Aflah's workspace
Runs
92
Name
8 visualized
State
Notes
User
Tags
Created
Runtime
Sweep
activation
adlr_autoresume
adlr_autoresume_interval
allow_chopped
apply_query_key_layer_scaling
attention_config
attention_dropout
attention_softmax_in_fp32
batch_size
bf16.enabled
bias_dropout_fusion
bias_gelu_fusion
char_level_ppl
checkpoint_activations
checkpoint_factor
checkpoint_in_cpu
checkpoint_num_layers
checkpoint_scale
checkpoint_validation_with_forward_pass
clip_grad
config_files.1_1B_BS_32.yml
config_files.1_1B_BS_32_No_TE.yml
config_files.1_1B_BS_48.yml
config_files.1_1B_BS_48_No_TE.yml
config_files.1_1B_BS_48_No_TE_With_Softmax_Fusion.yml
config_files.1_1B_BS_48_With_Softmax_Fusion.yml
contiguous_checkpointing
coord_check
curriculum_seqlen
data_impl
data_path
data_types.grad_accum_dtype
dataset_impl
deepscale
deepspeed
deepspeed_activation_checkpointing
deepspeed_mpi
deepspeed_slurm
distributed_backend
dpo_beta
dpo_fp32
dpo_reference_free
dump_state
dynamic_loss_scale
Running
-
aflah
2h 54m 46s
-
swiglu
false
1000
true
false
["flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash"]
0
false
64
true
false
false
false
true
500
false
1
linear
false
1
-
-
-
-
-
-
false
false
0
mmap
/u/afkhan/Artifacts/RoPE_Pct/Datasets/FineWeb_Edu_100B_Merged_text_document
fp32
gpt2
false
true
true
false
false
nccl
0.1
true
false
false
true
Running
-
aflah
2h 54m 46s
-
swiglu
false
1000
true
false
["flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash"]
0
false
64
true
false
false
false
true
500
false
1
linear
false
1
-
-
-
-
-
-
false
false
0
mmap
/u/afkhan/Artifacts/RoPE_Pct/Datasets/FineWeb_Edu_100B_Merged_text_document
fp32
gpt2
false
true
true
false
false
nccl
0.1
true
false
false
true
Running
-
aflah
2h 54m 46s
-
swiglu
false
1000
true
false
["flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash"]
0
false
64
true
false
false
false
true
500
false
1
linear
false
1
-
-
-
-
-
-
false
false
0
mmap
/u/afkhan/Artifacts/RoPE_Pct/Datasets/FineWeb_Edu_100B_Merged_text_document
fp32
gpt2
false
true
true
false
false
nccl
0.1
true
false
false
true
Running
-
aflah
2h 55m 1s
-
swiglu
false
1000
true
false
["flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash"]
0
false
64
true
false
false
false
true
500
false
1
linear
false
1
-
-
-
-
-
-
false
false
0
mmap
/u/afkhan/Artifacts/RoPE_Pct/Datasets/FineWeb_Edu_100B_Merged_text_document
fp32
gpt2
false
true
true
false
false
nccl
0.1
true
false
false
true
Running
-
aflah
3h 44m 20s
-
swiglu
false
1000
true
false
["flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash"]
0
false
64
true
false
false
false
true
500
false
1
linear
false
1
-
-
-
-
-
-
false
false
0
mmap
/u/afkhan/Artifacts/RoPE_Pct/Datasets/FineWeb_Edu_100B_Merged_text_document
fp32
gpt2
false
true
true
false
false
nccl
0.1
true
false
false
true
Running
-
aflah
3h 44m 16s
-
swiglu
false
1000
true
false
["flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash"]
0
false
64
true
false
false
false
true
500
false
1
linear
false
1
-
-
-
-
-
-
false
false
0
mmap
/u/afkhan/Artifacts/RoPE_Pct/Datasets/FineWeb_Edu_100B_Merged_text_document
fp32
gpt2
false
true
true
false
false
nccl
0.1
true
false
false
true
Running
-
aflah
3h 44m 26s
-
swiglu
false
1000
true
false
["flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash"]
0
false
64
true
false
false
false
true
500
false
1
linear
false
1
-
-
-
-
-
-
false
false
0
mmap
/u/afkhan/Artifacts/RoPE_Pct/Datasets/FineWeb_Edu_100B_Merged_text_document
fp32
gpt2
false
true
true
false
false
nccl
0.1
true
false
false
true
Running
-
aflah
3h 44m 20s
-
swiglu
false
1000
true
false
["flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash"]
0
false
64
true
false
false
false
true
500
false
1
linear
false
1
-
-
-
-
-
-
false
false
0
mmap
/u/afkhan/Artifacts/RoPE_Pct/Datasets/FineWeb_Edu_100B_Merged_text_document
fp32
gpt2
false
true
true
false
false
nccl
0.1
true
false
false
true
Failed
-
aflah
4m 22s
-
swiglu
false
1000
true
false
["flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash"]
0
false
128
true
false
false
false
false
500
false
1
linear
false
1
-
-
-
-
-
-
false
false
0
mmap
/u/afkhan/Artifacts/RoPE_Pct/Datasets/FineWeb_Edu_100B_Merged_text_document
bf16
gpt2
false
true
true
false
false
nccl
0.1
true
false
false
true
Failed
-
aflah
4m 22s
-
swiglu
false
1000
true
false
["flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash"]
0
false
128
true
false
false
false
false
500
false
1
linear
false
1
-
-
-
-
-
-
false
false
0
mmap
/u/afkhan/Artifacts/RoPE_Pct/Datasets/FineWeb_Edu_100B_Merged_text_document
bf16
gpt2
false
true
true
false
false
nccl
0.1
true
false
false
true
Failed
-
aflah
4m 23s
-
swiglu
false
1000
true
false
["flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash"]
0
false
128
true
false
false
false
false
500
false
1
linear
false
1
-
-
-
-
-
-
false
false
0
mmap
/u/afkhan/Artifacts/RoPE_Pct/Datasets/FineWeb_Edu_100B_Merged_text_document
bf16
gpt2
false
true
true
false
false
nccl
0.1
true
false
false
true
Failed
-
aflah
4m 24s
-
swiglu
false
1000
true
false
["flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash"]
0
false
128
true
false
false
false
false
500
false
1
linear
false
1
-
-
-
-
-
-
false
false
0
mmap
/u/afkhan/Artifacts/RoPE_Pct/Datasets/FineWeb_Edu_100B_Merged_text_document
bf16
gpt2
false
true
true
false
false
nccl
0.1
true
false
false
true
Failed
-
aflah
4m 19s
-
swiglu
false
1000
true
false
["flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash"]
0
false
128
true
false
false
false
false
500
false
1
linear
false
1
-
-
-
-
-
-
false
false
0
mmap
/u/afkhan/Artifacts/RoPE_Pct/Datasets/FineWeb_Edu_100B_Merged_text_document
bf16
gpt2
false
true
true
false
false
nccl
0.1
true
false
false
true
Failed
-
aflah
4m 20s
-
swiglu
false
1000
true
false
["flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash"]
0
false
128
true
false
false
false
false
500
false
1
linear
false
1
-
-
-
-
-
-
false
false
0
mmap
/u/afkhan/Artifacts/RoPE_Pct/Datasets/FineWeb_Edu_100B_Merged_text_document
bf16
gpt2
false
true
true
false
false
nccl
0.1
true
false
false
true
Failed
-
aflah
4m 20s
-
swiglu
false
1000
true
false
["flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash"]
0
false
128
true
false
false
false
false
500
false
1
linear
false
1
-
-
-
-
-
-
false
false
0
mmap
/u/afkhan/Artifacts/RoPE_Pct/Datasets/FineWeb_Edu_100B_Merged_text_document
bf16
gpt2
false
true
true
false
false
nccl
0.1
true
false
false
true
Failed
-
aflah
4m 20s
-
swiglu
false
1000
true
false
["flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash"]
0
false
128
true
false
false
false
false
500
false
1
linear
false
1
-
-
-
-
-
-
false
false
0
mmap
/u/afkhan/Artifacts/RoPE_Pct/Datasets/FineWeb_Edu_100B_Merged_text_document
bf16
gpt2
false
true
true
false
false
nccl
0.1
true
false
false
true
Failed
-
aflah
4m 32s
-
swiglu
false
1000
true
false
["flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash"]
0
false
128
true
false
false
false
false
500
false
1
linear
false
1
-
-
-
-
-
-
false
false
0
mmap
/u/afkhan/Artifacts/RoPE_Pct/Datasets/FineWeb_Edu_100B_Merged_text_document
bf16
gpt2
false
true
true
false
false
nccl
0.1
true
false
false
true
Failed
-
aflah
4m 33s
-
swiglu
false
1000
true
false
["flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash"]
0
false
128
true
false
false
false
false
500
false
1
linear
false
1
-
-
-
-
-
-
false
false
0
mmap
/u/afkhan/Artifacts/RoPE_Pct/Datasets/FineWeb_Edu_100B_Merged_text_document
bf16
gpt2
false
true
true
false
false
nccl
0.1
true
false
false
true
Failed
-
aflah
4m 33s
-
swiglu
false
1000
true
false
["flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash"]
0
false
128
true
false
false
false
false
500
false
1
linear
false
1
-
-
-
-
-
-
false
false
0
mmap
/u/afkhan/Artifacts/RoPE_Pct/Datasets/FineWeb_Edu_100B_Merged_text_document
bf16
gpt2
false
true
true
false
false
nccl
0.1
true
false
false
true
Failed
-
aflah
4m 34s
-
swiglu
false
1000
true
false
["flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash"]
0
false
128
true
false
false
false
false
500
false
1
linear
false
1
-
-
-
-
-
-
false
false
0
mmap
/u/afkhan/Artifacts/RoPE_Pct/Datasets/FineWeb_Edu_100B_Merged_text_document
bf16
gpt2
false
true
true
false
false
nccl
0.1
true
false
false
true
Failed
-
aflah
1h 1m 36s
-
swiglu
false
1000
true
false
["flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash"]
0
false
48
true
false
false
false
true
1000
false
1
linear
false
1
-
-
-
-
-
-
false
false
0
mmap
/scratch/sws0/user/afkhan/RoPE_Pct/Datasets/FineWeb_Edu_100B_Merged_text_document
fp32
gpt2
false
true
true
false
true
nccl
0.1
true
false
false
true
Failed
-
aflah
49m 25s
-
swiglu
false
1000
true
false
["flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash"]
0
false
48
true
false
false
false
true
1000
false
1
linear
false
1
-
-
-
-
-
-
false
false
0
mmap
/scratch/sws0/user/afkhan/RoPE_Pct/Datasets/FineWeb_Edu_100B_Merged_text_document
fp32
gpt2
false
true
true
false
true
nccl
0.1
true
false
false
true
Failed
-
aflah
1h 1m 6s
-
swiglu
false
1000
true
false
["flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash"]
0
false
48
true
false
false
false
true
1000
false
1
linear
false
1
-
-
-
-
-
-
false
false
0
mmap
/scratch/sws0/user/afkhan/RoPE_Pct/Datasets/FineWeb_Edu_100B_Merged_text_document
fp32
gpt2
false
true
true
false
true
nccl
0.1
true
false
false
true
Failed
-
aflah
51m 13s
-
swiglu
false
1000
true
false
["flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash"]
0
false
48
true
false
false
false
true
1000
false
1
linear
false
1
-
-
-
-
-
-
false
false
0
mmap
/scratch/sws0/user/afkhan/RoPE_Pct/Datasets/FineWeb_Edu_100B_Merged_text_document
fp32
gpt2
false
true
true
false
true
nccl
0.1
true
false
false
true
Crashed
-
aflah
30s
-
swiglu
false
1000
true
false
["flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash"]
0
false
48
true
false
false
false
true
1000
false
1
linear
false
1
-
-
-
-
-
-
false
false
0
mmap
/scratch/sws0/user/afkhan/RoPE_Pct/Datasets/FineWeb_Edu_100B_Merged_text_document
fp32
gpt2
false
true
true
false
true
nccl
0.1
true
false
false
true
Crashed
-
aflah
0s
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
Failed
-
aflah
30m 9s
-
swiglu
false
1000
true
false
["flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash"]
0
false
48
true
false
false
false
true
1000
false
1
linear
false
1
-
-
-
-
-
-
false
false
0
mmap
/scratch/sws0/user/afkhan/RoPE_Pct/Datasets/FineWeb_Edu_100B_Merged_text_document
fp32
gpt2
false
true
true
false
true
nccl
0.1
true
false
false
true
Crashed
-
aflah
0s
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
Failed
-
aflah
10m 52s
-
swiglu
false
1000
true
false
["flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash"]
0
false
48
true
false
false
false
true
500
false
1
linear
false
1
-
-
-
-
-
-
false
false
0
mmap
/scratch/sws0/user/afkhan/RoPE_Pct/Datasets/FineWeb_Edu_100B_Merged_text_document
fp32
gpt2
false
true
true
false
false
nccl
0.1
true
false
false
true
Failed
-
aflah
49s
-
swiglu
false
1000
true
false
["flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash"]
0
false
48
true
false
false
false
true
500
false
1
linear
false
1
-
-
-
-
-
-
false
false
0
mmap
/scratch/sws0/user/afkhan/RoPE_Pct/Datasets/FineWeb_Edu_100B_Merged_text_document
fp32
gpt2
false
true
true
false
false
nccl
0.1
true
false
false
true
Failed
-
aflah
54s
-
swiglu
false
1000
true
false
["flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash"]
0
false
48
true
false
false
false
true
500
false
1
linear
false
1
-
-
-
-
-
-
false
false
0
mmap
/scratch/sws0/user/afkhan/RoPE_Pct/Datasets/FineWeb_Edu_100B_Merged_text_document
fp32
gpt2
false
true
true
false
false
nccl
0.1
true
false
false
true
Crashed
-
aflah
4m 46s
-
swiglu
false
1000
true
false
["flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash"]
0
false
48
true
false
false
false
true
500
false
1
linear
false
1
-
-
-
-
-
-
false
false
0
mmap
/scratch/sws0/user/afkhan/RoPE_Pct/Datasets/FineWeb_Edu_100B_Merged_text_document
fp32
gpt2
false
true
true
false
false
nccl
0.1
true
false
false
true
Failed
-
aflah
23s
-
swiglu
false
1000
true
false
["flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash"]
0
false
48
true
false
false
false
true
500
false
1
linear
false
1
-
-
-
-
-
-
false
false
0
mmap
/scratch/sws0/user/afkhan/RoPE_Pct/Datasets/FineWeb_Edu_100B_Merged_text_document
fp32
gpt2
false
true
true
false
false
nccl
0.1
true
false
false
true
Failed
-
aflah
7s
-
swiglu
false
1000
true
false
["flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash"]
0
false
48
true
false
false
false
true
500
false
1
linear
false
1
-
-
-
-
-
-
false
false
0
mmap
/scratch/sws0/user/afkhan/RoPE_Pct/Datasets/FineWeb_Edu_100B_Merged_text_document
fp32
gpt2
false
true
true
false
false
nccl
0.1
true
false
false
true
Failed
-
aflah
7m 11s
-
swiglu
false
1000
true
false
["flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash"]
0
false
48
true
false
false
false
true
500
false
1
linear
false
1
-
-
-
-
-
-
false
false
0
mmap
/scratch/sws0/user/afkhan/RoPE_Pct/Datasets/FineWeb_Edu_100B_Merged_text_document
fp32
gpt2
false
true
true
false
false
nccl
0.1
true
false
false
true
Failed
-
aflah
7m 39s
-
swiglu
false
1000
true
false
["flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash"]
0
false
48
true
false
false
false
true
500
false
1
linear
false
1
-
-
-
-
-
-
false
false
0
mmap
/scratch/sws0/user/afkhan/RoPE_Pct/Datasets/FineWeb_Edu_100B_Merged_text_document
fp32
gpt2
false
true
true
false
false
nccl
0.1
true
false
false
true
Failed
-
aflah
7s
-
swiglu
false
1000
true
false
["flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash"]
0
false
48
true
false
false
false
true
500
false
1
linear
false
1
-
-
-
-
-
-
false
false
0
mmap
/scratch/sws0/user/afkhan/RoPE_Pct/Datasets/FineWeb_Edu_100B_Merged_text_document
fp32
gpt2
false
true
true
false
false
nccl
0.1
true
false
false
true
Failed
-
aflah
23s
-
swiglu
false
1000
true
false
["flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash"]
0
false
48
true
false
false
false
true
500
false
1
linear
false
1
-
-
-
-
-
-
false
false
0
mmap
/scratch/sws0/user/afkhan/RoPE_Pct/Datasets/FineWeb_Edu_100B_Merged_text_document
fp32
gpt2
false
true
true
false
false
nccl
0.1
true
false
false
true
Failed
-
aflah
42s
-
swiglu
false
1000
true
false
["flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash"]
0
false
48
true
false
false
false
true
500
false
1
linear
false
1
-
-
-
-
-
-
false
false
0
mmap
/scratch/sws0/user/afkhan/RoPE_Pct/Datasets/FineWeb_Edu_100B_Merged_text_document
fp32
gpt2
false
true
true
false
false
nccl
0.1
true
false
false
true
Failed
-
aflah
7m 3s
-
swiglu
false
1000
true
false
["flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash"]
0
false
48
true
false
false
false
true
500
false
1
linear
false
1
-
-
-
-
-
-
false
false
0
mmap
/scratch/sws0/user/afkhan/RoPE_Pct/Datasets/FineWeb_Edu_100B_Merged_text_document
fp32
gpt2
false
true
true
false
false
nccl
0.1
true
false
false
true
Failed
-
aflah
7m 59s
-
swiglu
false
1000
true
false
["flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash"]
0
false
48
true
false
false
false
true
500
false
1
linear
false
1
-
-
-
-
-
-
false
false
0
mmap
/scratch/sws0/user/afkhan/RoPE_Pct/Datasets/FineWeb_Edu_100B_Merged_text_document
fp32
gpt2
false
true
true
false
false
nccl
0.1
true
false
false
true
Crashed
-
aflah
2m 1s
-
swiglu
false
1000
true
false
["flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash"]
0
false
48
true
false
false
false
true
500
false
1
linear
false
1
-
-
-
-
-
-
false
false
0
mmap
/scratch/sws0/user/afkhan/RoPE_Pct/Datasets/FineWeb_Edu_100B_Merged_text_document
fp32
gpt2
false
true
true
false
false
nccl
0.1
true
false
false
true
Failed
-
aflah
11m 55s
-
swiglu
false
1000
true
false
["flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash"]
0
false
48
true
false
false
false
true
500
false
1
linear
false
1
-
-
-
-
-
-
false
false
0
mmap
/scratch/sws0/user/afkhan/RoPE_Pct/Datasets/FineWeb_Edu_100B_Merged_text_document
fp32
gpt2
false
true
true
false
false
nccl
0.1
true
false
false
true
Failed
-
aflah
7m 20s
-
swiglu
false
1000
true
false
["flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash"]
0
false
48
true
false
false
false
true
500
false
1
linear
false
1
-
-
-
-
-
-
false
false
0
mmap
/scratch/sws0/user/afkhan/RoPE_Pct/Datasets/FineWeb_Edu_100B_Merged_text_document
fp32
gpt2
false
true
true
false
false
nccl
0.1
true
false
false
true
Crashed
-
aflah
8m 1s
-
swiglu
false
1000
true
false
["flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash"]
0
false
48
true
false
false
false
true
500
false
1
linear
false
1
-
-
-
-
-
-
false
false
0
mmap
/scratch/sws0/user/afkhan/RoPE_Pct/Datasets/FineWeb_Edu_100B_Merged_text_document
fp32
gpt2
false
true
true
false
false
nccl
0.1
true
false
false
true
Crashed
-
aflah
0s
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
Crashed
-
aflah
7m 31s
-
swiglu
false
1000
true
false
["flash","flash","flash","flash","flash","flash","flash","flash"]
0
false
48
true
false
false
false
true
500
false
1
linear
false
1
-
-
-
-
-
-
false
false
0
mmap
/scratch/sws0/user/afkhan/RoPE_Pct/Datasets/FineWeb_Edu_100B_Merged_text_document
fp32
gpt2
false
true
true
false
false
nccl
0.1
true
false
false
true
Crashed
-
aflah
3m 46s
-
swiglu
false
1000
true
false
["flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash"]
0
false
48
true
false
false
false
true
500
false
1
linear
false
1
-
-
-
-
-
-
false
false
0
mmap
/scratch/sws0/user/afkhan/RoPE_Pct/Datasets/FineWeb_Edu_100B_Merged_text_document
fp32
gpt2
false
true
true
false
false
nccl
0.1
true
false
false
true
Crashed
-
aflah
46s
-
swiglu
false
1000
true
false
["flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash"]
0
false
48
true
false
false
false
true
500
false
1
linear
false
1
-
-
-
-
-
-
false
false
0
mmap
/scratch/sws0/user/afkhan/RoPE_Pct/Datasets/FineWeb_Edu_100B_Merged_text_document
fp32
gpt2
false
true
true
false
false
nccl
0.1
true
false
false
true
Failed
-
aflah
16s
-
swiglu
false
1000
true
false
["flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash","flash"]
0
false
48
true
false
false
false
true
500
false
1
linear
false
1
-
-
-
-
-
-
false
false
0
mmap
/scratch/sws0/user/afkhan/RoPE_Pct/Datasets/FineWeb_Edu_100B_Merged_text_document
fp32
gpt2
false
true
true
false
false
nccl
0.1
true
false
false
true
1-50
of 92