lm1-4b2-84b-c4-repetitions / 4b284b21bc4 /evaluation /generation /slim.4b284b21bc4_gem_xsum_article_DOC_summary_0.json
Muennighoff's picture
Add files
a1243c9
{
"results": [
{
"task_name": "gem_xsum",
"prompt_name": "article_DOC_summary",
"rouge1_precision": 0.14714404834539455,
"dataset_path": "GEM/xsum",
"dataset_name": null,
"subset": "",
"rouge1_precision_stderr": 0.0018923895784899547
},
{
"task_name": "gem_xsum",
"prompt_name": "article_DOC_summary",
"rouge1_recall": 0.35332808198249066,
"dataset_path": "GEM/xsum",
"dataset_name": null,
"subset": "",
"rouge1_recall_stderr": 0.004277854613117222
},
{
"task_name": "gem_xsum",
"prompt_name": "article_DOC_summary",
"rouge1_fmeasure": 0.20448305051370513,
"dataset_path": "GEM/xsum",
"dataset_name": null,
"subset": "",
"rouge1_fmeasure_stderr": 0.0024499517599214865
},
{
"task_name": "gem_xsum",
"prompt_name": "article_DOC_summary",
"rouge2_precision": 0.03290270141635618,
"dataset_path": "GEM/xsum",
"dataset_name": null,
"subset": "",
"rouge2_precision_stderr": 0.0010989269503369368
},
{
"task_name": "gem_xsum",
"prompt_name": "article_DOC_summary",
"rouge2_recall": 0.08287973270989689,
"dataset_path": "GEM/xsum",
"dataset_name": null,
"subset": "",
"rouge2_recall_stderr": 0.002833032880998302
},
{
"task_name": "gem_xsum",
"prompt_name": "article_DOC_summary",
"rouge2_fmeasure": 0.04639360161894793,
"dataset_path": "GEM/xsum",
"dataset_name": null,
"subset": "",
"rouge2_fmeasure_stderr": 0.0015361212037212923
},
{
"task_name": "gem_xsum",
"prompt_name": "article_DOC_summary",
"rougeL_precision": 0.10929554255441323,
"dataset_path": "GEM/xsum",
"dataset_name": null,
"subset": "",
"rougeL_precision_stderr": 0.001387362394565063
},
{
"task_name": "gem_xsum",
"prompt_name": "article_DOC_summary",
"rougeL_recall": 0.26469649902339626,
"dataset_path": "GEM/xsum",
"dataset_name": null,
"subset": "",
"rougeL_recall_stderr": 0.0033616815736178403
},
{
"task_name": "gem_xsum",
"prompt_name": "article_DOC_summary",
"rougeL_fmeasure": 0.1522143356903949,
"dataset_path": "GEM/xsum",
"dataset_name": null,
"subset": "",
"rougeL_fmeasure_stderr": 0.0018364801701113477
},
{
"task_name": "gem_xsum",
"prompt_name": "article_DOC_summary",
"rougeLsum_precision": 0.11672705515751206,
"dataset_path": "GEM/xsum",
"dataset_name": null,
"subset": "",
"rougeLsum_precision_stderr": 0.001546854617689576
},
{
"task_name": "gem_xsum",
"prompt_name": "article_DOC_summary",
"rougeLsum_recall": 0.28315180080173324,
"dataset_path": "GEM/xsum",
"dataset_name": null,
"subset": "",
"rougeLsum_recall_stderr": 0.0037966298013545237
},
{
"task_name": "gem_xsum",
"prompt_name": "article_DOC_summary",
"rougeLsum_fmeasure": 0.1627172387554665,
"dataset_path": "GEM/xsum",
"dataset_name": null,
"subset": "",
"rougeLsum_fmeasure_stderr": 0.0020740152357133783
},
{
"task_name": "gem_xsum",
"prompt_name": "article_DOC_summary",
"bleu": 1.8973746751821576,
"dataset_path": "GEM/xsum",
"dataset_name": null,
"subset": "",
"bleu_stderr": 0.07374608873039461
}
],
"config": {
"model": "hf-causal",
"model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-c4-repetitions/4b284b21bc4/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16",
"task_args": "",
"num_fewshot": 0,
"batch_size": 16,
"device": "cuda",
"use_cache": false,
"limit": 3000,
"bootstrap_iters": 10,
"seed": 1234
}
}