lm1-4b2-84b-c4-repetitions / 4b284b42bc4 /evaluation /generation /slim.4b284b42bc4_gem_xsum_article_DOC_summary_1.json
Muennighoff's picture
Add files
a1243c9
raw
history blame
4 kB
{
"results": [
{
"task_name": "gem_xsum",
"prompt_name": "article_DOC_summary",
"rouge1_precision": 0.1369839651831878,
"dataset_path": "GEM/xsum",
"dataset_name": null,
"subset": "",
"rouge1_precision_stderr": 0.0019614322408207006
},
{
"task_name": "gem_xsum",
"prompt_name": "article_DOC_summary",
"rouge1_recall": 0.3369949215642884,
"dataset_path": "GEM/xsum",
"dataset_name": null,
"subset": "",
"rouge1_recall_stderr": 0.004522579510481593
},
{
"task_name": "gem_xsum",
"prompt_name": "article_DOC_summary",
"rouge1_fmeasure": 0.19244278875333556,
"dataset_path": "GEM/xsum",
"dataset_name": null,
"subset": "",
"rouge1_fmeasure_stderr": 0.002639391462026543
},
{
"task_name": "gem_xsum",
"prompt_name": "article_DOC_summary",
"rouge2_precision": 0.031094803643512716,
"dataset_path": "GEM/xsum",
"dataset_name": null,
"subset": "",
"rouge2_precision_stderr": 0.0011365997631264868
},
{
"task_name": "gem_xsum",
"prompt_name": "article_DOC_summary",
"rouge2_recall": 0.07935713496492708,
"dataset_path": "GEM/xsum",
"dataset_name": null,
"subset": "",
"rouge2_recall_stderr": 0.002884276945599807
},
{
"task_name": "gem_xsum",
"prompt_name": "article_DOC_summary",
"rouge2_fmeasure": 0.04413377405232099,
"dataset_path": "GEM/xsum",
"dataset_name": null,
"subset": "",
"rouge2_fmeasure_stderr": 0.0015985481401232032
},
{
"task_name": "gem_xsum",
"prompt_name": "article_DOC_summary",
"rougeL_precision": 0.10657563716596334,
"dataset_path": "GEM/xsum",
"dataset_name": null,
"subset": "",
"rougeL_precision_stderr": 0.0014875062360428326
},
{
"task_name": "gem_xsum",
"prompt_name": "article_DOC_summary",
"rougeL_recall": 0.26467978376956175,
"dataset_path": "GEM/xsum",
"dataset_name": null,
"subset": "",
"rougeL_recall_stderr": 0.0036163241442920165
},
{
"task_name": "gem_xsum",
"prompt_name": "article_DOC_summary",
"rougeL_fmeasure": 0.1500620628581487,
"dataset_path": "GEM/xsum",
"dataset_name": null,
"subset": "",
"rougeL_fmeasure_stderr": 0.0020207447957827454
},
{
"task_name": "gem_xsum",
"prompt_name": "article_DOC_summary",
"rougeLsum_precision": 0.1078060619083588,
"dataset_path": "GEM/xsum",
"dataset_name": null,
"subset": "",
"rougeLsum_precision_stderr": 0.0016045831813046104
},
{
"task_name": "gem_xsum",
"prompt_name": "article_DOC_summary",
"rougeLsum_recall": 0.2680535986457037,
"dataset_path": "GEM/xsum",
"dataset_name": null,
"subset": "",
"rougeLsum_recall_stderr": 0.0038953175735036904
},
{
"task_name": "gem_xsum",
"prompt_name": "article_DOC_summary",
"rougeLsum_fmeasure": 0.15187454343375792,
"dataset_path": "GEM/xsum",
"dataset_name": null,
"subset": "",
"rougeLsum_fmeasure_stderr": 0.0021906040942089064
},
{
"task_name": "gem_xsum",
"prompt_name": "article_DOC_summary",
"bleu": 1.7714825425476433,
"dataset_path": "GEM/xsum",
"dataset_name": null,
"subset": "",
"bleu_stderr": 0.10905675609895228
}
],
"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": 1,
"batch_size": 16,
"device": "cuda",
"use_cache": false,
"limit": 3000,
"bootstrap_iters": 10,
"seed": 1234
}
}