{ "results": [ { "task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "bleu": 0.45724995573151395, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "bleu_stderr": 0.03077826387670849 }, { "task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge1_precision": 0.07380410032029427, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "rouge1_precision_stderr": 0.0013950698189371862 }, { "task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge1_recall": 0.36979685211837077, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "rouge1_recall_stderr": 0.005157808096954796 }, { "task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge1_fmeasure": 0.11499758191359032, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "rouge1_fmeasure_stderr": 0.0018677715006027427 }, { "task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge2_precision": 0.03456277372759004, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "rouge2_precision_stderr": 0.0008655744665680597 }, { "task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge2_recall": 0.1825581650807761, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "rouge2_recall_stderr": 0.0037692839645507878 }, { "task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rouge2_fmeasure": 0.053994419166879803, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "rouge2_fmeasure_stderr": 0.001195483166076756 }, { "task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeL_precision": 0.06966555184597864, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "rougeL_precision_stderr": 0.0012665956123840754 }, { "task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeL_recall": 0.34681007385001145, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "rougeL_recall_stderr": 0.004679678346399935 }, { "task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeL_fmeasure": 0.10864238895715833, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "rougeL_fmeasure_stderr": 0.0017176631324308034 }, { "task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeLsum_precision": 0.07031937468305927, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "rougeLsum_precision_stderr": 0.0013198255014853241 }, { "task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeLsum_recall": 0.35067051099532537, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "rougeLsum_recall_stderr": 0.004753075684894469 }, { "task_name": "GEM/web_nlg_en", "prompt_name": "PALM_prompt", "rougeLsum_fmeasure": 0.10948950405713026, "dataset_path": "GEM/web_nlg", "dataset_name": "en", "subset": null, "rougeLsum_fmeasure_stderr": 0.0017632128912827953 } ], "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": 1, "batch_size": 16, "device": "cuda", "use_cache": false, "limit": 3000, "bootstrap_iters": 10, "seed": 1234 } }