|
{ |
|
"results": { |
|
"arc_challenge": { |
|
"acc,none": 0.31569965870307165, |
|
"acc_stderr,none": 0.013582571095815295, |
|
"acc_norm,none": 0.3515358361774744, |
|
"acc_norm_stderr,none": 0.013952413699600931 |
|
}, |
|
"arc_easy": { |
|
"acc,none": 0.7032828282828283, |
|
"acc_stderr,none": 0.009373559492986851, |
|
"acc_norm,none": 0.6372053872053872, |
|
"acc_norm_stderr,none": 0.009865936757013938 |
|
}, |
|
"boolq": { |
|
"acc,none": 0.67217125382263, |
|
"acc_stderr,none": 0.008210243237673385 |
|
}, |
|
"hellaswag": { |
|
"acc,none": 0.5037841067516431, |
|
"acc_stderr,none": 0.004989638507409938, |
|
"acc_norm,none": 0.6727743477394941, |
|
"acc_norm_stderr,none": 0.004682414968323615 |
|
}, |
|
"lambada_openai": { |
|
"perplexity,none": 3.928303151284302, |
|
"perplexity_stderr,none": 0.08380809965264784, |
|
"acc,none": 0.7056083834659421, |
|
"acc_stderr,none": 0.006349750457397497 |
|
}, |
|
"openbookqa": { |
|
"acc,none": 0.264, |
|
"acc_stderr,none": 0.019732885585922098, |
|
"acc_norm,none": 0.38, |
|
"acc_norm_stderr,none": 0.02172888143870172 |
|
}, |
|
"piqa": { |
|
"acc,none": 0.7611534276387377, |
|
"acc_stderr,none": 0.009948120385337496, |
|
"acc_norm,none": 0.7698585418933623, |
|
"acc_norm_stderr,none": 0.009820832826839813 |
|
}, |
|
"sciq": { |
|
"acc,none": 0.904, |
|
"acc_stderr,none": 0.009320454434783203, |
|
"acc_norm,none": 0.85, |
|
"acc_norm_stderr,none": 0.01129723982340931 |
|
}, |
|
"wikitext": { |
|
"word_perplexity,none": 16.10381134238307, |
|
"byte_perplexity,none": 1.5811322783219102, |
|
"bits_per_byte,none": 0.6609580693383097 |
|
}, |
|
"winogrande": { |
|
"acc,none": 0.6353591160220995, |
|
"acc_stderr,none": 0.013527746622429842 |
|
} |
|
}, |
|
"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 0x7f1b6d8b9120>", |
|
"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 0x7f1b6d8b9360>", |
|
"doc_to_target": "<function doc_to_target at 0x7f1b6d8b96c0>", |
|
"doc_to_choice": "<function doc_to_choice at 0x7f1b6d8b9a20>", |
|
"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=EleutherAI/pythia-12b,parallelize=True", |
|
"batch_size": "4", |
|
"batch_sizes": [], |
|
"device": null, |
|
"use_cache": null, |
|
"limit": null, |
|
"bootstrap_iters": 100000 |
|
}, |
|
"git_hash": "d1a44c8" |
|
} |