| bootstrapping for stddev: perplexity | |
| { | |
| "results": { | |
| "arc_challenge": { | |
| "acc,none": 0.19283276450511946, | |
| "acc_stderr,none": 0.01152905546566333, | |
| "acc_norm,none": 0.24488054607508533, | |
| "acc_norm_stderr,none": 0.012566273985131358 | |
| }, | |
| "arc_easy": { | |
| "acc,none": 0.4671717171717172, | |
| "acc_stderr,none": 0.010237645778853858, | |
| "acc_norm,none": 0.4132996632996633, | |
| "acc_norm_stderr,none": 0.010104361780747516 | |
| }, | |
| "boolq": { | |
| "acc,none": 0.6149847094801223, | |
| "acc_stderr,none": 0.00851066875102728 | |
| }, | |
| "hellaswag": { | |
| "acc,none": 0.28958374825731925, | |
| "acc_stderr,none": 0.004526422125860652, | |
| "acc_norm,none": 0.3016331408086039, | |
| "acc_norm_stderr,none": 0.004580288728196038 | |
| }, | |
| "lambada_openai": { | |
| "perplexity,none": 40.49750927655119, | |
| "perplexity_stderr,none": 1.9470980651595484, | |
| "acc,none": 0.35066951290510384, | |
| "acc_stderr,none": 0.006648045374603881 | |
| }, | |
| "openbookqa": { | |
| "acc,none": 0.172, | |
| "acc_stderr,none": 0.01689386887634748, | |
| "acc_norm,none": 0.28, | |
| "acc_norm_stderr,none": 0.020099950647503237 | |
| }, | |
| "piqa": { | |
| "acc,none": 0.6332970620239391, | |
| "acc_stderr,none": 0.011243625019038255, | |
| "acc_norm,none": 0.6262241566920566, | |
| "acc_norm_stderr,none": 0.011287972563201014 | |
| }, | |
| "sciq": { | |
| "acc,none": 0.753, | |
| "acc_stderr,none": 0.013644675781314128, | |
| "acc_norm,none": 0.67, | |
| "acc_norm_stderr,none": 0.014876872027456732 | |
| }, | |
| "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": 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", | |
| "template_aliases": "", | |
| "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", | |
| "template_aliases": "", | |
| "doc_to_text": "", | |
| "doc_to_target": "<function wikitext_detokenizer at 0x7fd1a1c44040>", | |
| "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 0x7fd1a1c16ef0>", | |
| "doc_to_target": "<function doc_to_target at 0x7fd1a1c17370>", | |
| "doc_to_choice": "<function doc_to_choice at 0x7fd1a1c175b0>", | |
| "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": 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": 0, | |
| "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: 0, batch_size: 16 | |
| | Task |Version|Filter| Metric | Value | |Stderr| | |
| |--------------|-------|------|---------------|------:|---|-----:| | |
| |arc_challenge |Yaml |none |acc | 0.1928|± |0.0115| | |
| | | |none |acc_norm | 0.2449|± |0.0126| | |
| |arc_easy |Yaml |none |acc | 0.4672|± |0.0102| | |
| | | |none |acc_norm | 0.4133|± |0.0101| | |
| |boolq |Yaml |none |acc | 0.6150|± |0.0085| | |
| |hellaswag |Yaml |none |acc | 0.2896|± |0.0045| | |
| | | |none |acc_norm | 0.3016|± |0.0046| | |
| |lambada_openai|Yaml |none |perplexity |40.4975|± |1.9471| | |
| | | |none |acc | 0.3507|± |0.0066| | |
| |openbookqa |Yaml |none |acc | 0.1720|± |0.0169| | |
| | | |none |acc_norm | 0.2800|± |0.0201| | |
| |piqa |Yaml |none |acc | 0.6333|± |0.0112| | |
| | | |none |acc_norm | 0.6262|± |0.0113| | |
| |sciq |Yaml |none |acc | 0.7530|± |0.0136| | |
| | | |none |acc_norm | 0.6700|± |0.0149| | |
| |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| | |