{ "results": [ { "task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge1_precision": 0.1498248405216555, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "rouge1_precision_stderr": 0.0018423908624139891 }, { "task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge1_recall": 0.25526647462429297, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "rouge1_recall_stderr": 0.002588155452951415 }, { "task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge1_fmeasure": 0.1751592790344999, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "rouge1_fmeasure_stderr": 0.0017874794849447823 }, { "task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge2_precision": 0.02866254588676867, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "rouge2_precision_stderr": 0.0007271444111163778 }, { "task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge2_recall": 0.05162759513352221, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "rouge2_recall_stderr": 0.0014037908842865225 }, { "task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rouge2_fmeasure": 0.033925070200158246, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "rouge2_fmeasure_stderr": 0.0008240877531204439 }, { "task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeL_precision": 0.11555678082540916, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "rougeL_precision_stderr": 0.0012586001477032337 }, { "task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeL_recall": 0.20559491764149926, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "rougeL_recall_stderr": 0.002138172468666332 }, { "task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeL_fmeasure": 0.13711284339871613, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "rougeL_fmeasure_stderr": 0.001264815697203119 }, { "task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeLsum_precision": 0.13771072102711007, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "rougeLsum_precision_stderr": 0.0016874302363856556 }, { "task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeLsum_recall": 0.23587046561796698, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "rougeLsum_recall_stderr": 0.0024016834853047104 }, { "task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "rougeLsum_fmeasure": 0.16124043802649227, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "rougeLsum_fmeasure_stderr": 0.0016384576957041044 }, { "task_name": "GEM/wiki_lingua_en", "prompt_name": "tldr_en", "bleu": 1.484894171357125, "dataset_path": "GEM/wiki_lingua", "dataset_name": "en", "subset": null, "bleu_stderr": 0.04279862989387049 } ], "config": { "model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-c4-repetitions/4b284b17bc4/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 } }