{ "results": [ { "task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "bleu": 0.43549317288896894, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "bleu_stderr": 0.029438186163177924 }, { "task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge1_precision": 0.07179524471867899, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "rouge1_precision_stderr": 0.0013752072779383184 }, { "task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge1_recall": 0.35855038856048876, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "rouge1_recall_stderr": 0.005049635846993475 }, { "task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge1_fmeasure": 0.11204264924342298, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "rouge1_fmeasure_stderr": 0.0018816879797699437 }, { "task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge2_precision": 0.032801419147362856, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "rouge2_precision_stderr": 0.0008197872630256377 }, { "task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge2_recall": 0.1723852958712864, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "rouge2_recall_stderr": 0.0035877516735487143 }, { "task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge2_fmeasure": 0.051345397484036256, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "rouge2_fmeasure_stderr": 0.0011584347174914676 }, { "task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeL_precision": 0.06711558592890904, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "rougeL_precision_stderr": 0.00122163800184802 }, { "task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeL_recall": 0.33387823961526397, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "rougeL_recall_stderr": 0.004537882130758048 }, { "task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeL_fmeasure": 0.10481665765175784, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "rougeL_fmeasure_stderr": 0.0016825296642133658 }, { "task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeLsum_precision": 0.06830552553162243, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "rougeLsum_precision_stderr": 0.001292240550330291 }, { "task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeLsum_recall": 0.33957294457499176, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "rougeLsum_recall_stderr": 0.004661961230072316 }, { "task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeLsum_fmeasure": 0.10653343348961458, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "rougeLsum_fmeasure_stderr": 0.0017665097203702323 } ], "config": { "model": "hf-causal", "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-c4-repetitions/4b284b21bc4/transformers,use_accelerate=True,tokenizer=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/gpt2,dtype=bfloat16", "task_args": "", "num_fewshot": 1, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234 } }