Tristan commited on
Commit
9cb1df7
1 Parent(s): cc2cae5

Training in progress, epoch 1

Browse files
eval_job_output.txt CHANGED
@@ -1,4 +1,4 @@
1
- slurm submission log: 2024-05-20 10:11:58.094285
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:7635784
11
  #SBATCH --gres=gpu:1
12
- #SBATCH --job-name=tthrush-job-616941
13
  #SBATCH --mem=60G
14
  #SBATCH --nodelist=sphinx1
15
  #SBATCH --open-mode=append
16
- #SBATCH --output=/juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/70m_llms_more_data_test_normalized/pythia-70m_lambada_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/70m_llms_more_data_test_normalized/pythia-70m_lambada_1,revision=main,dtype=float16,trust_remote_code=True --tasks xnli_en,xnli_fr,sciq,piqa,lambada,arc_easy,default --device cuda --output_path /juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/70m_llms_more_data_test_normalized/pythia-70m_lambada_1/perf'
28
 
29
  ###############################
30
 
@@ -34,7 +34,7 @@ submission to slurm complete!
34
  ###############################
35
  slurm submission output
36
 
37
- Submitted batch job 7635785
38
 
39
 
40
 
 
1
+ slurm submission log: 2024-05-20 23:23:27.371856
2
  created following sbatch script:
3
 
4
  ###############################
 
7
 
8
  #SBATCH --account=nlp
9
  #SBATCH --cpus-per-task=16
10
+ #SBATCH --dependency=afterok:7637748
11
  #SBATCH --gres=gpu:1
12
+ #SBATCH --job-name=tthrush-job-3721601
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_lambada_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_lambada_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_lambada_1/perf'
28
 
29
  ###############################
30
 
 
34
  ###############################
35
  slurm submission output
36
 
37
+ Submitted batch job 7637749
38
 
39
 
40
 
logs/events.out.tfevents.1716308514.sphinx2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:257611007ccfd41e4fd40b67e89ea2075a626f6d63ce5067506a079f780fcf57
3
+ size 95660
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bb8d015d5deeb4596c1c2571fda097c75337b0581995c6add76635b1dfbee19c
3
  size 281715176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f104511d464cbbad6068ca714fcc8667ef092a1315771a0fbde39d2e11df9bf8
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 sha256:568669cbcf9b891a1f04a6d41a2a715454fe3436ba39cf254f31ce95433cfb00
3
  size 5240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f9f882bebb2fbd53a27d14200322ecf44d5ab68340ca21591ff251e96b5a61b
3
  size 5240