|
{ |
|
"results": { |
|
"arc_challenge": { |
|
"acc,none": 0.3302047781569966, |
|
"acc_stderr,none": 0.013743085603760427, |
|
"acc_norm,none": 0.34897610921501704, |
|
"acc_norm_stderr,none": 0.013928933461382497 |
|
}, |
|
"arc_easy": { |
|
"acc,none": 0.6624579124579124, |
|
"acc_stderr,none": 0.009703117820790301, |
|
"acc_norm,none": 0.5917508417508418, |
|
"acc_norm_stderr,none": 0.010085566195791252 |
|
}, |
|
"boolq": { |
|
"acc,none": 0.6247706422018349, |
|
"acc_stderr,none": 0.008468397820914273 |
|
}, |
|
"hellaswag": { |
|
"acc,none": 0.46773551085441145, |
|
"acc_stderr,none": 0.00497938187671261, |
|
"acc_norm,none": 0.6072495518820952, |
|
"acc_norm_stderr,none": 0.004873640184773437 |
|
}, |
|
"lambada_openai": { |
|
"perplexity,none": 4.4821107933393245, |
|
"perplexity_stderr,none": 0.12203127098816188, |
|
"acc,none": 0.6349699204346982, |
|
"acc_stderr,none": 0.006707380989588293 |
|
}, |
|
"openbookqa": { |
|
"acc,none": 0.264, |
|
"acc_stderr,none": 0.019732885585922087, |
|
"acc_norm,none": 0.396, |
|
"acc_norm_stderr,none": 0.02189352994166582 |
|
}, |
|
"piqa": { |
|
"acc,none": 0.7535364526659413, |
|
"acc_stderr,none": 0.01005481078967182, |
|
"acc_norm,none": 0.7453754080522307, |
|
"acc_norm_stderr,none": 0.01016443223706048 |
|
}, |
|
"sciq": { |
|
"acc,none": 0.863, |
|
"acc_stderr,none": 0.010878848714333304, |
|
"acc_norm,none": 0.803, |
|
"acc_norm_stderr,none": 0.012583693787968144 |
|
}, |
|
"wikitext": { |
|
"word_perplexity,none": 21.92791944465979, |
|
"byte_perplexity,none": 1.6636811907626483, |
|
"bits_per_byte,none": 0.734378998038975 |
|
}, |
|
"winogrande": { |
|
"acc,none": 0.5966850828729282, |
|
"acc_stderr,none": 0.013787257285896238 |
|
} |
|
}, |
|
"configs": { |
|
"arc_challenge": { |
|
"task": "arc_challenge", |
|
"group": [ |
|
"ai2_arc", |
|
"multiple_choice" |
|
], |
|
"dataset_path": "ai2_arc", |
|
"dataset_name": "ARC-Challenge", |
|
"training_split": "train", |
|
"validation_split": "validation", |
|
"test_split": "test", |
|
"doc_to_text": "Question: {{question}}\nAnswer:", |
|
"doc_to_target": "{{choices.label.index(answerKey)}}", |
|
"doc_to_choice": "{{choices.text}}", |
|
"description": "", |
|
"target_delimiter": " ", |
|
"fewshot_delimiter": "\n\n", |
|
"num_fewshot": 0, |
|
"metric_list": [ |
|
{ |
|
"metric": "acc", |
|
"aggregation": "mean", |
|
"higher_is_better": true |
|
}, |
|
{ |
|
"metric": "acc_norm", |
|
"aggregation": "mean", |
|
"higher_is_better": true |
|
} |
|
], |
|
"output_type": "multiple_choice", |
|
"repeats": 1, |
|
"should_decontaminate": true, |
|
"doc_to_decontamination_query": "Question: {{question}}\nAnswer:" |
|
}, |
|
"arc_easy": { |
|
"task": "arc_easy", |
|
"group": [ |
|
"ai2_arc", |
|
"multiple_choice" |
|
], |
|
"dataset_path": "ai2_arc", |
|
"dataset_name": "ARC-Easy", |
|
"training_split": "train", |
|
"validation_split": "validation", |
|
"test_split": "test", |
|
"doc_to_text": "Question: {{question}}\nAnswer:", |
|
"doc_to_target": "{{choices.label.index(answerKey)}}", |
|
"doc_to_choice": "{{choices.text}}", |
|
"description": "", |
|
"target_delimiter": " ", |
|
"fewshot_delimiter": "\n\n", |
|
"num_fewshot": 0, |
|
"metric_list": [ |
|
{ |
|
"metric": "acc", |
|
"aggregation": "mean", |
|
"higher_is_better": true |
|
}, |
|
{ |
|
"metric": "acc_norm", |
|
"aggregation": "mean", |
|
"higher_is_better": true |
|
} |
|
], |
|
"output_type": "multiple_choice", |
|
"repeats": 1, |
|
"should_decontaminate": true, |
|
"doc_to_decontamination_query": "Question: {{question}}\nAnswer:" |
|
}, |
|
"boolq": { |
|
"task": "boolq", |
|
"group": [ |
|
"super-glue-lm-eval-v1" |
|
], |
|
"dataset_path": "super_glue", |
|
"dataset_name": "boolq", |
|
"training_split": "train", |
|
"validation_split": "validation", |
|
"doc_to_text": "{{passage}}\nQuestion: {{question}}?\nAnswer:", |
|
"doc_to_target": "label", |
|
"doc_to_choice": [ |
|
"no", |
|
"yes" |
|
], |
|
"description": "", |
|
"target_delimiter": " ", |
|
"fewshot_delimiter": "\n\n", |
|
"num_fewshot": 0, |
|
"metric_list": [ |
|
{ |
|
"metric": "acc" |
|
} |
|
], |
|
"output_type": "multiple_choice", |
|
"repeats": 1, |
|
"should_decontaminate": true, |
|
"doc_to_decontamination_query": "passage" |
|
}, |
|
"hellaswag": { |
|
"task": "hellaswag", |
|
"group": [ |
|
"multiple_choice" |
|
], |
|
"dataset_path": "hellaswag", |
|
"training_split": "train", |
|
"validation_split": "validation", |
|
"doc_to_text": "{% set text = activity_label ~ ': ' ~ ctx_a ~ ' ' ~ ctx_b.capitalize() %}{{text|trim|replace(' [title]', '. ')|regex_replace('\\[.*?\\]', '')|replace(' ', ' ')}}", |
|
"doc_to_target": "{{label}}", |
|
"doc_to_choice": "{{endings|map('trim')|map('replace', ' [title]', '. ')|map('regex_replace', '\\[.*?\\]', '')|map('replace', ' ', ' ')|list}}", |
|
"description": "", |
|
"target_delimiter": " ", |
|
"fewshot_delimiter": "\n\n", |
|
"num_fewshot": 0, |
|
"metric_list": [ |
|
{ |
|
"metric": "acc", |
|
"aggregation": "mean", |
|
"higher_is_better": true |
|
}, |
|
{ |
|
"metric": "acc_norm", |
|
"aggregation": "mean", |
|
"higher_is_better": true |
|
} |
|
], |
|
"output_type": "multiple_choice", |
|
"repeats": 1, |
|
"should_decontaminate": false |
|
}, |
|
"lambada_openai": { |
|
"task": "lambada_openai", |
|
"group": [ |
|
"lambada", |
|
"loglikelihood", |
|
"perplexity" |
|
], |
|
"dataset_path": "EleutherAI/lambada_openai", |
|
"dataset_name": "default", |
|
"test_split": "test", |
|
"doc_to_text": "{{text.split(' ')[:-1]|join(' ')}}", |
|
"doc_to_target": "{{' '+text.split(' ')[-1]}}", |
|
"description": "", |
|
"target_delimiter": " ", |
|
"fewshot_delimiter": "\n\n", |
|
"num_fewshot": 0, |
|
"metric_list": [ |
|
{ |
|
"metric": "perplexity", |
|
"aggregation": "perplexity", |
|
"higher_is_better": false |
|
}, |
|
{ |
|
"metric": "acc", |
|
"aggregation": "mean", |
|
"higher_is_better": true |
|
} |
|
], |
|
"output_type": "loglikelihood", |
|
"repeats": 1, |
|
"should_decontaminate": true, |
|
"doc_to_decontamination_query": "{{text}}" |
|
}, |
|
"openbookqa": { |
|
"task": "openbookqa", |
|
"group": [ |
|
"multiple_choice" |
|
], |
|
"dataset_path": "openbookqa", |
|
"dataset_name": "main", |
|
"training_split": "train", |
|
"validation_split": "validation", |
|
"test_split": "test", |
|
"doc_to_text": "question_stem", |
|
"doc_to_target": "{{choices.label.index(answerKey.lstrip())}}", |
|
"doc_to_choice": "{{choices.text}}", |
|
"description": "", |
|
"target_delimiter": " ", |
|
"fewshot_delimiter": "\n\n", |
|
"num_fewshot": 0, |
|
"metric_list": [ |
|
{ |
|
"metric": "acc", |
|
"aggregation": "mean", |
|
"higher_is_better": true |
|
}, |
|
{ |
|
"metric": "acc_norm", |
|
"aggregation": "mean", |
|
"higher_is_better": true |
|
} |
|
], |
|
"output_type": "multiple_choice", |
|
"repeats": 1, |
|
"should_decontaminate": true, |
|
"doc_to_decontamination_query": "question_stem" |
|
}, |
|
"piqa": { |
|
"task": "piqa", |
|
"group": [ |
|
"multiple_choice" |
|
], |
|
"dataset_path": "piqa", |
|
"training_split": "train", |
|
"validation_split": "validation", |
|
"doc_to_text": "Question: {{goal}}\nAnswer:", |
|
"doc_to_target": "label", |
|
"doc_to_choice": "{{[sol1, sol2]}}", |
|
"description": "", |
|
"target_delimiter": " ", |
|
"fewshot_delimiter": "\n\n", |
|
"num_fewshot": 0, |
|
"metric_list": [ |
|
{ |
|
"metric": "acc", |
|
"aggregation": "mean", |
|
"higher_is_better": true |
|
}, |
|
{ |
|
"metric": "acc_norm", |
|
"aggregation": "mean", |
|
"higher_is_better": true |
|
} |
|
], |
|
"output_type": "multiple_choice", |
|
"repeats": 1, |
|
"should_decontaminate": true, |
|
"doc_to_decontamination_query": "goal" |
|
}, |
|
"sciq": { |
|
"task": "sciq", |
|
"group": [ |
|
"multiple_choice" |
|
], |
|
"dataset_path": "sciq", |
|
"training_split": "train", |
|
"validation_split": "validation", |
|
"test_split": "test", |
|
"doc_to_text": "{{support.lstrip()}}\nQuestion: {{question}}\nAnswer:", |
|
"doc_to_target": 3, |
|
"doc_to_choice": "{{[distractor1, distractor2, distractor3, correct_answer]}}", |
|
"description": "", |
|
"target_delimiter": " ", |
|
"fewshot_delimiter": "\n\n", |
|
"num_fewshot": 0, |
|
"metric_list": [ |
|
{ |
|
"metric": "acc", |
|
"aggregation": "mean", |
|
"higher_is_better": true |
|
}, |
|
{ |
|
"metric": "acc_norm", |
|
"aggregation": "mean", |
|
"higher_is_better": true |
|
} |
|
], |
|
"output_type": "multiple_choice", |
|
"repeats": 1, |
|
"should_decontaminate": true, |
|
"doc_to_decontamination_query": "{{support}} {{question}}" |
|
}, |
|
"wikitext": { |
|
"task": "wikitext", |
|
"group": [ |
|
"perplexity", |
|
"loglikelihood_rolling" |
|
], |
|
"dataset_path": "EleutherAI/wikitext_document_level", |
|
"dataset_name": "wikitext-2-raw-v1", |
|
"training_split": "train", |
|
"validation_split": "validation", |
|
"test_split": "test", |
|
"doc_to_text": "", |
|
"doc_to_target": "<function wikitext_detokenizer at 0x7feb0f9c1120>", |
|
"description": "", |
|
"target_delimiter": " ", |
|
"fewshot_delimiter": "\n\n", |
|
"num_fewshot": 0, |
|
"metric_list": [ |
|
{ |
|
"metric": "word_perplexity" |
|
}, |
|
{ |
|
"metric": "byte_perplexity" |
|
}, |
|
{ |
|
"metric": "bits_per_byte" |
|
} |
|
], |
|
"output_type": "loglikelihood_rolling", |
|
"repeats": 1, |
|
"should_decontaminate": true, |
|
"doc_to_decontamination_query": "{{page}}" |
|
}, |
|
"winogrande": { |
|
"task": "winogrande", |
|
"dataset_path": "winogrande", |
|
"dataset_name": "winogrande_xl", |
|
"training_split": "train", |
|
"validation_split": "validation", |
|
"doc_to_text": "<function doc_to_text at 0x7feb0f9c1360>", |
|
"doc_to_target": "<function doc_to_target at 0x7feb0f9c16c0>", |
|
"doc_to_choice": "<function doc_to_choice at 0x7feb0f9c1a20>", |
|
"description": "", |
|
"target_delimiter": " ", |
|
"fewshot_delimiter": "\n\n", |
|
"num_fewshot": 0, |
|
"metric_list": [ |
|
{ |
|
"metric": "acc", |
|
"aggregation": "mean", |
|
"higher_is_better": true |
|
} |
|
], |
|
"output_type": "multiple_choice", |
|
"repeats": 1, |
|
"should_decontaminate": true, |
|
"doc_to_decontamination_query": "sentence" |
|
} |
|
}, |
|
"versions": { |
|
"arc_challenge": "Yaml", |
|
"arc_easy": "Yaml", |
|
"boolq": "Yaml", |
|
"hellaswag": "Yaml", |
|
"lambada_openai": "Yaml", |
|
"openbookqa": "Yaml", |
|
"piqa": "Yaml", |
|
"sciq": "Yaml", |
|
"wikitext": "Yaml", |
|
"winogrande": "Yaml" |
|
}, |
|
"config": { |
|
"model": "hf", |
|
"model_args": "pretrained=lomahony/eleuther-pythia2.8b-hh-dpo", |
|
"batch_size": "16", |
|
"batch_sizes": [], |
|
"device": null, |
|
"use_cache": null, |
|
"limit": null, |
|
"bootstrap_iters": 100000 |
|
}, |
|
"git_hash": "d1a44c8" |
|
} |