Tristan commited on
Commit
04397cc
1 Parent(s): 2bec443

Training in progress, epoch 0

Browse files
eval_job_output.txt CHANGED
@@ -1,4 +1,4 @@
1
- slurm submission log: 2024-05-19 16:02:35.052926
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:7632890
11
  #SBATCH --gres=gpu:1
12
- #SBATCH --job-name=tthrush-job-4928875
13
  #SBATCH --mem=60G
14
  #SBATCH --nodelist=sphinx1
15
  #SBATCH --open-mode=append
16
- #SBATCH --output=/juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/llms_more_data_test_normalized/pythia-14m_piqa_4/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/llms_more_data_test_normalized/pythia-14m_piqa_4,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/llms_more_data_test_normalized/pythia-14m_piqa_4/perf'
28
 
29
  ###############################
30
 
@@ -34,7 +34,7 @@ submission to slurm complete!
34
  ###############################
35
  slurm submission output
36
 
37
- Submitted batch job 7632892
38
 
39
 
40
 
 
1
+ slurm submission log: 2024-05-19 16:02:35.597700
2
  created following sbatch script:
3
 
4
  ###############################
 
7
 
8
  #SBATCH --account=nlp
9
  #SBATCH --cpus-per-task=16
10
+ #SBATCH --dependency=afterok:7632893
11
  #SBATCH --gres=gpu:1
12
+ #SBATCH --job-name=tthrush-job-2196999
13
  #SBATCH --mem=60G
14
  #SBATCH --nodelist=sphinx1
15
  #SBATCH --open-mode=append
16
+ #SBATCH --output=/juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/llms_more_data_test_normalized/pythia-14m_piqa_5/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/llms_more_data_test_normalized/pythia-14m_piqa_5,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/llms_more_data_test_normalized/pythia-14m_piqa_5/perf'
28
 
29
  ###############################
30
 
 
34
  ###############################
35
  slurm submission output
36
 
37
+ Submitted batch job 7632894
38
 
39
 
40
 
logs/events.out.tfevents.1716185141.sphinx2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a68999642a3d8c765796468c7174caf8cf1401f14c06e1e6c1eb1cd99b7036fa
3
+ size 62936
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:09ccfef32a627e0d7e62fbe76d8cba01547eee94d01de4e6e1f7ce478983d8d3
3
  size 56279344
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:567d828a80890ace8979aa6e0c255775e6425a49c377e6afbd960880955be555
3
  size 56279344
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 sha256:8d53ff6c4e6a34c1422e855ecc65d5ad58af551f0f6d7c1449a8afec64b29f2b
3
  size 5176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:69800b2a8a7c5d39ccfdf1e956c6b91de55b9f9ed946b9643d838ef9a07ff6ee
3
  size 5176