Training in progress, epoch 0
Browse files- eval_job_output.txt +12 -12
- logs/events.out.tfevents.1717088355.sphinx2 +3 -0
- model.safetensors +1 -1
- train_job_output.txt +0 -0
- training_args.bin +1 -1
eval_job_output.txt
CHANGED
@@ -1,4 +1,4 @@
|
|
1 |
-
slurm submission log: 2024-05-29 11:13:
|
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:
|
11 |
#SBATCH --gres=gpu:1
|
12 |
-
#SBATCH --job-name=tthrush-job-
|
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/
|
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/
|
28 |
|
29 |
###############################
|
30 |
|
@@ -34,13 +34,13 @@ submission to slurm complete!
|
|
34 |
###############################
|
35 |
slurm submission output
|
36 |
|
37 |
-
Submitted batch job
|
38 |
|
39 |
|
40 |
|
41 |
###############################
|
42 |
|
43 |
-
slurm submission log: 2024-05-29
|
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:
|
53 |
#SBATCH --gres=gpu:1
|
54 |
-
#SBATCH --job-name=tthrush-job-
|
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/
|
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/
|
70 |
|
71 |
###############################
|
72 |
|
@@ -76,7 +76,7 @@ submission to slurm complete!
|
|
76 |
###############################
|
77 |
slurm submission output
|
78 |
|
79 |
-
Submitted batch job
|
80 |
|
81 |
|
82 |
|
|
|
1 |
+
slurm submission log: 2024-05-29 11:13:45.364693
|
2 |
created following sbatch script:
|
3 |
|
4 |
###############################
|
|
|
7 |
|
8 |
#SBATCH --account=nlp
|
9 |
#SBATCH --cpus-per-task=16
|
10 |
+
#SBATCH --dependency=afterok:7667666
|
11 |
#SBATCH --gres=gpu:1
|
12 |
+
#SBATCH --job-name=tthrush-job-756186
|
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_sciq_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_post_hoc_projection/llms/pythia-70m_sciq_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_sciq_1/perf'
|
28 |
|
29 |
###############################
|
30 |
|
|
|
34 |
###############################
|
35 |
slurm submission output
|
36 |
|
37 |
+
Submitted batch job 7667667
|
38 |
|
39 |
|
40 |
|
41 |
###############################
|
42 |
|
43 |
+
slurm submission log: 2024-05-29 23:06:18.859369
|
44 |
created following sbatch script:
|
45 |
|
46 |
###############################
|
|
|
49 |
|
50 |
#SBATCH --account=nlp
|
51 |
#SBATCH --cpus-per-task=16
|
52 |
+
#SBATCH --dependency=afterok:7670041
|
53 |
#SBATCH --gres=gpu:1
|
54 |
+
#SBATCH --job-name=tthrush-job-2958657
|
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_sciq_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_post_hoc_projection/llms/pythia-70m_sciq_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_sciq_1/perf'
|
70 |
|
71 |
###############################
|
72 |
|
|
|
76 |
###############################
|
77 |
slurm submission output
|
78 |
|
79 |
+
Submitted batch job 7670042
|
80 |
|
81 |
|
82 |
|
logs/events.out.tfevents.1717088355.sphinx2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8b3c4d5abc222ab1ef768e47ad702284105b1a536d13ae6afb4df91ce5b0ea57
|
3 |
+
size 95497
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 281715176
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cf24ad94ee41b89160c0c9b6bed80def6b32035743c3017c614dbda5be8497b3
|
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:
|
3 |
size 5240
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:df628b70a115e806ac64421171dd0f02966ee9a198b0b00792fc1f100bbeefbd
|
3 |
size 5240
|