Training in progress, epoch 0
Browse files- eval_job_output.txt +12 -54
- logs/events.out.tfevents.1717044033.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-
|
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/
|
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/
|
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-
|
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/
|
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/
|
70 |
|
71 |
###############################
|
72 |
|
@@ -76,49 +76,7 @@ submission to slurm complete!
|
|
76 |
###############################
|
77 |
slurm submission output
|
78 |
|
79 |
-
Submitted batch job
|
80 |
-
|
81 |
-
|
82 |
-
|
83 |
-
###############################
|
84 |
-
|
85 |
-
slurm submission log: 2024-05-27 23:24:09.065268
|
86 |
-
created following sbatch script:
|
87 |
-
|
88 |
-
###############################
|
89 |
-
|
90 |
-
#!/bin/bash
|
91 |
-
|
92 |
-
#SBATCH --account=nlp
|
93 |
-
#SBATCH --cpus-per-task=16
|
94 |
-
#SBATCH --dependency=afterok:7659790
|
95 |
-
#SBATCH --gres=gpu:1
|
96 |
-
#SBATCH --job-name=tthrush-job-1491095
|
97 |
-
#SBATCH --mem=60G
|
98 |
-
#SBATCH --nodelist=sphinx1
|
99 |
-
#SBATCH --open-mode=append
|
100 |
-
#SBATCH --output=/juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/test_ordinal_projection_big_diff/llms/pythia-70m_default_1/eval_job_output.txt
|
101 |
-
#SBATCH --partition=sphinx
|
102 |
-
#SBATCH --time=14-0
|
103 |
-
|
104 |
-
# activate your desired anaconda environment
|
105 |
-
. /nlp/scr/tthrush/miniconda3/etc/profile.d/conda.sh ; conda activate pretraining-coreset-selection
|
106 |
-
|
107 |
-
# cd to working directory
|
108 |
-
cd .
|
109 |
-
|
110 |
-
# launch commands
|
111 |
-
srun --unbuffered run_as_child_processes 'lm_eval --model hf --model_args pretrained=/juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/test_ordinal_projection_big_diff/llms/pythia-70m_default_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/test_ordinal_projection_big_diff/llms/pythia-70m_default_1/perf'
|
112 |
-
|
113 |
-
###############################
|
114 |
-
|
115 |
-
submission to slurm complete!
|
116 |
-
|
117 |
-
|
118 |
-
###############################
|
119 |
-
slurm submission output
|
120 |
-
|
121 |
-
Submitted batch job 7659791
|
122 |
|
123 |
|
124 |
|
|
|
1 |
+
slurm submission log: 2024-05-29 11:13:31.307422
|
2 |
created following sbatch script:
|
3 |
|
4 |
###############################
|
|
|
7 |
|
8 |
#SBATCH --account=nlp
|
9 |
#SBATCH --cpus-per-task=16
|
10 |
+
#SBATCH --dependency=afterok:7667618
|
11 |
#SBATCH --gres=gpu:1
|
12 |
+
#SBATCH --job-name=tthrush-job-4528189
|
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/scaling_law_ridge_post_hoc_projection/llms/pythia-70m_default_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/scaling_law_ridge_post_hoc_projection/llms/pythia-70m_default_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/scaling_law_ridge_post_hoc_projection/llms/pythia-70m_default_1/perf'
|
28 |
|
29 |
###############################
|
30 |
|
|
|
34 |
###############################
|
35 |
slurm submission output
|
36 |
|
37 |
+
Submitted batch job 7667619
|
38 |
|
39 |
|
40 |
|
41 |
###############################
|
42 |
|
43 |
+
slurm submission log: 2024-05-29 16:28:53.263828
|
44 |
created following sbatch script:
|
45 |
|
46 |
###############################
|
|
|
49 |
|
50 |
#SBATCH --account=nlp
|
51 |
#SBATCH --cpus-per-task=16
|
52 |
+
#SBATCH --dependency=afterok:7668774
|
53 |
#SBATCH --gres=gpu:1
|
54 |
+
#SBATCH --job-name=tthrush-job-2556097
|
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/scaling_law_ridge_post_hoc_projection/llms/pythia-70m_default_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/scaling_law_ridge_post_hoc_projection/llms/pythia-70m_default_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/scaling_law_ridge_post_hoc_projection/llms/pythia-70m_default_1/perf'
|
70 |
|
71 |
###############################
|
72 |
|
|
|
76 |
###############################
|
77 |
slurm submission output
|
78 |
|
79 |
+
Submitted batch job 7668775
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
80 |
|
81 |
|
82 |
|
logs/events.out.tfevents.1717044033.sphinx2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0101cf325456456ff8069be0df5e8959ea25bcf0839a5e0090d852988b5dfe0f
|
3 |
+
size 95750
|
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 sha256:81e845c709a9a347172378d5fae8ee755b4d0428b3f168d9e3adda5472e81fa5
|
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:ea86094b90a105bd9f738af535472619b216dc0ec0b2cf4964bc4b9c23a5798d
|
3 |
size 5240
|