Igoro's group workspace
Group: 20B_pretrain
Name
144 visualized
State
Notes
User
Tags
Created
Runtime
Sweep
activation
adlr_autoresume
adlr_autoresume_interval
apply_query_key_layer_scaling
attention-dropout
attention_config
attention_dropout
attention_softmax_in_fp32
batch_size
bias-gelu-fusion
bias_dropout_fusion
bias_gelu_fusion
char_level_ppl
checkpoint-activations
checkpoint-num-layers
checkpoint_activations
checkpoint_factor
checkpoint_in_cpu
checkpoint_num_layers
checkpoint_scale
checkpoint_validation_with_forward_pass
clip_grad
config_files.20B.yml
config_files.20B_P3.yml
config_files.20B_code.yml
config_files.20B_fork.yml
config_files.20B_math.yml
config_files.test20B.yml
contiguous_checkpointing
coord_check
curriculum_seqlen
data-impl
data-path
data_impl
data_path
deepscale
deepspeed
deepspeed_activation_checkpointing
deepspeed_mpi
deepspeed_slurm
detect_nvlink_pairs
distributed-backend
distributed_backend
dump_state
Finished
-
stellaathena
main
9d 10h 10m 31s
-
gelu
false
1000
false
-
["global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global"]
0
false
4
-
false
true
false
-
-
true
-
false
1
-
false
1
-
-
-
-
-
-
false
-
-
-
-
mmap
/mnt/ssd-1/data/pile_20B_tokenizer/pile_20B_tokenizer_text_document
false
true
true
false
-
false
-
nccl
false
Finished
-
stellaathena
main
9d 10h 10m 30s
-
gelu
false
1000
false
-
["global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global"]
0
false
4
-
false
true
false
-
-
true
-
false
1
-
false
1
-
-
-
-
-
-
false
-
-
-
-
mmap
/mnt/ssd-1/data/pile_20B_tokenizer/pile_20B_tokenizer_text_document
false
true
true
false
-
false
-
nccl
false
Finished
-
stellaathena
main
9d 10h 10m 30s
-
gelu
false
1000
false
-
["global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global"]
0
false
4
-
false
true
false
-
-
true
-
false
1
-
false
1
-
-
-
-
-
-
false
-
-
-
-
mmap
/mnt/ssd-1/data/pile_20B_tokenizer/pile_20B_tokenizer_text_document
false
true
true
false
-
false
-
nccl
false
Finished
-
stellaathena
main
9d 10h 10m 30s
-
gelu
false
1000
false
-
["global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global"]
0
false
4
-
false
true
false
-
-
true
-
false
1
-
false
1
-
-
-
-
-
-
false
-
-
-
-
mmap
/mnt/ssd-1/data/pile_20B_tokenizer/pile_20B_tokenizer_text_document
false
true
true
false
-
false
-
nccl
false
Finished
-
stellaathena
main
9d 10h 10m 31s
-
gelu
false
1000
false
-
["global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global"]
0
false
4
-
false
true
false
-
-
true
-
false
1
-
false
1
-
-
-
-
-
-
false
-
-
-
-
mmap
/mnt/ssd-1/data/pile_20B_tokenizer/pile_20B_tokenizer_text_document
false
true
true
false
-
false
-
nccl
false
Finished
-
stellaathena
main
9d 10h 10m 31s
-
gelu
false
1000
false
-
["global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global"]
0
false
4
-
false
true
false
-
-
true
-
false
1
-
false
1
-
-
-
-
-
-
false
-
-
-
-
mmap
/mnt/ssd-1/data/pile_20B_tokenizer/pile_20B_tokenizer_text_document
false
true
true
false
-
false
-
nccl
false
Finished
-
stellaathena
main
9d 10h 10m 30s
-
gelu
false
1000
false
-
["global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global"]
0
false
4
-
false
true
false
-
-
true
-
false
1
-
false
1
-
-
-
-
-
-
false
-
-
-
-
mmap
/mnt/ssd-1/data/pile_20B_tokenizer/pile_20B_tokenizer_text_document
false
true
true
false
-
false
-
nccl
false
Finished
-
stellaathena
main
9d 10h 10m 31s
-
gelu
false
1000
false
-
["global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global"]
0
false
4
-
false
true
false
-
-
true
-
false
1
-
false
1
-
-
-
-
-
-
false
-
-
-
-
mmap
/mnt/ssd-1/data/pile_20B_tokenizer/pile_20B_tokenizer_text_document
false
true
true
false
-
false
-
nccl
false
Finished
-
stellaathena
main
9d 10h 10m 30s
-
gelu
false
1000
false
-
["global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global"]
0
false
4
-
false
true
false
-
-
true
-
false
1
-
false
1
-
-
-
-
-
-
false
-
-
-
-
mmap
/mnt/ssd-1/data/pile_20B_tokenizer/pile_20B_tokenizer_text_document
false
true
true
false
-
false
-
nccl
false
Finished
-
stellaathena
main
9d 10h 10m 31s
-
gelu
false
1000
false
-
["global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global"]
0
false
4
-
false
true
false
-
-
true
-
false
1
-
false
1
-
-
-
-
-
-
false
-
-
-
-
mmap
/mnt/ssd-1/data/pile_20B_tokenizer/pile_20B_tokenizer_text_document
false
true
true
false
-
false
-
nccl
false
Finished
-
stellaathena
main
9d 10h 10m 30s
-
gelu
false
1000
false
-
["global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global"]
0
false
4
-
false
true
false
-
-
true
-
false
1
-
false
1
-
-
-
-
-
-
false
-
-
-
-
mmap
/mnt/ssd-1/data/pile_20B_tokenizer/pile_20B_tokenizer_text_document
false
true
true
false
-
false
-
nccl
false
Finished
-
stellaathena
main
9d 10h 10m 30s
-
gelu
false
1000
false
-
["global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global"]
0
false
4
-
false
true
false
-
-
true
-
false
1
-
false
1
-
-
-
-
-
-
false
-
-
-
-
mmap
/mnt/ssd-1/data/pile_20B_tokenizer/pile_20B_tokenizer_text_document
false
true
true
false
-
false
-
nccl
false
Finished
-
stellaathena
main
25d 2h 14s
-
gelu
false
1000
false
-
["global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global"]
0
false
4
-
false
true
false
-
-
true
-
false
1
-
false
1
-
-
-
-
-
-
false
-
-
-
-
mmap
/mnt/ssd-1/data/pile_20B_tokenizer/pile_20B_tokenizer_text_document
false
true
true
false
-
false
-
nccl
false
Finished
-
stellaathena
main
25d 2h 15s
-
gelu
false
1000
false
-
["global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global"]
0
false
4
-
false
true
false
-
-
true
-
false
1
-
false
1
-
-
-
-
-
-
false
-
-
-
-
mmap
/mnt/ssd-1/data/pile_20B_tokenizer/pile_20B_tokenizer_text_document
false
true
true
false
-
false
-
nccl
false
Finished
-
stellaathena
main
25d 2h 11s
-
gelu
false
1000
false
-
["global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global"]
0
false
4
-
false
true
false
-
-
true
-
false
1
-
false
1
-
-
-
-
-
-
false
-
-
-
-
mmap
/mnt/ssd-1/data/pile_20B_tokenizer/pile_20B_tokenizer_text_document
false
true
true
false
-
false
-
nccl
false
Crashed
-
stellaathena
main
25d 2h 13m 25s
-
gelu
false
1000
false
-
["global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global"]
0
false
4
-
false
true
false
-
-
true
-
false
1
-
false
1
-
-
-
-
-
-
false
-
-
-
-
mmap
/mnt/ssd-1/data/pile_20B_tokenizer/pile_20B_tokenizer_text_document
false
true
true
false
-
false
-
nccl
false
Finished
-
stellaathena
main
25d 2h 6s
-
gelu
false
1000
false
-
["global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global"]
0
false
4
-
false
true
false
-
-
true
-
false
1
-
false
1
-
-
-
-
-
-
false
-
-
-
-
mmap
/mnt/ssd-1/data/pile_20B_tokenizer/pile_20B_tokenizer_text_document
false
true
true
false
-
false
-
nccl
false
Crashed
-
stellaathena
main
25d 2h 6m 50s
-
gelu
false
1000
false
-
["global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global"]
0
false
4
-
false
true
false
-
-
true
-
false
1
-
false
1
-
-
-
-
-
-
false
-
-
-
-
mmap
/mnt/ssd-1/data/pile_20B_tokenizer/pile_20B_tokenizer_text_document
false
true
true
false
-
false
-
nccl
false
Finished
-
stellaathena
main
25d 2h 2s
-
gelu
false
1000
false
-
["global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global"]
0
false
4
-
false
true
false
-
-
true
-
false
1
-
false
1
-
-
-
-
-
-
false
-
-
-
-
mmap
/mnt/ssd-1/data/pile_20B_tokenizer/pile_20B_tokenizer_text_document
false
true
true
false
-
false
-
nccl
false
Finished
-
stellaathena
main
25d 2h
-
gelu
false
1000
false
-
["global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global","global"]
0
false
4
-
false
true
false
-
-
true
-
false
1
-
false
1
-
-
-
-
-
-
false
-
-
-
-
mmap
/mnt/ssd-1/data/pile_20B_tokenizer/pile_20B_tokenizer_text_document
false
true
true
false
-
false
-
nccl
false
1-20
of 144