初始化项目,由ModelHub XC社区提供模型
Model: lomahony/eleuther-pythia2.8b-hh-sft Source: Original Platform
This commit is contained in:
@@ -0,0 +1,24 @@
|
||||
bootstrapping for stddev: perplexity
|
||||
hf (pretrained=EleutherAI/pythia-2.8b), limit: None, num_fewshot: 0, batch_size: 16
|
||||
| Task |Version|Filter| Metric | Value | |Stderr|
|
||||
|--------------|-------|------|---------------|------:|---|-----:|
|
||||
|arc_challenge |Yaml |none |acc | 0.2952|± |0.0133|
|
||||
| | |none |acc_norm | 0.3311|± |0.0138|
|
||||
|arc_easy |Yaml |none |acc | 0.6448|± |0.0098|
|
||||
| | |none |acc_norm | 0.5871|± |0.0101|
|
||||
|boolq |Yaml |none |acc | 0.6474|± |0.0084|
|
||||
|hellaswag |Yaml |none |acc | 0.4532|± |0.0050|
|
||||
| | |none |acc_norm | 0.5926|± |0.0049|
|
||||
|lambada_openai|Yaml |none |perplexity | 5.0370|± |0.1191|
|
||||
| | |none |acc | 0.6472|± |0.0067|
|
||||
|openbookqa |Yaml |none |acc | 0.2400|± |0.0191|
|
||||
| | |none |acc_norm | 0.3580|± |0.0215|
|
||||
|piqa |Yaml |none |acc | 0.7394|± |0.0102|
|
||||
| | |none |acc_norm | 0.7356|± |0.0103|
|
||||
|sciq |Yaml |none |acc | 0.8870|± |0.0100|
|
||||
| | |none |acc_norm | 0.8350|± |0.0117|
|
||||
|wikitext |Yaml |none |word_perplexity|20.0571| | |
|
||||
| | |none |byte_perplexity| 1.6394| | |
|
||||
| | |none |bits_per_byte | 0.7132| | |
|
||||
|winogrande |Yaml |none |acc | 0.5975|± |0.0138|
|
||||
|
||||
404
base-2.8b-eval-files/EleutherAI-pythia-2.8b-0shot/results.json
Normal file
404
base-2.8b-eval-files/EleutherAI-pythia-2.8b-0shot/results.json
Normal file
@@ -0,0 +1,404 @@
|
||||
{
|
||||
"results": {
|
||||
"arc_challenge": {
|
||||
"acc,none": 0.295221843003413,
|
||||
"acc_stderr,none": 0.013329750293382316,
|
||||
"acc_norm,none": 0.3310580204778157,
|
||||
"acc_norm_stderr,none": 0.013752062419817836
|
||||
},
|
||||
"arc_easy": {
|
||||
"acc,none": 0.6447811447811448,
|
||||
"acc_stderr,none": 0.009820245899287126,
|
||||
"acc_norm,none": 0.5871212121212122,
|
||||
"acc_norm_stderr,none": 0.010102837421104667
|
||||
},
|
||||
"boolq": {
|
||||
"acc,none": 0.6474006116207951,
|
||||
"acc_stderr,none": 0.008356412493562119
|
||||
},
|
||||
"hellaswag": {
|
||||
"acc,none": 0.4531965743875722,
|
||||
"acc_stderr,none": 0.004967872475383267,
|
||||
"acc_norm,none": 0.5926110336586338,
|
||||
"acc_norm_stderr,none": 0.00490344168000382
|
||||
},
|
||||
"lambada_openai": {
|
||||
"perplexity,none": 5.0369907596068435,
|
||||
"perplexity_stderr,none": 0.11909165322070424,
|
||||
"acc,none": 0.6471958082670289,
|
||||
"acc_stderr,none": 0.006657279471298494
|
||||
},
|
||||
"openbookqa": {
|
||||
"acc,none": 0.24,
|
||||
"acc_stderr,none": 0.019118866653759753,
|
||||
"acc_norm,none": 0.358,
|
||||
"acc_norm_stderr,none": 0.02146143486285912
|
||||
},
|
||||
"piqa": {
|
||||
"acc,none": 0.7393906420021763,
|
||||
"acc_stderr,none": 0.010241826155811627,
|
||||
"acc_norm,none": 0.735582154515778,
|
||||
"acc_norm_stderr,none": 0.01028978724476717
|
||||
},
|
||||
"sciq": {
|
||||
"acc,none": 0.887,
|
||||
"acc_stderr,none": 0.010016552866696846,
|
||||
"acc_norm,none": 0.835,
|
||||
"acc_norm_stderr,none": 0.011743632866916171
|
||||
},
|
||||
"wikitext": {
|
||||
"word_perplexity,none": 20.05713713364702,
|
||||
"byte_perplexity,none": 1.6394022363791052,
|
||||
"bits_per_byte,none": 0.7131698710530711
|
||||
},
|
||||
"winogrande": {
|
||||
"acc,none": 0.5974743488555643,
|
||||
"acc_stderr,none": 0.013782866831703043
|
||||
}
|
||||
},
|
||||
"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",
|
||||
"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",
|
||||
"doc_to_text": "",
|
||||
"doc_to_target": "<function wikitext_detokenizer at 0x7fbdfeb25120>",
|
||||
"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 0x7fbdfeb25360>",
|
||||
"doc_to_target": "<function doc_to_target at 0x7fbdfeb256c0>",
|
||||
"doc_to_choice": "<function doc_to_choice at 0x7fbdfeb25a20>",
|
||||
"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": 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=EleutherAI/pythia-2.8b",
|
||||
"batch_size": "16",
|
||||
"batch_sizes": [],
|
||||
"device": null,
|
||||
"use_cache": null,
|
||||
"limit": null,
|
||||
"bootstrap_iters": 100000
|
||||
},
|
||||
"git_hash": "d1a44c8"
|
||||
}
|
||||
@@ -0,0 +1,24 @@
|
||||
bootstrapping for stddev: perplexity
|
||||
hf (pretrained=EleutherAI/pythia-2.8b), limit: None, num_fewshot: 5, batch_size: 8
|
||||
| Task |Version|Filter| Metric | Value | |Stderr|
|
||||
|--------------|-------|------|---------------|------:|---|-----:|
|
||||
|arc_challenge |Yaml |none |acc | 0.3123|± |0.0135|
|
||||
| | |none |acc_norm | 0.3549|± |0.0140|
|
||||
|arc_easy |Yaml |none |acc | 0.6700|± |0.0096|
|
||||
| | |none |acc_norm | 0.6759|± |0.0096|
|
||||
|boolq |Yaml |none |acc | 0.6664|± |0.0082|
|
||||
|hellaswag |Yaml |none |acc | 0.4504|± |0.0050|
|
||||
| | |none |acc_norm | 0.6031|± |0.0049|
|
||||
|lambada_openai|Yaml |none |perplexity | 6.4479|± |0.1602|
|
||||
| | |none |acc | 0.5948|± |0.0068|
|
||||
|openbookqa |Yaml |none |acc | 0.2480|± |0.0193|
|
||||
| | |none |acc_norm | 0.3720|± |0.0216|
|
||||
|piqa |Yaml |none |acc | 0.7427|± |0.0102|
|
||||
| | |none |acc_norm | 0.7443|± |0.0102|
|
||||
|sciq |Yaml |none |acc | 0.9440|± |0.0073|
|
||||
| | |none |acc_norm | 0.9400|± |0.0075|
|
||||
|wikitext |Yaml |none |word_perplexity|20.0571| | |
|
||||
| | |none |byte_perplexity| 1.6394| | |
|
||||
| | |none |bits_per_byte | 0.7132| | |
|
||||
|winogrande |Yaml |none |acc | 0.5943|± |0.0138|
|
||||
|
||||
404
base-2.8b-eval-files/EleutherAI-pythia-2.8b-5shot/results.json
Normal file
404
base-2.8b-eval-files/EleutherAI-pythia-2.8b-5shot/results.json
Normal file
@@ -0,0 +1,404 @@
|
||||
{
|
||||
"results": {
|
||||
"arc_challenge": {
|
||||
"acc,none": 0.3122866894197952,
|
||||
"acc_stderr,none": 0.013542598541688065,
|
||||
"acc_norm,none": 0.35494880546075086,
|
||||
"acc_norm_stderr,none": 0.01398303690409409
|
||||
},
|
||||
"arc_easy": {
|
||||
"acc,none": 0.67003367003367,
|
||||
"acc_stderr,none": 0.009648311574241036,
|
||||
"acc_norm,none": 0.6759259259259259,
|
||||
"acc_norm_stderr,none": 0.009603728850095387
|
||||
},
|
||||
"boolq": {
|
||||
"acc,none": 0.6663608562691131,
|
||||
"acc_stderr,none": 0.008246805985556868
|
||||
},
|
||||
"hellaswag": {
|
||||
"acc,none": 0.450408285202151,
|
||||
"acc_stderr,none": 0.0049651776330499236,
|
||||
"acc_norm,none": 0.6030671181039634,
|
||||
"acc_norm_stderr,none": 0.0048826194841666
|
||||
},
|
||||
"lambada_openai": {
|
||||
"perplexity,none": 6.447861085824152,
|
||||
"perplexity_stderr,none": 0.16023935097204245,
|
||||
"acc,none": 0.5947991461284688,
|
||||
"acc_stderr,none": 0.0068396269826581525
|
||||
},
|
||||
"openbookqa": {
|
||||
"acc,none": 0.248,
|
||||
"acc_stderr,none": 0.019332342821239103,
|
||||
"acc_norm,none": 0.372,
|
||||
"acc_norm_stderr,none": 0.0216371979857224
|
||||
},
|
||||
"piqa": {
|
||||
"acc,none": 0.7426550598476604,
|
||||
"acc_stderr,none": 0.01019992106479251,
|
||||
"acc_norm,none": 0.7442872687704026,
|
||||
"acc_norm_stderr,none": 0.010178690109459857
|
||||
},
|
||||
"sciq": {
|
||||
"acc,none": 0.944,
|
||||
"acc_stderr,none": 0.007274401481697066,
|
||||
"acc_norm,none": 0.94,
|
||||
"acc_norm_stderr,none": 0.007513751157474921
|
||||
},
|
||||
"wikitext": {
|
||||
"word_perplexity,none": 20.05713713364702,
|
||||
"byte_perplexity,none": 1.6394022363791052,
|
||||
"bits_per_byte,none": 0.7131698710530711
|
||||
},
|
||||
"winogrande": {
|
||||
"acc,none": 0.5943172849250198,
|
||||
"acc_stderr,none": 0.013800206336014201
|
||||
}
|
||||
},
|
||||
"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 0x7f80942fd120>",
|
||||
"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 0x7f80942fd360>",
|
||||
"doc_to_target": "<function doc_to_target at 0x7f80942fd6c0>",
|
||||
"doc_to_choice": "<function doc_to_choice at 0x7f80942fda20>",
|
||||
"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=EleutherAI/pythia-2.8b",
|
||||
"batch_size": "8",
|
||||
"batch_sizes": [],
|
||||
"device": null,
|
||||
"use_cache": null,
|
||||
"limit": null,
|
||||
"bootstrap_iters": 100000
|
||||
},
|
||||
"git_hash": "d1a44c8"
|
||||
}
|
||||
Reference in New Issue
Block a user