{ "results": [ { "task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "bleu": 0.6721480622931579, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "bleu_stderr": 0.04364421620033658 }, { "task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge1_precision": 0.07312830538850522, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "rouge1_precision_stderr": 0.0012172573610058964 }, { "task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge1_recall": 0.41786672242074735, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "rouge1_recall_stderr": 0.00514089320113892 }, { "task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge1_fmeasure": 0.11682333840421252, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "rouge1_fmeasure_stderr": 0.0016784638187503072 }, { "task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge2_precision": 0.03391327016863078, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "rouge2_precision_stderr": 0.0007434663573137818 }, { "task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge2_recall": 0.21097279270777233, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "rouge2_recall_stderr": 0.003962368460085698 }, { "task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge2_fmeasure": 0.05451282884342794, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "rouge2_fmeasure_stderr": 0.001075049065599178 }, { "task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeL_precision": 0.06674973450321794, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "rougeL_precision_stderr": 0.001076625707211798 }, { "task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeL_recall": 0.3763932336189791, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "rougeL_recall_stderr": 0.004418572944831253 }, { "task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeL_fmeasure": 0.10645004232970325, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "rougeL_fmeasure_stderr": 0.0014835449120631779 }, { "task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeLsum_precision": 0.06947768209278911, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "rougeLsum_precision_stderr": 0.0011601752390396401 }, { "task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeLsum_recall": 0.39433935812714066, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "rougeLsum_recall_stderr": 0.00474918433328278 }, { "task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeLsum_fmeasure": 0.1108401266606722, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "rougeLsum_fmeasure_stderr": 0.0015949626703580934 } ], "config": { "model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-c4-repetitions/4b284b84bc4/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 } }