| slurm submission log: 2024-05-27 12:34:08.291942 | |
| created following sbatch script: | |
| ############################### | |
| #!/bin/bash | |
| #SBATCH --account=nlp | |
| #SBATCH --cpus-per-task=16 | |
| #SBATCH --dependency=afterok:7656663 | |
| #SBATCH --gres=gpu:1 | |
| #SBATCH --job-name=tthrush-job-3309802 | |
| #SBATCH --mem=60G | |
| #SBATCH --nodelist=sphinx1 | |
| #SBATCH --open-mode=append | |
| #SBATCH --output=/juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/test_ordinal_projection_big_diff/llms/pythia-70m_sciq_1/eval_job_output.txt | |
| #SBATCH --partition=sphinx | |
| #SBATCH --time=14-0 | |
| # activate your desired anaconda environment | |
| . /nlp/scr/tthrush/miniconda3/etc/profile.d/conda.sh ; conda activate pretraining-coreset-selection | |
| # cd to working directory | |
| cd . | |
| # launch commands | |
| 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_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_big_diff/llms/pythia-70m_sciq_1/perf' | |
| ############################### | |
| submission to slurm complete! | |
| ############################### | |
| slurm submission output | |
| Submitted batch job 7656664 | |
| ############################### | |
| ############################### | |
| start time: 2024-05-27 12:47:58.516681 | |
| machine: sphinx1 | |
| conda env: pretraining-coreset-selection | |
| ############################### | |
| running following processes | |
| lm_eval --model hf --model_args pretrained=/juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/test_ordinal_projection_big_diff/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_big_diff/llms/pythia-70m_sciq_1/perf | |
| ############################### | |
| command outputs: | |
| 2024-05-27:12:48:01,194 INFO [utils.py:145] Note: detected 255 virtual cores but NumExpr set to maximum of 64, check "NUMEXPR_MAX_THREADS" environment variable. | |
| 2024-05-27:12:48:01,194 INFO [utils.py:148] Note: NumExpr detected 255 cores but "NUMEXPR_MAX_THREADS" not set, so enforcing safe limit of 8. | |
| 2024-05-27:12:48:01,194 INFO [utils.py:160] NumExpr defaulting to 8 threads. | |
| 2024-05-27:12:48:01,508 INFO [config.py:58] PyTorch version 2.2.2 available. | |
| 2024-05-27:12:48:05,349 INFO [__main__.py:156] Verbosity set to INFO | |
| 2024-05-27:12:48:12,734 WARNING [__init__.py:194] Some tasks could not be loaded due to missing dependencies. Run with `--verbosity DEBUG` for full details. | |
| /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 | |
| You can avoid this message in future by passing the argument `trust_remote_code=True`. | |
| Passing `trust_remote_code=True` will be mandatory to load this dataset from the next major release of `datasets`. | |
| warnings.warn( | |
| 2024-05-27:12:49:29,060 WARNING [__init__.py:194] Some tasks could not be loaded due to missing dependencies. Run with `--verbosity DEBUG` for full details. | |
| 2024-05-27:12:49:29,064 INFO [__main__.py:229] Selected Tasks: ['arc_easy', 'lambada', 'piqa', 'sciq', 'xnli_de', 'xnli_en', 'xnli_es', 'xnli_fr'] | |
| 2024-05-27:12:49:29,360 INFO [huggingface.py:148] Using device 'cuda' | |
| Traceback (most recent call last): | |
| File "/nlp/scr/tthrush/miniconda3/envs/pretraining-coreset-selection/bin/lm_eval", line 8, in <module> | |
| sys.exit(cli_evaluate()) | |
| File "/sailhome/tthrush/lm-evaluation-harness/lm_eval/__main__.py", line 231, in cli_evaluate | |
| results = evaluator.simple_evaluate( | |
| File "/sailhome/tthrush/lm-evaluation-harness/lm_eval/utils.py", line 415, in _wrapper | |
| return fn(*args, **kwargs) | |
| File "/sailhome/tthrush/lm-evaluation-harness/lm_eval/evaluator.py", line 98, in simple_evaluate | |
| lm = lm_eval.api.registry.get_model(model).create_from_arg_string( | |
| File "/sailhome/tthrush/lm-evaluation-harness/lm_eval/api/model.py", line 134, in create_from_arg_string | |
| return cls(**args, **args2) | |
| File "/sailhome/tthrush/lm-evaluation-harness/lm_eval/models/huggingface.py", line 174, in __init__ | |
| self._get_config( | |
| File "/sailhome/tthrush/lm-evaluation-harness/lm_eval/models/huggingface.py", line 420, in _get_config | |
| self._config = transformers.AutoConfig.from_pretrained( | |
| 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 | |
| config_dict, unused_kwargs = PretrainedConfig.get_config_dict(pretrained_model_name_or_path, **kwargs) | |
| File "/nlp/scr/tthrush/miniconda3/envs/pretraining-coreset-selection/lib/python3.10/site-packages/transformers/configuration_utils.py", line 631, in get_config_dict | |
| config_dict, kwargs = cls._get_config_dict(pretrained_model_name_or_path, **kwargs) | |
| File "/nlp/scr/tthrush/miniconda3/envs/pretraining-coreset-selection/lib/python3.10/site-packages/transformers/configuration_utils.py", line 686, in _get_config_dict | |
| resolved_config_file = cached_file( | |
| File "/nlp/scr/tthrush/miniconda3/envs/pretraining-coreset-selection/lib/python3.10/site-packages/transformers/utils/hub.py", line 369, in cached_file | |
| raise EnvironmentError( | |
| OSError: /juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/test_ordinal_projection_big_diff/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_projection_big_diff/llms/pythia-70m_sciq_1/tree/main' for available files. | |
| ############################### | |
| end time: 2024-05-27 12:49:38.627024 | |
| elapsed time: 0:01:40.110343 | |
| slurm submission log: 2024-05-27 23:18:54.461453 | |
| created following sbatch script: | |
| ############################### | |
| #!/bin/bash | |
| #SBATCH --account=nlp | |
| #SBATCH --cpus-per-task=16 | |
| #SBATCH --dependency=afterok:7659769 | |
| #SBATCH --gres=gpu:1 | |
| #SBATCH --job-name=tthrush-job-2147042 | |
| #SBATCH --mem=60G | |
| #SBATCH --nodelist=sphinx1 | |
| #SBATCH --open-mode=append | |
| #SBATCH --output=/juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/test_ordinal_projection_big_diff/llms/pythia-70m_sciq_1/eval_job_output.txt | |
| #SBATCH --partition=sphinx | |
| #SBATCH --time=14-0 | |
| # activate your desired anaconda environment | |
| . /nlp/scr/tthrush/miniconda3/etc/profile.d/conda.sh ; conda activate pretraining-coreset-selection | |
| # cd to working directory | |
| cd . | |
| # launch commands | |
| 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_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_big_diff/llms/pythia-70m_sciq_1/perf' | |
| ############################### | |
| submission to slurm complete! | |
| ############################### | |
| slurm submission output | |
| Submitted batch job 7659770 | |
| ############################### | |
| slurm submission log: 2024-05-27 23:24:16.563525 | |
| created following sbatch script: | |
| ############################### | |
| #!/bin/bash | |
| #SBATCH --account=nlp | |
| #SBATCH --cpus-per-task=16 | |
| #SBATCH --dependency=afterok:7659811 | |
| #SBATCH --gres=gpu:1 | |
| #SBATCH --job-name=tthrush-job-2456365 | |
| #SBATCH --mem=60G | |
| #SBATCH --nodelist=sphinx1 | |
| #SBATCH --open-mode=append | |
| #SBATCH --output=/juice5/scr5/tthrush/pretraining-coreset-selection/llm_pretraining/test_ordinal_projection_big_diff/llms/pythia-70m_sciq_1/eval_job_output.txt | |
| #SBATCH --partition=sphinx | |
| #SBATCH --time=14-0 | |
| # activate your desired anaconda environment | |
| . /nlp/scr/tthrush/miniconda3/etc/profile.d/conda.sh ; conda activate pretraining-coreset-selection | |
| # cd to working directory | |
| cd . | |
| # launch commands | |
| 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_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_big_diff/llms/pythia-70m_sciq_1/perf' | |
| ############################### | |
| submission to slurm complete! | |
| ############################### | |
| slurm submission output | |
| Submitted batch job 7659812 | |
| ############################### | |