Tristan commited on
Commit
cd5c9f8
1 Parent(s): 7571c8a

Training in progress, epoch 0

Browse files
eval_job_output.txt CHANGED
@@ -1,4 +1,4 @@
1
- slurm submission log: 2024-05-25 22:01:16.904818
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:7651389
11
  #SBATCH --gres=gpu:1
12
- #SBATCH --job-name=tthrush-job-1695127
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_constrained_big_upsample/llms/pythia-70m_sciq_1/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/test_ordinal_constrained_big_upsample/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/test_ordinal_constrained_big_upsample/llms/pythia-70m_sciq_1/perf'
28
 
29
  ###############################
30
 
@@ -34,13 +34,13 @@ submission to slurm complete!
34
  ###############################
35
  slurm submission output
36
 
37
- Submitted batch job 7651390
38
 
39
 
40
 
41
  ###############################
42
 
43
- slurm submission log: 2024-05-25 22:02:26.073999
44
  created following sbatch script:
45
 
46
  ###############################
@@ -49,24 +49,24 @@ created following sbatch script:
49
 
50
  #SBATCH --account=nlp
51
  #SBATCH --cpus-per-task=16
52
- #SBATCH --dependency=afterok:7651420
53
  #SBATCH --gres=gpu:1
54
- #SBATCH --job-name=tthrush-job-1839927
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_constrained_big_upsample/llms/pythia-70m_sciq_1/eval_job_output.txt
59
  #SBATCH --partition=sphinx
60
  #SBATCH --time=14-0
61
 
62
  # activate your desired anaconda environment
63
- . /nlp/scr/tthrush/miniconda3/envs/pretraining-coreset-selection/etc/profile.d/conda.sh ; conda activate pretraining-coreset-selection
64
 
65
  # cd to working directory
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_constrained_big_upsample/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/test_ordinal_constrained_big_upsample/llms/pythia-70m_sciq_1/perf'
70
 
71
  ###############################
72
 
@@ -76,13 +76,13 @@ submission to slurm complete!
76
  ###############################
77
  slurm submission output
78
 
79
- Submitted batch job 7651421
80
 
81
 
82
 
83
  ###############################
84
 
85
- slurm submission log: 2024-05-25 22:12:51.200849
86
  created following sbatch script:
87
 
88
  ###############################
@@ -91,24 +91,24 @@ created following sbatch script:
91
 
92
  #SBATCH --account=nlp
93
  #SBATCH --cpus-per-task=16
94
- #SBATCH --dependency=afterok:7651461
95
  #SBATCH --gres=gpu:1
96
- #SBATCH --job-name=tthrush-job-1012098
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_constrained_big_upsample/llms/pythia-70m_sciq_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/envs/pretraining-coreset-selection/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_constrained_big_upsample/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/test_ordinal_constrained_big_upsample/llms/pythia-70m_sciq_1/perf'
112
 
113
  ###############################
114
 
@@ -118,13 +118,13 @@ submission to slurm complete!
118
  ###############################
119
  slurm submission output
120
 
121
- Submitted batch job 7651462
122
 
123
 
124
 
125
  ###############################
126
 
127
- slurm submission log: 2024-05-25 22:15:56.896223
128
  created following sbatch script:
129
 
130
  ###############################
@@ -133,24 +133,24 @@ created following sbatch script:
133
 
134
  #SBATCH --account=nlp
135
  #SBATCH --cpus-per-task=16
136
- #SBATCH --dependency=afterok:7651489
137
  #SBATCH --gres=gpu:1
138
- #SBATCH --job-name=tthrush-job-4600543
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_constrained_big_upsample/llms/pythia-70m_sciq_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/envs/pretraining-coreset-selection/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_constrained_big_upsample/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/test_ordinal_constrained_big_upsample/llms/pythia-70m_sciq_1/perf'
154
 
155
  ###############################
156
 
@@ -160,49 +160,7 @@ submission to slurm complete!
160
  ###############################
161
  slurm submission output
162
 
163
- Submitted batch job 7651490
164
-
165
-
166
-
167
- ###############################
168
-
169
- slurm submission log: 2024-05-25 22:18:15.756710
170
- created following sbatch script:
171
-
172
- ###############################
173
-
174
- #!/bin/bash
175
-
176
- #SBATCH --account=nlp
177
- #SBATCH --cpus-per-task=16
178
- #SBATCH --dependency=afterok:7651519
179
- #SBATCH --gres=gpu:1
180
- #SBATCH --job-name=tthrush-job-3920714
181
- #SBATCH --mem=60G
182
- #SBATCH --nodelist=sphinx1
183
- #SBATCH --open-mode=append
184
- #SBATCH --output=/juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/test_ordinal_constrained_big_upsample/llms/pythia-70m_sciq_1/eval_job_output.txt
185
- #SBATCH --partition=sphinx
186
- #SBATCH --time=14-0
187
-
188
- # activate your desired anaconda environment
189
- . /nlp/scr/tthrush/miniconda3/envs/pretraining-coreset-selection/etc/profile.d/conda.sh ; conda activate pretraining-coreset-selection
190
-
191
- # cd to working directory
192
- cd .
193
-
194
- # launch commands
195
- srun --unbuffered run_as_child_processes 'lm_eval --model hf --model_args pretrained=/juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/test_ordinal_constrained_big_upsample/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/test_ordinal_constrained_big_upsample/llms/pythia-70m_sciq_1/perf'
196
-
197
- ###############################
198
-
199
- submission to slurm complete!
200
-
201
-
202
- ###############################
203
- slurm submission output
204
-
205
- Submitted batch job 7651520
206
 
207
 
208
 
 
1
+ slurm submission log: 2024-05-26 22:30:16.881627
2
  created following sbatch script:
3
 
4
  ###############################
 
7
 
8
  #SBATCH --account=nlp
9
  #SBATCH --cpus-per-task=16
10
+ #SBATCH --dependency=afterok:7653571
11
  #SBATCH --gres=gpu:1
12
+ #SBATCH --job-name=tthrush-job-1485795
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/llms/pythia-70m_sciq_1/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/test_ordinal_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/test_ordinal_projection/llms/pythia-70m_sciq_1/perf'
28
 
29
  ###############################
30
 
 
34
  ###############################
35
  slurm submission output
36
 
37
+ Submitted batch job 7653572
38
 
39
 
40
 
41
  ###############################
42
 
43
+ slurm submission log: 2024-05-26 22:32:57.780747
44
  created following sbatch script:
45
 
46
  ###############################
 
49
 
50
  #SBATCH --account=nlp
51
  #SBATCH --cpus-per-task=16
52
+ #SBATCH --dependency=afterok:7653601
53
  #SBATCH --gres=gpu:1
54
+ #SBATCH --job-name=tthrush-job-1570626
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/llms/pythia-70m_sciq_1/eval_job_output.txt
59
  #SBATCH --partition=sphinx
60
  #SBATCH --time=14-0
61
 
62
  # activate your desired anaconda environment
63
+ . /nlp/scr/tthrush/miniconda3/etc/profile.d/conda.sh ; conda activate pretraining-coreset-selection
64
 
65
  # cd to working directory
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/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/test_ordinal_projection/llms/pythia-70m_sciq_1/perf'
70
 
71
  ###############################
72
 
 
76
  ###############################
77
  slurm submission output
78
 
79
+ Submitted batch job 7653602
80
 
81
 
82
 
83
  ###############################
84
 
85
+ slurm submission log: 2024-05-26 22:58:10.061545
86
  created following sbatch script:
87
 
88
  ###############################
 
91
 
92
  #SBATCH --account=nlp
93
  #SBATCH --cpus-per-task=16
94
+ #SBATCH --dependency=afterok:7653656
95
  #SBATCH --gres=gpu:1
96
+ #SBATCH --job-name=tthrush-job-2260487
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/llms/pythia-70m_sciq_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/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/test_ordinal_projection/llms/pythia-70m_sciq_1/perf'
112
 
113
  ###############################
114
 
 
118
  ###############################
119
  slurm submission output
120
 
121
+ Submitted batch job 7653657
122
 
123
 
124
 
125
  ###############################
126
 
127
+ slurm submission log: 2024-05-26 23:16:43.694904
128
  created following sbatch script:
129
 
130
  ###############################
 
133
 
134
  #SBATCH --account=nlp
135
  #SBATCH --cpus-per-task=16
136
+ #SBATCH --dependency=afterok:7653713
137
  #SBATCH --gres=gpu:1
138
+ #SBATCH --job-name=tthrush-job-1947317
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_sciq_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_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/test_ordinal_projection/llms/pythia-70m_sciq_1/perf'
154
 
155
  ###############################
156
 
 
160
  ###############################
161
  slurm submission output
162
 
163
+ Submitted batch job 7653714
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
164
 
165
 
166
 
logs/events.out.tfevents.1716829581.sphinx2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25ef87f6540f776d967c4d8d36e2cb5f3d58dc2405ea906d0552b60895080725
3
+ size 11094
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b1fd836ec21c7a2c679ea96ed79df3709951f735a7f4fe1a592a3182e9b55154
3
  size 281715176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5db492fd28db820251fbd110ccd3f42c1428ec6e5dd84b1a8f105eeb39fc81cb
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 sha256:209af55204bf74f64a94dcd9521d29859d618933c50d5cfa614440e26a8531f0
3
- size 5240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:04627cb5fbe82be9fcc5f4e83b525aa07f866ab882c470a7103ad6fc1b58ed72
3
+ size 5176