| bootstrapping for stddev: perplexity | |
| { | |
| "results": { | |
| "arc_challenge": { | |
| "acc,none": 0.20563139931740615, | |
| "acc_stderr,none": 0.011810745260742547, | |
| "acc_norm,none": 0.24744027303754265, | |
| "acc_norm_stderr,none": 0.01261035266329267 | |
| }, | |
| "arc_easy": { | |
| "acc,none": 0.46380471380471383, | |
| "acc_stderr,none": 0.01023286555034674, | |
| "acc_norm,none": 0.4385521885521885, | |
| "acc_norm_stderr,none": 0.010182010275471116 | |
| }, | |
| "boolq": { | |
| "acc,none": 0.6055045871559633, | |
| "acc_stderr,none": 0.008548152025770934 | |
| }, | |
| "hellaswag": { | |
| "acc,none": 0.2885879306910974, | |
| "acc_stderr,none": 0.004521798577922137, | |
| "acc_norm,none": 0.3088030272854013, | |
| "acc_norm_stderr,none": 0.004610554974411229 | |
| }, | |
| "lambada_openai": { | |
| "perplexity,none": 68.78788187981594, | |
| "perplexity_stderr,none": 3.3418985414978897, | |
| "acc,none": 0.2815835435668543, | |
| "acc_stderr,none": 0.006266194106395877 | |
| }, | |
| "openbookqa": { | |
| "acc,none": 0.158, | |
| "acc_stderr,none": 0.01632804980457984, | |
| "acc_norm,none": 0.254, | |
| "acc_norm_stderr,none": 0.019486596801643368 | |
| }, | |
| "piqa": { | |
| "acc,none": 0.6284004352557128, | |
| "acc_stderr,none": 0.011274603006724757, | |
| "acc_norm,none": 0.6332970620239391, | |
| "acc_norm_stderr,none": 0.01124362501903826 | |
| }, | |
| "sciq": { | |
| "acc,none": 0.76, | |
| "acc_stderr,none": 0.013512312258920836, | |
| "acc_norm,none": 0.737, | |
| "acc_norm_stderr,none": 0.013929286594259724 | |
| }, | |
| "wikitext": { | |
| "word_perplexity,none": 75.24993841350984, | |
| "byte_perplexity,none": 2.0386909133746456, | |
| "bits_per_byte,none": 1.0276430644458452 | |
| }, | |
| "winogrande": { | |
| "acc,none": 0.5138121546961326, | |
| "acc_stderr,none": 0.014047122916440419 | |
| } | |
| }, | |
| "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": 5, | |
| "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": 5, | |
| "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": 5, | |
| "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": 5, | |
| "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", | |
| "template_aliases": "", | |
| "doc_to_text": "{{text.split(' ')[:-1]|join(' ')}}", | |
| "doc_to_target": "{{' '+text.split(' ')[-1]}}", | |
| "description": "", | |
| "target_delimiter": " ", | |
| "fewshot_delimiter": "\n\n", | |
| "num_fewshot": 5, | |
| "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": 5, | |
| "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": 5, | |
| "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": 5, | |
| "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", | |
| "template_aliases": "", | |
| "doc_to_text": "", | |
| "doc_to_target": "<function wikitext_detokenizer at 0x7ff6ce1e4040>", | |
| "description": "", | |
| "target_delimiter": " ", | |
| "fewshot_delimiter": "\n\n", | |
| "num_fewshot": 5, | |
| "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 0x7ff6ce1b6ef0>", | |
| "doc_to_target": "<function doc_to_target at 0x7ff6ce1b7370>", | |
| "doc_to_choice": "<function doc_to_choice at 0x7ff6ce1b75b0>", | |
| "description": "", | |
| "target_delimiter": " ", | |
| "fewshot_delimiter": "\n\n", | |
| "num_fewshot": 5, | |
| "metric_list": [ | |
| { | |
| "metric": "acc", | |
| "aggregation": "mean", | |
| "higher_is_better": true | |
| } | |
| ], | |
| "output_type": "multiple_choice", | |
| "repeats": 1, | |
| "should_decontaminate": false | |
| } | |
| }, | |
| "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-pythia160m-hh-dpo", | |
| "num_fewshot": 5, | |
| "batch_size": 16, | |
| "batch_sizes": [], | |
| "device": "cuda:0", | |
| "use_cache": null, | |
| "limit": null, | |
| "bootstrap_iters": 100000 | |
| }, | |
| "git_hash": "4e44f0a" | |
| } | |
| hf (pretrained=lomahony/eleuther-pythia160m-hh-dpo), limit: None, num_fewshot: 5, batch_size: 16 | |
| | Task |Version|Filter| Metric | Value | |Stderr| | |
| |--------------|-------|------|---------------|------:|---|-----:| | |
| |arc_challenge |Yaml |none |acc | 0.2056|± |0.0118| | |
| | | |none |acc_norm | 0.2474|± |0.0126| | |
| |arc_easy |Yaml |none |acc | 0.4638|± |0.0102| | |
| | | |none |acc_norm | 0.4386|± |0.0102| | |
| |boolq |Yaml |none |acc | 0.6055|± |0.0085| | |
| |hellaswag |Yaml |none |acc | 0.2886|± |0.0045| | |
| | | |none |acc_norm | 0.3088|± |0.0046| | |
| |lambada_openai|Yaml |none |perplexity |68.7879|± |3.3419| | |
| | | |none |acc | 0.2816|± |0.0063| | |
| |openbookqa |Yaml |none |acc | 0.1580|± |0.0163| | |
| | | |none |acc_norm | 0.2540|± |0.0195| | |
| |piqa |Yaml |none |acc | 0.6284|± |0.0113| | |
| | | |none |acc_norm | 0.6333|± |0.0112| | |
| |sciq |Yaml |none |acc | 0.7600|± |0.0135| | |
| | | |none |acc_norm | 0.7370|± |0.0139| | |
| |wikitext |Yaml |none |word_perplexity|75.2499| | | | |
| | | |none |byte_perplexity| 2.0387| | | | |
| | | |none |bits_per_byte | 1.0276| | | | |
| |winogrande |Yaml |none |acc | 0.5138|± |0.0140| | |