Hugging Face's logo

Tristan
/
pythia-70m_lambada

Text Generation
Transformers
TensorBoard
Safetensors
gpt_neox
text-generation-inference
Inference Endpoints
Model card Files Metrics Community
Tristan commited on
Commit
bc65de4
•
1 Parent(s): 9f3c41f

Training in progress, epoch 1

Browse files
Files changed (5) hide show
  1. eval_job_output.txt +12 -12
  2. logs/events.out.tfevents.1715583717.sphinx2 +3 -0
  3. model.safetensors +1 -1
  4. train_job_output.txt +0 -0
  5. training_args.bin +1 -1
eval_job_output.txt CHANGED
@@ -1,4 +1,4 @@
1
- slurm submission log: 2024-05-11 17:55:08.806518
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:7598879
11
  #SBATCH --gres=gpu:1
12
- #SBATCH --job-name=tthrush-job-4230185
13
  #SBATCH --mem=60G
14
  #SBATCH --nodelist=sphinx2
15
  #SBATCH --open-mode=append
16
- #SBATCH --output=/juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/llms_5/pythia-70m_lambada/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_5/pythia-70m_lambada,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_5/pythia-70m_lambada/perf'
28
 
29
  ###############################
30
 
@@ -34,13 +34,13 @@ submission to slurm complete!
34
  ###############################
35
  slurm submission output
36
 
37
- Submitted batch job 7598880
38
 
39
 
40
 
41
  ###############################
42
 
43
- slurm submission log: 2024-05-11 18:01:41.465835
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:7598918
53
  #SBATCH --gres=gpu:1
54
- #SBATCH --job-name=tthrush-job-3667297
55
  #SBATCH --mem=60G
56
  #SBATCH --nodelist=sphinx2
57
  #SBATCH --open-mode=append
58
- #SBATCH --output=/juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/llms_5/pythia-70m_lambada/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/llms_5/pythia-70m_lambada,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_5/pythia-70m_lambada/perf'
70
 
71
  ###############################
72
 
@@ -76,7 +76,7 @@ submission to slurm complete!
76
  ###############################
77
  slurm submission output
78
 
79
- Submitted batch job 7598919
80
 
81
 
82
 
 
1
+ slurm submission log: 2024-05-12 23:27:17.655209
2
  created following sbatch script:
3
 
4
  ###############################
 
7
 
8
  #SBATCH --account=nlp
9
  #SBATCH --cpus-per-task=16
10
+ #SBATCH --dependency=afterok:7604170
11
  #SBATCH --gres=gpu:1
12
+ #SBATCH --job-name=tthrush-job-1808418
13
  #SBATCH --mem=60G
14
  #SBATCH --nodelist=sphinx2
15
  #SBATCH --open-mode=append
16
+ #SBATCH --output=/juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/llms_6/pythia-70m_lambada/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_6/pythia-70m_lambada,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_6/pythia-70m_lambada/perf'
28
 
29
  ###############################
30
 
 
34
  ###############################
35
  slurm submission output
36
 
37
+ Submitted batch job 7604171
38
 
39
 
40
 
41
  ###############################
42
 
43
+ slurm submission log: 2024-05-12 23:29:48.415861
44
  created following sbatch script:
45
 
46
  ###############################
 
49
 
50
  #SBATCH --account=nlp
51
  #SBATCH --cpus-per-task=16
52
+ #SBATCH --dependency=afterok:7604191
53
  #SBATCH --gres=gpu:1
54
+ #SBATCH --job-name=tthrush-job-3010855
55
  #SBATCH --mem=60G
56
  #SBATCH --nodelist=sphinx2
57
  #SBATCH --open-mode=append
58
+ #SBATCH --output=/juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/llms_6/pythia-70m_lambada/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/llms_6/pythia-70m_lambada,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_6/pythia-70m_lambada/perf'
70
 
71
  ###############################
72
 
 
76
  ###############################
77
  slurm submission output
78
 
79
+ Submitted batch job 7604192
80
 
81
 
82
 
logs/events.out.tfevents.1715583717.sphinx2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:484afdb8b79dec31981e1d726c592dc2750b12371f28d4eca014c500ae41d69b
3
+ size 11168
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:001382bb3f45756abe4dd662329baccfdf220192f269285c5a09eee3fb321b5e
3
  size 281715176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2791d20fb04b57f1d9f9b0c2585021757097f74a43375600434c9bc34e2225ab
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 sha256:2da111285bed0ec1d858a678861c745da34f50e70eb0de1533eace5a6e22c6d8
3
  size 5112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ca511f8a115accae3e0ed2ce918fc188299dc53a37ad975ca209430b925fe5a
3
  size 5112