Hugging Face's logo

Tristan
/
pythia-70m_piqa

Text Generation
Transformers
TensorBoard
Safetensors
gpt_neox
text-generation-inference
Inference Endpoints
Model card Files Metrics Community
Tristan commited on
Commit
4140976
•
1 Parent(s): 505d91e

Training in progress, epoch 1

Browse files
Files changed (6) hide show
  1. config.json +1 -1
  2. eval_job_output.txt +6 -6
  3. logs/events.out.tfevents.1715991452.sphinx2 +3 -0
  4. model.safetensors +1 -1
  5. train_job_output.txt +0 -0
  6. training_args.bin +2 -2
config.json CHANGED
@@ -23,7 +23,7 @@
23
  "rotary_pct": 0.25,
24
  "tie_word_embeddings": false,
25
  "torch_dtype": "float32",
26
- "transformers_version": "4.39.3",
27
  "use_cache": true,
28
  "use_parallel_residual": true,
29
  "vocab_size": 50304
 
23
  "rotary_pct": 0.25,
24
  "tie_word_embeddings": false,
25
  "torch_dtype": "float32",
26
+ "transformers_version": "4.40.2",
27
  "use_cache": true,
28
  "use_parallel_residual": true,
29
  "vocab_size": 50304
eval_job_output.txt CHANGED
@@ -1,4 +1,4 @@
1
- slurm submission log: 2024-05-13 15:14:50.506486
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:7606389
11
  #SBATCH --gres=gpu:1
12
- #SBATCH --job-name=tthrush-job-2046963
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_kmeans/pythia-70m_piqa/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_kmeans/pythia-70m_piqa,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_kmeans/pythia-70m_piqa/perf'
28
 
29
  ###############################
30
 
@@ -34,7 +34,7 @@ submission to slurm complete!
34
  ###############################
35
  slurm submission output
36
 
37
- Submitted batch job 7606390
38
 
39
 
40
 
 
1
+ slurm submission log: 2024-05-17 11:42:19.909263
2
  created following sbatch script:
3
 
4
  ###############################
 
7
 
8
  #SBATCH --account=nlp
9
  #SBATCH --cpus-per-task=16
10
+ #SBATCH --dependency=afterok:7625429
11
  #SBATCH --gres=gpu:1
12
+ #SBATCH --job-name=tthrush-job-3702838
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_more_data/pythia-70m_piqa/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/pythia-70m_piqa,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/pythia-70m_piqa/perf'
28
 
29
  ###############################
30
 
 
34
  ###############################
35
  slurm submission output
36
 
37
+ Submitted batch job 7625430
38
 
39
 
40
 
logs/events.out.tfevents.1715991452.sphinx2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b1a05dbc500bc5ab1bda5cd149d7b36ab74c4fae2aba28ff2c9a7b6271bbba1
3
+ size 95376
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:230655d690d27602231861ae6fb8860826a5d999c857d75b99ea408bd43c5d95
3
  size 281715176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d81c43125e8d6cf5c649f2ee162fdd68b9c8a127e463f79f7f060659106d15c
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:a9d9b3fd6d467819e2aaaf96d660e4fa87d4f8e77cdd33621121defc7b7aef7e
3
- size 5112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8393c460eb50590ae60427791c221a45176e7cf1659cd2b0b8665a63ce559b8
3
+ size 5176