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-033-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-033-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-034-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-034-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-034-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-035-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-035-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-036-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-036-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-037-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-037-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-038-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-038-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-039-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-039-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-040-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-040-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-041-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-041-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-042-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-042-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-042-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-043-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-043-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-043-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-044-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-044-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-044-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-045-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-045-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-046-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-046-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-046-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-046-00003.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-047-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-047-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-048-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-048-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-049-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-049-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-050-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-050-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-051-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-051-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-052-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-052-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-052-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-053-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-053-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-053-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-054-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-054-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-055-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-055-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-055-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-056-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-056-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-056-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-057-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-057-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-057-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-058-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-058-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-059-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-059-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-060-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-060-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-061-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-061-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-062-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-062-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-062-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-063-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-063-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-063-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-064-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-064-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-064-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-065-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-065-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-065-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-066-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-066-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-067-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-067-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-068-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-068-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-069-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-069-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-070-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-070-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-071-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-071-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-072-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-072-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-073-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-073-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-074-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-074-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-075-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-075-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-076-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-076-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-077-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-077-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-078-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-078-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-079-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-079-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-080-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-080-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-081-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-081-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-082-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-082-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-083-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-083-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-084-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-084-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-085-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-085-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-086-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-086-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-087-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-087-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-088-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-088-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-089-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-089-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-089-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-090-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-090-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-091-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-091-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-091-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-092-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-092-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-093-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-093-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-093-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-094-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-094-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-094-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-095-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-095-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-096-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-096-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-097-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-097-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-097-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-098-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-098-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-099-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-099-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-100-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-100-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-100-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-101-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-101-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-102-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-102-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-103-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-103-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-104-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-104-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-105-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-105-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-106-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-106-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-106-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-107-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-107-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-108-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-108-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-109-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-109-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-109-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-110-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-110-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-110-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-111-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-111-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-112-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-112-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-113-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-113-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-114-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-114-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-114-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-115-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-115-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-116-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-116-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-117-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-117-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-118-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-118-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-119-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-119-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-120-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-120-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-120-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-121-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-121-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-122-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-122-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-122-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-123-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-123-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-123-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-124-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-124-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-125-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-125-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-126-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-126-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-127-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-127-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-127-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-128-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-128-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-129-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-129-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-129-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-130-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-130-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-131-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-131-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-132-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-132-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-133-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-133-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-133-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-134-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-134-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-134-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-135-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-135-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-135-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-136-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-136-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-137-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-137-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-137-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-138-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-138-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-139-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-139-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-140-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-140-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-141-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-141-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-141-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-142-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-142-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-142-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-143-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-143-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-144-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-144-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-144-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-145-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-145-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-145-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-146-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-146-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-146-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-147-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-147-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-147-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-148-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-148-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-149-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-149-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-149-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-150-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-150-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-150-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-150-00003.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-151-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-151-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-152-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-152-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-153-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-153-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-154-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-154-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-155-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-155-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-155-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-156-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-156-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-157-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-157-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-157-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-158-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-158-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-159-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-159-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-160-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-160-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-161-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-161-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-161-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-162-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-162-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-163-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-163-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-164-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-164-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-165-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-165-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-165-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-166-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-166-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-166-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-167-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-167-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-167-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-168-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-168-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-169-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-169-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-170-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-170-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-171-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-171-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-172-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-172-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-173-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-173-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-173-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-174-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-174-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-174-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-175-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-175-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-175-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-176-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-176-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-176-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-177-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-177-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-178-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-178-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-179-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-179-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-180-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-180-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-181-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-181-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-182-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-182-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-182-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-183-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-183-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-183-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-184-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-184-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-185-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-185-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-185-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-186-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-186-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-186-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-187-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-187-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-187-00002.npy"]
true
true
16
0
2
2
1
2
false
0
1000
false
-1
[{"data":{"drop_last":true,"pad_direction":"right","paths":null,"persistent_workers":false,"prefetch_factor":null,"timeout":0,"datasets":{"m2d2_s2orc-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/m2d2_s2orc/val.npy"],"manosphere-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/manosphere/val.npy"],"pile-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/pile/val.npy"],"twitterAEE-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/twitterAEE/val.npy"],"wikitext_103-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/wikitext_103/val.npy"],"4chan-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/4chan/val.npy"],"c4_en-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/c4_en/val.npy"],"ice-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/ice/val.npy"],"m2d2_wiki-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/m2d2_wiki/val.npy"],"mc4_en-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/mc4_en/val.npy"],"ptb-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/ptb/val.npy"],"c4_100_domains-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/c4_100_domains/val.npy"],"gab-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/gab/val.npy"]},"num_workers":0,"pin_memory":false},"device_eval_batch_size":null,"label":"all-small-ppl-validation","subset_num_batches":null,"type":"lm"},{"label":"piqa","subset_num_batches":null,"type":"downstream","data":{"datasets":null,"timeout":0,"drop_last":false,"num_workers":0,"pad_direction":"right","paths":null,"persistent_workers":false,"pin_memory":false,"prefetch_factor":null},"device_eval_batch_size":null},{"data":{"datasets":null,"drop_last":false,"pad_direction":"right","paths":null,"pin_memory":false,"prefetch_factor":null,"timeout":0,"num_workers":0,"persistent_workers":false},"device_eval_batch_size":null,"label":"hellaswag","subset_num_batches":null,"type":"downstream"},{"data":{"datasets":null,"num_workers":0,"pad_direction":"right","persistent_workers":false,"prefetch_factor":null,"timeout":0,"drop_last":false,"paths":null,"pin_memory":false},"device_eval_batch_size":null,"label":"winogrande","subset_num_batches":null,"type":"downstream"},{"label":"openbook_qa","subset_num_batches":null,"type":"downstream","data":{"datasets":null,"drop_last":false,"num_workers":0,"pad_direction":"right","persistent_workers":false,"paths":null,"pin_memory":false,"prefetch_factor":null,"timeout":0},"device_eval_batch_size":null},{"data":{"datasets":null,"pin_memory":false,"timeout":0,"drop_last":false,"num_workers":0,"pad_direction":"right","paths":null,"persistent_workers":false,"prefetch_factor":null},"device_eval_batch_size":null,"label":"sciq","subset_num_batches":null,"type":"downstream"},{"label":"arc_easy","subset_num_batches":null,"type":"downstream","data":{"datasets":null,"num_workers":0,"pad_direction":"right","persistent_workers":false,"pin_memory":false,"prefetch_factor":null,"timeout":0,"drop_last":false,"paths":null},"device_eval_batch_size":null},{"type":"downstream","data":{"datasets":null,"drop_last":false,"num_workers":0,"paths":null,"persistent_workers":false,"prefetch_factor":null,"timeout":0,"pad_direction":"right","pin_memory":false},"device_eval_batch_size":null,"label":"copa","subset_num_batches":null},{"data":{"num_workers":0,"paths":null,"persistent_workers":false,"pin_memory":false,"prefetch_factor":null,"timeout":0,"datasets":null,"drop_last":false,"pad_direction":"right"},"device_eval_batch_size":null,"label":"rte","subset_num_batches":null,"type":"downstream"},{"data":{"prefetch_factor":null,"timeout":0,"drop_last":false,"num_workers":0,"paths":null,"persistent_workers":false,"pin_memory":false,"datasets":null,"pad_direction":"right"},"device_eval_batch_size":null,"label":"commitment_bank","subset_num_batches":null,"type":"downstream"},{"data":{"persistent_workers":false,"prefetch_factor":null,"datasets":null,"drop_last":false,"pad_direction":"right","pin_memory":false,"timeout":0,"num_workers":0,"paths":null},"device_eval_batch_size":null,"label":"mrpc","subset_num_batches":null,"type":"downstream"},{"data":{"prefetch_factor":null,"timeout":0,"datasets":null,"persistent_workers":false,"pin_memory":false,"drop_last":false,"num_workers":0,"pad_direction":"right","paths":null},"device_eval_batch_size":null,"label":"sst2","subset_num_batches":null,"type":"downstream"}]
-
false
mixed
ShardingStrategy.FULL_SHARD
true
one_in_four
-
-
2048
/scratch/project_462000229/checkpoints/5122842/latest
2e12T
1
swiglu
false
8
0
false
false
false
1
Finished
-
epwalsh
mosaicml-7b-v1
38m 33s
-
fine_grained
50
-
-
1
true
-
0
right
["/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-000-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-000-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-001-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-001-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-002-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-002-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-003-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-003-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-004-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-004-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-005-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-005-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-006-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-006-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-006-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-007-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-007-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-008-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-008-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-008-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-009-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-009-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-010-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-010-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-010-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-011-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-011-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-012-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-012-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-013-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-013-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-013-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-014-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-014-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-014-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-015-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-015-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-016-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-016-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-017-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-017-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-018-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-018-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-019-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-019-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-020-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-020-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-021-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-021-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-022-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-022-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-023-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-023-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-024-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-024-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-025-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-025-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-025-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-026-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-026-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-027-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-027-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-027-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-028-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-028-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-028-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-029-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-029-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-030-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-030-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-031-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-031-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-032-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-032-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-033-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-033-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-033-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-034-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-034-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-034-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-035-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-035-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-036-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-036-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-037-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-037-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-038-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-038-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-039-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-039-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-040-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-040-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-041-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-041-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-042-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-042-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-042-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-043-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-043-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-043-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-044-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-044-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-044-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-045-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-045-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-046-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-046-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-046-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-046-00003.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-047-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-047-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-048-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-048-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-049-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-049-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-050-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-050-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-051-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-051-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-052-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-052-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-052-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-053-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-053-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-053-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-054-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-054-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-055-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-055-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-055-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-056-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-056-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-056-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-057-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-057-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-057-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-058-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-058-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-059-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-059-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-060-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-060-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-061-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-061-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-062-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-062-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-062-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-063-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-063-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-063-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-064-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-064-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-064-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-065-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-065-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-065-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-066-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-066-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-067-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-067-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-068-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-068-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-069-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-069-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-070-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-070-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-071-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-071-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-072-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-072-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-073-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-073-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-074-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-074-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-075-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-075-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-076-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-076-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-077-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-077-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-078-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-078-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-079-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-079-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-080-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-080-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-081-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-081-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-082-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-082-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-083-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-083-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-084-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-084-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-085-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-085-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-086-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-086-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-087-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-087-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-088-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-088-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-089-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-089-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-089-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-090-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-090-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-091-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-091-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-091-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-092-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-092-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-093-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-093-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-093-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-094-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-094-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-094-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-095-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-095-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-096-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-096-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-097-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-097-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-097-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-098-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-098-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-099-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-099-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-100-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-100-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-100-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-101-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-101-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-102-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-102-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-103-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-103-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-104-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-104-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-105-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-105-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-106-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-106-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-106-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-107-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-107-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-108-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-108-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-109-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-109-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-109-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-110-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-110-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-110-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-111-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-111-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-112-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-112-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-113-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-113-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-114-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-114-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-114-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-115-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-115-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-116-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-116-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-117-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-117-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-118-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-118-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-119-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-119-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-120-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-120-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-120-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-121-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-121-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-122-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-122-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-122-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-123-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-123-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-123-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-124-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-124-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-125-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-125-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-126-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-126-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-127-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-127-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-127-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-128-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-128-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-129-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-129-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-129-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-130-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-130-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-131-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-131-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-132-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-132-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-133-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-133-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-133-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-134-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-134-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-134-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-135-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-135-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-135-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-136-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-136-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-137-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-137-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-137-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-138-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-138-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-139-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-139-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-140-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-140-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-141-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-141-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-141-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-142-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-142-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-142-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-143-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-143-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-144-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-144-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-144-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-145-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-145-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-145-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-146-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-146-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-146-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-147-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-147-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-147-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-148-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-148-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-149-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-149-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-149-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-150-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-150-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-150-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-150-00003.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-151-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-151-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-152-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-152-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-153-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-153-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-154-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-154-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-155-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-155-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-155-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-156-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-156-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-157-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-157-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-157-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-158-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-158-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-159-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-159-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-160-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-160-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-161-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-161-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-161-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-162-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-162-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-163-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-163-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-164-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-164-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-165-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-165-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-165-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-166-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-166-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-166-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-167-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-167-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-167-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-168-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-168-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-169-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-169-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-170-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-170-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-171-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-171-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-172-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-172-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-173-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-173-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-173-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-174-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-174-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-174-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-175-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-175-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-175-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-176-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-176-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-176-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-177-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-177-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-178-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-178-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-179-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-179-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-180-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-180-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-181-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-181-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-182-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-182-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-182-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-183-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-183-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-183-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-184-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-184-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-185-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-185-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-185-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-186-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-186-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-186-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-187-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-187-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-187-00002.npy"]
true
true
16
0
2
2
1
2
false
0
1000
false
-1
[{"data":{"drop_last":true,"paths":null,"persistent_workers":false,"pin_memory":false,"timeout":0,"num_workers":0,"pad_direction":"right","prefetch_factor":null,"datasets":{"ptb-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/ptb/val.npy"],"c4_100_domains-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/c4_100_domains/val.npy"],"c4_en-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/c4_en/val.npy"],"gab-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/gab/val.npy"],"ice-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/ice/val.npy"],"mc4_en-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/mc4_en/val.npy"],"twitterAEE-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/twitterAEE/val.npy"],"wikitext_103-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/wikitext_103/val.npy"],"4chan-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/4chan/val.npy"],"m2d2_s2orc-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/m2d2_s2orc/val.npy"],"m2d2_wiki-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/m2d2_wiki/val.npy"],"manosphere-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/manosphere/val.npy"],"pile-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/pile/val.npy"]}},"device_eval_batch_size":null,"label":"all-small-ppl-validation","subset_num_batches":null,"type":"lm"},{"label":"piqa","subset_num_batches":null,"type":"downstream","data":{"datasets":null,"drop_last":false,"num_workers":0,"pad_direction":"right","persistent_workers":false,"paths":null,"pin_memory":false,"prefetch_factor":null,"timeout":0},"device_eval_batch_size":null},{"data":{"datasets":null,"drop_last":false,"num_workers":0,"timeout":0,"pad_direction":"right","paths":null,"persistent_workers":false,"pin_memory":false,"prefetch_factor":null},"device_eval_batch_size":null,"label":"hellaswag","subset_num_batches":null,"type":"downstream"},{"data":{"pin_memory":false,"timeout":0,"paths":null,"persistent_workers":false,"prefetch_factor":null,"datasets":null,"drop_last":false,"num_workers":0,"pad_direction":"right"},"device_eval_batch_size":null,"label":"winogrande","subset_num_batches":null,"type":"downstream"},{"type":"downstream","data":{"datasets":null,"pad_direction":"right","paths":null,"pin_memory":false,"drop_last":false,"num_workers":0,"persistent_workers":false,"prefetch_factor":null,"timeout":0},"device_eval_batch_size":null,"label":"openbook_qa","subset_num_batches":null},{"data":{"paths":null,"persistent_workers":false,"pin_memory":false,"prefetch_factor":null,"timeout":0,"datasets":null,"drop_last":false,"num_workers":0,"pad_direction":"right"},"device_eval_batch_size":null,"label":"sciq","subset_num_batches":null,"type":"downstream"},{"subset_num_batches":null,"type":"downstream","data":{"num_workers":0,"pad_direction":"right","paths":null,"persistent_workers":false,"prefetch_factor":null,"datasets":null,"drop_last":false,"pin_memory":false,"timeout":0},"device_eval_batch_size":null,"label":"arc_easy"},{"device_eval_batch_size":null,"label":"copa","subset_num_batches":null,"type":"downstream","data":{"datasets":null,"num_workers":0,"pad_direction":"right","persistent_workers":false,"timeout":0,"drop_last":false,"paths":null,"pin_memory":false,"prefetch_factor":null}},{"subset_num_batches":null,"type":"downstream","data":{"datasets":null,"drop_last":false,"num_workers":0,"timeout":0,"pad_direction":"right","paths":null,"persistent_workers":false,"pin_memory":false,"prefetch_factor":null},"device_eval_batch_size":null,"label":"rte"},{"subset_num_batches":null,"type":"downstream","data":{"drop_last":false,"num_workers":0,"persistent_workers":false,"prefetch_factor":null,"timeout":0,"datasets":null,"pad_direction":"right","paths":null,"pin_memory":false},"device_eval_batch_size":null,"label":"commitment_bank"},{"data":{"num_workers":0,"prefetch_factor":null,"timeout":0,"datasets":null,"drop_last":false,"pad_direction":"right","paths":null,"persistent_workers":false,"pin_memory":false},"device_eval_batch_size":null,"label":"mrpc","subset_num_batches":null,"type":"downstream"},{"label":"sst2","subset_num_batches":null,"type":"downstream","data":{"timeout":0,"datasets":null,"pad_direction":"right","paths":null,"prefetch_factor":null,"drop_last":false,"num_workers":0,"persistent_workers":false,"pin_memory":false},"device_eval_batch_size":null}]
-
false
mixed
ShardingStrategy.FULL_SHARD
true
one_in_four
-
-
2048
/scratch/project_462000229/checkpoints/5079547/latest
2e12T
1
swiglu
false
8
0
false
false
false
1
Finished
-
epwalsh
mosaicml-7b-v1
21m 15s
-
fine_grained
50
-
-
1
true
-
0
right
["/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-000-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-000-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-001-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-001-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-002-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-002-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-003-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-003-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-004-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-004-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-005-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-005-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-006-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-006-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-006-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-007-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-007-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-008-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-008-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-008-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-009-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-009-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-010-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-010-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-010-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-011-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-011-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-012-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-012-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-013-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-013-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-013-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-014-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-014-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-014-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-015-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-015-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-016-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-016-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-017-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-017-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-018-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-018-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-019-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-019-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-020-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-020-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-021-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-021-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-022-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-022-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-023-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-023-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-024-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-024-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-025-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-025-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-025-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-026-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-026-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-027-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-027-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-027-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-028-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-028-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-028-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-029-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-029-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-030-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-030-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-031-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-031-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-032-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-032-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-033-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-033-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-033-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-034-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-034-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-034-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-035-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-035-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-036-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-036-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-037-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-037-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-038-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-038-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-039-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-039-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-040-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-040-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-041-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-041-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-042-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-042-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-042-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-043-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-043-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-043-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-044-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-044-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-044-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-045-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-045-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-046-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-046-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-046-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-046-00003.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-047-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-047-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-048-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-048-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-049-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-049-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-050-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-050-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-051-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-051-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-052-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-052-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-052-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-053-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-053-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-053-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-054-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-054-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-055-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-055-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-055-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-056-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-056-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-056-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-057-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-057-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-057-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-058-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-058-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-059-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-059-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-060-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-060-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-061-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-061-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-062-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-062-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-062-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-063-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-063-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-063-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-064-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-064-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-064-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-065-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-065-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-065-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-066-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-066-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-067-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-067-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-068-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-068-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-069-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-069-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-070-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-070-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-071-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-071-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-072-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-072-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-073-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-073-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-074-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-074-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-075-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-075-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-076-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-076-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-077-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-077-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-078-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-078-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-079-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-079-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-080-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-080-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-081-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-081-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-082-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-082-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-083-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-083-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-084-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-084-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-085-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-085-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-086-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-086-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-087-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-087-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-088-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-088-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-089-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-089-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-089-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-090-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-090-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-091-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-091-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-091-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-092-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-092-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-093-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-093-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-093-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-094-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-094-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-094-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-095-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-095-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-096-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-096-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-097-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-097-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-097-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-098-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-098-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-099-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-099-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-100-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-100-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-100-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-101-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-101-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-102-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-102-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-103-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-103-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-104-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-104-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-105-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-105-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-106-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-106-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-106-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-107-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-107-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-108-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-108-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-109-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-109-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-109-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-110-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-110-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-110-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-111-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-111-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-112-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-112-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-113-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-113-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-114-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-114-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-114-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-115-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-115-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-116-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-116-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-117-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-117-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-118-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-118-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-119-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-119-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-120-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-120-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-120-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-121-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-121-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-122-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-122-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-122-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-123-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-123-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-123-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-124-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-124-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-125-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-125-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-126-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-126-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-127-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-127-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-127-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-128-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-128-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-129-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-129-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-129-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-130-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-130-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-131-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-131-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-132-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-132-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-133-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-133-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-133-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-134-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-134-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-134-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-135-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-135-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-135-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-136-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-136-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-137-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-137-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-137-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-138-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-138-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-139-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-139-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-140-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-140-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-141-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-141-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-141-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-142-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-142-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-142-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-143-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-143-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-144-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-144-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-144-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-145-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-145-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-145-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-146-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-146-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-146-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-147-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-147-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-147-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-148-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-148-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-149-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-149-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-149-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-150-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-150-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-150-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-150-00003.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-151-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-151-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-152-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-152-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-153-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-153-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-154-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-154-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-155-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-155-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-155-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-156-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-156-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-157-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-157-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-157-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-158-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-158-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-159-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-159-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-160-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-160-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-161-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-161-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-161-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-162-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-162-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-163-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-163-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-164-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-164-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-165-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-165-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-165-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-166-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-166-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-166-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-167-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-167-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-167-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-168-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-168-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-169-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-169-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-170-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-170-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-171-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-171-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-172-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-172-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-173-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-173-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-173-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-174-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-174-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-174-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-175-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-175-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-175-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-176-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-176-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-176-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-177-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-177-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-178-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-178-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-179-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-179-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-180-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-180-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-181-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-181-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-182-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-182-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-182-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-183-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-183-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-183-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-184-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-184-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-185-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-185-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-185-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-186-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-186-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-186-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-187-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-187-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-187-00002.npy"]
true
true
16
0
2
2
1
2
false
0
1000
false
-1
[{"data":{"datasets":{"gab-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/gab/val.npy"],"m2d2_s2orc-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/m2d2_s2orc/val.npy"],"m2d2_wiki-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/m2d2_wiki/val.npy"],"manosphere-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/manosphere/val.npy"],"mc4_en-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/mc4_en/val.npy"],"pile-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/pile/val.npy"],"ptb-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/ptb/val.npy"],"4chan-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/4chan/val.npy"],"c4_100_domains-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/c4_100_domains/val.npy"],"ice-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/ice/val.npy"],"twitterAEE-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/twitterAEE/val.npy"],"wikitext_103-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/wikitext_103/val.npy"],"c4_en-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/c4_en/val.npy"]},"pad_direction":"right","paths":null,"pin_memory":false,"drop_last":true,"num_workers":0,"persistent_workers":false,"prefetch_factor":null,"timeout":0},"device_eval_batch_size":null,"label":"all-small-ppl-validation","subset_num_batches":null,"type":"lm"},{"data":{"num_workers":0,"persistent_workers":false,"pin_memory":false,"prefetch_factor":null,"pad_direction":"right","paths":null,"timeout":0,"datasets":null,"drop_last":false},"device_eval_batch_size":null,"label":"piqa","subset_num_batches":null,"type":"downstream"},{"device_eval_batch_size":null,"label":"hellaswag","subset_num_batches":null,"type":"downstream","data":{"datasets":null,"drop_last":false,"num_workers":0,"persistent_workers":false,"timeout":0,"pad_direction":"right","paths":null,"pin_memory":false,"prefetch_factor":null}},{"label":"winogrande","subset_num_batches":null,"type":"downstream","data":{"pad_direction":"right","paths":null,"prefetch_factor":null,"timeout":0,"num_workers":0,"persistent_workers":false,"pin_memory":false,"datasets":null,"drop_last":false},"device_eval_batch_size":null},{"data":{"datasets":null,"drop_last":false,"num_workers":0,"pad_direction":"right","persistent_workers":false,"pin_memory":false,"prefetch_factor":null,"timeout":0,"paths":null},"device_eval_batch_size":null,"label":"openbook_qa","subset_num_batches":null,"type":"downstream"},{"subset_num_batches":null,"type":"downstream","data":{"paths":null,"persistent_workers":false,"prefetch_factor":null,"drop_last":false,"pin_memory":false,"timeout":0,"datasets":null,"num_workers":0,"pad_direction":"right"},"device_eval_batch_size":null,"label":"sciq"},{"device_eval_batch_size":null,"label":"arc_easy","subset_num_batches":null,"type":"downstream","data":{"timeout":0,"datasets":null,"paths":null,"pin_memory":false,"drop_last":false,"num_workers":0,"pad_direction":"right","persistent_workers":false,"prefetch_factor":null}},{"type":"downstream","data":{"paths":null,"persistent_workers":false,"timeout":0,"datasets":null,"drop_last":false,"pad_direction":"right","pin_memory":false,"prefetch_factor":null,"num_workers":0},"device_eval_batch_size":null,"label":"copa","subset_num_batches":null},{"label":"rte","subset_num_batches":null,"type":"downstream","data":{"drop_last":false,"persistent_workers":false,"pin_memory":false,"timeout":0,"num_workers":0,"pad_direction":"right","paths":null,"prefetch_factor":null,"datasets":null},"device_eval_batch_size":null},{"device_eval_batch_size":null,"label":"commitment_bank","subset_num_batches":null,"type":"downstream","data":{"datasets":null,"drop_last":false,"num_workers":0,"paths":null,"pin_memory":false,"prefetch_factor":null,"timeout":0,"pad_direction":"right","persistent_workers":false}},{"label":"mrpc","subset_num_batches":null,"type":"downstream","data":{"drop_last":false,"pad_direction":"right","persistent_workers":false,"pin_memory":false,"timeout":0,"datasets":null,"num_workers":0,"paths":null,"prefetch_factor":null},"device_eval_batch_size":null},{"device_eval_batch_size":null,"label":"sst2","subset_num_batches":null,"type":"downstream","data":{"datasets":null,"drop_last":false,"paths":null,"persistent_workers":false,"pin_memory":false,"timeout":0,"num_workers":0,"pad_direction":"right","prefetch_factor":null}}]
-
false
mixed
ShardingStrategy.FULL_SHARD
true
one_in_four
-
-
2048
/scratch/project_462000229/checkpoints/5074623/latest
2e12T
1
swiglu
false
8
0
false
false
false
1
Finished
-
epwalsh
mosaicml-7b-v1
35m 51s
-
fine_grained
50
-
-
1
true
-
0
right
["/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-000-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-000-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-001-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-001-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-002-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-002-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-003-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-003-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-004-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-004-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-005-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-005-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-006-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-006-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-006-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-007-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-007-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-008-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-008-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-008-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-009-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-009-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-010-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-010-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-010-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-011-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-011-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-012-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-012-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-013-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-013-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-013-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-014-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-014-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-014-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-015-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-015-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-016-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-016-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-017-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-017-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-018-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-018-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-019-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-019-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-020-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-020-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-021-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-021-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-022-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-022-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-023-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-023-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-024-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-024-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-025-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-025-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-025-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-026-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-026-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-027-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-027-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-027-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-028-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-028-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-028-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-029-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-029-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-030-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-030-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-031-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-031-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-032-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-032-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-033-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-033-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-033-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-034-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-034-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-034-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-035-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-035-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-036-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-036-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-037-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-037-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-038-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-038-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-039-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-039-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-040-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-040-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-041-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-041-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-042-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-042-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-042-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-043-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-043-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-043-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-044-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-044-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-044-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-045-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-045-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-046-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-046-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-046-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-046-00003.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-047-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-047-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-048-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-048-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-049-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-049-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-050-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-050-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-051-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-051-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-052-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-052-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-052-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-053-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-053-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-053-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-054-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-054-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-055-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-055-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-055-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-056-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-056-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-056-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-057-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-057-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-057-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-058-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-058-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-059-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-059-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-060-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-060-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-061-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-061-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-062-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-062-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-062-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-063-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-063-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-063-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-064-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-064-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-064-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-065-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-065-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-065-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-066-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-066-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-067-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-067-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-068-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-068-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-069-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-069-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-070-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-070-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-071-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-071-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-072-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-072-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-073-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-073-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-074-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-074-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-075-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-075-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-076-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-076-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-077-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-077-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-078-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-078-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-079-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-079-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-080-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-080-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-081-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-081-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-082-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-082-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-083-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-083-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-084-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-084-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-085-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-085-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-086-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-086-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-087-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-087-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-088-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-088-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-089-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-089-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-089-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-090-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-090-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-091-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-091-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-091-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-092-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-092-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-093-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-093-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-093-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-094-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-094-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-094-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-095-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-095-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-096-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-096-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-097-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-097-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-097-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-098-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-098-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-099-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-099-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-100-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-100-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-100-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-101-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-101-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-102-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-102-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-103-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-103-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-104-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-104-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-105-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-105-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-106-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-106-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-106-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-107-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-107-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-108-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-108-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-109-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-109-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-109-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-110-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-110-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-110-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-111-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-111-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-112-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-112-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-113-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-113-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-114-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-114-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-114-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-115-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-115-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-116-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-116-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-117-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-117-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-118-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-118-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-119-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-119-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-120-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-120-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-120-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-121-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-121-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-122-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-122-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-122-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-123-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-123-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-123-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-124-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-124-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-125-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-125-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-126-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-126-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-127-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-127-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-127-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-128-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-128-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-129-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-129-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-129-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-130-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-130-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-131-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-131-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-132-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-132-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-133-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-133-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-133-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-134-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-134-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-134-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-135-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-135-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-135-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-136-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-136-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-137-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-137-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-137-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-138-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-138-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-139-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-139-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-140-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-140-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-141-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-141-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-141-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-142-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-142-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-142-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-143-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-143-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-144-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-144-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-144-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-145-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-145-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-145-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-146-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-146-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-146-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-147-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-147-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-147-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-148-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-148-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-149-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-149-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-149-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-150-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-150-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-150-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-150-00003.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-151-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-151-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-152-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-152-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-153-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-153-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-154-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-154-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-155-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-155-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-155-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-156-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-156-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-157-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-157-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-157-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-158-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-158-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-159-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-159-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-160-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-160-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-161-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-161-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-161-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-162-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-162-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-163-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-163-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-164-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-164-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-165-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-165-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-165-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-166-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-166-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-166-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-167-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-167-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-167-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-168-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-168-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-169-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-169-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-170-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-170-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-171-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-171-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-172-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-172-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-173-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-173-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-173-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-174-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-174-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-174-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-175-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-175-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-175-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-176-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-176-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-176-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-177-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-177-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-178-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-178-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-179-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-179-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-180-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-180-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-181-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-181-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-182-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-182-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-182-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-183-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-183-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-183-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-184-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-184-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-185-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-185-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-185-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-186-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-186-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-186-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-187-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-187-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-187-00002.npy"]
true
true
16
0
2
2
1
2
false
0
1000
false
-1
[{"device_eval_batch_size":null,"label":"all-small-ppl-validation","subset_num_batches":null,"type":"lm","data":{"num_workers":0,"pad_direction":"right","paths":null,"persistent_workers":false,"pin_memory":false,"timeout":0,"datasets":{"pile-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/pile/val.npy"],"ptb-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/ptb/val.npy"],"twitterAEE-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/twitterAEE/val.npy"],"4chan-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/4chan/val.npy"],"c4_100_domains-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/c4_100_domains/val.npy"],"c4_en-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/c4_en/val.npy"],"m2d2_s2orc-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/m2d2_s2orc/val.npy"],"manosphere-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/manosphere/val.npy"],"mc4_en-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/mc4_en/val.npy"],"wikitext_103-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/wikitext_103/val.npy"],"gab-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/gab/val.npy"],"ice-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/ice/val.npy"],"m2d2_wiki-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/m2d2_wiki/val.npy"]},"drop_last":true,"prefetch_factor":null}},{"data":{"datasets":null,"drop_last":false,"num_workers":0,"pad_direction":"right","paths":null,"pin_memory":false,"timeout":0,"persistent_workers":false,"prefetch_factor":null},"device_eval_batch_size":null,"label":"piqa","subset_num_batches":null,"type":"downstream"},{"type":"downstream","data":{"datasets":null,"drop_last":false,"paths":null,"pin_memory":false,"prefetch_factor":null,"timeout":0,"num_workers":0,"pad_direction":"right","persistent_workers":false},"device_eval_batch_size":null,"label":"hellaswag","subset_num_batches":null},{"data":{"pad_direction":"right","timeout":0,"datasets":null,"drop_last":false,"num_workers":0,"paths":null,"persistent_workers":false,"pin_memory":false,"prefetch_factor":null},"device_eval_batch_size":null,"label":"winogrande","subset_num_batches":null,"type":"downstream"},{"data":{"datasets":null,"pad_direction":"right","paths":null,"pin_memory":false,"prefetch_factor":null,"drop_last":false,"num_workers":0,"persistent_workers":false,"timeout":0},"device_eval_batch_size":null,"label":"openbook_qa","subset_num_batches":null,"type":"downstream"},{"data":{"drop_last":false,"num_workers":0,"paths":null,"timeout":0,"datasets":null,"pad_direction":"right","persistent_workers":false,"pin_memory":false,"prefetch_factor":null},"device_eval_batch_size":null,"label":"sciq","subset_num_batches":null,"type":"downstream"},{"label":"arc_easy","subset_num_batches":null,"type":"downstream","data":{"datasets":null,"num_workers":0,"pad_direction":"right","paths":null,"prefetch_factor":null,"drop_last":false,"persistent_workers":false,"pin_memory":false,"timeout":0},"device_eval_batch_size":null},{"subset_num_batches":null,"type":"downstream","data":{"datasets":null,"num_workers":0,"pad_direction":"right","persistent_workers":false,"pin_memory":false,"drop_last":false,"paths":null,"prefetch_factor":null,"timeout":0},"device_eval_batch_size":null,"label":"copa"},{"type":"downstream","data":{"datasets":null,"pad_direction":"right","pin_memory":false,"prefetch_factor":null,"timeout":0,"drop_last":false,"num_workers":0,"paths":null,"persistent_workers":false},"device_eval_batch_size":null,"label":"rte","subset_num_batches":null},{"data":{"datasets":null,"drop_last":false,"num_workers":0,"pin_memory":false,"prefetch_factor":null,"timeout":0,"pad_direction":"right","paths":null,"persistent_workers":false},"device_eval_batch_size":null,"label":"commitment_bank","subset_num_batches":null,"type":"downstream"},{"data":{"prefetch_factor":null,"drop_last":false,"num_workers":0,"pad_direction":"right","pin_memory":false,"timeout":0,"datasets":null,"paths":null,"persistent_workers":false},"device_eval_batch_size":null,"label":"mrpc","subset_num_batches":null,"type":"downstream"},{"label":"sst2","subset_num_batches":null,"type":"downstream","data":{"num_workers":0,"pad_direction":"right","pin_memory":false,"prefetch_factor":null,"timeout":0,"paths":null,"persistent_workers":false,"datasets":null,"drop_last":false},"device_eval_batch_size":null}]
-
false
mixed
ShardingStrategy.FULL_SHARD
true
one_in_four
-
-
2048
/scratch/project_462000229/checkpoints/5070211/latest
2e12T
1
swiglu
false
8
0
false
false
false
1
Finished
-
epwalsh
mosaicml-7b-v1
33m 45s
-
fine_grained
50
-
-
1
true
-
0
right
["/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-000-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-000-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-001-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-001-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-002-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-002-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-003-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-003-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-004-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-004-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-005-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-005-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-006-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-006-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-006-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-007-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-007-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-008-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-008-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-008-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-009-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-009-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-010-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-010-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-010-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-011-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-011-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-012-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-012-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-013-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-013-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-013-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-014-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-014-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-014-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-015-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-015-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-016-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-016-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-017-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-017-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-018-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-018-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-019-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-019-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-020-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-020-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-021-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-021-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-022-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-022-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-023-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-023-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-024-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-024-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-025-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-025-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-025-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-026-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-026-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-027-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-027-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-027-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-028-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-028-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-028-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-029-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-029-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-030-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-030-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-031-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-031-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-032-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-032-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-033-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-033-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-033-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-034-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-034-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-034-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-035-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-035-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-036-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-036-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-037-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-037-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-038-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-038-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-039-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-039-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-040-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-040-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-041-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-041-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-042-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-042-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-042-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-043-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-043-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-043-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-044-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-044-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-044-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-045-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-045-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-046-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-046-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-046-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-046-00003.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-047-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-047-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-048-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-048-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-049-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-049-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-050-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-050-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-051-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-051-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-052-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-052-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-052-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-053-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-053-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-053-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-054-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-054-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-055-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-055-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-055-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-056-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-056-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-056-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-057-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-057-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-057-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-058-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-058-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-059-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-059-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-060-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-060-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-061-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-061-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-062-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-062-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-062-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-063-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-063-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-063-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-064-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-064-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-064-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-065-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-065-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-065-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-066-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-066-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-067-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-067-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-068-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-068-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-069-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-069-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-070-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-070-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-071-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-071-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-072-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-072-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-073-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-073-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-074-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-074-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-075-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-075-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-076-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-076-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-077-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-077-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-078-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-078-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-079-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-079-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-080-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-080-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-081-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-081-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-082-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-082-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-083-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-083-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-084-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-084-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-085-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-085-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-086-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-086-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-087-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-087-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-088-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-088-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-089-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-089-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-089-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-090-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-090-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-091-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-091-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-091-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-092-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-092-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-093-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-093-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-093-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-094-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-094-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-094-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-095-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-095-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-096-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-096-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-097-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-097-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-097-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-098-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-098-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-099-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-099-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-100-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-100-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-100-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-101-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-101-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-102-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-102-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-103-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-103-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-104-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-104-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-105-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-105-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-106-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-106-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-106-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-107-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-107-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-108-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-108-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-109-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-109-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-109-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-110-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-110-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-110-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-111-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-111-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-112-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-112-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-113-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-113-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-114-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-114-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-114-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-115-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-115-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-116-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-116-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-117-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-117-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-118-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-118-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-119-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-119-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-120-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-120-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-120-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-121-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-121-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-122-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-122-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-122-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-123-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-123-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-123-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-124-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-124-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-125-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-125-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-126-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-126-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-127-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-127-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-127-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-128-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-128-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-129-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-129-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-129-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-130-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-130-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-131-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-131-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-132-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-132-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-133-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-133-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-133-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-134-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-134-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-134-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-135-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-135-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-135-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-136-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-136-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-137-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-137-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-137-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-138-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-138-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-139-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-139-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-140-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-140-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-141-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-141-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-141-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-142-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-142-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-142-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-143-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-143-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-144-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-144-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-144-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-145-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-145-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-145-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-146-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-146-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-146-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-147-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-147-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-147-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-148-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-148-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-149-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-149-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-149-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-150-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-150-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-150-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-150-00003.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-151-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-151-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-152-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-152-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-153-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-153-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-154-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-154-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-155-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-155-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-155-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-156-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-156-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-157-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-157-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-157-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-158-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-158-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-159-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-159-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-160-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-160-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-161-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-161-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-161-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-162-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-162-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-163-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-163-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-164-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-164-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-165-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-165-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-165-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-166-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-166-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-166-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-167-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-167-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-167-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-168-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-168-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-169-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-169-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-170-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-170-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-171-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-171-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-172-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-172-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-173-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-173-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-173-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-174-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-174-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-174-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-175-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-175-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-175-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-176-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-176-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-176-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-177-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-177-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-178-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-178-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-179-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-179-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-180-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-180-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-181-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-181-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-182-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-182-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-182-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-183-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-183-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-183-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-184-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-184-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-185-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-185-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-185-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-186-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-186-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-186-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-187-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-187-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-187-00002.npy"]
true
true
16
0
2
2
1
2
false
0
1000
false
-1
[{"label":"all-small-ppl-validation","subset_num_batches":null,"type":"lm","data":{"drop_last":true,"pad_direction":"right","persistent_workers":false,"timeout":0,"datasets":{"c4_en-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/c4_en/val.npy"],"gab-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/gab/val.npy"],"ice-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/ice/val.npy"],"manosphere-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/manosphere/val.npy"],"mc4_en-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/mc4_en/val.npy"],"twitterAEE-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/twitterAEE/val.npy"],"wikitext_103-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/wikitext_103/val.npy"],"4chan-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/4chan/val.npy"],"c4_100_domains-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/c4_100_domains/val.npy"],"m2d2_s2orc-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/m2d2_s2orc/val.npy"],"m2d2_wiki-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/m2d2_wiki/val.npy"],"pile-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/pile/val.npy"],"ptb-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/ptb/val.npy"]},"num_workers":0,"paths":null,"pin_memory":false,"prefetch_factor":null},"device_eval_batch_size":null},{"data":{"datasets":null,"drop_last":false,"persistent_workers":false,"prefetch_factor":null,"timeout":0,"num_workers":0,"pad_direction":"right","paths":null,"pin_memory":false},"device_eval_batch_size":null,"label":"piqa","subset_num_batches":null,"type":"downstream"},{"device_eval_batch_size":null,"label":"hellaswag","subset_num_batches":null,"type":"downstream","data":{"prefetch_factor":null,"timeout":0,"num_workers":0,"pin_memory":false,"datasets":null,"drop_last":false,"pad_direction":"right","paths":null,"persistent_workers":false}},{"data":{"prefetch_factor":null,"timeout":0,"num_workers":0,"paths":null,"pin_memory":false,"datasets":null,"drop_last":false,"pad_direction":"right","persistent_workers":false},"device_eval_batch_size":null,"label":"winogrande","subset_num_batches":null,"type":"downstream"},{"data":{"paths":null,"datasets":null,"drop_last":false,"pad_direction":"right","persistent_workers":false,"pin_memory":false,"prefetch_factor":null,"timeout":0,"num_workers":0},"device_eval_batch_size":null,"label":"openbook_qa","subset_num_batches":null,"type":"downstream"},{"subset_num_batches":null,"type":"downstream","data":{"datasets":null,"num_workers":0,"paths":null,"pin_memory":false,"prefetch_factor":null,"timeout":0,"drop_last":false,"pad_direction":"right","persistent_workers":false},"device_eval_batch_size":null,"label":"sciq"},{"subset_num_batches":null,"type":"downstream","data":{"datasets":null,"drop_last":false,"num_workers":0,"paths":null,"prefetch_factor":null,"timeout":0,"pad_direction":"right","persistent_workers":false,"pin_memory":false},"device_eval_batch_size":null,"label":"arc_easy"},{"type":"downstream","data":{"datasets":null,"drop_last":false,"pad_direction":"right","paths":null,"prefetch_factor":null,"timeout":0,"num_workers":0,"persistent_workers":false,"pin_memory":false},"device_eval_batch_size":null,"label":"copa","subset_num_batches":null},{"data":{"datasets":null,"paths":null,"persistent_workers":false,"drop_last":false,"num_workers":0,"pad_direction":"right","pin_memory":false,"prefetch_factor":null,"timeout":0},"device_eval_batch_size":null,"label":"rte","subset_num_batches":null,"type":"downstream"},{"data":{"persistent_workers":false,"prefetch_factor":null,"timeout":0,"num_workers":0,"pin_memory":false,"datasets":null,"drop_last":false,"pad_direction":"right","paths":null},"device_eval_batch_size":null,"label":"commitment_bank","subset_num_batches":null,"type":"downstream"},{"device_eval_batch_size":null,"label":"mrpc","subset_num_batches":null,"type":"downstream","data":{"datasets":null,"drop_last":false,"pad_direction":"right","paths":null,"persistent_workers":false,"prefetch_factor":null,"timeout":0,"num_workers":0,"pin_memory":false}},{"label":"sst2","subset_num_batches":null,"type":"downstream","data":{"paths":null,"persistent_workers":false,"pin_memory":false,"prefetch_factor":null,"timeout":0,"datasets":null,"drop_last":false,"pad_direction":"right","num_workers":0},"device_eval_batch_size":null}]
-
false
mixed
ShardingStrategy.FULL_SHARD
true
one_in_four
-
-
2048
/scratch/project_462000229/checkpoints/5054254/latest
2e12T
1
swiglu
false
8
0
false
false
false
1
Finished
-
epwalsh
mosaicml-7b-v1
10m 52s
-
fine_grained
50
-
-
1
true
-
0
right
["/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-000-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-000-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-001-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-001-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-002-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-002-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-003-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-003-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-004-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-004-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-005-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-005-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-006-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-006-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-006-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-007-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-007-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-008-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-008-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-008-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-009-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-009-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-010-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-010-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-010-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-011-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-011-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-012-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-012-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-013-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-013-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-013-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-014-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-014-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-014-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-015-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-015-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-016-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-016-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-017-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-017-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-018-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-018-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-019-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-019-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-020-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-020-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-021-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-021-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-022-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-022-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-023-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-023-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-024-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-024-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-025-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-025-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-025-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-026-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-026-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-027-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-027-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-027-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-028-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-028-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-028-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-029-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-029-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-030-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-030-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-031-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-031-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-032-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-032-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-033-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-033-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-033-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-034-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-034-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-034-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-035-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-035-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-036-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-036-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-037-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-037-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-038-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-038-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-039-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-039-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-040-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-040-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-041-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-041-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-042-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-042-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-042-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-043-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-043-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-043-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-044-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-044-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-044-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-045-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-045-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-046-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-046-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-046-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-046-00003.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-047-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-047-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-048-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-048-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-049-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-049-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-050-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-050-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-051-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-051-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-052-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-052-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-052-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-053-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-053-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-053-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-054-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-054-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-055-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-055-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-055-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-056-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-056-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-056-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-057-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-057-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-057-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-058-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-058-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-059-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-059-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-060-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-060-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-061-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-061-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-062-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-062-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-062-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-063-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-063-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-063-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-064-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-064-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-064-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-065-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-065-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-065-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-066-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-066-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-067-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-067-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-068-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-068-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-069-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-069-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-070-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-070-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-071-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-071-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-072-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-072-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-073-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-073-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-074-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-074-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-075-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-075-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-076-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-076-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-077-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-077-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-078-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-078-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-079-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-079-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-080-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-080-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-081-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-081-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-082-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-082-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-083-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-083-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-084-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-084-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-085-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-085-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-086-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-086-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-087-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-087-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-088-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-088-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-089-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-089-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-089-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-090-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-090-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-091-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-091-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-091-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-092-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-092-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-093-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-093-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-093-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-094-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-094-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-094-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-095-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-095-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-096-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-096-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-097-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-097-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-097-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-098-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-098-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-099-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-099-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-100-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-100-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-100-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-101-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-101-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-102-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-102-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-103-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-103-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-104-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-104-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-105-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-105-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-106-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-106-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-106-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-107-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-107-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-108-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-108-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-109-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-109-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-109-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-110-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-110-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-110-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-111-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-111-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-112-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-112-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-113-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-113-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-114-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-114-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-114-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-115-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-115-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-116-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-116-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-117-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-117-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-118-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-118-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-119-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-119-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-120-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-120-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-120-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-121-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-121-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-122-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-122-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-122-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-123-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-123-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-123-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-124-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-124-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-125-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-125-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-126-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-126-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-127-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-127-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-127-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-128-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-128-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-129-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-129-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-129-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-130-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-130-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-131-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-131-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-132-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-132-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-133-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-133-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-133-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-134-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-134-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-134-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-135-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-135-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-135-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-136-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-136-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-137-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-137-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-137-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-138-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-138-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-139-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-139-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-140-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-140-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-141-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-141-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-141-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-142-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-142-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-142-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-143-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-143-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-144-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-144-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-144-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-145-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-145-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-145-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-146-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-146-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-146-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-147-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-147-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-147-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-148-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-148-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-149-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-149-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-149-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-150-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-150-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-150-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-150-00003.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-151-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-151-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-152-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-152-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-153-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-153-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-154-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-154-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-155-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-155-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-155-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-156-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-156-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-157-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-157-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-157-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-158-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-158-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-159-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-159-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-160-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-160-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-161-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-161-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-161-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-162-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-162-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-163-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-163-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-164-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-164-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-165-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-165-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-165-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-166-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-166-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-166-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-167-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-167-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-167-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-168-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-168-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-169-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-169-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-170-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-170-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-171-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-171-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-172-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-172-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-173-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-173-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-173-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-174-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-174-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-174-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-175-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-175-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-175-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-176-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-176-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-176-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-177-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-177-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-178-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-178-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-179-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-179-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-180-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-180-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-181-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-181-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-182-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-182-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-182-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-183-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-183-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-183-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-184-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-184-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-185-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-185-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-185-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-186-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-186-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-186-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-187-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-187-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-187-00002.npy"]
true
true
16
0
2
2
1
2
false
0
1000
false
-1
[{"data":{"drop_last":true,"num_workers":0,"persistent_workers":false,"prefetch_factor":null,"pad_direction":"right","paths":null,"pin_memory":false,"timeout":0,"datasets":{"c4_100_domains-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/c4_100_domains/val.npy"],"c4_en-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/c4_en/val.npy"],"ice-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/ice/val.npy"],"manosphere-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/manosphere/val.npy"],"pile-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/pile/val.npy"],"ptb-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/ptb/val.npy"],"wikitext_103-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/wikitext_103/val.npy"],"4chan-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/4chan/val.npy"],"gab-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/gab/val.npy"],"m2d2_s2orc-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/m2d2_s2orc/val.npy"],"m2d2_wiki-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/m2d2_wiki/val.npy"],"mc4_en-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/mc4_en/val.npy"],"twitterAEE-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/twitterAEE/val.npy"]}},"device_eval_batch_size":null,"label":"all-small-ppl-validation","subset_num_batches":null,"type":"lm"},{"label":"piqa","subset_num_batches":null,"type":"downstream","data":{"drop_last":false,"num_workers":0,"persistent_workers":false,"pin_memory":false,"prefetch_factor":null,"pad_direction":"right","paths":null,"timeout":0,"datasets":null},"device_eval_batch_size":null},{"data":{"paths":null,"pin_memory":false,"prefetch_factor":null,"timeout":0,"datasets":null,"drop_last":false,"num_workers":0,"pad_direction":"right","persistent_workers":false},"device_eval_batch_size":null,"label":"hellaswag","subset_num_batches":null,"type":"downstream"},{"data":{"datasets":null,"drop_last":false,"num_workers":0,"pad_direction":"right","persistent_workers":false,"pin_memory":false,"prefetch_factor":null,"paths":null,"timeout":0},"device_eval_batch_size":null,"label":"winogrande","subset_num_batches":null,"type":"downstream"},{"device_eval_batch_size":null,"label":"openbook_qa","subset_num_batches":null,"type":"downstream","data":{"num_workers":0,"paths":null,"persistent_workers":false,"datasets":null,"drop_last":false,"pad_direction":"right","pin_memory":false,"prefetch_factor":null,"timeout":0}},{"data":{"prefetch_factor":null,"datasets":null,"persistent_workers":false,"timeout":0,"drop_last":false,"num_workers":0,"pad_direction":"right","paths":null,"pin_memory":false},"device_eval_batch_size":null,"label":"sciq","subset_num_batches":null,"type":"downstream"},{"data":{"paths":null,"pin_memory":false,"timeout":0,"drop_last":false,"num_workers":0,"pad_direction":"right","persistent_workers":false,"prefetch_factor":null,"datasets":null},"device_eval_batch_size":null,"label":"arc_easy","subset_num_batches":null,"type":"downstream"},{"device_eval_batch_size":null,"label":"copa","subset_num_batches":null,"type":"downstream","data":{"drop_last":false,"num_workers":0,"pad_direction":"right","paths":null,"persistent_workers":false,"pin_memory":false,"prefetch_factor":null,"timeout":0,"datasets":null}},{"data":{"num_workers":0,"pad_direction":"right","paths":null,"timeout":0,"datasets":null,"drop_last":false,"persistent_workers":false,"pin_memory":false,"prefetch_factor":null},"device_eval_batch_size":null,"label":"rte","subset_num_batches":null,"type":"downstream"},{"subset_num_batches":null,"type":"downstream","data":{"pad_direction":"right","pin_memory":false,"timeout":0,"drop_last":false,"num_workers":0,"paths":null,"persistent_workers":false,"prefetch_factor":null,"datasets":null},"device_eval_batch_size":null,"label":"commitment_bank"},{"data":{"datasets":null,"drop_last":false,"num_workers":0,"paths":null,"persistent_workers":false,"pin_memory":false,"prefetch_factor":null,"pad_direction":"right","timeout":0},"device_eval_batch_size":null,"label":"mrpc","subset_num_batches":null,"type":"downstream"},{"data":{"datasets":null,"num_workers":0,"pin_memory":false,"drop_last":false,"pad_direction":"right","paths":null,"persistent_workers":false,"prefetch_factor":null,"timeout":0},"device_eval_batch_size":null,"label":"sst2","subset_num_batches":null,"type":"downstream"}]
-
false
mixed
ShardingStrategy.FULL_SHARD
true
one_in_four
-
-
2048
/scratch/project_462000229/checkpoints/5043439/latest
2e12T
1
swiglu
false
8
0
false
false
false
1
Finished
-
epwalsh
mosaicml-7b-v1
3m 49s
-
fine_grained
50
-
-
1
true
-
0
right
["/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-000-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-000-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-001-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-001-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-002-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-002-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-003-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-003-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-004-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-004-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-005-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-005-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-006-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-006-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-006-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-007-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-007-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-008-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-008-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-008-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-009-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-009-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-010-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-010-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-010-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-011-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-011-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-012-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-012-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-013-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-013-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-013-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-014-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-014-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-014-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-015-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-015-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-016-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-016-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-017-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-017-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-018-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-018-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-019-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-019-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-020-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-020-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-021-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-021-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-022-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-022-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-023-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-023-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-024-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-024-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-025-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-025-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-025-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-026-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-026-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-027-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-027-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-027-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-028-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-028-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-028-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-029-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-029-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-030-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-030-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-031-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-031-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-032-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-032-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-033-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-033-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-033-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-034-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-034-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-034-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-035-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-035-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-036-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-036-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-037-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-037-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-038-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-038-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-039-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-039-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-040-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-040-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-041-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-041-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-042-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-042-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-042-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-043-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-043-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-043-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-044-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-044-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-044-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-045-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-045-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-046-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-046-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-046-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-046-00003.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-047-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-047-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-048-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-048-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-049-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-049-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-050-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-050-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-051-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-051-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-052-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-052-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-052-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-053-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-053-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-053-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-054-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-054-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-055-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-055-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-055-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-056-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-056-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-056-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-057-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-057-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-057-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-058-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-058-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-059-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-059-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-060-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-060-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-061-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-061-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-062-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-062-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-062-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-063-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-063-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-063-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-064-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-064-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-064-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-065-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-065-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-065-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-066-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-066-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-067-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-067-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-068-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-068-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-069-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-069-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-070-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-070-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-071-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-071-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-072-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-072-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-073-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-073-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-074-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-074-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-075-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-075-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-076-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-076-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-077-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-077-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-078-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-078-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-079-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-079-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-080-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-080-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-081-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-081-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-082-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-082-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-083-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-083-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-084-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-084-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-085-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-085-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-086-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-086-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-087-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-087-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-088-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-088-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-089-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-089-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-089-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-090-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-090-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-091-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-091-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-091-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-092-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-092-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-093-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-093-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-093-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-094-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-094-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-094-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-095-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-095-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-096-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-096-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-097-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-097-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-097-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-098-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-098-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-099-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-099-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-100-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-100-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-100-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-101-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-101-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-102-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-102-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-103-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-103-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-104-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-104-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-105-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-105-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-106-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-106-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-106-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-107-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-107-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-108-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-108-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-109-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-109-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-109-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-110-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-110-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-110-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-111-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-111-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-112-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-112-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-113-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-113-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-114-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-114-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-114-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-115-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-115-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-116-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-116-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-117-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-117-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-118-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-118-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-119-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-119-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-120-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-120-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-120-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-121-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-121-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-122-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-122-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-122-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-123-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-123-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-123-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-124-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-124-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-125-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-125-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-126-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-126-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-127-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-127-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-127-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-128-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-128-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-129-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-129-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-129-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-130-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-130-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-131-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-131-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-132-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-132-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-133-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-133-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-133-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-134-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-134-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-134-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-135-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-135-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-135-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-136-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-136-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-137-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-137-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-137-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-138-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-138-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-139-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-139-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-140-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-140-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-141-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-141-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-141-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-142-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-142-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-142-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-143-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-143-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-144-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-144-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-144-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-145-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-145-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-145-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-146-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-146-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-146-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-147-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-147-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-147-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-148-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-148-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-149-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-149-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-149-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-150-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-150-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-150-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-150-00003.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-151-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-151-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-152-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-152-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-153-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-153-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-154-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-154-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-155-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-155-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-155-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-156-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-156-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-157-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-157-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-157-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-158-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-158-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-159-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-159-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-160-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-160-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-161-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-161-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-161-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-162-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-162-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-163-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-163-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-164-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-164-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-165-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-165-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-165-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-166-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-166-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-166-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-167-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-167-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-167-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-168-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-168-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-169-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-169-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-170-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-170-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-171-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-171-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-172-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-172-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-173-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-173-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-173-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-174-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-174-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-174-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-175-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-175-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-175-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-176-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-176-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-176-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-177-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-177-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-178-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-178-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-179-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-179-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-180-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-180-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-181-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-181-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-182-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-182-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-182-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-183-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-183-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-183-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-184-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-184-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-185-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-185-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-185-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-186-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-186-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-186-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-187-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-187-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-187-00002.npy"]
true
true
16
0
2
2
1
2
false
0
1000
false
-1
[{"label":"all-small-ppl-validation","subset_num_batches":null,"type":"lm","data":{"datasets":{"ice-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/ice/val.npy"],"manosphere-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/manosphere/val.npy"],"mc4_en-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/mc4_en/val.npy"],"pile-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/pile/val.npy"],"ptb-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/ptb/val.npy"],"wikitext_103-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/wikitext_103/val.npy"],"c4_100_domains-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/c4_100_domains/val.npy"],"c4_en-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/c4_en/val.npy"],"gab-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/gab/val.npy"],"m2d2_s2orc-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/m2d2_s2orc/val.npy"],"m2d2_wiki-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/m2d2_wiki/val.npy"],"twitterAEE-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/twitterAEE/val.npy"],"4chan-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/4chan/val.npy"]},"drop_last":true,"num_workers":0,"pad_direction":"right","paths":null,"persistent_workers":false,"pin_memory":false,"prefetch_factor":null,"timeout":0},"device_eval_batch_size":null},{"data":{"datasets":null,"num_workers":0,"pad_direction":"right","paths":null,"persistent_workers":false,"pin_memory":false,"prefetch_factor":null,"timeout":0,"drop_last":false},"device_eval_batch_size":null,"label":"piqa","subset_num_batches":null,"type":"downstream"},{"data":{"timeout":0,"datasets":null,"num_workers":0,"pad_direction":"right","pin_memory":false,"drop_last":false,"paths":null,"persistent_workers":false,"prefetch_factor":null},"device_eval_batch_size":null,"label":"hellaswag","subset_num_batches":null,"type":"downstream"},{"device_eval_batch_size":null,"label":"winogrande","subset_num_batches":null,"type":"downstream","data":{"datasets":null,"num_workers":0,"pad_direction":"right","pin_memory":false,"prefetch_factor":null,"timeout":0,"drop_last":false,"paths":null,"persistent_workers":false}},{"data":{"datasets":null,"drop_last":false,"num_workers":0,"pad_direction":"right","paths":null,"persistent_workers":false,"pin_memory":false,"timeout":0,"prefetch_factor":null},"device_eval_batch_size":null,"label":"openbook_qa","subset_num_batches":null,"type":"downstream"},{"data":{"datasets":null,"num_workers":0,"paths":null,"persistent_workers":false,"prefetch_factor":null,"timeout":0,"drop_last":false,"pad_direction":"right","pin_memory":false},"device_eval_batch_size":null,"label":"sciq","subset_num_batches":null,"type":"downstream"},{"type":"downstream","data":{"datasets":null,"pad_direction":"right","paths":null,"persistent_workers":false,"timeout":0,"drop_last":false,"num_workers":0,"pin_memory":false,"prefetch_factor":null},"device_eval_batch_size":null,"label":"arc_easy","subset_num_batches":null},{"subset_num_batches":null,"type":"downstream","data":{"timeout":0,"datasets":null,"drop_last":false,"pad_direction":"right","persistent_workers":false,"pin_memory":false,"num_workers":0,"paths":null,"prefetch_factor":null},"device_eval_batch_size":null,"label":"copa"},{"type":"downstream","data":{"datasets":null,"pad_direction":"right","paths":null,"persistent_workers":false,"pin_memory":false,"prefetch_factor":null,"timeout":0,"drop_last":false,"num_workers":0},"device_eval_batch_size":null,"label":"rte","subset_num_batches":null},{"device_eval_batch_size":null,"label":"commitment_bank","subset_num_batches":null,"type":"downstream","data":{"pin_memory":false,"prefetch_factor":null,"timeout":0,"datasets":null,"drop_last":false,"pad_direction":"right","persistent_workers":false,"num_workers":0,"paths":null}},{"data":{"datasets":null,"drop_last":false,"pad_direction":"right","paths":null,"persistent_workers":false,"pin_memory":false,"timeout":0,"num_workers":0,"prefetch_factor":null},"device_eval_batch_size":null,"label":"mrpc","subset_num_batches":null,"type":"downstream"},{"data":{"datasets":null,"drop_last":false,"num_workers":0,"pad_direction":"right","persistent_workers":false,"prefetch_factor":null,"timeout":0,"paths":null,"pin_memory":false},"device_eval_batch_size":null,"label":"sst2","subset_num_batches":null,"type":"downstream"}]
-
false
mixed
ShardingStrategy.FULL_SHARD
true
one_in_four
-
-
2048
/scratch/project_462000229/checkpoints/4984563/latest
2e12T
1
swiglu
false
8
0
false
false
false
1
Finished
-
epwalsh
mosaicml-7b-v1
32m 59s
-
fine_grained
50
-
-
1
true
-
0
right
["/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-000-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-000-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-001-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-001-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-002-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-002-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-003-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-003-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-004-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-004-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-005-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-005-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-006-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-006-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-006-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-007-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-007-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-008-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-008-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-008-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-009-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-009-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-010-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-010-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-010-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-011-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-011-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-012-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-012-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-013-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-013-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-013-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-014-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-014-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-014-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-015-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-015-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-016-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-016-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-017-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-017-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-018-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-018-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-019-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-019-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-020-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-020-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-021-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-021-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-022-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-022-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-023-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-023-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-024-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-024-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-025-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-025-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-025-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-026-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-026-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-027-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-027-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-027-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-028-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-028-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-028-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-029-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-029-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-030-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-030-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-031-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-031-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-032-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-032-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-033-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-033-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-033-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-034-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-034-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-034-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-035-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-035-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-036-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-036-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-037-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-037-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-038-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-038-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-039-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-039-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-040-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-040-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-041-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-041-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-042-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-042-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-042-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-043-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-043-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-043-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-044-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-044-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-044-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-045-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-045-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-046-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-046-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-046-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-046-00003.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-047-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-047-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-048-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-048-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-049-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-049-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-050-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-050-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-051-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-051-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-052-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-052-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-052-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-053-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-053-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-053-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-054-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-054-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-055-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-055-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-055-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-056-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-056-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-056-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-057-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-057-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-057-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-058-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-058-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-059-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-059-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-060-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-060-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-061-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-061-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-062-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-062-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-062-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-063-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-063-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-063-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-064-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-064-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-064-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-065-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-065-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-065-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-066-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-066-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-067-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-067-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-068-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-068-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-069-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-069-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-070-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-070-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-071-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-071-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-072-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-072-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-073-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-073-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-074-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-074-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-075-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-075-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-076-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-076-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-077-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-077-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-078-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-078-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-079-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-079-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-080-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-080-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-081-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-081-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-082-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-082-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-083-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-083-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-084-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-084-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-085-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-085-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-086-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-086-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-087-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-087-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-088-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-088-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-089-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-089-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-089-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-090-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-090-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-091-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-091-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-091-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-092-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-092-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-093-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-093-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-093-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-094-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-094-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-094-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-095-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-095-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-096-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-096-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-097-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-097-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-097-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-098-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-098-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-099-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-099-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-100-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-100-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-100-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-101-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-101-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-102-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-102-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-103-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-103-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-104-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-104-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-105-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-105-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-106-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-106-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-106-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-107-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-107-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-108-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-108-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-109-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-109-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-109-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-110-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-110-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-110-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-111-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-111-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-112-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-112-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-113-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-113-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-114-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-114-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-114-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-115-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-115-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-116-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-116-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-117-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-117-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-118-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-118-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-119-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-119-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-120-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-120-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-120-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-121-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-121-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-122-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-122-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-122-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-123-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-123-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-123-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-124-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-124-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-125-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-125-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-126-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-126-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-127-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-127-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-127-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-128-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-128-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-129-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-129-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-129-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-130-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-130-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-131-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-131-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-132-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-132-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-133-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-133-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-133-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-134-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-134-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-134-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-135-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-135-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-135-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-136-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-136-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-137-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-137-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-137-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-138-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-138-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-139-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-139-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-140-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-140-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-141-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-141-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-141-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-142-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-142-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-142-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-143-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-143-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-144-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-144-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-144-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-145-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-145-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-145-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-146-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-146-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-146-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-147-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-147-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-147-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-148-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-148-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-149-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-149-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-149-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-150-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-150-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-150-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-150-00003.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-151-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-151-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-152-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-152-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-153-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-153-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-154-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-154-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-155-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-155-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-155-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-156-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-156-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-157-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-157-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-157-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-158-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-158-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-159-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-159-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-160-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-160-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-161-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-161-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-161-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-162-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-162-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-163-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-163-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-164-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-164-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-165-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-165-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-165-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-166-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-166-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-166-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-167-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-167-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-167-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-168-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-168-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-169-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-169-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-170-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-170-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-171-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-171-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-172-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-172-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-173-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-173-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-173-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-174-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-174-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-174-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-175-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-175-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-175-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-176-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-176-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-176-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-177-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-177-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-178-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-178-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-179-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-179-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-180-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-180-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-181-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-181-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-182-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-182-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-182-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-183-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-183-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-183-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-184-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-184-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-185-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-185-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-185-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-186-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-186-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-186-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-187-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-187-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-187-00002.npy"]
true
true
16
0
2
2
1
2
false
-
1000
false
-1
[{"data":{"drop_last":true,"num_workers":0,"paths":null,"prefetch_factor":null,"timeout":0,"datasets":{"c4_100_domains-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/c4_100_domains/val.npy"],"c4_en-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/c4_en/val.npy"],"gab-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/gab/val.npy"],"m2d2_s2orc-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/m2d2_s2orc/val.npy"],"m2d2_wiki-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/m2d2_wiki/val.npy"],"manosphere-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/manosphere/val.npy"],"mc4_en-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/mc4_en/val.npy"],"pile-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/pile/val.npy"],"4chan-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/4chan/val.npy"],"ice-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/ice/val.npy"],"ptb-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/ptb/val.npy"],"twitterAEE-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/twitterAEE/val.npy"],"wikitext_103-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/wikitext_103/val.npy"]},"pad_direction":"right","persistent_workers":false,"pin_memory":false},"device_eval_batch_size":null,"label":"all-small-ppl-validation","subset_num_batches":null,"type":"lm"},{"label":"piqa","subset_num_batches":null,"type":"downstream","data":{"pin_memory":false,"prefetch_factor":null,"timeout":0,"num_workers":0,"datasets":null,"drop_last":false,"pad_direction":"right","paths":null,"persistent_workers":false},"device_eval_batch_size":null},{"device_eval_batch_size":null,"label":"hellaswag","subset_num_batches":null,"type":"downstream","data":{"paths":null,"datasets":null,"num_workers":0,"persistent_workers":false,"pin_memory":false,"prefetch_factor":null,"timeout":0,"drop_last":false,"pad_direction":"right"}},{"data":{"datasets":null,"num_workers":0,"pad_direction":"right","paths":null,"pin_memory":false,"prefetch_factor":null,"drop_last":false,"persistent_workers":false,"timeout":0},"device_eval_batch_size":null,"label":"winogrande","subset_num_batches":null,"type":"downstream"},{"data":{"num_workers":0,"pad_direction":"right","datasets":null,"paths":null,"persistent_workers":false,"pin_memory":false,"prefetch_factor":null,"timeout":0,"drop_last":false},"device_eval_batch_size":null,"label":"openbook_qa","subset_num_batches":null,"type":"downstream"},{"type":"downstream","data":{"datasets":null,"drop_last":false,"num_workers":0,"pad_direction":"right","persistent_workers":false,"prefetch_factor":null,"paths":null,"pin_memory":false,"timeout":0},"device_eval_batch_size":null,"label":"sciq","subset_num_batches":null},{"label":"arc_easy","subset_num_batches":null,"type":"downstream","data":{"datasets":null,"drop_last":false,"pad_direction":"right","persistent_workers":false,"pin_memory":false,"prefetch_factor":null,"timeout":0,"num_workers":0,"paths":null},"device_eval_batch_size":null},{"type":"downstream","data":{"paths":null,"persistent_workers":false,"datasets":null,"pin_memory":false,"prefetch_factor":null,"timeout":0,"drop_last":false,"num_workers":0,"pad_direction":"right"},"device_eval_batch_size":null,"label":"copa","subset_num_batches":null},{"device_eval_batch_size":null,"label":"rte","subset_num_batches":null,"type":"downstream","data":{"drop_last":false,"num_workers":0,"pad_direction":"right","persistent_workers":false,"pin_memory":false,"prefetch_factor":null,"timeout":0,"datasets":null,"paths":null}},{"device_eval_batch_size":null,"label":"commitment_bank","subset_num_batches":null,"type":"downstream","data":{"timeout":0,"datasets":null,"pad_direction":"right","paths":null,"persistent_workers":false,"pin_memory":false,"prefetch_factor":null,"drop_last":false,"num_workers":0}},{"type":"downstream","data":{"datasets":null,"num_workers":0,"paths":null,"persistent_workers":false,"drop_last":false,"pad_direction":"right","pin_memory":false,"prefetch_factor":null,"timeout":0},"device_eval_batch_size":null,"label":"mrpc","subset_num_batches":null},{"label":"sst2","subset_num_batches":null,"type":"downstream","data":{"pad_direction":"right","persistent_workers":false,"pin_memory":false,"prefetch_factor":null,"datasets":null,"drop_last":false,"num_workers":0,"paths":null,"timeout":0},"device_eval_batch_size":null}]
-
false
mixed
ShardingStrategy.FULL_SHARD
true
one_in_four
-
-
2048
/scratch/project_462000229/checkpoints/4969731/latest
476837
1
swiglu
false
8
0
false
false
false
1
Finished
-
epwalsh
mosaicml-7b-v1
31m 42s
-
fine_grained
50
-
-
1
true
-
0
right
["/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-000-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-000-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-001-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-001-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-002-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-002-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-003-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-003-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-004-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-004-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-005-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-005-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-006-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-006-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-006-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-007-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-007-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-008-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-008-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-008-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-009-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-009-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-010-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-010-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-010-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-011-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-011-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-012-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-012-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-013-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-013-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-013-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-014-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-014-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-014-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-015-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-015-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-016-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-016-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-017-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-017-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-018-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-018-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-019-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-019-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-020-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-020-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-021-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-021-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-022-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-022-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-023-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-023-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-024-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-024-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-025-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-025-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-025-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-026-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-026-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-027-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-027-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-027-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-028-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-028-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-028-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-029-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-029-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-030-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-030-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-031-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-031-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-032-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-032-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-033-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-033-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-033-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-034-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-034-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-034-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-035-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-035-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-036-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-036-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-037-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-037-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-038-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-038-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-039-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-039-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-040-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-040-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-041-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-041-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-042-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-042-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-042-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-043-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-043-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-043-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-044-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-044-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-044-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-045-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-045-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-046-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-046-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-046-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-046-00003.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-047-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-047-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-048-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-048-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-049-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-049-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-050-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-050-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-051-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-051-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-052-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-052-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-052-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-053-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-053-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-053-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-054-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-054-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-055-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-055-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-055-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-056-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-056-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-056-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-057-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-057-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-057-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-058-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-058-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-059-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-059-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-060-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-060-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-061-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-061-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-062-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-062-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-062-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-063-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-063-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-063-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-064-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-064-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-064-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-065-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-065-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-065-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-066-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-066-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-067-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-067-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-068-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-068-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-069-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-069-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-070-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-070-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-071-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-071-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-072-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-072-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-073-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-073-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-074-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-074-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-075-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-075-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-076-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-076-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-077-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-077-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-078-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-078-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-079-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-079-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-080-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-080-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-081-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-081-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-082-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-082-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-083-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-083-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-084-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-084-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-085-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-085-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-086-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-086-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-087-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-087-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-088-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-088-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-089-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-089-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-089-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-090-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-090-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-091-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-091-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-091-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-092-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-092-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-093-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-093-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-093-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-094-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-094-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-094-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-095-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-095-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-096-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-096-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-097-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-097-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-097-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-098-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-098-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-099-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-099-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-100-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-100-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-100-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-101-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-101-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-102-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-102-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-103-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-103-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-104-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-104-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-105-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-105-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-106-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-106-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-106-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-107-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-107-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-108-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-108-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-109-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-109-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-109-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-110-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-110-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-110-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-111-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-111-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-112-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-112-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-113-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-113-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-114-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-114-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-114-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-115-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-115-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-116-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-116-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-117-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-117-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-118-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-118-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-119-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-119-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-120-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-120-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-120-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-121-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-121-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-122-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-122-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-122-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-123-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-123-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-123-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-124-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-124-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-125-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-125-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-126-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-126-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-127-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-127-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-127-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-128-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-128-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-129-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-129-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-129-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-130-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-130-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-131-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-131-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-132-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-132-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-133-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-133-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-133-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-134-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-134-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-134-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-135-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-135-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-135-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-136-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-136-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-137-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-137-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-137-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-138-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-138-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-139-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-139-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-140-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-140-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-141-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-141-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-141-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-142-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-142-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-142-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-143-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-143-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-144-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-144-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-144-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-145-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-145-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-145-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-146-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-146-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-146-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-147-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-147-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-147-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-148-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-148-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-149-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-149-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-149-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-150-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-150-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-150-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-150-00003.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-151-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-151-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-152-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-152-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-153-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-153-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-154-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-154-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-155-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-155-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-155-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-156-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-156-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-157-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-157-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-157-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-158-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-158-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-159-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-159-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-160-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-160-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-161-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-161-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-161-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-162-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-162-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-163-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-163-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-164-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-164-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-165-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-165-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-165-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-166-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-166-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-166-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-167-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-167-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-167-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-168-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-168-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-169-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-169-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-170-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-170-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-171-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-171-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-172-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-172-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-173-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-173-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-173-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-174-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-174-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-174-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-175-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-175-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-175-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-176-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-176-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-176-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-177-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-177-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-178-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-178-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-179-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-179-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-180-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-180-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-181-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-181-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-182-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-182-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-182-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-183-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-183-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-183-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-184-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-184-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-185-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-185-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-185-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-186-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-186-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-186-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-187-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-187-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-187-00002.npy"]
true
true
16
0
2
2
1
2
false
-
1000
false
-1
[{"subset_num_batches":null,"type":"lm","data":{"drop_last":true,"num_workers":0,"pad_direction":"right","paths":null,"persistent_workers":false,"pin_memory":false,"timeout":0,"datasets":{"ice-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/ice/val.npy"],"m2d2_wiki-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/m2d2_wiki/val.npy"],"manosphere-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/manosphere/val.npy"],"ptb-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/ptb/val.npy"],"twitterAEE-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/twitterAEE/val.npy"],"4chan-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/4chan/val.npy"],"c4_100_domains-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/c4_100_domains/val.npy"],"c4_en-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/c4_en/val.npy"],"gab-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/gab/val.npy"],"m2d2_s2orc-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/m2d2_s2orc/val.npy"],"mc4_en-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/mc4_en/val.npy"],"pile-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/pile/val.npy"],"wikitext_103-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/wikitext_103/val.npy"]},"prefetch_factor":null},"device_eval_batch_size":null,"label":"all-small-ppl-validation"},{"data":{"timeout":0,"drop_last":false,"pad_direction":"right","persistent_workers":false,"pin_memory":false,"datasets":null,"num_workers":0,"paths":null,"prefetch_factor":null},"device_eval_batch_size":null,"label":"piqa","subset_num_batches":null,"type":"downstream"},{"data":{"datasets":null,"paths":null,"persistent_workers":false,"pin_memory":false,"timeout":0,"drop_last":false,"num_workers":0,"pad_direction":"right","prefetch_factor":null},"device_eval_batch_size":null,"label":"hellaswag","subset_num_batches":null,"type":"downstream"},{"data":{"num_workers":0,"pad_direction":"right","paths":null,"persistent_workers":false,"prefetch_factor":null,"timeout":0,"datasets":null,"drop_last":false,"pin_memory":false},"device_eval_batch_size":null,"label":"winogrande","subset_num_batches":null,"type":"downstream"},{"subset_num_batches":null,"type":"downstream","data":{"datasets":null,"drop_last":false,"num_workers":0,"pad_direction":"right","prefetch_factor":null,"paths":null,"persistent_workers":false,"pin_memory":false,"timeout":0},"device_eval_batch_size":null,"label":"openbook_qa"},{"label":"sciq","subset_num_batches":null,"type":"downstream","data":{"prefetch_factor":null,"datasets":null,"num_workers":0,"paths":null,"timeout":0,"drop_last":false,"pad_direction":"right","persistent_workers":false,"pin_memory":false},"device_eval_batch_size":null},{"data":{"paths":null,"persistent_workers":false,"prefetch_factor":null,"drop_last":false,"pin_memory":false,"timeout":0,"datasets":null,"num_workers":0,"pad_direction":"right"},"device_eval_batch_size":null,"label":"arc_easy","subset_num_batches":null,"type":"downstream"},{"subset_num_batches":null,"type":"downstream","data":{"drop_last":false,"num_workers":0,"persistent_workers":false,"prefetch_factor":null,"timeout":0,"datasets":null,"pad_direction":"right","paths":null,"pin_memory":false},"device_eval_batch_size":null,"label":"copa"},{"data":{"num_workers":0,"pad_direction":"right","persistent_workers":false,"pin_memory":false,"datasets":null,"drop_last":false,"paths":null,"prefetch_factor":null,"timeout":0},"device_eval_batch_size":null,"label":"rte","subset_num_batches":null,"type":"downstream"},{"label":"commitment_bank","subset_num_batches":null,"type":"downstream","data":{"datasets":null,"drop_last":false,"num_workers":0,"timeout":0,"pad_direction":"right","paths":null,"persistent_workers":false,"pin_memory":false,"prefetch_factor":null},"device_eval_batch_size":null},{"label":"mrpc","subset_num_batches":null,"type":"downstream","data":{"drop_last":false,"persistent_workers":false,"datasets":null,"num_workers":0,"pad_direction":"right","paths":null,"pin_memory":false,"prefetch_factor":null,"timeout":0},"device_eval_batch_size":null},{"device_eval_batch_size":null,"label":"sst2","subset_num_batches":null,"type":"downstream","data":{"pin_memory":false,"prefetch_factor":null,"datasets":null,"num_workers":0,"pad_direction":"right","timeout":0,"drop_last":false,"paths":null,"persistent_workers":false}}]
-
false
mixed
ShardingStrategy.FULL_SHARD
true
one_in_four
-
-
2048
/scratch/project_462000229/checkpoints/4960081/latest
476837
1
swiglu
false
8
0
false
false
false
1
Finished
-
epwalsh
mosaicml-7b-v1
16m 27s
-
fine_grained
50
-
-
1
true
-
0
right
["/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-000-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-000-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-001-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-001-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-002-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-002-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-003-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-003-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-004-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-004-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-005-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-005-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-006-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-006-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-006-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-007-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-007-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-008-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-008-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-008-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-009-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-009-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-010-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-010-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-010-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-011-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-011-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-012-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-012-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-013-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-013-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-013-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-014-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-014-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-014-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-015-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-015-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-016-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-016-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-017-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-017-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-018-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-018-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-019-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-019-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-020-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-020-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-021-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-021-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-022-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-022-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-023-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-023-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-024-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-024-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-025-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-025-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-025-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-026-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-026-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-027-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-027-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-027-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-028-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-028-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-028-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-029-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-029-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-030-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-030-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-031-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-031-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-032-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-032-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-033-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-033-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-033-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-034-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-034-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-034-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-035-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-035-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-036-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-036-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-037-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-037-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-038-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-038-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-039-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-039-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-040-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-040-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-041-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-041-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-042-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-042-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-042-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-043-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-043-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-043-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-044-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-044-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-044-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-045-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-045-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-046-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-046-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-046-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-046-00003.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-047-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-047-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-048-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-048-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-049-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-049-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-050-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-050-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-051-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-051-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-052-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-052-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-052-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-053-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-053-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-053-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-054-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-054-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-055-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-055-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-055-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-056-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-056-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-056-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-057-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-057-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-057-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-058-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-058-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-059-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-059-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-060-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-060-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-061-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-061-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-062-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-062-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-062-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-063-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-063-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-063-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-064-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-064-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-064-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-065-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-065-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-065-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-066-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-066-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-067-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-067-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-068-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-068-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-069-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-069-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-070-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-070-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-071-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-071-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-072-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-072-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-073-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-073-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-074-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-074-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-075-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-075-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-076-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-076-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-077-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-077-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-078-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-078-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-079-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-079-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-080-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-080-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-081-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-081-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-082-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-082-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-083-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-083-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-084-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-084-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-085-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-085-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-086-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-086-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-087-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-087-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-088-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-088-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-089-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-089-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-089-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-090-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-090-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-091-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-091-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-091-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-092-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-092-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-093-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-093-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-093-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-094-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-094-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-094-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-095-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-095-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-096-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-096-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-097-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-097-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-097-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-098-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-098-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-099-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-099-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-100-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-100-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-100-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-101-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-101-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-102-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-102-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-103-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-103-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-104-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-104-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-105-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-105-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-106-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-106-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-106-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-107-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-107-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-108-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-108-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-109-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-109-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-109-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-110-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-110-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-110-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-111-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-111-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-112-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-112-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-113-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-113-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-114-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-114-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-114-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-115-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-115-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-116-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-116-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-117-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-117-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-118-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-118-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-119-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-119-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-120-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-120-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-120-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-121-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-121-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-122-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-122-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-122-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-123-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-123-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-123-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-124-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-124-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-125-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-125-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-126-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-126-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-127-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-127-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-127-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-128-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-128-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-129-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-129-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-129-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-130-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-130-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-131-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-131-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-132-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-132-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-133-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-133-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-133-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-134-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-134-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-134-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-135-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-135-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-135-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-136-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-136-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-137-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-137-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-137-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-138-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-138-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-139-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-139-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-140-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-140-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-141-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-141-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-141-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-142-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-142-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-142-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-143-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-143-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-144-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-144-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-144-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-145-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-145-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-145-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-146-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-146-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-146-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-147-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-147-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-147-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-148-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-148-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-149-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-149-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-149-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-150-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-150-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-150-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-150-00003.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-151-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-151-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-152-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-152-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-153-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-153-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-154-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-154-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-155-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-155-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-155-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-156-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-156-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-157-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-157-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-157-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-158-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-158-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-159-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-159-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-160-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-160-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-161-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-161-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-161-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-162-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-162-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-163-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-163-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-164-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-164-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-165-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-165-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-165-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-166-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-166-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-166-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-167-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-167-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-167-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-168-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-168-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-169-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-169-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-170-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-170-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-171-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-171-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-172-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-172-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-173-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-173-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-173-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-174-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-174-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-174-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-175-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-175-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-175-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-176-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-176-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-176-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-177-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-177-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-178-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-178-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-179-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-179-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-180-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-180-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-181-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-181-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-182-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-182-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-182-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-183-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-183-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-183-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-184-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-184-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-185-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-185-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-185-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-186-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-186-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-186-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-187-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-187-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-187-00002.npy"]
true
true
16
0
2
2
1
2
false
-
1000
false
-1
[{"data":{"num_workers":0,"pad_direction":"right","paths":null,"persistent_workers":false,"pin_memory":false,"prefetch_factor":null,"datasets":{"m2d2_s2orc-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/m2d2_s2orc/val.npy"],"manosphere-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/manosphere/val.npy"],"ptb-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/ptb/val.npy"],"twitterAEE-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/twitterAEE/val.npy"],"wikitext_103-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/wikitext_103/val.npy"],"c4_100_domains-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/c4_100_domains/val.npy"],"gab-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/gab/val.npy"],"m2d2_wiki-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/m2d2_wiki/val.npy"],"mc4_en-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/mc4_en/val.npy"],"pile-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/pile/val.npy"],"4chan-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/4chan/val.npy"],"c4_en-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/c4_en/val.npy"],"ice-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/ice/val.npy"]},"drop_last":true,"timeout":0},"device_eval_batch_size":null,"label":"all-small-ppl-validation","subset_num_batches":null,"type":"lm"},{"label":"piqa","subset_num_batches":null,"type":"downstream","data":{"timeout":0,"datasets":null,"drop_last":false,"num_workers":0,"pad_direction":"right","paths":null,"persistent_workers":false,"pin_memory":false,"prefetch_factor":null},"device_eval_batch_size":null},{"device_eval_batch_size":null,"label":"hellaswag","subset_num_batches":null,"type":"downstream","data":{"datasets":null,"drop_last":false,"pad_direction":"right","persistent_workers":false,"pin_memory":false,"timeout":0,"num_workers":0,"paths":null,"prefetch_factor":null}},{"data":{"drop_last":false,"pad_direction":"right","persistent_workers":false,"prefetch_factor":null,"num_workers":0,"paths":null,"pin_memory":false,"timeout":0,"datasets":null},"device_eval_batch_size":null,"label":"winogrande","subset_num_batches":null,"type":"downstream"},{"type":"downstream","data":{"drop_last":false,"persistent_workers":false,"pin_memory":false,"datasets":null,"num_workers":0,"pad_direction":"right","paths":null,"prefetch_factor":null,"timeout":0},"device_eval_batch_size":null,"label":"openbook_qa","subset_num_batches":null},{"data":{"num_workers":0,"pad_direction":"right","paths":null,"persistent_workers":false,"pin_memory":false,"timeout":0,"datasets":null,"drop_last":false,"prefetch_factor":null},"device_eval_batch_size":null,"label":"sciq","subset_num_batches":null,"type":"downstream"},{"device_eval_batch_size":null,"label":"arc_easy","subset_num_batches":null,"type":"downstream","data":{"drop_last":false,"num_workers":0,"paths":null,"persistent_workers":false,"pin_memory":false,"timeout":0,"datasets":null,"pad_direction":"right","prefetch_factor":null}},{"device_eval_batch_size":null,"label":"copa","subset_num_batches":null,"type":"downstream","data":{"drop_last":false,"num_workers":0,"pad_direction":"right","pin_memory":false,"prefetch_factor":null,"timeout":0,"datasets":null,"paths":null,"persistent_workers":false}},{"data":{"pad_direction":"right","paths":null,"pin_memory":false,"datasets":null,"num_workers":0,"persistent_workers":false,"prefetch_factor":null,"timeout":0,"drop_last":false},"device_eval_batch_size":null,"label":"rte","subset_num_batches":null,"type":"downstream"},{"data":{"datasets":null,"drop_last":false,"persistent_workers":false,"pin_memory":false,"prefetch_factor":null,"timeout":0,"num_workers":0,"pad_direction":"right","paths":null},"device_eval_batch_size":null,"label":"commitment_bank","subset_num_batches":null,"type":"downstream"},{"data":{"prefetch_factor":null,"num_workers":0,"paths":null,"timeout":0,"datasets":null,"drop_last":false,"pad_direction":"right","persistent_workers":false,"pin_memory":false},"device_eval_batch_size":null,"label":"mrpc","subset_num_batches":null,"type":"downstream"},{"data":{"drop_last":false,"num_workers":0,"persistent_workers":false,"datasets":null,"pad_direction":"right","paths":null,"pin_memory":false,"prefetch_factor":null,"timeout":0},"device_eval_batch_size":null,"label":"sst2","subset_num_batches":null,"type":"downstream"}]
-
false
mixed
ShardingStrategy.FULL_SHARD
true
one_in_four
-
-
2048
/scratch/project_462000229/checkpoints/4952168/latest
476837
1
swiglu
false
8
0
false
false
false
1
Finished
-
epwalsh
mosaicml-7b-v1
12m 33s
-
fine_grained
50
-
-
1
true
-
0
right
["/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-000-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-000-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-001-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-001-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-002-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-002-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-003-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-003-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-004-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-004-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-005-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-005-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-006-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-006-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-006-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-007-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-007-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-008-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-008-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-008-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-009-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-009-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-010-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-010-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-010-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-011-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-011-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-012-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-012-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-013-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-013-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-013-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-014-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-014-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-014-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-015-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-015-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-016-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-016-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-017-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-017-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-018-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-018-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-019-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-019-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-020-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-020-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-021-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-021-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-022-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-022-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-023-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-023-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-024-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-024-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-025-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-025-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-025-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-026-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-026-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-027-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-027-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-027-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-028-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-028-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-028-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-029-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-029-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-030-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-030-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-031-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-031-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-032-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-032-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-033-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-033-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-033-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-034-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-034-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-034-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-035-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-035-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-036-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-036-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-037-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-037-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-038-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-038-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-039-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-039-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-040-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-040-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-041-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-041-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-042-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-042-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-042-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-043-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-043-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-043-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-044-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-044-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-044-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-045-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-045-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-046-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-046-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-046-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-046-00003.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-047-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-047-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-048-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-048-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-049-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-049-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-050-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-050-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-051-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-051-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-052-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-052-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-052-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-053-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-053-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-053-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-054-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-054-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-055-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-055-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-055-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-056-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-056-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-056-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-057-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-057-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-057-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-058-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-058-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-059-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-059-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-060-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-060-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-061-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-061-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-062-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-062-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-062-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-063-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-063-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-063-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-064-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-064-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-064-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-065-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-065-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-065-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-066-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-066-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-067-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-067-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-068-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-068-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-069-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-069-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-070-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-070-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-071-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-071-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-072-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-072-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-073-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-073-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-074-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-074-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-075-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-075-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-076-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-076-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-077-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-077-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-078-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-078-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-079-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-079-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-080-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-080-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-081-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-081-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-082-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-082-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-083-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-083-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-084-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-084-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-085-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-085-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-086-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-086-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-087-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-087-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-088-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-088-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-089-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-089-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-089-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-090-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-090-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-091-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-091-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-091-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-092-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-092-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-093-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-093-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-093-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-094-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-094-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-094-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-095-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-095-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-096-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-096-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-097-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-097-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-097-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-098-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-098-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-099-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-099-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-100-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-100-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-100-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-101-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-101-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-102-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-102-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-103-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-103-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-104-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-104-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-105-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-105-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-106-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-106-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-106-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-107-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-107-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-108-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-108-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-109-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-109-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-109-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-110-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-110-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-110-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-111-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-111-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-112-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-112-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-113-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-113-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-114-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-114-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-114-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-115-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-115-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-116-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-116-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-117-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-117-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-118-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-118-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-119-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-119-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-120-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-120-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-120-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-121-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-121-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-122-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-122-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-122-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-123-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-123-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-123-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-124-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-124-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-125-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-125-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-126-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-126-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-127-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-127-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-127-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-128-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-128-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-129-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-129-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-129-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-130-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-130-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-131-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-131-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-132-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-132-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-133-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-133-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-133-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-134-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-134-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-134-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-135-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-135-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-135-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-136-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-136-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-137-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-137-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-137-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-138-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-138-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-139-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-139-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-140-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-140-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-141-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-141-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-141-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-142-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-142-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-142-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-143-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-143-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-144-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-144-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-144-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-145-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-145-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-145-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-146-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-146-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-146-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-147-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-147-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-147-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-148-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-148-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-149-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-149-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-149-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-150-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-150-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-150-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-150-00003.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-151-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-151-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-152-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-152-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-153-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-153-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-154-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-154-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-155-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-155-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-155-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-156-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-156-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-157-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-157-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-157-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-158-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-158-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-159-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-159-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-160-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-160-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-161-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-161-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-161-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-162-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-162-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-163-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-163-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-164-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-164-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-165-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-165-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-165-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-166-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-166-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-166-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-167-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-167-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-167-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-168-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-168-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-169-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-169-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-170-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-170-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-171-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-171-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-172-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-172-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-173-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-173-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-173-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-174-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-174-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-174-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-175-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-175-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-175-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-176-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-176-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-176-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-177-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-177-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-178-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-178-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-179-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-179-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-180-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-180-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-181-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-181-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-182-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-182-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-182-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-183-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-183-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-183-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-184-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-184-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-185-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-185-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-185-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-186-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-186-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-186-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-187-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-187-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-187-00002.npy"]
true
true
16
0
2
2
1
2
false
-
1000
false
-1
[{"type":"lm","data":{"datasets":{"wikitext_103-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/wikitext_103/val.npy"],"4chan-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/4chan/val.npy"],"ice-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/ice/val.npy"],"m2d2_s2orc-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/m2d2_s2orc/val.npy"],"m2d2_wiki-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/m2d2_wiki/val.npy"],"manosphere-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/manosphere/val.npy"],"mc4_en-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/mc4_en/val.npy"],"ptb-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/ptb/val.npy"],"twitterAEE-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/twitterAEE/val.npy"],"c4_100_domains-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/c4_100_domains/val.npy"],"c4_en-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/c4_en/val.npy"],"gab-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/gab/val.npy"],"pile-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/pile/val.npy"]},"num_workers":0,"pad_direction":"right","paths":null,"pin_memory":false,"timeout":0,"drop_last":true,"persistent_workers":false,"prefetch_factor":null},"device_eval_batch_size":null,"label":"all-small-ppl-validation","subset_num_batches":null},{"data":{"drop_last":false,"paths":null,"timeout":0,"num_workers":0,"pad_direction":"right","persistent_workers":false,"pin_memory":false,"prefetch_factor":null,"datasets":null},"device_eval_batch_size":null,"label":"piqa","subset_num_batches":null,"type":"downstream"},{"type":"downstream","data":{"drop_last":false,"num_workers":0,"pad_direction":"right","paths":null,"pin_memory":false,"prefetch_factor":null,"timeout":0,"datasets":null,"persistent_workers":false},"device_eval_batch_size":null,"label":"hellaswag","subset_num_batches":null},{"data":{"datasets":null,"drop_last":false,"num_workers":0,"pad_direction":"right","paths":null,"pin_memory":false,"prefetch_factor":null,"persistent_workers":false,"timeout":0},"device_eval_batch_size":null,"label":"winogrande","subset_num_batches":null,"type":"downstream"},{"data":{"datasets":null,"pad_direction":"right","pin_memory":false,"prefetch_factor":null,"timeout":0,"drop_last":false,"num_workers":0,"paths":null,"persistent_workers":false},"device_eval_batch_size":null,"label":"openbook_qa","subset_num_batches":null,"type":"downstream"},{"subset_num_batches":null,"type":"downstream","data":{"pad_direction":"right","paths":null,"persistent_workers":false,"prefetch_factor":null,"timeout":0,"datasets":null,"drop_last":false,"num_workers":0,"pin_memory":false},"device_eval_batch_size":null,"label":"sciq"},{"data":{"datasets":null,"paths":null,"persistent_workers":false,"pin_memory":false,"prefetch_factor":null,"drop_last":false,"num_workers":0,"pad_direction":"right","timeout":0},"device_eval_batch_size":null,"label":"arc_easy","subset_num_batches":null,"type":"downstream"},{"data":{"pin_memory":false,"num_workers":0,"pad_direction":"right","paths":null,"persistent_workers":false,"prefetch_factor":null,"timeout":0,"datasets":null,"drop_last":false},"device_eval_batch_size":null,"label":"copa","subset_num_batches":null,"type":"downstream"},{"data":{"num_workers":0,"pad_direction":"right","paths":null,"pin_memory":false,"prefetch_factor":null,"drop_last":false,"persistent_workers":false,"timeout":0,"datasets":null},"device_eval_batch_size":null,"label":"rte","subset_num_batches":null,"type":"downstream"},{"data":{"datasets":null,"num_workers":0,"pad_direction":"right","persistent_workers":false,"pin_memory":false,"timeout":0,"drop_last":false,"paths":null,"prefetch_factor":null},"device_eval_batch_size":null,"label":"commitment_bank","subset_num_batches":null,"type":"downstream"},{"type":"downstream","data":{"datasets":null,"pad_direction":"right","pin_memory":false,"timeout":0,"drop_last":false,"num_workers":0,"paths":null,"persistent_workers":false,"prefetch_factor":null},"device_eval_batch_size":null,"label":"mrpc","subset_num_batches":null},{"type":"downstream","data":{"pin_memory":false,"prefetch_factor":null,"timeout":0,"datasets":null,"drop_last":false,"num_workers":0,"pad_direction":"right","paths":null,"persistent_workers":false},"device_eval_batch_size":null,"label":"sst2","subset_num_batches":null}]
-
false
mixed
ShardingStrategy.FULL_SHARD
true
one_in_four
-
-
2048
/scratch/project_462000229/checkpoints/4952168/latest
476837
1
swiglu
false
8
0
false
false
false
1
Finished
-
epwalsh
mosaicml-7b-v1
29m 57s
-
fine_grained
50
-
-
1
true
-
0
right
["/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-000-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-000-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-001-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-001-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-002-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-002-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-003-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-003-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-004-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-004-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-005-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-005-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-006-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-006-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-006-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-007-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-007-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-008-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-008-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-008-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-009-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-009-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-010-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-010-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-010-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-011-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-011-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-012-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-012-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-013-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-013-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-013-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-014-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-014-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-014-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-015-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-015-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-016-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-016-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-017-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-017-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-018-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-018-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-019-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-019-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-020-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-020-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-021-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-021-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-022-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-022-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-023-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-023-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-024-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-024-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-025-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-025-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-025-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-026-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-026-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-027-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-027-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-027-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-028-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-028-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-028-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-029-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-029-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-030-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-030-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-031-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-031-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-032-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-032-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-033-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-033-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-033-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-034-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-034-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-034-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-035-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-035-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-036-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-036-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-037-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-037-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-038-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-038-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-039-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-039-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-040-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-040-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-041-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-041-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-042-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-042-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-042-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-043-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-043-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-043-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-044-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-044-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-044-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-045-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-045-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-046-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-046-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-046-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-046-00003.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-047-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-047-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-048-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-048-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-049-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-049-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-050-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-050-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-051-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-051-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-052-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-052-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-052-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-053-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-053-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-053-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-054-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-054-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-055-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-055-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-055-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-056-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-056-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-056-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-057-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-057-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-057-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-058-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-058-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-059-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-059-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-060-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-060-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-061-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-061-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-062-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-062-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-062-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-063-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-063-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-063-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-064-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-064-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-064-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-065-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-065-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-065-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-066-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-066-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-067-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-067-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-068-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-068-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-069-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-069-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-070-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-070-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-071-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-071-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-072-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-072-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-073-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-073-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-074-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-074-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-075-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-075-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-076-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-076-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-077-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-077-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-078-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-078-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-079-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-079-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-080-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-080-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-081-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-081-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-082-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-082-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-083-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-083-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-084-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-084-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-085-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-085-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-086-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-086-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-087-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-087-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-088-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-088-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-089-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-089-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-089-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-090-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-090-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-091-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-091-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-091-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-092-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-092-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-093-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-093-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-093-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-094-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-094-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-094-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-095-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-095-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-096-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-096-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-097-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-097-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-097-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-098-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-098-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-099-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-099-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-100-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-100-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-100-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-101-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-101-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-102-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-102-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-103-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-103-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-104-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-104-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-105-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-105-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-106-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-106-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-106-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-107-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-107-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-108-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-108-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-109-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-109-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-109-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-110-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-110-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-110-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-111-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-111-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-112-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-112-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-113-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-113-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-114-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-114-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-114-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-115-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-115-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-116-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-116-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-117-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-117-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-118-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-118-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-119-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-119-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-120-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-120-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-120-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-121-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-121-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-122-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-122-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-122-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-123-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-123-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-123-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-124-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-124-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-125-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-125-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-126-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-126-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-127-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-127-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-127-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-128-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-128-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-129-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-129-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-129-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-130-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-130-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-131-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-131-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-132-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-132-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-133-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-133-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-133-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-134-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-134-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-134-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-135-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-135-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-135-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-136-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-136-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-137-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-137-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-137-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-138-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-138-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-139-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-139-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-140-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-140-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-141-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-141-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-141-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-142-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-142-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-142-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-143-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-143-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-144-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-144-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-144-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-145-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-145-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-145-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-146-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-146-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-146-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-147-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-147-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-147-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-148-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-148-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-149-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-149-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-149-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-150-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-150-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-150-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-150-00003.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-151-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-151-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-152-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-152-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-153-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-153-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-154-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-154-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-155-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-155-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-155-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-156-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-156-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-157-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-157-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-157-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-158-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-158-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-159-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-159-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-160-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-160-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-161-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-161-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-161-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-162-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-162-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-163-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-163-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-164-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-164-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-165-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-165-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-165-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-166-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-166-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-166-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-167-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-167-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-167-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-168-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-168-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-169-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-169-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-170-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-170-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-171-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-171-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-172-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-172-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-173-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-173-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-173-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-174-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-174-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-174-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-175-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-175-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-175-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-176-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-176-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-176-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-177-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-177-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-178-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-178-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-179-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-179-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-180-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-180-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-181-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-181-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-182-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-182-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-182-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-183-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-183-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-183-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-184-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-184-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-185-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-185-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-185-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-186-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-186-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-186-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-187-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-187-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-187-00002.npy"]
true
true
16
0
2
2
1
2
false
-
1000
false
-1
[{"data":{"prefetch_factor":null,"timeout":0,"datasets":{"4chan-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/4chan/val.npy"],"c4_100_domains-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/c4_100_domains/val.npy"],"c4_en-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/c4_en/val.npy"],"gab-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/gab/val.npy"],"manosphere-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/manosphere/val.npy"],"ptb-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/ptb/val.npy"],"twitterAEE-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/twitterAEE/val.npy"],"ice-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/ice/val.npy"],"m2d2_s2orc-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/m2d2_s2orc/val.npy"],"m2d2_wiki-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/m2d2_wiki/val.npy"],"mc4_en-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/mc4_en/val.npy"],"pile-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/pile/val.npy"],"wikitext_103-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/wikitext_103/val.npy"]},"num_workers":0,"pad_direction":"right","paths":null,"pin_memory":false,"drop_last":true,"persistent_workers":false},"device_eval_batch_size":null,"label":"all-small-ppl-validation","subset_num_batches":null,"type":"lm"},{"data":{"pin_memory":false,"paths":null,"prefetch_factor":null,"timeout":0,"datasets":null,"drop_last":false,"num_workers":0,"pad_direction":"right","persistent_workers":false},"device_eval_batch_size":null,"label":"piqa","subset_num_batches":null,"type":"downstream"},{"device_eval_batch_size":null,"label":"hellaswag","subset_num_batches":null,"type":"downstream","data":{"persistent_workers":false,"pin_memory":false,"timeout":0,"drop_last":false,"num_workers":0,"pad_direction":"right","prefetch_factor":null,"datasets":null,"paths":null}},{"data":{"pin_memory":false,"prefetch_factor":null,"datasets":null,"pad_direction":"right","persistent_workers":false,"timeout":0,"drop_last":false,"num_workers":0,"paths":null},"device_eval_batch_size":null,"label":"winogrande","subset_num_batches":null,"type":"downstream"},{"label":"openbook_qa","subset_num_batches":null,"type":"downstream","data":{"pad_direction":"right","persistent_workers":false,"prefetch_factor":null,"datasets":null,"num_workers":0,"paths":null,"pin_memory":false,"timeout":0,"drop_last":false},"device_eval_batch_size":null},{"data":{"paths":null,"persistent_workers":false,"pin_memory":false,"prefetch_factor":null,"timeout":0,"datasets":null,"drop_last":false,"num_workers":0,"pad_direction":"right"},"device_eval_batch_size":null,"label":"sciq","subset_num_batches":null,"type":"downstream"},{"subset_num_batches":null,"type":"downstream","data":{"drop_last":false,"pad_direction":"right","persistent_workers":false,"pin_memory":false,"prefetch_factor":null,"timeout":0,"datasets":null,"num_workers":0,"paths":null},"device_eval_batch_size":null,"label":"arc_easy"},{"data":{"datasets":null,"pad_direction":"right","paths":null,"timeout":0,"drop_last":false,"num_workers":0,"persistent_workers":false,"pin_memory":false,"prefetch_factor":null},"device_eval_batch_size":null,"label":"copa","subset_num_batches":null,"type":"downstream"},{"type":"downstream","data":{"datasets":null,"num_workers":0,"pad_direction":"right","persistent_workers":false,"prefetch_factor":null,"drop_last":false,"paths":null,"pin_memory":false,"timeout":0},"device_eval_batch_size":null,"label":"rte","subset_num_batches":null},{"data":{"drop_last":false,"pad_direction":"right","paths":null,"pin_memory":false,"prefetch_factor":null,"datasets":null,"num_workers":0,"persistent_workers":false,"timeout":0},"device_eval_batch_size":null,"label":"commitment_bank","subset_num_batches":null,"type":"downstream"},{"data":{"pad_direction":"right","paths":null,"pin_memory":false,"prefetch_factor":null,"drop_last":false,"num_workers":0,"persistent_workers":false,"timeout":0,"datasets":null},"device_eval_batch_size":null,"label":"mrpc","subset_num_batches":null,"type":"downstream"},{"data":{"datasets":null,"num_workers":0,"paths":null,"pin_memory":false,"drop_last":false,"pad_direction":"right","persistent_workers":false,"prefetch_factor":null,"timeout":0},"device_eval_batch_size":null,"label":"sst2","subset_num_batches":null,"type":"downstream"}]
-
false
mixed
ShardingStrategy.FULL_SHARD
true
one_in_four
-
-
2048
/scratch/project_462000229/checkpoints/4934066/latest
476837
1
swiglu
false
8
0
false
false
false
1
Finished
-
epwalsh
mosaicml-7b-v1
8m 51s
-
fine_grained
50
-
-
1
true
-
0
right
["/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-000-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-000-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-001-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-001-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-002-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-002-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-003-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-003-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-004-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-004-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-005-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-005-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-006-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-006-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-006-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-007-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-007-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-008-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-008-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-008-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-009-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-009-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-010-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-010-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-010-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-011-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-011-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-012-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-012-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-013-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-013-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-013-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-014-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-014-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-014-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-015-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-015-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-016-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-016-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-017-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-017-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-018-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-018-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-019-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-019-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-020-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-020-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-021-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-021-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-022-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-022-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-023-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-023-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-024-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-024-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-025-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-025-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-025-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-026-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-026-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-027-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-027-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-027-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-028-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-028-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-028-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-029-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-029-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-030-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-030-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-031-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-031-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-032-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-032-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-033-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-033-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-033-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-034-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-034-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-034-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-035-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-035-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-036-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-036-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-037-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-037-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-038-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-038-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-039-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-039-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-040-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-040-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-041-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-041-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-042-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-042-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-042-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-043-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-043-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-043-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-044-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-044-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-044-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-045-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-045-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-046-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-046-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-046-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-046-00003.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-047-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-047-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-048-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-048-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-049-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-049-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-050-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-050-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-051-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-051-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-052-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-052-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-052-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-053-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-053-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-053-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-054-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-054-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-055-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-055-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-055-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-056-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-056-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-056-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-057-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-057-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-057-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-058-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-058-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-059-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-059-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-060-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-060-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-061-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-061-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-062-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-062-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-062-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-063-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-063-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-063-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-064-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-064-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-064-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-065-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-065-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-065-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-066-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-066-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-067-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-067-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-068-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-068-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-069-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-069-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-070-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-070-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-071-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-071-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-072-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-072-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-073-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-073-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-074-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-074-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-075-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-075-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-076-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-076-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-077-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-077-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-078-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-078-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-079-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-079-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-080-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-080-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-081-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-081-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-082-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-082-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-083-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-083-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-084-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-084-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-085-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-085-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-086-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-086-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-087-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-087-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-088-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-088-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-089-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-089-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-089-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-090-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-090-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-091-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-091-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-091-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-092-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-092-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-093-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-093-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-093-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-094-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-094-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-094-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-095-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-095-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-096-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-096-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-097-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-097-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-097-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-098-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-098-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-099-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-099-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-100-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-100-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-100-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-101-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-101-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-102-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-102-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-103-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-103-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-104-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-104-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-105-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-105-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-106-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-106-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-106-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-107-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-107-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-108-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-108-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-109-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-109-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-109-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-110-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-110-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-110-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-111-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-111-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-112-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-112-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-113-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-113-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-114-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-114-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-114-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-115-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-115-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-116-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-116-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-117-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-117-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-118-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-118-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-119-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-119-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-120-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-120-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-120-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-121-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-121-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-122-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-122-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-122-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-123-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-123-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-123-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-124-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-124-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-125-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-125-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-126-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-126-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-127-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-127-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-127-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-128-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-128-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-129-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-129-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-129-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-130-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-130-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-131-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-131-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-132-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-132-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-133-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-133-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-133-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-134-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-134-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-134-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-135-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-135-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-135-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-136-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-136-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-137-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-137-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-137-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-138-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-138-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-139-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-139-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-140-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-140-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-141-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-141-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-141-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-142-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-142-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-142-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-143-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-143-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-144-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-144-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-144-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-145-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-145-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-145-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-146-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-146-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-146-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-147-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-147-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-147-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-148-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-148-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-149-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-149-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-149-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-150-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-150-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-150-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-150-00003.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-151-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-151-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-152-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-152-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-153-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-153-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-154-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-154-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-155-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-155-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-155-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-156-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-156-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-157-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-157-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-157-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-158-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-158-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-159-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-159-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-160-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-160-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-161-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-161-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-161-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-162-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-162-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-163-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-163-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-164-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-164-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-165-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-165-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-165-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-166-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-166-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-166-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-167-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-167-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-167-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-168-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-168-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-169-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-169-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-170-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-170-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-171-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-171-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-172-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-172-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-173-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-173-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-173-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-174-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-174-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-174-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-175-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-175-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-175-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-176-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-176-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-176-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-177-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-177-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-178-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-178-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-179-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-179-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-180-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-180-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-181-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-181-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-182-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-182-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-182-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-183-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-183-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-183-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-184-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-184-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-185-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-185-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-185-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-186-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-186-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-186-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-187-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-187-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-187-00002.npy"]
true
true
16
0
2
2
1
2
false
-
1000
false
-1
[{"data":{"datasets":{"mc4_en-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/mc4_en/val.npy"],"pile-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/pile/val.npy"],"wikitext_103-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/wikitext_103/val.npy"],"4chan-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/4chan/val.npy"],"c4_100_domains-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/c4_100_domains/val.npy"],"ice-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/ice/val.npy"],"m2d2_wiki-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/m2d2_wiki/val.npy"],"ptb-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/ptb/val.npy"],"twitterAEE-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/twitterAEE/val.npy"],"c4_en-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/c4_en/val.npy"],"gab-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/gab/val.npy"],"m2d2_s2orc-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/m2d2_s2orc/val.npy"],"manosphere-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/manosphere/val.npy"]},"pad_direction":"right","paths":null,"persistent_workers":false,"pin_memory":false,"timeout":0,"drop_last":true,"num_workers":0,"prefetch_factor":null},"device_eval_batch_size":null,"label":"all-small-ppl-validation","subset_num_batches":null,"type":"lm"},{"label":"piqa","subset_num_batches":null,"type":"downstream","data":{"num_workers":0,"pad_direction":"right","timeout":0,"datasets":null,"paths":null,"persistent_workers":false,"pin_memory":false,"prefetch_factor":null,"drop_last":false},"device_eval_batch_size":null},{"data":{"persistent_workers":false,"prefetch_factor":null,"timeout":0,"pad_direction":"right","pin_memory":false,"datasets":null,"drop_last":false,"num_workers":0,"paths":null},"device_eval_batch_size":null,"label":"hellaswag","subset_num_batches":null,"type":"downstream"},{"label":"winogrande","subset_num_batches":null,"type":"downstream","data":{"num_workers":0,"pad_direction":"right","persistent_workers":false,"datasets":null,"paths":null,"pin_memory":false,"prefetch_factor":null,"timeout":0,"drop_last":false},"device_eval_batch_size":null},{"label":"openbook_qa","subset_num_batches":null,"type":"downstream","data":{"datasets":null,"drop_last":false,"num_workers":0,"pad_direction":"right","pin_memory":false,"timeout":0,"paths":null,"persistent_workers":false,"prefetch_factor":null},"device_eval_batch_size":null},{"device_eval_batch_size":null,"label":"sciq","subset_num_batches":null,"type":"downstream","data":{"datasets":null,"drop_last":false,"pin_memory":false,"num_workers":0,"pad_direction":"right","paths":null,"persistent_workers":false,"prefetch_factor":null,"timeout":0}},{"label":"arc_easy","subset_num_batches":null,"type":"downstream","data":{"num_workers":0,"pad_direction":"right","paths":null,"prefetch_factor":null,"timeout":0,"persistent_workers":false,"pin_memory":false,"datasets":null,"drop_last":false},"device_eval_batch_size":null},{"subset_num_batches":null,"type":"downstream","data":{"num_workers":0,"pin_memory":false,"prefetch_factor":null,"timeout":0,"datasets":null,"drop_last":false,"pad_direction":"right","paths":null,"persistent_workers":false},"device_eval_batch_size":null,"label":"copa"},{"label":"rte","subset_num_batches":null,"type":"downstream","data":{"datasets":null,"num_workers":0,"pad_direction":"right","paths":null,"persistent_workers":false,"pin_memory":false,"timeout":0,"drop_last":false,"prefetch_factor":null},"device_eval_batch_size":null},{"label":"commitment_bank","subset_num_batches":null,"type":"downstream","data":{"persistent_workers":false,"prefetch_factor":null,"num_workers":0,"pin_memory":false,"timeout":0,"datasets":null,"drop_last":false,"pad_direction":"right","paths":null},"device_eval_batch_size":null},{"label":"mrpc","subset_num_batches":null,"type":"downstream","data":{"paths":null,"pin_memory":false,"datasets":null,"persistent_workers":false,"prefetch_factor":null,"timeout":0,"drop_last":false,"num_workers":0,"pad_direction":"right"},"device_eval_batch_size":null},{"device_eval_batch_size":null,"label":"sst2","subset_num_batches":null,"type":"downstream","data":{"num_workers":0,"pad_direction":"right","paths":null,"persistent_workers":false,"prefetch_factor":null,"timeout":0,"pin_memory":false,"datasets":null,"drop_last":false}}]
-
false
mixed
ShardingStrategy.FULL_SHARD
true
one_in_four
-
-
2048
/scratch/project_462000229/checkpoints/4909260/latest
476837
1
swiglu
false
8
0
false
false
false
1
Finished
-
epwalsh
mosaicml-7b-v1
25m 22s
-
fine_grained
50
-
-
1
true
-
0
right
["/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-000-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-000-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-001-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-001-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-002-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-002-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-003-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-003-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-004-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-004-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-005-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-005-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-006-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-006-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-006-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-007-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-007-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-008-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-008-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-008-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-009-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-009-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-010-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-010-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-010-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-011-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-011-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-012-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-012-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-013-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-013-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-013-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-014-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-014-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-014-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-015-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-015-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-016-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-016-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-017-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-017-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-018-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-018-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-019-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-019-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-020-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-020-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-021-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-021-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-022-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-022-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-023-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-023-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-024-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-024-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-025-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-025-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-025-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-026-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-026-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-027-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-027-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-027-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-028-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-028-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-028-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-029-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-029-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-030-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-030-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-031-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-031-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-032-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-032-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-033-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-033-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-033-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-034-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-034-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-034-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-035-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-035-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-036-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-036-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-037-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-037-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-038-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-038-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-039-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-039-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-040-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-040-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-041-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-041-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-042-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-042-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-042-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-043-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-043-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-043-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-044-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-044-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-044-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-045-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-045-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-046-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-046-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-046-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-046-00003.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-047-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-047-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-048-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-048-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-049-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-049-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-050-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-050-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-051-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-051-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-052-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-052-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-052-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-053-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-053-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-053-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-054-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-054-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-055-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-055-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-055-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-056-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-056-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-056-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-057-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-057-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-057-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-058-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-058-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-059-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-059-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-060-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-060-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-061-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-061-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-062-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-062-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-062-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-063-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-063-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-063-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-064-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-064-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-064-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-065-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-065-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-065-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-066-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-066-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-067-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-067-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-068-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-068-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-069-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-069-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-070-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-070-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-071-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-071-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-072-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-072-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-073-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-073-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-074-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-074-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-075-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-075-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-076-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-076-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-077-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-077-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-078-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-078-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-079-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-079-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-080-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-080-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-081-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-081-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-082-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-082-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-083-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-083-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-084-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-084-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-085-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-085-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-086-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-086-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-087-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-087-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-088-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-088-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-089-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-089-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-089-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-090-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-090-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-091-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-091-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-091-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-092-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-092-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-093-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-093-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-093-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-094-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-094-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-094-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-095-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-095-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-096-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-096-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-097-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-097-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-097-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-098-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-098-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-099-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-099-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-100-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-100-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-100-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-101-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-101-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-102-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-102-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-103-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-103-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-104-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-104-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-105-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-105-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-106-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-106-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-106-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-107-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-107-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-108-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-108-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-109-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-109-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-109-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-110-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-110-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-110-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-111-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-111-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-112-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-112-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-113-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-113-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-114-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-114-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-114-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-115-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-115-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-116-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-116-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-117-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-117-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-118-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-118-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-119-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-119-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-120-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-120-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-120-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-121-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-121-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-122-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-122-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-122-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-123-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-123-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-123-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-124-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-124-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-125-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-125-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-126-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-126-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-127-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-127-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-127-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-128-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-128-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-129-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-129-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-129-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-130-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-130-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-131-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-131-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-132-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-132-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-133-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-133-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-133-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-134-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-134-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-134-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-135-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-135-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-135-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-136-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-136-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-137-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-137-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-137-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-138-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-138-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-139-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-139-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-140-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-140-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-141-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-141-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-141-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-142-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-142-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-142-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-143-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-143-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-144-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-144-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-144-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-145-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-145-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-145-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-146-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-146-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-146-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-147-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-147-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-147-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-148-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-148-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-149-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-149-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-149-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-150-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-150-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-150-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-150-00003.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-151-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-151-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-152-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-152-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-153-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-153-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-154-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-154-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-155-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-155-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-155-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-156-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-156-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-157-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-157-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-157-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-158-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-158-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-159-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-159-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-160-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-160-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-161-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-161-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-161-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-162-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-162-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-163-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-163-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-164-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-164-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-165-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-165-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-165-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-166-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-166-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-166-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-167-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-167-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-167-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-168-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-168-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-169-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-169-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-170-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-170-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-171-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-171-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-172-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-172-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-173-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-173-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-173-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-174-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-174-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-174-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-175-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-175-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-175-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-176-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-176-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-176-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-177-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-177-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-178-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-178-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-179-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-179-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-180-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-180-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-181-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-181-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-182-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-182-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-182-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-183-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-183-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-183-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-184-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-184-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-185-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-185-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-185-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-186-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-186-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-186-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-187-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-187-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-187-00002.npy"]
true
true
16
0
2
2
1
2
false
-
1000
false
-1
[{"data":{"persistent_workers":false,"prefetch_factor":null,"datasets":{"ice-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/ice/val.npy"],"pile-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/pile/val.npy"],"ptb-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/ptb/val.npy"],"twitterAEE-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/twitterAEE/val.npy"],"4chan-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/4chan/val.npy"],"m2d2_s2orc-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/m2d2_s2orc/val.npy"],"m2d2_wiki-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/m2d2_wiki/val.npy"],"manosphere-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/manosphere/val.npy"],"mc4_en-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/mc4_en/val.npy"],"wikitext_103-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/wikitext_103/val.npy"],"c4_100_domains-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/c4_100_domains/val.npy"],"c4_en-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/c4_en/val.npy"],"gab-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/gab/val.npy"]},"pad_direction":"right","paths":null,"pin_memory":false,"timeout":0,"drop_last":true,"num_workers":0},"device_eval_batch_size":null,"label":"all-small-ppl-validation","subset_num_batches":null,"type":"lm"},{"subset_num_batches":null,"type":"downstream","data":{"timeout":0,"datasets":null,"drop_last":false,"num_workers":0,"pad_direction":"right","persistent_workers":false,"paths":null,"pin_memory":false,"prefetch_factor":null},"device_eval_batch_size":null,"label":"piqa"},{"data":{"persistent_workers":false,"prefetch_factor":null,"timeout":0,"datasets":null,"drop_last":false,"pad_direction":"right","pin_memory":false,"num_workers":0,"paths":null},"device_eval_batch_size":null,"label":"hellaswag","subset_num_batches":null,"type":"downstream"},{"data":{"pin_memory":false,"datasets":null,"drop_last":false,"persistent_workers":false,"prefetch_factor":null,"timeout":0,"num_workers":0,"pad_direction":"right","paths":null},"device_eval_batch_size":null,"label":"winogrande","subset_num_batches":null,"type":"downstream"},{"type":"downstream","data":{"persistent_workers":false,"pin_memory":false,"prefetch_factor":null,"timeout":0,"pad_direction":"right","paths":null,"datasets":null,"drop_last":false,"num_workers":0},"device_eval_batch_size":null,"label":"openbook_qa","subset_num_batches":null},{"type":"downstream","data":{"pad_direction":"right","persistent_workers":false,"pin_memory":false,"prefetch_factor":null,"timeout":0,"num_workers":0,"paths":null,"datasets":null,"drop_last":false},"device_eval_batch_size":null,"label":"sciq","subset_num_batches":null},{"data":{"drop_last":false,"pad_direction":"right","persistent_workers":false,"prefetch_factor":null,"num_workers":0,"paths":null,"pin_memory":false,"timeout":0,"datasets":null},"device_eval_batch_size":null,"label":"arc_easy","subset_num_batches":null,"type":"downstream"},{"data":{"datasets":null,"drop_last":false,"persistent_workers":false,"pin_memory":false,"timeout":0,"num_workers":0,"pad_direction":"right","paths":null,"prefetch_factor":null},"device_eval_batch_size":null,"label":"copa","subset_num_batches":null,"type":"downstream"},{"type":"downstream","data":{"datasets":null,"drop_last":false,"num_workers":0,"pad_direction":"right","paths":null,"persistent_workers":false,"pin_memory":false,"prefetch_factor":null,"timeout":0},"device_eval_batch_size":null,"label":"rte","subset_num_batches":null},{"device_eval_batch_size":null,"label":"commitment_bank","subset_num_batches":null,"type":"downstream","data":{"persistent_workers":false,"datasets":null,"paths":null,"pin_memory":false,"prefetch_factor":null,"timeout":0,"drop_last":false,"num_workers":0,"pad_direction":"right"}},{"data":{"drop_last":false,"pad_direction":"right","paths":null,"datasets":null,"num_workers":0,"persistent_workers":false,"pin_memory":false,"prefetch_factor":null,"timeout":0},"device_eval_batch_size":null,"label":"mrpc","subset_num_batches":null,"type":"downstream"},{"device_eval_batch_size":null,"label":"sst2","subset_num_batches":null,"type":"downstream","data":{"datasets":null,"paths":null,"timeout":0,"drop_last":false,"num_workers":0,"pad_direction":"right","persistent_workers":false,"pin_memory":false,"prefetch_factor":null}}]
-
false
mixed
ShardingStrategy.FULL_SHARD
true
one_in_four
-
-
2048
/scratch/project_462000229/checkpoints/4896746/latest
476837
1
swiglu
false
8
0
false
false
false
1
Finished
-
epwalsh
mosaicml-7b-v1
24m 37s
-
fine_grained
50
-
-
1
true
-
0
right
["/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-000-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-000-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-001-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-001-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-002-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-002-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-003-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-003-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-004-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-004-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-005-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-005-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-006-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-006-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-006-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-007-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-007-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-008-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-008-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-008-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-009-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-009-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-010-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-010-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-010-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-011-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-011-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-012-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-012-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-013-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-013-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-013-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-014-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-014-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-014-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-015-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-015-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-016-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-016-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-017-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-017-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-018-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-018-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-019-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-019-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-020-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-020-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-021-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-021-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-022-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-022-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-023-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-023-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-024-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-024-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-025-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-025-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-025-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-026-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-026-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-027-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-027-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-027-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-028-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-028-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-028-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-029-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-029-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-030-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-030-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-031-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-031-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-032-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-032-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-033-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-033-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-033-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-034-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-034-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-034-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-035-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-035-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-036-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-036-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-037-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-037-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-038-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-038-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-039-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-039-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-040-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-040-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-041-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-041-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-042-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-042-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-042-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-043-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-043-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-043-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-044-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-044-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-044-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-045-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-045-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-046-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-046-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-046-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-046-00003.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-047-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-047-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-048-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-048-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-049-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-049-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-050-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-050-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-051-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-051-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-052-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-052-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-052-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-053-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-053-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-053-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-054-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-054-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-055-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-055-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-055-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-056-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-056-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-056-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-057-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-057-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-057-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-058-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-058-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-059-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-059-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-060-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-060-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-061-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-061-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-062-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-062-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-062-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-063-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-063-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-063-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-064-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-064-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-064-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-065-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-065-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-065-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-066-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-066-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-067-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-067-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-068-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-068-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-069-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-069-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-070-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-070-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-071-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-071-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-072-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-072-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-073-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-073-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-074-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-074-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-075-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-075-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-076-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-076-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-077-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-077-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-078-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-078-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-079-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-079-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-080-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-080-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-081-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-081-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-082-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-082-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-083-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-083-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-084-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-084-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-085-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-085-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-086-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-086-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-087-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-087-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-088-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-088-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-089-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-089-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-089-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-090-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-090-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-091-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-091-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-091-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-092-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-092-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-093-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-093-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-093-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-094-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-094-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-094-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-095-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-095-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-096-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-096-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-097-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-097-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-097-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-098-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-098-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-099-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-099-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-100-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-100-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-100-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-101-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-101-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-102-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-102-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-103-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-103-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-104-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-104-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-105-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-105-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-106-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-106-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-106-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-107-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-107-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-108-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-108-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-109-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-109-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-109-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-110-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-110-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-110-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-111-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-111-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-112-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-112-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-113-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-113-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-114-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-114-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-114-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-115-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-115-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-116-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-116-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-117-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-117-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-118-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-118-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-119-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-119-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-120-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-120-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-120-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-121-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-121-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-122-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-122-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-122-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-123-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-123-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-123-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-124-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-124-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-125-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-125-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-126-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-126-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-127-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-127-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-127-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-128-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-128-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-129-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-129-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-129-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-130-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-130-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-131-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-131-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-132-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-132-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-133-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-133-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-133-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-134-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-134-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-134-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-135-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-135-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-135-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-136-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-136-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-137-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-137-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-137-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-138-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-138-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-139-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-139-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-140-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-140-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-141-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-141-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-141-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-142-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-142-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-142-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-143-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-143-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-144-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-144-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-144-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-145-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-145-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-145-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-146-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-146-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-146-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-147-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-147-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-147-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-148-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-148-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-149-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-149-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-149-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-150-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-150-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-150-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-150-00003.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-151-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-151-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-152-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-152-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-153-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-153-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-154-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-154-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-155-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-155-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-155-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-156-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-156-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-157-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-157-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-157-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-158-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-158-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-159-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-159-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-160-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-160-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-161-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-161-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-161-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-162-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-162-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-163-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-163-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-164-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-164-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-165-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-165-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-165-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-166-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-166-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-166-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-167-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-167-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-167-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-168-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-168-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-169-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-169-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-170-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-170-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-171-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-171-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-172-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-172-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-173-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-173-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-173-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-174-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-174-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-174-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-175-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-175-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-175-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-176-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-176-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-176-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-177-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-177-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-178-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-178-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-179-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-179-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-180-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-180-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-181-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-181-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-182-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-182-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-182-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-183-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-183-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-183-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-184-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-184-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-185-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-185-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-185-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-186-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-186-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-186-00002.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-187-00000.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-187-00001.npy","/pfs/lustref1/flash/project_462000229/preprocessed/olmo-mix/v1_5-sample/gpt-neox-20b-pii-special/part-187-00002.npy"]
true
true
16
0
2
2
1
2
false
-
1000
false
-1
[{"data":{"drop_last":true,"pad_direction":"right","paths":null,"pin_memory":false,"timeout":0,"datasets":{"pile-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/pile/val.npy"],"c4_en-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/c4_en/val.npy"],"m2d2_wiki-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/m2d2_wiki/val.npy"],"manosphere-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/manosphere/val.npy"],"ptb-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/ptb/val.npy"],"twitterAEE-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/twitterAEE/val.npy"],"wikitext_103-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/wikitext_103/val.npy"],"4chan-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/4chan/val.npy"],"c4_100_domains-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/c4_100_domains/val.npy"],"gab-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/gab/val.npy"],"ice-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/ice/val.npy"],"m2d2_s2orc-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/m2d2_s2orc/val.npy"],"mc4_en-validation":["/scratch/project_462000229/eval-data/perplexity/v2_small_gptneox20b/mc4_en/val.npy"]},"num_workers":0,"persistent_workers":false,"prefetch_factor":null},"device_eval_batch_size":null,"label":"all-small-ppl-validation","subset_num_batches":null,"type":"lm"},{"device_eval_batch_size":null,"label":"piqa","subset_num_batches":null,"type":"downstream","data":{"datasets":null,"pad_direction":"right","paths":null,"prefetch_factor":null,"drop_last":false,"num_workers":0,"persistent_workers":false,"pin_memory":false,"timeout":0}},{"data":{"timeout":0,"datasets":null,"paths":null,"persistent_workers":false,"pin_memory":false,"drop_last":false,"num_workers":0,"pad_direction":"right","prefetch_factor":null},"device_eval_batch_size":null,"label":"hellaswag","subset_num_batches":null,"type":"downstream"},{"subset_num_batches":null,"type":"downstream","data":{"pin_memory":false,"prefetch_factor":null,"timeout":0,"datasets":null,"drop_last":false,"num_workers":0,"pad_direction":"right","persistent_workers":false,"paths":null},"device_eval_batch_size":null,"label":"winogrande"},{"type":"downstream","data":{"pad_direction":"right","paths":null,"pin_memory":false,"prefetch_factor":null,"timeout":0,"datasets":null,"drop_last":false,"num_workers":0,"persistent_workers":false},"device_eval_batch_size":null,"label":"openbook_qa","subset_num_batches":null},{"data":{"prefetch_factor":null,"timeout":0,"drop_last":false,"num_workers":0,"paths":null,"pin_memory":false,"datasets":null,"pad_direction":"right","persistent_workers":false},"device_eval_batch_size":null,"label":"sciq","subset_num_batches":null,"type":"downstream"},{"data":{"pin_memory":false,"timeout":0,"num_workers":0,"pad_direction":"right","paths":null,"persistent_workers":false,"prefetch_factor":null,"datasets":null,"drop_last":false},"device_eval_batch_size":null,"label":"arc_easy","subset_num_batches":null,"type":"downstream"},{"data":{"drop_last":false,"num_workers":0,"persistent_workers":false,"datasets":null,"pad_direction":"right","paths":null,"pin_memory":false,"prefetch_factor":null,"timeout":0},"device_eval_batch_size":null,"label":"copa","subset_num_batches":null,"type":"downstream"},{"data":{"drop_last":false,"pad_direction":"right","paths":null,"persistent_workers":false,"prefetch_factor":null,"timeout":0,"datasets":null,"num_workers":0,"pin_memory":false},"device_eval_batch_size":null,"label":"rte","subset_num_batches":null,"type":"downstream"},{"label":"commitment_bank","subset_num_batches":null,"type":"downstream","data":{"datasets":null,"drop_last":false,"pad_direction":"right","persistent_workers":false,"pin_memory":false,"num_workers":0,"paths":null,"prefetch_factor":null,"timeout":0},"device_eval_batch_size":null},{"subset_num_batches":null,"type":"downstream","data":{"paths":null,"prefetch_factor":null,"datasets":null,"num_workers":0,"pad_direction":"right","persistent_workers":false,"pin_memory":false,"timeout":0,"drop_last":false},"device_eval_batch_size":null,"label":"mrpc"},{"label":"sst2","subset_num_batches":null,"type":"downstream","data":{"drop_last":false,"num_workers":0,"paths":null,"persistent_workers":false,"prefetch_factor":null,"datasets":null,"pad_direction":"right","pin_memory":false,"timeout":0},"device_eval_batch_size":null}]
-
false
mixed
ShardingStrategy.FULL_SHARD
true
one_in_four
-
-
2048
/pfs/lustref1/flash/project_462000229/checkpoints/4886437/latest
476837
1
swiglu
false
8
0
false
false
false
1
1-20
of 24