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
6265804
•
1 Parent(s): 53f566a

Training in progress, epoch 1

Browse files
Files changed (5) hide show
  1. eval_job_output.txt +7 -7
  2. logs/events.out.tfevents.1715681284.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: 2024-05-13 15:14:51.306399
2
  created following sbatch script:
3
 
4
  ###############################
@@ -7,24 +7,24 @@ created following sbatch script:
7
 
8
  #SBATCH --account=nlp
9
  #SBATCH --cpus-per-task=16
10
- #SBATCH --dependency=afterok:7606392
11
  #SBATCH --gres=gpu:1
12
- #SBATCH --job-name=tthrush-job-3035743
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_lambada/eval_job_output.txt
17
  #SBATCH --partition=sphinx
18
  #SBATCH --time=14-0
19
 
20
  # activate your desired anaconda environment
21
- . /nlp/scr/tthrush/miniconda3/envs/pretraining-coreset-selection/etc/profile.d/conda.sh ; conda activate pretraining-coreset-selection
22
 
23
  # cd to working directory
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_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_kmeans/pythia-70m_lambada/perf'
28
 
29
  ###############################
30
 
@@ -34,7 +34,7 @@ submission to slurm complete!
34
  ###############################
35
  slurm submission output
36
 
37
- Submitted batch job 7606393
38
 
39
 
40
 
 
1
+ slurm submission log: 2024-05-13 22:25:17.263290
2
  created following sbatch script:
3
 
4
  ###############################
 
7
 
8
  #SBATCH --account=nlp
9
  #SBATCH --cpus-per-task=16
10
+ #SBATCH --dependency=afterok:7608407
11
  #SBATCH --gres=gpu:1
12
+ #SBATCH --job-name=tthrush-job-3643749
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_basic/pythia-70m_lambada/eval_job_output.txt
17
  #SBATCH --partition=sphinx
18
  #SBATCH --time=14-0
19
 
20
  # activate your desired anaconda environment
21
+ . /nlp/scr/tthrush/miniconda3/etc/profile.d/conda.sh ; conda activate pretraining-coreset-selection
22
 
23
  # cd to working directory
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_basic/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_basic/pythia-70m_lambada/perf'
28
 
29
  ###############################
30
 
 
34
  ###############################
35
  slurm submission output
36
 
37
+ Submitted batch job 7608408
38
 
39
 
40
 
logs/events.out.tfevents.1715681284.sphinx2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c27a100b5825883b141b602191e91448caf7b728659d8ccd235b58d159c54591
3
+ size 10969
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0f8dcf0725db6f7b0fff4c58b247010a659751395d53d87596342604c18e031d
3
  size 281715176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfa0c63ce6c07778d7f034ccae2c3e0eb41385b0c7e4f751101b3bbe6e70c94a
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 sha256:1e92f5e13116104b7ed7ba9ca109800719e24435f79b910350b44b0559d0237a
3
  size 5112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d23c36ce5b084128790b26ccc616e7a9cd0fd35093c93895ed9a1a7f724a468
3
  size 5112