Tristan commited on
Commit
ff89a1c
1 Parent(s): 5097648

Training in progress, epoch 1

Browse files
eval_job_output.txt CHANGED
@@ -1,4 +1,4 @@
1
- slurm submission log: 2024-05-20 23:23:34.884664
2
  created following sbatch script:
3
 
4
  ###############################
@@ -7,13 +7,13 @@ created following sbatch script:
7
 
8
  #SBATCH --account=nlp
9
  #SBATCH --cpus-per-task=16
10
- #SBATCH --dependency=afterok:7637764
11
  #SBATCH --gres=gpu:1
12
- #SBATCH --job-name=tthrush-job-2829433
13
  #SBATCH --mem=60G
14
  #SBATCH --nodelist=sphinx1
15
  #SBATCH --open-mode=append
16
- #SBATCH --output=/juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/test_ordinal_clipped_scaled_mean/llms/pythia-70m_sciq_1/eval_job_output.txt
17
  #SBATCH --partition=sphinx
18
  #SBATCH --time=14-0
19
 
@@ -24,7 +24,7 @@ created following sbatch script:
24
  cd .
25
 
26
  # launch commands
27
- srun --unbuffered run_as_child_processes 'lm_eval --model hf --model_args pretrained=/juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/test_ordinal_clipped_scaled_mean/llms/pythia-70m_sciq_1,revision=main,dtype=float16,trust_remote_code=True --tasks xnli_en,xnli_fr,sciq,piqa,lambada,arc_easy --device cuda --output_path /juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/test_ordinal_clipped_scaled_mean/llms/pythia-70m_sciq_1/perf'
28
 
29
  ###############################
30
 
@@ -34,7 +34,7 @@ submission to slurm complete!
34
  ###############################
35
  slurm submission output
36
 
37
- Submitted batch job 7637765
38
 
39
 
40
 
 
1
+ slurm submission log: 2024-05-20 23:23:25.682813
2
  created following sbatch script:
3
 
4
  ###############################
 
7
 
8
  #SBATCH --account=nlp
9
  #SBATCH --cpus-per-task=16
10
+ #SBATCH --dependency=afterok:7637742
11
  #SBATCH --gres=gpu:1
12
+ #SBATCH --job-name=tthrush-job-1473087
13
  #SBATCH --mem=60G
14
  #SBATCH --nodelist=sphinx1
15
  #SBATCH --open-mode=append
16
+ #SBATCH --output=/juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/test_ordinal_clipped_scaled/llms/pythia-70m_sciq_1/eval_job_output.txt
17
  #SBATCH --partition=sphinx
18
  #SBATCH --time=14-0
19
 
 
24
  cd .
25
 
26
  # launch commands
27
+ srun --unbuffered run_as_child_processes 'lm_eval --model hf --model_args pretrained=/juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/test_ordinal_clipped_scaled/llms/pythia-70m_sciq_1,revision=main,dtype=float16,trust_remote_code=True --tasks xnli_en,xnli_fr,sciq,piqa,lambada,arc_easy --device cuda --output_path /juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/test_ordinal_clipped_scaled/llms/pythia-70m_sciq_1/perf'
28
 
29
  ###############################
30
 
 
34
  ###############################
35
  slurm submission output
36
 
37
+ Submitted batch job 7637743
38
 
39
 
40
 
logs/events.out.tfevents.1716302139.sphinx2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54f9f05e787b51506ae6d94ad57443cba9f21e7fc9d00dd2031b8ba429da3c22
3
+ size 95648
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6a5aa6c4a6b1993c46624d7051989d2340b9c9130cb3bde31922f9ff1ff9b77a
3
  size 281715176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09d84270040ceca82dc15a4388c4b665b21b56b4351768ba347f58081b53e3fd
3
  size 281715176
train_job_output.txt CHANGED
The diff for this file is too large to render. See raw diff
 
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dbf984f6f8e5351ae5507a52b7524a2aec7fd2eb23073a8cae95e8c3d977584b
3
- size 5240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce8c68572ae640438186e4bbb1f34f00a7686c8c0261f06d0c6d518ab3ccf1f5
3
+ size 5176