lm1-4b2-84b-c4-repetitions
/
4b284b42bc4
/evaluation
/generation
/slim.4b284b42bc4_gem_xsum_article_DOC_summary_5.json
{ | |
"results": [ | |
{ | |
"task_name": "gem_xsum", | |
"prompt_name": "article_DOC_summary", | |
"rouge1_precision": 0.003263719197769084, | |
"dataset_path": "GEM/xsum", | |
"dataset_name": null, | |
"subset": "", | |
"rouge1_precision_stderr": 0.0008887617448902996 | |
}, | |
{ | |
"task_name": "gem_xsum", | |
"prompt_name": "article_DOC_summary", | |
"rouge1_recall": 0.0028345456514645845, | |
"dataset_path": "GEM/xsum", | |
"dataset_name": null, | |
"subset": "", | |
"rouge1_recall_stderr": 0.0008116977743173961 | |
}, | |
{ | |
"task_name": "gem_xsum", | |
"prompt_name": "article_DOC_summary", | |
"rouge1_fmeasure": 0.002997767517780879, | |
"dataset_path": "GEM/xsum", | |
"dataset_name": null, | |
"subset": "", | |
"rouge1_fmeasure_stderr": 0.0008334506629000642 | |
}, | |
{ | |
"task_name": "gem_xsum", | |
"prompt_name": "article_DOC_summary", | |
"rouge2_precision": 0.0004590858641913026, | |
"dataset_path": "GEM/xsum", | |
"dataset_name": null, | |
"subset": "", | |
"rouge2_precision_stderr": 0.00021377485443811557 | |
}, | |
{ | |
"task_name": "gem_xsum", | |
"prompt_name": "article_DOC_summary", | |
"rouge2_recall": 0.00041953329689178745, | |
"dataset_path": "GEM/xsum", | |
"dataset_name": null, | |
"subset": "", | |
"rouge2_recall_stderr": 0.00021411305439143847 | |
}, | |
{ | |
"task_name": "gem_xsum", | |
"prompt_name": "article_DOC_summary", | |
"rouge2_fmeasure": 0.0004337191943913522, | |
"dataset_path": "GEM/xsum", | |
"dataset_name": null, | |
"subset": "", | |
"rouge2_fmeasure_stderr": 0.00021214389566854186 | |
}, | |
{ | |
"task_name": "gem_xsum", | |
"prompt_name": "article_DOC_summary", | |
"rougeL_precision": 0.0023145025817495005, | |
"dataset_path": "GEM/xsum", | |
"dataset_name": null, | |
"subset": "", | |
"rougeL_precision_stderr": 0.0006312757980824667 | |
}, | |
{ | |
"task_name": "gem_xsum", | |
"prompt_name": "article_DOC_summary", | |
"rougeL_recall": 0.0019717134578344517, | |
"dataset_path": "GEM/xsum", | |
"dataset_name": null, | |
"subset": "", | |
"rougeL_recall_stderr": 0.0005600175515270516 | |
}, | |
{ | |
"task_name": "gem_xsum", | |
"prompt_name": "article_DOC_summary", | |
"rougeL_fmeasure": 0.002106529594577242, | |
"dataset_path": "GEM/xsum", | |
"dataset_name": null, | |
"subset": "", | |
"rougeL_fmeasure_stderr": 0.0005845294157065285 | |
}, | |
{ | |
"task_name": "gem_xsum", | |
"prompt_name": "article_DOC_summary", | |
"rougeLsum_precision": 0.0026347083023874887, | |
"dataset_path": "GEM/xsum", | |
"dataset_name": null, | |
"subset": "", | |
"rougeLsum_precision_stderr": 0.0007273791404483311 | |
}, | |
{ | |
"task_name": "gem_xsum", | |
"prompt_name": "article_DOC_summary", | |
"rougeLsum_recall": 0.00225801889401816, | |
"dataset_path": "GEM/xsum", | |
"dataset_name": null, | |
"subset": "", | |
"rougeLsum_recall_stderr": 0.000653191190142516 | |
}, | |
{ | |
"task_name": "gem_xsum", | |
"prompt_name": "article_DOC_summary", | |
"rougeLsum_fmeasure": 0.0024033045589119204, | |
"dataset_path": "GEM/xsum", | |
"dataset_name": null, | |
"subset": "", | |
"rougeLsum_fmeasure_stderr": 0.0006766571604709825 | |
}, | |
{ | |
"task_name": "gem_xsum", | |
"prompt_name": "article_DOC_summary", | |
"bleu": 3.120169018915429e-39, | |
"dataset_path": "GEM/xsum", | |
"dataset_name": null, | |
"subset": "", | |
"bleu_stderr": 2.777103521919484e-32 | |
} | |
], | |
"config": { | |
"model": "hf-causal", | |
"model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-c4-repetitions/4b284b42bc4/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", | |
"task_args": "", | |
"num_fewshot": 5, | |
"batch_size": 16, | |
"device": "cuda", | |
"use_cache": false, | |
"limit": 3000, | |
"bootstrap_iters": 10, | |
"seed": 1234 | |
} | |
} |