lm1-4b2-84b-oscar-repetitions / 4b284b28boscar /evaluation /generation /slim.4b284b28boscar_GEM-wiki_lingua_en_tldr_en_4.json
Muennighoff's picture
Add files
8170937
raw
history blame contribute delete
No virus
4.1 kB
{
"results": [
{
"task_name": "GEM/wiki_lingua_en",
"prompt_name": "tldr_en",
"rouge1_precision": 0.092208189110962,
"dataset_path": "GEM/wiki_lingua",
"dataset_name": "en",
"subset": null,
"rouge1_precision_stderr": 0.0034189214358844324
},
{
"task_name": "GEM/wiki_lingua_en",
"prompt_name": "tldr_en",
"rouge1_recall": 0.07224586073962391,
"dataset_path": "GEM/wiki_lingua",
"dataset_name": "en",
"subset": null,
"rouge1_recall_stderr": 0.002716708158950956
},
{
"task_name": "GEM/wiki_lingua_en",
"prompt_name": "tldr_en",
"rouge1_fmeasure": 0.06668350472619872,
"dataset_path": "GEM/wiki_lingua",
"dataset_name": "en",
"subset": null,
"rouge1_fmeasure_stderr": 0.0023223709305170443
},
{
"task_name": "GEM/wiki_lingua_en",
"prompt_name": "tldr_en",
"rouge2_precision": 0.0276141917171982,
"dataset_path": "GEM/wiki_lingua",
"dataset_name": "en",
"subset": null,
"rouge2_precision_stderr": 0.0016764660911735634
},
{
"task_name": "GEM/wiki_lingua_en",
"prompt_name": "tldr_en",
"rouge2_recall": 0.021177864192540377,
"dataset_path": "GEM/wiki_lingua",
"dataset_name": "en",
"subset": null,
"rouge2_recall_stderr": 0.0012371206877780988
},
{
"task_name": "GEM/wiki_lingua_en",
"prompt_name": "tldr_en",
"rouge2_fmeasure": 0.01919932938843845,
"dataset_path": "GEM/wiki_lingua",
"dataset_name": "en",
"subset": null,
"rouge2_fmeasure_stderr": 0.0010049481476114978
},
{
"task_name": "GEM/wiki_lingua_en",
"prompt_name": "tldr_en",
"rougeL_precision": 0.07354514541641334,
"dataset_path": "GEM/wiki_lingua",
"dataset_name": "en",
"subset": null,
"rougeL_precision_stderr": 0.002828654152146427
},
{
"task_name": "GEM/wiki_lingua_en",
"prompt_name": "tldr_en",
"rougeL_recall": 0.056562703185008854,
"dataset_path": "GEM/wiki_lingua",
"dataset_name": "en",
"subset": null,
"rougeL_recall_stderr": 0.002168458322152195
},
{
"task_name": "GEM/wiki_lingua_en",
"prompt_name": "tldr_en",
"rougeL_fmeasure": 0.05216028088524061,
"dataset_path": "GEM/wiki_lingua",
"dataset_name": "en",
"subset": null,
"rougeL_fmeasure_stderr": 0.0018383425985936733
},
{
"task_name": "GEM/wiki_lingua_en",
"prompt_name": "tldr_en",
"rougeLsum_precision": 0.0875093402820744,
"dataset_path": "GEM/wiki_lingua",
"dataset_name": "en",
"subset": null,
"rougeLsum_precision_stderr": 0.003281948169701787
},
{
"task_name": "GEM/wiki_lingua_en",
"prompt_name": "tldr_en",
"rougeLsum_recall": 0.06780620805618982,
"dataset_path": "GEM/wiki_lingua",
"dataset_name": "en",
"subset": null,
"rougeLsum_recall_stderr": 0.0025609050791819783
},
{
"task_name": "GEM/wiki_lingua_en",
"prompt_name": "tldr_en",
"rougeLsum_fmeasure": 0.062781251763141,
"dataset_path": "GEM/wiki_lingua",
"dataset_name": "en",
"subset": null,
"rougeLsum_fmeasure_stderr": 0.002197731580536598
},
{
"task_name": "GEM/wiki_lingua_en",
"prompt_name": "tldr_en",
"bleu": 0.13483879286922137,
"dataset_path": "GEM/wiki_lingua",
"dataset_name": "en",
"subset": null,
"bleu_stderr": 0.011222185156728685
}
],
"config": {
"model": "hf-causal",
"model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-oscar-repetitions/4b284b28boscar/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16",
"task_args": "",
"num_fewshot": 4,
"batch_size": 16,
"device": "cuda",
"use_cache": false,
"limit": 3000,
"bootstrap_iters": 10,
"seed": 1234
}
}