Training in progress, epoch 0
Browse files- eval_job_output.txt +18 -60
- logs/events.out.tfevents.1716893914.sphinx2 +3 -0
- model.safetensors +1 -1
- train_job_output.txt +0 -0
- training_args.bin +2 -2
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 |
|
@@ -76,13 +76,13 @@ 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-
|
86 |
created following sbatch script:
|
87 |
|
88 |
###############################
|
@@ -91,13 +91,13 @@ created following sbatch script:
|
|
91 |
|
92 |
#SBATCH --account=nlp
|
93 |
#SBATCH --cpus-per-task=16
|
94 |
-
#SBATCH --dependency=afterok:
|
95 |
#SBATCH --gres=gpu:1
|
96 |
-
#SBATCH --job-name=tthrush-job-
|
97 |
#SBATCH --mem=60G
|
98 |
#SBATCH --nodelist=sphinx1
|
99 |
#SBATCH --open-mode=append
|
100 |
-
#SBATCH --output=/juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/
|
101 |
#SBATCH --partition=sphinx
|
102 |
#SBATCH --time=14-0
|
103 |
|
@@ -108,7 +108,7 @@ created following sbatch script:
|
|
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/
|
112 |
|
113 |
###############################
|
114 |
|
@@ -118,49 +118,7 @@ submission to slurm complete!
|
|
118 |
###############################
|
119 |
slurm submission output
|
120 |
|
121 |
-
Submitted batch job
|
122 |
-
|
123 |
-
|
124 |
-
|
125 |
-
###############################
|
126 |
-
|
127 |
-
slurm submission log: 2024-05-26 23:16:37.954366
|
128 |
-
created following sbatch script:
|
129 |
-
|
130 |
-
###############################
|
131 |
-
|
132 |
-
#!/bin/bash
|
133 |
-
|
134 |
-
#SBATCH --account=nlp
|
135 |
-
#SBATCH --cpus-per-task=16
|
136 |
-
#SBATCH --dependency=afterok:7653692
|
137 |
-
#SBATCH --gres=gpu:1
|
138 |
-
#SBATCH --job-name=tthrush-job-1152535
|
139 |
-
#SBATCH --mem=60G
|
140 |
-
#SBATCH --nodelist=sphinx1
|
141 |
-
#SBATCH --open-mode=append
|
142 |
-
#SBATCH --output=/juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/test_ordinal_projection/llms/pythia-70m_default_1/eval_job_output.txt
|
143 |
-
#SBATCH --partition=sphinx
|
144 |
-
#SBATCH --time=14-0
|
145 |
-
|
146 |
-
# activate your desired anaconda environment
|
147 |
-
. /nlp/scr/tthrush/miniconda3/etc/profile.d/conda.sh ; conda activate pretraining-coreset-selection
|
148 |
-
|
149 |
-
# cd to working directory
|
150 |
-
cd .
|
151 |
-
|
152 |
-
# launch commands
|
153 |
-
srun --unbuffered run_as_child_processes 'lm_eval --model hf --model_args pretrained=/juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/test_ordinal_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/test_ordinal_projection/llms/pythia-70m_default_1/perf'
|
154 |
-
|
155 |
-
###############################
|
156 |
-
|
157 |
-
submission to slurm complete!
|
158 |
-
|
159 |
-
|
160 |
-
###############################
|
161 |
-
slurm submission output
|
162 |
-
|
163 |
-
Submitted batch job 7653693
|
164 |
|
165 |
|
166 |
|
|
|
1 |
+
slurm submission log: 2024-05-27 12:34:01.996971
|
2 |
created following sbatch script:
|
3 |
|
4 |
###############################
|
|
|
7 |
|
8 |
#SBATCH --account=nlp
|
9 |
#SBATCH --cpus-per-task=16
|
10 |
+
#SBATCH --dependency=afterok:7656642
|
11 |
#SBATCH --gres=gpu:1
|
12 |
+
#SBATCH --job-name=tthrush-job-3294461
|
13 |
#SBATCH --mem=60G
|
14 |
#SBATCH --nodelist=sphinx1
|
15 |
#SBATCH --open-mode=append
|
16 |
+
#SBATCH --output=/juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/test_ordinal_projection_big_diff/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/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'
|
28 |
|
29 |
###############################
|
30 |
|
|
|
34 |
###############################
|
35 |
slurm submission output
|
36 |
|
37 |
+
Submitted batch job 7656643
|
38 |
|
39 |
|
40 |
|
41 |
###############################
|
42 |
|
43 |
+
slurm submission log: 2024-05-27 23:18:48.257074
|
44 |
created following sbatch script:
|
45 |
|
46 |
###############################
|
|
|
49 |
|
50 |
#SBATCH --account=nlp
|
51 |
#SBATCH --cpus-per-task=16
|
52 |
+
#SBATCH --dependency=afterok:7659748
|
53 |
#SBATCH --gres=gpu:1
|
54 |
+
#SBATCH --job-name=tthrush-job-4032027
|
55 |
#SBATCH --mem=60G
|
56 |
#SBATCH --nodelist=sphinx1
|
57 |
#SBATCH --open-mode=append
|
58 |
+
#SBATCH --output=/juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/test_ordinal_projection_big_diff/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/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'
|
70 |
|
71 |
###############################
|
72 |
|
|
|
76 |
###############################
|
77 |
slurm submission output
|
78 |
|
79 |
+
Submitted batch job 7659749
|
80 |
|
81 |
|
82 |
|
83 |
###############################
|
84 |
|
85 |
+
slurm submission log: 2024-05-27 23:24:09.065268
|
86 |
created following sbatch script:
|
87 |
|
88 |
###############################
|
|
|
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 |
|
|
|
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 |
|
|
|
118 |
###############################
|
119 |
slurm submission output
|
120 |
|
121 |
+
Submitted batch job 7659791
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
122 |
|
123 |
|
124 |
|
logs/events.out.tfevents.1716893914.sphinx2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:46d4bdbfbe5761d7056e13b715344a777583501e6d625796459f1236c5881dcc
|
3 |
+
size 11766
|
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 sha256:0b6eea337fa1f3d6e834370139d0769d4a0bb08ecacb7a2eb27fc5db7c7b7954
|
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
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:27bc4d89b732f28d40be81b5f6e283ed05e3aac6fb6fe01e1e2e7fe7f9b49605
|
3 |
+
size 5240
|