初始化项目，由ModelHub XC社区提供模型
Model: lomahony/eleuther-pythia6.9b-hh-sft Source: Original Platform
This commit is contained in:
ModelHub XC
404
sft-6.9b-eval-files/sft-pythia-6.9b-5shot/results.json
Normal file
404
sft-6.9b-eval-files/sft-pythia-6.9b-5shot/results.json
Normal file
@@ -0,0 +1,404 @@
|
||||
{
|
||||
"results": {
|
||||
"arc_challenge": {
|
||||
"acc,none": 0.3583617747440273,
|
||||
"acc_stderr,none": 0.014012883334859871,
|
||||
"acc_norm,none": 0.3848122866894198,
|
||||
"acc_norm_stderr,none": 0.014218371065251107
|
||||
},
|
||||
"arc_easy": {
|
||||
"acc,none": 0.7104377104377104,
|
||||
"acc_stderr,none": 0.0093068389121739,
|
||||
"acc_norm,none": 0.7133838383838383,
|
||||
"acc_norm_stderr,none": 0.009278551100969293
|
||||
},
|
||||
"boolq": {
|
||||
"acc,none": 0.6663608562691131,
|
||||
"acc_stderr,none": 0.008246805985556873
|
||||
},
|
||||
"hellaswag": {
|
||||
"acc,none": 0.48287193786098387,
|
||||
"acc_stderr,none": 0.004986852842576715,
|
||||
"acc_norm,none": 0.6445927106154152,
|
||||
"acc_norm_stderr,none": 0.004776583530909558
|
||||
},
|
||||
"lambada_openai": {
|
||||
"perplexity,none": 5.021473818972182,
|
||||
"perplexity_stderr,none": 0.12279168525921821,
|
||||
"acc,none": 0.6384630312439356,
|
||||
"acc_stderr,none": 0.006693546839258681
|
||||
},
|
||||
"openbookqa": {
|
||||
"acc,none": 0.276,
|
||||
"acc_stderr,none": 0.020011219298073528,
|
||||
"acc_norm,none": 0.37,
|
||||
"acc_norm_stderr,none": 0.021613289165165785
|
||||
},
|
||||
"piqa": {
|
||||
"acc,none": 0.7687704026115343,
|
||||
"acc_stderr,none": 0.009837063180625329,
|
||||
"acc_norm,none": 0.7709466811751904,
|
||||
"acc_norm_stderr,none": 0.009804509865175504
|
||||
},
|
||||
"sciq": {
|
||||
"acc,none": 0.952,
|
||||
"acc_stderr,none": 0.006763264133666668,
|
||||
"acc_norm,none": 0.954,
|
||||
"acc_norm_stderr,none": 0.006627814717380702
|
||||
},
|
||||
"wikitext": {
|
||||
"word_perplexity,none": 18.072185827315998,
|
||||
"byte_perplexity,none": 1.6114783437385283,
|
||||
"bits_per_byte,none": 0.6883848005035924
|
||||
},
|
||||
"winogrande": {
|
||||
"acc,none": 0.6156274664561957,
|
||||
"acc_stderr,none": 0.01367156760083619
|
||||
}
|
||||
},
|
||||
"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",
|
||||
"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",
|
||||
"doc_to_text": "",
|
||||
"doc_to_target": "<function wikitext_detokenizer at 0x7fed99361120>",
|
||||
"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 0x7fed99361360>",
|
||||
"doc_to_target": "<function doc_to_target at 0x7fed993616c0>",
|
||||
"doc_to_choice": "<function doc_to_choice at 0x7fed99361a20>",
|
||||
"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": 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=lomahony/eleuther-pythia6.9b-hh-sft",
|
||||
"batch_size": "4",
|
||||
"batch_sizes": [],
|
||||
"device": null,
|
||||
"use_cache": null,
|
||||
"limit": null,
|
||||
"bootstrap_iters": 100000
|
||||
},
|
||||
"git_hash": "d1a44c8"
|
||||
}
|
||||
Reference in New Issue
Block a user