431 lines
13 KiB
Plaintext
431 lines
13 KiB
Plaintext
bootstrapping for stddev: perplexity
|
|
{
|
|
"results": {
|
|
"arc_challenge": {
|
|
"acc,none": 0.2431740614334471,
|
|
"acc_stderr,none": 0.012536554144587082,
|
|
"acc_norm,none": 0.27303754266211605,
|
|
"acc_norm_stderr,none": 0.013019332762635751
|
|
},
|
|
"arc_easy": {
|
|
"acc,none": 0.5441919191919192,
|
|
"acc_stderr,none": 0.010219631763437853,
|
|
"acc_norm,none": 0.47853535353535354,
|
|
"acc_norm_stderr,none": 0.010250325159456656
|
|
},
|
|
"boolq": {
|
|
"acc,none": 0.618960244648318,
|
|
"acc_stderr,none": 0.008493937524439329
|
|
},
|
|
"hellaswag": {
|
|
"acc,none": 0.3488348934475204,
|
|
"acc_stderr,none": 0.004756275875018267,
|
|
"acc_norm,none": 0.41545508862776337,
|
|
"acc_norm_stderr,none": 0.004917931778593191
|
|
},
|
|
"lambada_openai": {
|
|
"perplexity,none": 9.320713747126444,
|
|
"perplexity_stderr,none": 0.32204382695401407,
|
|
"acc,none": 0.5148457209392587,
|
|
"acc_stderr,none": 0.006962906440875391
|
|
},
|
|
"openbookqa": {
|
|
"acc,none": 0.204,
|
|
"acc_stderr,none": 0.018039369104138645,
|
|
"acc_norm,none": 0.3,
|
|
"acc_norm_stderr,none": 0.02051442622562805
|
|
},
|
|
"piqa": {
|
|
"acc,none": 0.6789989118607181,
|
|
"acc_stderr,none": 0.010892641574707904,
|
|
"acc_norm,none": 0.6811751904243744,
|
|
"acc_norm_stderr,none": 0.010873037534333416
|
|
},
|
|
"sciq": {
|
|
"acc,none": 0.809,
|
|
"acc_stderr,none": 0.012436787112179501,
|
|
"acc_norm,none": 0.717,
|
|
"acc_norm_stderr,none": 0.01425181090648174
|
|
},
|
|
"wikitext": {
|
|
"word_perplexity,none": 38.90357956698245,
|
|
"byte_perplexity,none": 1.8285957273924667,
|
|
"bits_per_byte,none": 0.8707361540620543
|
|
},
|
|
"winogrande": {
|
|
"acc,none": 0.5272296764009471,
|
|
"acc_stderr,none": 0.014031631629827694
|
|
}
|
|
},
|
|
"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 0x7f40312f8040>",
|
|
"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 0x7f40312caef0>",
|
|
"doc_to_target": "<function doc_to_target at 0x7f40312cb370>",
|
|
"doc_to_choice": "<function doc_to_choice at 0x7f40312cb5b0>",
|
|
"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-pythia410m-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-pythia410m-hh-dpo), limit: None, num_fewshot: 0, batch_size: 16
|
|
| Task |Version|Filter| Metric | Value | |Stderr|
|
|
|--------------|-------|------|---------------|------:|---|-----:|
|
|
|arc_challenge |Yaml |none |acc | 0.2432|± |0.0125|
|
|
| | |none |acc_norm | 0.2730|± |0.0130|
|
|
|arc_easy |Yaml |none |acc | 0.5442|± |0.0102|
|
|
| | |none |acc_norm | 0.4785|± |0.0103|
|
|
|boolq |Yaml |none |acc | 0.6190|± |0.0085|
|
|
|hellaswag |Yaml |none |acc | 0.3488|± |0.0048|
|
|
| | |none |acc_norm | 0.4155|± |0.0049|
|
|
|lambada_openai|Yaml |none |perplexity | 9.3207|± |0.3220|
|
|
| | |none |acc | 0.5148|± |0.0070|
|
|
|openbookqa |Yaml |none |acc | 0.2040|± |0.0180|
|
|
| | |none |acc_norm | 0.3000|± |0.0205|
|
|
|piqa |Yaml |none |acc | 0.6790|± |0.0109|
|
|
| | |none |acc_norm | 0.6812|± |0.0109|
|
|
|sciq |Yaml |none |acc | 0.8090|± |0.0124|
|
|
| | |none |acc_norm | 0.7170|± |0.0143|
|
|
|wikitext |Yaml |none |word_perplexity|38.9036| | |
|
|
| | |none |byte_perplexity| 1.8286| | |
|
|
| | |none |bits_per_byte | 0.8707| | |
|
|
|winogrande |Yaml |none |acc | 0.5272|± |0.0140|
|
|
|