{ "results": [ { "task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "bleu": 1.1673998473534046, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "bleu_stderr": 0.09133948510400369 }, { "task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge1_precision": 0.2125195111528658, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "rouge1_precision_stderr": 0.005730453983133926 }, { "task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge1_recall": 0.40637639113635166, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "rouge1_recall_stderr": 0.004933922377880338 }, { "task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge1_fmeasure": 0.23196338111553216, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "rouge1_fmeasure_stderr": 0.004558457306896048 }, { "task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge2_precision": 0.11875092253811664, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "rouge2_precision_stderr": 0.0039714331213516595 }, { "task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge2_recall": 0.22248575515884728, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "rouge2_recall_stderr": 0.004014145150661029 }, { "task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge2_fmeasure": 0.12559736589051002, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "rouge2_fmeasure_stderr": 0.003188817274548042 }, { "task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeL_precision": 0.1843607825179914, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "rougeL_precision_stderr": 0.0048800492055134925 }, { "task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeL_recall": 0.370665372766866, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "rougeL_recall_stderr": 0.004464677380992271 }, { "task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeL_fmeasure": 0.2038615706419507, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "rougeL_fmeasure_stderr": 0.003812860468542949 }, { "task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeLsum_precision": 0.19370515184964268, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "rougeLsum_precision_stderr": 0.005184788234116766 }, { "task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeLsum_recall": 0.3806829975264072, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "rougeLsum_recall_stderr": 0.004583640895651089 }, { "task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeLsum_fmeasure": 0.2125920854603434, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "rougeLsum_fmeasure_stderr": 0.004058013873763605 } ], "config": { "model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-8b7-178b-oscar-repetitions/8b7178b44b/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 } }