eleuther-pythia70m-hh-sft / base-70m-eval-files /EleutherAI-pythia-70m-0shot-shelloutput.txt
lomahony's picture
Upload 8 files
aaae80f
bootstrapping for stddev: perplexity
{
"results": {
"arc_challenge": {
"acc,none": 0.1757679180887372,
"acc_stderr,none": 0.011122850863120485,
"acc_norm,none": 0.21843003412969283,
"acc_norm_stderr,none": 0.012074291605700975
},
"arc_easy": {
"acc,none": 0.37542087542087543,
"acc_stderr,none": 0.00993621852711428,
"acc_norm,none": 0.3522727272727273,
"acc_norm_stderr,none": 0.009801753933112785
},
"boolq": {
"acc,none": 0.5886850152905199,
"acc_stderr,none": 0.00860639542630921
},
"hellaswag": {
"acc,none": 0.2666799442342163,
"acc_stderr,none": 0.004413198640053973,
"acc_norm,none": 0.27384983071101376,
"acc_norm_stderr,none": 0.004450214826707207
},
"lambada_openai": {
"perplexity,none": 130.96389727138103,
"perplexity_stderr,none": 5.501211486155379,
"acc,none": 0.22705220260042694,
"acc_stderr,none": 0.005836466732850104
},
"openbookqa": {
"acc,none": 0.126,
"acc_stderr,none": 0.014855617750787541,
"acc_norm,none": 0.254,
"acc_norm_stderr,none": 0.01948659680164337
},
"piqa": {
"acc,none": 0.5984766050054406,
"acc_stderr,none": 0.011437324373397844,
"acc_norm,none": 0.5919477693144722,
"acc_norm_stderr,none": 0.011466872778651264
},
"sciq": {
"acc,none": 0.64,
"acc_stderr,none": 0.015186527932040117,
"acc_norm,none": 0.564,
"acc_norm_stderr,none": 0.015689173023144064
},
"wikitext": {
"word_perplexity,none": 112.6458354552029,
"byte_perplexity,none": 2.1788907860475493,
"bits_per_byte,none": 1.1235938851292067
},
"winogrande": {
"acc,none": 0.5295974743488555,
"acc_stderr,none": 0.014027843827840085
}
},
"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 0x7f8221504040>",
"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 0x7f82214d6ef0>",
"doc_to_target": "<function doc_to_target at 0x7f82214d7370>",
"doc_to_choice": "<function doc_to_choice at 0x7f82214d75b0>",
"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=EleutherAI/pythia-70m",
"num_fewshot": 0,
"batch_size": 16,
"batch_sizes": [],
"device": "cuda:0",
"use_cache": null,
"limit": null,
"bootstrap_iters": 100000
},
"git_hash": "4e44f0a"
}
hf (pretrained=EleutherAI/pythia-70m), limit: None, num_fewshot: 0, batch_size: 16
| Task |Version|Filter| Metric | Value | |Stderr|
|--------------|-------|------|---------------|-------:|---|-----:|
|arc_challenge |Yaml |none |acc | 0.1758|± |0.0111|
| | |none |acc_norm | 0.2184|± |0.0121|
|arc_easy |Yaml |none |acc | 0.3754|± |0.0099|
| | |none |acc_norm | 0.3523|± |0.0098|
|boolq |Yaml |none |acc | 0.5887|± |0.0086|
|hellaswag |Yaml |none |acc | 0.2667|± |0.0044|
| | |none |acc_norm | 0.2738|± |0.0045|
|lambada_openai|Yaml |none |perplexity |130.9639|± |5.5012|
| | |none |acc | 0.2271|± |0.0058|
|openbookqa |Yaml |none |acc | 0.1260|± |0.0149|
| | |none |acc_norm | 0.2540|± |0.0195|
|piqa |Yaml |none |acc | 0.5985|± |0.0114|
| | |none |acc_norm | 0.5919|± |0.0115|
|sciq |Yaml |none |acc | 0.6400|± |0.0152|
| | |none |acc_norm | 0.5640|± |0.0157|
|wikitext |Yaml |none |word_perplexity|112.6458| | |
| | |none |byte_perplexity| 2.1789| | |
| | |none |bits_per_byte | 1.1236| | |
|winogrande |Yaml |none |acc | 0.5296|± |0.0140|