{ "results": [ { "task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge1_precision": 0.2332474242904849, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "rouge1_precision_stderr": 0.0031768172038711467 }, { "task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge1_recall": 0.29410268890498986, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "rouge1_recall_stderr": 0.002958828414438297 }, { "task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge1_fmeasure": 0.21836409386191818, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "rouge1_fmeasure_stderr": 0.001989518194370473 }, { "task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge2_precision": 0.06566711930000235, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "rouge2_precision_stderr": 0.0019413943466877388 }, { "task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge2_recall": 0.07670871046547496, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "rouge2_recall_stderr": 0.0016787739182338268 }, { "task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge2_fmeasure": 0.05650249608530642, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "rouge2_fmeasure_stderr": 0.0011487340298214372 }, { "task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeL_precision": 0.1752085713341631, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "rougeL_precision_stderr": 0.0026584779502129303 }, { "task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeL_recall": 0.21819240455646285, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "rougeL_recall_stderr": 0.002276168106614223 }, { "task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeL_fmeasure": 0.1603606067900483, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "rougeL_fmeasure_stderr": 0.0014157142739287894 }, { "task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeLsum_precision": 0.22112816157170134, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "rougeLsum_precision_stderr": 0.0030769042746772593 }, { "task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeLsum_recall": 0.2776979400072693, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "rougeLsum_recall_stderr": 0.002813335835445409 }, { "task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeLsum_fmeasure": 0.20617794726883687, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "rougeLsum_fmeasure_stderr": 0.0018867289872942854 }, { "task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "bleu": 3.123719853905042, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "bleu_stderr": 0.09435758546693512 } ], "config": { "model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-c4-repetitions/4b284b28bc4/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 2, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234 } }