Tristan commited on
Commit
1b5eb9e
1 Parent(s): c87c8ef

Training in progress, epoch 1

Browse files
eval_job_output.txt CHANGED
@@ -1,4 +1,4 @@
1
- slurm submission log: 2024-05-29 11:13:39.876829
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:7667648
11
  #SBATCH --gres=gpu:1
12
- #SBATCH --job-name=tthrush-job-1666955
13
  #SBATCH --mem=60G
14
  #SBATCH --nodelist=sphinx1
15
  #SBATCH --open-mode=append
16
- #SBATCH --output=/juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/paper_writeup_tests/ordinal_post_hoc_projection/llms/pythia-70m_piqa_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/paper_writeup_tests/ordinal_post_hoc_projection/llms/pythia-70m_piqa_1,revision=main,dtype=float16,trust_remote_code=True --tasks piqa,arc_easy,xnli_en,xnli_fr,xnli_de,xnli_es,sciq,lambada --device cuda --output_path /juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/paper_writeup_tests/ordinal_post_hoc_projection/llms/pythia-70m_piqa_1/perf'
28
 
29
  ###############################
30
 
@@ -34,13 +34,13 @@ submission to slurm complete!
34
  ###############################
35
  slurm submission output
36
 
37
- Submitted batch job 7667649
38
 
39
 
40
 
41
  ###############################
42
 
43
- slurm submission log: 2024-05-29 23:06:15.453295
44
  created following sbatch script:
45
 
46
  ###############################
@@ -49,13 +49,13 @@ created following sbatch script:
49
 
50
  #SBATCH --account=nlp
51
  #SBATCH --cpus-per-task=16
52
- #SBATCH --dependency=afterok:7670029
53
  #SBATCH --gres=gpu:1
54
- #SBATCH --job-name=tthrush-job-2497219
55
  #SBATCH --mem=60G
56
  #SBATCH --nodelist=sphinx1
57
  #SBATCH --open-mode=append
58
- #SBATCH --output=/juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/paper_writeup_tests/ordinal_post_hoc_projection/llms/pythia-70m_piqa_1/eval_job_output.txt
59
  #SBATCH --partition=sphinx
60
  #SBATCH --time=14-0
61
 
@@ -66,7 +66,7 @@ created following sbatch script:
66
  cd .
67
 
68
  # launch commands
69
- srun --unbuffered run_as_child_processes 'lm_eval --model hf --model_args pretrained=/juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/paper_writeup_tests/ordinal_post_hoc_projection/llms/pythia-70m_piqa_1,revision=main,dtype=float16,trust_remote_code=True --tasks piqa,arc_easy,xnli_en,xnli_fr,xnli_de,xnli_es,sciq,lambada --device cuda --output_path /juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/paper_writeup_tests/ordinal_post_hoc_projection/llms/pythia-70m_piqa_1/perf'
70
 
71
  ###############################
72
 
@@ -76,7 +76,7 @@ submission to slurm complete!
76
  ###############################
77
  slurm submission output
78
 
79
- Submitted batch job 7670030
80
 
81
 
82
 
 
1
+ slurm submission log: 2024-05-29 11:13:47.896797
2
  created following sbatch script:
3
 
4
  ###############################
 
7
 
8
  #SBATCH --account=nlp
9
  #SBATCH --cpus-per-task=16
10
+ #SBATCH --dependency=afterok:7667675
11
  #SBATCH --gres=gpu:1
12
+ #SBATCH --job-name=tthrush-job-22691
13
  #SBATCH --mem=60G
14
  #SBATCH --nodelist=sphinx1
15
  #SBATCH --open-mode=append
16
+ #SBATCH --output=/juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/paper_writeup_tests/ordinal_constrained/llms/pythia-70m_piqa_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/paper_writeup_tests/ordinal_constrained/llms/pythia-70m_piqa_1,revision=main,dtype=float16,trust_remote_code=True --tasks piqa,arc_easy,xnli_en,xnli_fr,xnli_de,xnli_es,sciq,lambada --device cuda --output_path /juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/paper_writeup_tests/ordinal_constrained/llms/pythia-70m_piqa_1/perf'
28
 
29
  ###############################
30
 
 
34
  ###############################
35
  slurm submission output
36
 
37
+ Submitted batch job 7667676
38
 
39
 
40
 
41
  ###############################
42
 
43
+ slurm submission log: 2024-05-30 08:40:45.086554
44
  created following sbatch script:
45
 
46
  ###############################
 
49
 
50
  #SBATCH --account=nlp
51
  #SBATCH --cpus-per-task=16
52
+ #SBATCH --dependency=afterok:7670590
53
  #SBATCH --gres=gpu:1
54
+ #SBATCH --job-name=tthrush-job-4422312
55
  #SBATCH --mem=60G
56
  #SBATCH --nodelist=sphinx1
57
  #SBATCH --open-mode=append
58
+ #SBATCH --output=/juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/paper_writeup_tests/ordinal_constrained/llms/pythia-70m_piqa_1/eval_job_output.txt
59
  #SBATCH --partition=sphinx
60
  #SBATCH --time=14-0
61
 
 
66
  cd .
67
 
68
  # launch commands
69
+ srun --unbuffered run_as_child_processes 'lm_eval --model hf --model_args pretrained=/juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/paper_writeup_tests/ordinal_constrained/llms/pythia-70m_piqa_1,revision=main,dtype=float16,trust_remote_code=True --tasks piqa,arc_easy,xnli_en,xnli_fr,xnli_de,xnli_es,sciq,lambada --device cuda --output_path /juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/paper_writeup_tests/ordinal_constrained/llms/pythia-70m_piqa_1/perf'
70
 
71
  ###############################
72
 
 
76
  ###############################
77
  slurm submission output
78
 
79
+ Submitted batch job 7670592
80
 
81
 
82
 
logs/events.out.tfevents.1717098841.sphinx2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8cc514ad6173de4c1606e64d30de3530e31c10cf2c8ce297b8d9964afdc85fd7
3
+ size 95684
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:aaea92d40aebd09edd83b146f1b0f291a3b474ba66eced61d616466ffe58bc67
3
  size 281715176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b6ce70be5c0afdf67f56f41bd1860da066eb7fbc7eeeb8120d946b0c9ea3767
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 sha256:50d71ccbb43e27d02a09852ad0f7511aa2e5c54d9fc569dcaf108d3ed8935706
3
  size 5240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e251cd6d41d02fed33ef402a5f3ec1141dde0d06a4783c3f4a4b40b18eb7089c
3
  size 5240