Training in progress, epoch 0
Browse files- eval_job_output.txt +248 -6
- logs/events.out.tfevents.1716462340.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 +7,255 @@ 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 +266,7 @@ 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 |
|
@@ -34,7 +276,7 @@ submission to slurm complete!
|
|
34 |
###############################
|
35 |
slurm submission output
|
36 |
|
37 |
-
Submitted batch job
|
38 |
|
39 |
|
40 |
|
|
|
1 |
+
slurm submission log: 2024-05-22 17:07:25.162212
|
2 |
created following sbatch script:
|
3 |
|
4 |
###############################
|
|
|
7 |
|
8 |
#SBATCH --account=nlp
|
9 |
#SBATCH --cpus-per-task=16
|
10 |
+
#SBATCH --dependency=afterok:7642740
|
11 |
#SBATCH --gres=gpu:1
|
12 |
+
#SBATCH --job-name=tthrush-job-2791360
|
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/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_constrained/llms/pythia-70m_sciq_1,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/test_ordinal_constrained/llms/pythia-70m_sciq_1/perf'
|
28 |
+
|
29 |
+
###############################
|
30 |
+
|
31 |
+
submission to slurm complete!
|
32 |
+
|
33 |
+
|
34 |
+
###############################
|
35 |
+
slurm submission output
|
36 |
+
|
37 |
+
Submitted batch job 7642741
|
38 |
+
|
39 |
+
|
40 |
+
|
41 |
+
###############################
|
42 |
+
|
43 |
+
slurm submission log: 2024-05-22 17:23:51.579657
|
44 |
+
created following sbatch script:
|
45 |
+
|
46 |
+
###############################
|
47 |
+
|
48 |
+
#!/bin/bash
|
49 |
+
|
50 |
+
#SBATCH --account=nlp
|
51 |
+
#SBATCH --cpus-per-task=16
|
52 |
+
#SBATCH --dependency=afterok:7642780
|
53 |
+
#SBATCH --gres=gpu:1
|
54 |
+
#SBATCH --job-name=tthrush-job-1978619
|
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/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/llms/pythia-70m_sciq_1,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/test_ordinal_constrained/llms/pythia-70m_sciq_1/perf'
|
70 |
+
|
71 |
+
###############################
|
72 |
+
|
73 |
+
submission to slurm complete!
|
74 |
+
|
75 |
+
|
76 |
+
###############################
|
77 |
+
slurm submission output
|
78 |
+
|
79 |
+
Submitted batch job 7642781
|
80 |
+
|
81 |
+
|
82 |
+
|
83 |
+
###############################
|
84 |
+
|
85 |
+
slurm submission log: 2024-05-22 17:29:15.965569
|
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:7642805
|
95 |
+
#SBATCH --gres=gpu:1
|
96 |
+
#SBATCH --job-name=tthrush-job-2597090
|
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/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/llms/pythia-70m_sciq_1,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/test_ordinal_constrained/llms/pythia-70m_sciq_1/perf'
|
112 |
+
|
113 |
+
###############################
|
114 |
+
|
115 |
+
submission to slurm complete!
|
116 |
+
|
117 |
+
|
118 |
+
###############################
|
119 |
+
slurm submission output
|
120 |
+
|
121 |
+
Submitted batch job 7642806
|
122 |
+
|
123 |
+
|
124 |
+
|
125 |
+
###############################
|
126 |
+
|
127 |
+
/var/lib/slurm/slurmd/job7642806/slurm_script: line 16: /nlp/scr/tthrush/miniconda3/envs/pretraining-coreset-selection/etc/profile.d/conda.sh: No such file or directory
|
128 |
+
|
129 |
+
CommandNotFoundError: Your shell has not been properly configured to use 'conda activate'.
|
130 |
+
To initialize your shell, run
|
131 |
+
|
132 |
+
$ conda init <SHELL_NAME>
|
133 |
+
|
134 |
+
Currently supported shells are:
|
135 |
+
- bash
|
136 |
+
- fish
|
137 |
+
- tcsh
|
138 |
+
- xonsh
|
139 |
+
- zsh
|
140 |
+
- powershell
|
141 |
+
|
142 |
+
See 'conda init --help' for more information and options.
|
143 |
+
|
144 |
+
IMPORTANT: You may need to close and restart your shell after running 'conda init'.
|
145 |
+
|
146 |
+
|
147 |
+
###############################
|
148 |
+
start time: 2024-05-22 17:31:53.790973
|
149 |
+
machine: sphinx1
|
150 |
+
conda env: pretraining-coreset-selection
|
151 |
+
###############################
|
152 |
+
running following processes
|
153 |
+
|
154 |
+
lm_eval --model hf --model_args pretrained=/juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/test_ordinal_constrained/llms/pythia-70m_sciq_1,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/test_ordinal_constrained/llms/pythia-70m_sciq_1/perf
|
155 |
+
|
156 |
+
|
157 |
+
###############################
|
158 |
+
command outputs:
|
159 |
+
|
160 |
+
|
161 |
+
2024-05-22:17:31:59,220 INFO [utils.py:145] Note: detected 255 virtual cores but NumExpr set to maximum of 64, check "NUMEXPR_MAX_THREADS" environment variable.
|
162 |
+
2024-05-22:17:31:59,220 INFO [utils.py:148] Note: NumExpr detected 255 cores but "NUMEXPR_MAX_THREADS" not set, so enforcing safe limit of 8.
|
163 |
+
2024-05-22:17:31:59,220 INFO [utils.py:160] NumExpr defaulting to 8 threads.
|
164 |
+
2024-05-22:17:31:59,893 INFO [config.py:58] PyTorch version 2.2.2 available.
|
165 |
+
2024-05-22:17:32:04,203 INFO [__main__.py:156] Verbosity set to INFO
|
166 |
+
2024-05-22:17:32:14,116 WARNING [__init__.py:194] Some tasks could not be loaded due to missing dependencies. Run with `--verbosity DEBUG` for full details.
|
167 |
+
/nlp/scr/tthrush/miniconda3/envs/pretraining-coreset-selection/lib/python3.10/site-packages/datasets/load.py:1429: FutureWarning: The repository for hails/mmlu_no_train contains custom code which must be executed to correctly load the dataset. You can inspect the repository content at https://hf.co/datasets/hails/mmlu_no_train
|
168 |
+
You can avoid this message in future by passing the argument `trust_remote_code=True`.
|
169 |
+
Passing `trust_remote_code=True` will be mandatory to load this dataset from the next major release of `datasets`.
|
170 |
+
warnings.warn(
|
171 |
+
2024-05-22:17:33:33,299 WARNING [__init__.py:194] Some tasks could not be loaded due to missing dependencies. Run with `--verbosity DEBUG` for full details.
|
172 |
+
2024-05-22:17:33:33,305 INFO [__main__.py:229] Selected Tasks: ['arc_easy', 'lambada', 'piqa', 'sciq', 'xnli_en', 'xnli_fr']
|
173 |
+
2024-05-22:17:33:33,714 INFO [huggingface.py:148] Using device 'cuda'
|
174 |
+
Traceback (most recent call last):
|
175 |
+
File "/nlp/scr/tthrush/miniconda3/envs/pretraining-coreset-selection/bin/lm_eval", line 8, in <module>
|
176 |
+
sys.exit(cli_evaluate())
|
177 |
+
File "/sailhome/tthrush/lm-evaluation-harness/lm_eval/__main__.py", line 231, in cli_evaluate
|
178 |
+
results = evaluator.simple_evaluate(
|
179 |
+
File "/sailhome/tthrush/lm-evaluation-harness/lm_eval/utils.py", line 415, in _wrapper
|
180 |
+
return fn(*args, **kwargs)
|
181 |
+
File "/sailhome/tthrush/lm-evaluation-harness/lm_eval/evaluator.py", line 98, in simple_evaluate
|
182 |
+
lm = lm_eval.api.registry.get_model(model).create_from_arg_string(
|
183 |
+
File "/sailhome/tthrush/lm-evaluation-harness/lm_eval/api/model.py", line 134, in create_from_arg_string
|
184 |
+
return cls(**args, **args2)
|
185 |
+
File "/sailhome/tthrush/lm-evaluation-harness/lm_eval/models/huggingface.py", line 174, in __init__
|
186 |
+
self._get_config(
|
187 |
+
File "/sailhome/tthrush/lm-evaluation-harness/lm_eval/models/huggingface.py", line 420, in _get_config
|
188 |
+
self._config = transformers.AutoConfig.from_pretrained(
|
189 |
+
File "/nlp/scr/tthrush/miniconda3/envs/pretraining-coreset-selection/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py", line 928, in from_pretrained
|
190 |
+
config_dict, unused_kwargs = PretrainedConfig.get_config_dict(pretrained_model_name_or_path, **kwargs)
|
191 |
+
File "/nlp/scr/tthrush/miniconda3/envs/pretraining-coreset-selection/lib/python3.10/site-packages/transformers/configuration_utils.py", line 631, in get_config_dict
|
192 |
+
config_dict, kwargs = cls._get_config_dict(pretrained_model_name_or_path, **kwargs)
|
193 |
+
File "/nlp/scr/tthrush/miniconda3/envs/pretraining-coreset-selection/lib/python3.10/site-packages/transformers/configuration_utils.py", line 686, in _get_config_dict
|
194 |
+
resolved_config_file = cached_file(
|
195 |
+
File "/nlp/scr/tthrush/miniconda3/envs/pretraining-coreset-selection/lib/python3.10/site-packages/transformers/utils/hub.py", line 369, in cached_file
|
196 |
+
raise EnvironmentError(
|
197 |
+
OSError: /juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/test_ordinal_constrained/llms/pythia-70m_sciq_1 does not appear to have a file named config.json. Checkout 'https://huggingface.co//juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/test_ordinal_constrained/llms/pythia-70m_sciq_1/tree/main' for available files.
|
198 |
+
###############################
|
199 |
+
end time: 2024-05-22 17:33:43.911118
|
200 |
+
elapsed time: 0:01:50.120145
|
201 |
+
slurm submission log: 2024-05-22 17:41:39.457215
|
202 |
+
created following sbatch script:
|
203 |
+
|
204 |
+
###############################
|
205 |
+
|
206 |
+
#!/bin/bash
|
207 |
+
|
208 |
+
#SBATCH --account=nlp
|
209 |
+
#SBATCH --cpus-per-task=16
|
210 |
+
#SBATCH --dependency=afterok:7642834
|
211 |
+
#SBATCH --gres=gpu:1
|
212 |
+
#SBATCH --job-name=tthrush-job-24240
|
213 |
+
#SBATCH --mem=60G
|
214 |
+
#SBATCH --nodelist=sphinx1
|
215 |
+
#SBATCH --open-mode=append
|
216 |
+
#SBATCH --output=/juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/test_ordinal_constrained/llms/pythia-70m_sciq_1/eval_job_output.txt
|
217 |
+
#SBATCH --partition=sphinx
|
218 |
+
#SBATCH --time=14-0
|
219 |
+
|
220 |
+
# activate your desired anaconda environment
|
221 |
+
. /nlp/scr/tthrush/miniconda3/envs/pretraining-coreset-selection/etc/profile.d/conda.sh ; conda activate pretraining-coreset-selection
|
222 |
+
|
223 |
+
# cd to working directory
|
224 |
+
cd .
|
225 |
+
|
226 |
+
# launch commands
|
227 |
+
srun --unbuffered run_as_child_processes 'lm_eval --model hf --model_args pretrained=/juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/test_ordinal_constrained/llms/pythia-70m_sciq_1,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/test_ordinal_constrained/llms/pythia-70m_sciq_1/perf'
|
228 |
+
|
229 |
+
###############################
|
230 |
+
|
231 |
+
submission to slurm complete!
|
232 |
+
|
233 |
+
|
234 |
+
###############################
|
235 |
+
slurm submission output
|
236 |
+
|
237 |
+
Submitted batch job 7642835
|
238 |
+
|
239 |
+
|
240 |
+
|
241 |
+
###############################
|
242 |
+
|
243 |
+
slurm submission log: 2024-05-22 19:52:23.060911
|
244 |
+
created following sbatch script:
|
245 |
+
|
246 |
+
###############################
|
247 |
+
|
248 |
+
#!/bin/bash
|
249 |
+
|
250 |
+
#SBATCH --account=nlp
|
251 |
+
#SBATCH --cpus-per-task=16
|
252 |
+
#SBATCH --dependency=afterok:7643057
|
253 |
+
#SBATCH --gres=gpu:1
|
254 |
+
#SBATCH --job-name=tthrush-job-4137796
|
255 |
+
#SBATCH --mem=60G
|
256 |
+
#SBATCH --nodelist=sphinx1
|
257 |
+
#SBATCH --open-mode=append
|
258 |
+
#SBATCH --output=/juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/test_ordinal_constrained/llms/pythia-70m_sciq_1/eval_job_output.txt
|
259 |
#SBATCH --partition=sphinx
|
260 |
#SBATCH --time=14-0
|
261 |
|
|
|
266 |
cd .
|
267 |
|
268 |
# launch commands
|
269 |
+
srun --unbuffered run_as_child_processes 'lm_eval --model hf --model_args pretrained=/juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/test_ordinal_constrained/llms/pythia-70m_sciq_1,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/test_ordinal_constrained/llms/pythia-70m_sciq_1/perf'
|
270 |
|
271 |
###############################
|
272 |
|
|
|
276 |
###############################
|
277 |
slurm submission output
|
278 |
|
279 |
+
Submitted batch job 7643058
|
280 |
|
281 |
|
282 |
|
logs/events.out.tfevents.1716462340.sphinx2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ceb8dfead4db2cd215bac5aca5134227d88e37cd309967443488c1220bdead2f
|
3 |
+
size 95428
|
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 sha256:5d1d0b5f6fe2fd1b3e778eb06905f9ff0b46cd859dd0d2696a8fdd8dfb3af932
|
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 5176
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:42604c6e8628be2643fe1460d9bd416ac8e71af2f5f0e7182a340f5cb4e9907f
|
3 |
size 5176
|