Tristan commited on
Commit
cf0be43
1 Parent(s): de9ba50

Training in progress, epoch 2

Browse files
eval_job_output.txt CHANGED
@@ -1,4 +1,4 @@
1
- slurm submission log: 2024-05-07 15:08:38.996246
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:7543221
11
  #SBATCH --gres=gpu:1
12
- #SBATCH --job-name=tthrush-job-877403
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/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/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/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 7543222
38
 
39
 
40
 
 
1
+ slurm submission log: 2024-05-09 15:03:34.490765
2
  created following sbatch script:
3
 
4
  ###############################
 
7
 
8
  #SBATCH --account=nlp
9
  #SBATCH --cpus-per-task=16
10
+ #SBATCH --dependency=afterok:7592325
11
  #SBATCH --gres=gpu:1
12
+ #SBATCH --job-name=tthrush-job-707129
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_2/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_2/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_2/pythia-70m_lambada/perf'
28
 
29
  ###############################
30
 
 
34
  ###############################
35
  slurm submission output
36
 
37
+ Submitted batch job 7592326
38
 
39
 
40
 
logs/events.out.tfevents.1715303565.sphinx2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5560e4ba8225972986bbfd28d31104cbcf88c5f156fbb086d6a068b2ad03509
3
+ size 17709
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:79239e83d982053f7b191dfb5ffb0c52ff05f3f601f59e181c1528e24212d018
3
  size 281715176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ba04c0f0eea27dded26accdfbfd61e8dbc12deb36f4739651d625a75d71d3a4
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:eabd14498e75d2cb992b4852bc87cf7ca2e048acac80bda769059748c08de03e
3
- size 5048
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec3c176db2130799a9567203f329d022f06795f8c51369fa4dd4c083e05ea6d8
3
+ size 5112