Training in progress, epoch 0
Browse files- config.json +1 -1
- eval_job_output.txt +341 -59
- logs/events.out.tfevents.1716139274.sphinx2 +3 -0
- model.safetensors +1 -1
- train_job_output.txt +0 -0
- training_args.bin +2 -2
config.json
CHANGED
@@ -23,7 +23,7 @@
|
|
23 |
"rotary_pct": 0.25,
|
24 |
"tie_word_embeddings": false,
|
25 |
"torch_dtype": "float32",
|
26 |
-
"transformers_version": "4.
|
27 |
"use_cache": true,
|
28 |
"use_parallel_residual": true,
|
29 |
"vocab_size": 50304
|
|
|
23 |
"rotary_pct": 0.25,
|
24 |
"tie_word_embeddings": false,
|
25 |
"torch_dtype": "float32",
|
26 |
+
"transformers_version": "4.40.2",
|
27 |
"use_cache": true,
|
28 |
"use_parallel_residual": true,
|
29 |
"vocab_size": 50304
|
eval_job_output.txt
CHANGED
@@ -1,4 +1,4 @@
|
|
1 |
-
slurm submission log: 2024-05-
|
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:
|
11 |
#SBATCH --gres=gpu:1
|
12 |
-
#SBATCH --job-name=tthrush-job-
|
13 |
#SBATCH --mem=60G
|
14 |
#SBATCH --nodelist=sphinx2
|
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 |
|
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/
|
28 |
|
29 |
###############################
|
30 |
|
@@ -34,67 +34,265 @@ submission to slurm complete!
|
|
34 |
###############################
|
35 |
slurm submission output
|
36 |
|
37 |
-
Submitted batch job
|
38 |
|
39 |
|
40 |
|
41 |
###############################
|
42 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
43 |
###############################
|
44 |
-
|
45 |
-
|
46 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
47 |
###############################
|
48 |
-
running following processes
|
49 |
|
50 |
-
|
51 |
|
52 |
|
53 |
###############################
|
54 |
-
|
|
|
|
|
|
|
55 |
|
56 |
|
57 |
-
2024-05-08:16:46:16,301 INFO [utils.py:145] Note: detected 255 virtual cores but NumExpr set to maximum of 64, check "NUMEXPR_MAX_THREADS" environment variable.
|
58 |
-
2024-05-08:16:46:16,301 INFO [utils.py:148] Note: NumExpr detected 255 cores but "NUMEXPR_MAX_THREADS" not set, so enforcing safe limit of 8.
|
59 |
-
2024-05-08:16:46:16,301 INFO [utils.py:160] NumExpr defaulting to 8 threads.
|
60 |
-
2024-05-08:16:46:18,703 INFO [config.py:58] PyTorch version 2.2.2 available.
|
61 |
-
2024-05-08:16:46:38,285 INFO [__main__.py:156] Verbosity set to INFO
|
62 |
-
2024-05-08:16:46:52,372 WARNING [__init__.py:194] Some tasks could not be loaded due to missing dependencies. Run with `--verbosity DEBUG` for full details.
|
63 |
-
/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
|
64 |
-
You can avoid this message in future by passing the argument `trust_remote_code=True`.
|
65 |
-
Passing `trust_remote_code=True` will be mandatory to load this dataset from the next major release of `datasets`.
|
66 |
-
warnings.warn(
|
67 |
-
2024-05-08:16:48:12,611 WARNING [__init__.py:194] Some tasks could not be loaded due to missing dependencies. Run with `--verbosity DEBUG` for full details.
|
68 |
-
2024-05-08:16:48:12,617 INFO [__main__.py:229] Selected Tasks: ['arc_easy', 'lambada', 'piqa', 'sciq', 'xnli_en', 'xnli_fr']
|
69 |
-
2024-05-08:16:48:12,899 INFO [huggingface.py:148] Using device 'cuda'
|
70 |
-
Traceback (most recent call last):
|
71 |
-
File "/nlp/scr/tthrush/miniconda3/envs/pretraining-coreset-selection/bin/lm_eval", line 8, in <module>
|
72 |
-
sys.exit(cli_evaluate())
|
73 |
-
File "/sailhome/tthrush/lm-evaluation-harness/lm_eval/__main__.py", line 231, in cli_evaluate
|
74 |
-
results = evaluator.simple_evaluate(
|
75 |
-
File "/sailhome/tthrush/lm-evaluation-harness/lm_eval/utils.py", line 415, in _wrapper
|
76 |
-
return fn(*args, **kwargs)
|
77 |
-
File "/sailhome/tthrush/lm-evaluation-harness/lm_eval/evaluator.py", line 98, in simple_evaluate
|
78 |
-
lm = lm_eval.api.registry.get_model(model).create_from_arg_string(
|
79 |
-
File "/sailhome/tthrush/lm-evaluation-harness/lm_eval/api/model.py", line 134, in create_from_arg_string
|
80 |
-
return cls(**args, **args2)
|
81 |
-
File "/sailhome/tthrush/lm-evaluation-harness/lm_eval/models/huggingface.py", line 174, in __init__
|
82 |
-
self._get_config(
|
83 |
-
File "/sailhome/tthrush/lm-evaluation-harness/lm_eval/models/huggingface.py", line 420, in _get_config
|
84 |
-
self._config = transformers.AutoConfig.from_pretrained(
|
85 |
-
File "/nlp/scr/tthrush/miniconda3/envs/pretraining-coreset-selection/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py", line 1138, in from_pretrained
|
86 |
-
config_dict, unused_kwargs = PretrainedConfig.get_config_dict(pretrained_model_name_or_path, **kwargs)
|
87 |
-
File "/nlp/scr/tthrush/miniconda3/envs/pretraining-coreset-selection/lib/python3.10/site-packages/transformers/configuration_utils.py", line 631, in get_config_dict
|
88 |
-
config_dict, kwargs = cls._get_config_dict(pretrained_model_name_or_path, **kwargs)
|
89 |
-
File "/nlp/scr/tthrush/miniconda3/envs/pretraining-coreset-selection/lib/python3.10/site-packages/transformers/configuration_utils.py", line 686, in _get_config_dict
|
90 |
-
resolved_config_file = cached_file(
|
91 |
-
File "/nlp/scr/tthrush/miniconda3/envs/pretraining-coreset-selection/lib/python3.10/site-packages/transformers/utils/hub.py", line 369, in cached_file
|
92 |
-
raise EnvironmentError(
|
93 |
-
OSError: /juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/llms/pythia-14m_piqa does not appear to have a file named config.json. Checkout 'https://huggingface.co//juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/llms/pythia-14m_piqa/tree/main' for available files.
|
94 |
###############################
|
95 |
-
|
96 |
-
|
97 |
-
slurm submission log: 2024-05-09 07:34:41.456517
|
98 |
created following sbatch script:
|
99 |
|
100 |
###############################
|
@@ -103,24 +301,108 @@ created following sbatch script:
|
|
103 |
|
104 |
#SBATCH --account=nlp
|
105 |
#SBATCH --cpus-per-task=16
|
106 |
-
#SBATCH --dependency=afterok:
|
107 |
#SBATCH --gres=gpu:1
|
108 |
-
#SBATCH --job-name=tthrush-job-
|
109 |
#SBATCH --mem=60G
|
110 |
#SBATCH --nodelist=sphinx2
|
111 |
#SBATCH --open-mode=append
|
112 |
-
#SBATCH --output=/juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
113 |
#SBATCH --partition=sphinx
|
114 |
#SBATCH --time=14-0
|
115 |
|
116 |
# activate your desired anaconda environment
|
117 |
-
. /nlp/scr/tthrush/miniconda3/etc/profile.d/conda.sh ; conda activate pretraining-coreset-selection
|
118 |
|
119 |
# cd to working directory
|
120 |
cd .
|
121 |
|
122 |
# launch commands
|
123 |
-
srun --unbuffered run_as_child_processes 'lm_eval --model hf --model_args pretrained=/juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/
|
124 |
|
125 |
###############################
|
126 |
|
@@ -130,7 +412,7 @@ submission to slurm complete!
|
|
130 |
###############################
|
131 |
slurm submission output
|
132 |
|
133 |
-
Submitted batch job
|
134 |
|
135 |
|
136 |
|
|
|
1 |
+
slurm submission log: 2024-05-19 09:14:41.870170
|
2 |
created following sbatch script:
|
3 |
|
4 |
###############################
|
|
|
7 |
|
8 |
#SBATCH --account=nlp
|
9 |
#SBATCH --cpus-per-task=16
|
10 |
+
#SBATCH --dependency=afterok:7631089
|
11 |
#SBATCH --gres=gpu:1
|
12 |
+
#SBATCH --job-name=tthrush-job-4203243
|
13 |
#SBATCH --mem=60G
|
14 |
#SBATCH --nodelist=sphinx2
|
15 |
#SBATCH --open-mode=append
|
16 |
+
#SBATCH --output=/juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/14m_llm_seeds_more_data/pythia-14m_piqa_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/14m_llm_seeds_more_data/pythia-14m_piqa_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/14m_llm_seeds_more_data/pythia-14m_piqa_1/perf'
|
28 |
|
29 |
###############################
|
30 |
|
|
|
34 |
###############################
|
35 |
slurm submission output
|
36 |
|
37 |
+
Submitted batch job 7631090
|
38 |
|
39 |
|
40 |
|
41 |
###############################
|
42 |
|
43 |
+
slurm submission log: 2024-05-19 09:16:21.073119
|
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:7631150
|
53 |
+
#SBATCH --gres=gpu:1
|
54 |
+
#SBATCH --job-name=tthrush-job-3010961
|
55 |
+
#SBATCH --mem=60G
|
56 |
+
#SBATCH --nodelist=sphinx2
|
57 |
+
#SBATCH --open-mode=append
|
58 |
+
#SBATCH --output=/juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/14m_llm_seeds_more_data/pythia-14m_piqa_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/14m_llm_seeds_more_data/pythia-14m_piqa_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/14m_llm_seeds_more_data/pythia-14m_piqa_1/perf'
|
70 |
+
|
71 |
+
###############################
|
72 |
+
|
73 |
+
submission to slurm complete!
|
74 |
+
|
75 |
+
|
76 |
+
###############################
|
77 |
+
slurm submission output
|
78 |
+
|
79 |
+
Submitted batch job 7631151
|
80 |
+
|
81 |
+
|
82 |
+
|
83 |
+
###############################
|
84 |
+
|
85 |
+
slurm submission log: 2024-05-19 09:25:08.396129
|
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:7631221
|
95 |
+
#SBATCH --gres=gpu:1
|
96 |
+
#SBATCH --job-name=tthrush-job-4399372
|
97 |
+
#SBATCH --mem=60G
|
98 |
+
#SBATCH --nodelist=sphinx2
|
99 |
+
#SBATCH --open-mode=append
|
100 |
+
#SBATCH --output=/juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/14m_llm_seeds_more_data/pythia-14m_piqa_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/14m_llm_seeds_more_data/pythia-14m_piqa_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/14m_llm_seeds_more_data/pythia-14m_piqa_1/perf'
|
112 |
+
|
113 |
+
###############################
|
114 |
+
|
115 |
+
submission to slurm complete!
|
116 |
+
|
117 |
+
|
118 |
+
###############################
|
119 |
+
slurm submission output
|
120 |
+
|
121 |
+
Submitted batch job 7631222
|
122 |
+
|
123 |
+
|
124 |
+
|
125 |
+
###############################
|
126 |
+
|
127 |
+
slurm submission log: 2024-05-19 09:27:21.404018
|
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:7631284
|
137 |
+
#SBATCH --gres=gpu:1
|
138 |
+
#SBATCH --job-name=tthrush-job-1884627
|
139 |
+
#SBATCH --mem=60G
|
140 |
+
#SBATCH --nodelist=sphinx2
|
141 |
+
#SBATCH --open-mode=append
|
142 |
+
#SBATCH --output=/juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/14m_llm_seeds_more_data/pythia-14m_piqa_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/14m_llm_seeds_more_data/pythia-14m_piqa_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/14m_llm_seeds_more_data/pythia-14m_piqa_1/perf'
|
154 |
+
|
155 |
+
###############################
|
156 |
+
|
157 |
+
submission to slurm complete!
|
158 |
+
|
159 |
+
|
160 |
+
###############################
|
161 |
+
slurm submission output
|
162 |
+
|
163 |
+
Submitted batch job 7631285
|
164 |
+
|
165 |
+
|
166 |
+
|
167 |
+
###############################
|
168 |
+
|
169 |
+
slurm submission log: 2024-05-19 09:28:18.004148
|
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:7631348
|
179 |
+
#SBATCH --gres=gpu:1
|
180 |
+
#SBATCH --job-name=tthrush-job-1636654
|
181 |
+
#SBATCH --mem=60G
|
182 |
+
#SBATCH --nodelist=sphinx2
|
183 |
+
#SBATCH --open-mode=append
|
184 |
+
#SBATCH --output=/juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/14m_llm_seeds_more_data/pythia-14m_piqa_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/14m_llm_seeds_more_data/pythia-14m_piqa_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/14m_llm_seeds_more_data/pythia-14m_piqa_1/perf'
|
196 |
+
|
197 |
+
###############################
|
198 |
+
|
199 |
+
submission to slurm complete!
|
200 |
+
|
201 |
+
|
202 |
+
###############################
|
203 |
+
slurm submission output
|
204 |
+
|
205 |
+
Submitted batch job 7631349
|
206 |
+
|
207 |
+
|
208 |
+
|
209 |
+
###############################
|
210 |
+
|
211 |
+
slurm submission log: 2024-05-19 09:29:20.681949
|
212 |
+
created following sbatch script:
|
213 |
+
|
214 |
+
###############################
|
215 |
+
|
216 |
+
#!/bin/bash
|
217 |
+
|
218 |
+
#SBATCH --account=nlp
|
219 |
+
#SBATCH --cpus-per-task=16
|
220 |
+
#SBATCH --dependency=afterok:7631409
|
221 |
+
#SBATCH --gres=gpu:1
|
222 |
+
#SBATCH --job-name=tthrush-job-2759412
|
223 |
+
#SBATCH --mem=60G
|
224 |
+
#SBATCH --nodelist=sphinx2
|
225 |
+
#SBATCH --open-mode=append
|
226 |
+
#SBATCH --output=/juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/14m_llm_seeds_more_data/pythia-14m_piqa_1/eval_job_output.txt
|
227 |
+
#SBATCH --partition=sphinx
|
228 |
+
#SBATCH --time=14-0
|
229 |
+
|
230 |
+
# activate your desired anaconda environment
|
231 |
+
. /nlp/scr/tthrush/miniconda3/envs/pretraining-coreset-selection/etc/profile.d/conda.sh ; conda activate pretraining-coreset-selection
|
232 |
+
|
233 |
+
# cd to working directory
|
234 |
+
cd .
|
235 |
+
|
236 |
+
# launch commands
|
237 |
+
srun --unbuffered run_as_child_processes 'lm_eval --model hf --model_args pretrained=/juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/14m_llm_seeds_more_data/pythia-14m_piqa_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/14m_llm_seeds_more_data/pythia-14m_piqa_1/perf'
|
238 |
+
|
239 |
+
###############################
|
240 |
+
|
241 |
+
submission to slurm complete!
|
242 |
+
|
243 |
+
|
244 |
+
###############################
|
245 |
+
slurm submission output
|
246 |
+
|
247 |
+
Submitted batch job 7631410
|
248 |
+
|
249 |
+
|
250 |
+
|
251 |
###############################
|
252 |
+
|
253 |
+
slurm submission log: 2024-05-19 09:30:34.292755
|
254 |
+
created following sbatch script:
|
255 |
+
|
256 |
+
###############################
|
257 |
+
|
258 |
+
#!/bin/bash
|
259 |
+
|
260 |
+
#SBATCH --account=nlp
|
261 |
+
#SBATCH --cpus-per-task=16
|
262 |
+
#SBATCH --dependency=afterok:7631469
|
263 |
+
#SBATCH --gres=gpu:1
|
264 |
+
#SBATCH --job-name=tthrush-job-4781467
|
265 |
+
#SBATCH --mem=60G
|
266 |
+
#SBATCH --nodelist=sphinx2
|
267 |
+
#SBATCH --open-mode=append
|
268 |
+
#SBATCH --output=/juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/14m_llm_seeds_more_data/pythia-14m_piqa_1/eval_job_output.txt
|
269 |
+
#SBATCH --partition=sphinx
|
270 |
+
#SBATCH --time=14-0
|
271 |
+
|
272 |
+
# activate your desired anaconda environment
|
273 |
+
. /nlp/scr/tthrush/miniconda3/envs/pretraining-coreset-selection/etc/profile.d/conda.sh ; conda activate pretraining-coreset-selection
|
274 |
+
|
275 |
+
# cd to working directory
|
276 |
+
cd .
|
277 |
+
|
278 |
+
# launch commands
|
279 |
+
srun --unbuffered run_as_child_processes 'lm_eval --model hf --model_args pretrained=/juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/14m_llm_seeds_more_data/pythia-14m_piqa_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/14m_llm_seeds_more_data/pythia-14m_piqa_1/perf'
|
280 |
+
|
281 |
###############################
|
|
|
282 |
|
283 |
+
submission to slurm complete!
|
284 |
|
285 |
|
286 |
###############################
|
287 |
+
slurm submission output
|
288 |
+
|
289 |
+
Submitted batch job 7631470
|
290 |
+
|
291 |
|
292 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
293 |
###############################
|
294 |
+
|
295 |
+
slurm submission log: 2024-05-19 09:31:39.869529
|
|
|
296 |
created following sbatch script:
|
297 |
|
298 |
###############################
|
|
|
301 |
|
302 |
#SBATCH --account=nlp
|
303 |
#SBATCH --cpus-per-task=16
|
304 |
+
#SBATCH --dependency=afterok:7631529
|
305 |
#SBATCH --gres=gpu:1
|
306 |
+
#SBATCH --job-name=tthrush-job-2913641
|
307 |
#SBATCH --mem=60G
|
308 |
#SBATCH --nodelist=sphinx2
|
309 |
#SBATCH --open-mode=append
|
310 |
+
#SBATCH --output=/juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/14m_llm_seeds_more_data/pythia-14m_piqa_1/eval_job_output.txt
|
311 |
+
#SBATCH --partition=sphinx
|
312 |
+
#SBATCH --time=14-0
|
313 |
+
|
314 |
+
# activate your desired anaconda environment
|
315 |
+
. /nlp/scr/tthrush/miniconda3/envs/pretraining-coreset-selection/etc/profile.d/conda.sh ; conda activate pretraining-coreset-selection
|
316 |
+
|
317 |
+
# cd to working directory
|
318 |
+
cd .
|
319 |
+
|
320 |
+
# launch commands
|
321 |
+
srun --unbuffered run_as_child_processes 'lm_eval --model hf --model_args pretrained=/juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/14m_llm_seeds_more_data/pythia-14m_piqa_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/14m_llm_seeds_more_data/pythia-14m_piqa_1/perf'
|
322 |
+
|
323 |
+
###############################
|
324 |
+
|
325 |
+
submission to slurm complete!
|
326 |
+
|
327 |
+
|
328 |
+
###############################
|
329 |
+
slurm submission output
|
330 |
+
|
331 |
+
Submitted batch job 7631530
|
332 |
+
|
333 |
+
|
334 |
+
|
335 |
+
###############################
|
336 |
+
|
337 |
+
slurm submission log: 2024-05-19 09:34:33.468022
|
338 |
+
created following sbatch script:
|
339 |
+
|
340 |
+
###############################
|
341 |
+
|
342 |
+
#!/bin/bash
|
343 |
+
|
344 |
+
#SBATCH --account=nlp
|
345 |
+
#SBATCH --cpus-per-task=16
|
346 |
+
#SBATCH --dependency=afterok:7631593
|
347 |
+
#SBATCH --gres=gpu:1
|
348 |
+
#SBATCH --job-name=tthrush-job-2085637
|
349 |
+
#SBATCH --mem=60G
|
350 |
+
#SBATCH --nodelist=sphinx2
|
351 |
+
#SBATCH --open-mode=append
|
352 |
+
#SBATCH --output=/juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/14m_llm_seeds_more_data/pythia-14m_piqa_1/eval_job_output.txt
|
353 |
+
#SBATCH --partition=sphinx
|
354 |
+
#SBATCH --time=14-0
|
355 |
+
|
356 |
+
# activate your desired anaconda environment
|
357 |
+
. /nlp/scr/tthrush/miniconda3/envs/pretraining-coreset-selection/etc/profile.d/conda.sh ; conda activate pretraining-coreset-selection
|
358 |
+
|
359 |
+
# cd to working directory
|
360 |
+
cd .
|
361 |
+
|
362 |
+
# launch commands
|
363 |
+
srun --unbuffered run_as_child_processes 'lm_eval --model hf --model_args pretrained=/juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/14m_llm_seeds_more_data/pythia-14m_piqa_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/14m_llm_seeds_more_data/pythia-14m_piqa_1/perf'
|
364 |
+
|
365 |
+
###############################
|
366 |
+
|
367 |
+
submission to slurm complete!
|
368 |
+
|
369 |
+
|
370 |
+
###############################
|
371 |
+
slurm submission output
|
372 |
+
|
373 |
+
Submitted batch job 7631594
|
374 |
+
|
375 |
+
|
376 |
+
|
377 |
+
###############################
|
378 |
+
|
379 |
+
slurm submission log: 2024-05-19 09:45:20.755632
|
380 |
+
created following sbatch script:
|
381 |
+
|
382 |
+
###############################
|
383 |
+
|
384 |
+
#!/bin/bash
|
385 |
+
|
386 |
+
#SBATCH --account=nlp
|
387 |
+
#SBATCH --cpus-per-task=16
|
388 |
+
#SBATCH --dependency=afterok:7631663
|
389 |
+
#SBATCH --gres=gpu:1
|
390 |
+
#SBATCH --job-name=tthrush-job-1519057
|
391 |
+
#SBATCH --mem=60G
|
392 |
+
#SBATCH --nodelist=sphinx1
|
393 |
+
#SBATCH --open-mode=append
|
394 |
+
#SBATCH --output=/juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/14m_llm_seeds_more_data/pythia-14m_piqa_1/eval_job_output.txt
|
395 |
#SBATCH --partition=sphinx
|
396 |
#SBATCH --time=14-0
|
397 |
|
398 |
# activate your desired anaconda environment
|
399 |
+
. /nlp/scr/tthrush/miniconda3/envs/pretraining-coreset-selection/etc/profile.d/conda.sh ; conda activate pretraining-coreset-selection
|
400 |
|
401 |
# cd to working directory
|
402 |
cd .
|
403 |
|
404 |
# launch commands
|
405 |
+
srun --unbuffered run_as_child_processes 'lm_eval --model hf --model_args pretrained=/juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/14m_llm_seeds_more_data/pythia-14m_piqa_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/14m_llm_seeds_more_data/pythia-14m_piqa_1/perf'
|
406 |
|
407 |
###############################
|
408 |
|
|
|
412 |
###############################
|
413 |
slurm submission output
|
414 |
|
415 |
+
Submitted batch job 7631664
|
416 |
|
417 |
|
418 |
|
logs/events.out.tfevents.1716139274.sphinx2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7205004b6380aaabe1bc990ab9d6ac1255680e7e4e7c874d56b4feff4207f3b8
|
3 |
+
size 62915
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 56279344
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3afd047f9e5e4ca187b5da65a2eb8e83ffe8cd36e546c2a2d02bb834f72e0369
|
3 |
size 56279344
|
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:a2bb7b3dce46a3ed23526d06f496a5d2feb3176cdf51b3c78e887057bddf0e2e
|
3 |
+
size 5176
|