初始化项目,由ModelHub XC社区提供模型
Model: lomahony/eleuther-pythia6.9b-hh-dpo Source: Original Platform
This commit is contained in:
24
dpo-6.9b-eval-files/dpo-pythia-6.9b-0shot-shelloutput.txt
Normal file
24
dpo-6.9b-eval-files/dpo-pythia-6.9b-0shot-shelloutput.txt
Normal file
@@ -0,0 +1,24 @@
|
||||
bootstrapping for stddev: perplexity
|
||||
hf (pretrained=lomahony/eleuther-pythia6.9b-hh-dpo), limit: None, num_fewshot: 0, batch_size: 4
|
||||
| Task |Version|Filter| Metric | Value | |Stderr|
|
||||
|--------------|-------|------|---------------|------:|---|-----:|
|
||||
|arc_challenge |Yaml |none |acc | 0.3242|± |0.0137|
|
||||
| | |none |acc_norm | 0.3541|± |0.0140|
|
||||
|arc_easy |Yaml |none |acc | 0.6860|± |0.0095|
|
||||
| | |none |acc_norm | 0.6149|± |0.0100|
|
||||
|boolq |Yaml |none |acc | 0.6688|± |0.0082|
|
||||
|hellaswag |Yaml |none |acc | 0.4910|± |0.0050|
|
||||
| | |none |acc_norm | 0.6487|± |0.0048|
|
||||
|lambada_openai|Yaml |none |perplexity | 3.7085|± |0.0866|
|
||||
| | |none |acc | 0.6947|± |0.0064|
|
||||
|openbookqa |Yaml |none |acc | 0.2760|± |0.0200|
|
||||
| | |none |acc_norm | 0.3860|± |0.0218|
|
||||
|piqa |Yaml |none |acc | 0.7622|± |0.0099|
|
||||
| | |none |acc_norm | 0.7704|± |0.0098|
|
||||
|sciq |Yaml |none |acc | 0.8940|± |0.0097|
|
||||
| | |none |acc_norm | 0.8300|± |0.0119|
|
||||
|wikitext |Yaml |none |word_perplexity|18.1988| | |
|
||||
| | |none |byte_perplexity| 1.6133| | |
|
||||
| | |none |bits_per_byte | 0.6900| | |
|
||||
|winogrande |Yaml |none |acc | 0.6235|± |0.0136|
|
||||
|
||||
404
dpo-6.9b-eval-files/dpo-pythia-6.9b-0shot/results.json
Normal file
404
dpo-6.9b-eval-files/dpo-pythia-6.9b-0shot/results.json
Normal file
@@ -0,0 +1,404 @@
|
||||
{
|
||||
"results": {
|
||||
"arc_challenge": {
|
||||
"acc,none": 0.3242320819112628,
|
||||
"acc_stderr,none": 0.013678810399518826,
|
||||
"acc_norm,none": 0.35409556313993173,
|
||||
"acc_norm_stderr,none": 0.013975454122756555
|
||||
},
|
||||
"arc_easy": {
|
||||
"acc,none": 0.686026936026936,
|
||||
"acc_stderr,none": 0.009523245335215506,
|
||||
"acc_norm,none": 0.61489898989899,
|
||||
"acc_norm_stderr,none": 0.00998521479873725
|
||||
},
|
||||
"boolq": {
|
||||
"acc,none": 0.6688073394495413,
|
||||
"acc_stderr,none": 0.008231583858517827
|
||||
},
|
||||
"hellaswag": {
|
||||
"acc,none": 0.4910376419040032,
|
||||
"acc_stderr,none": 0.004988979750014446,
|
||||
"acc_norm,none": 0.6486755626369249,
|
||||
"acc_norm_stderr,none": 0.00476408459717691
|
||||
},
|
||||
"lambada_openai": {
|
||||
"perplexity,none": 3.708528636318625,
|
||||
"perplexity_stderr,none": 0.08658115943815492,
|
||||
"acc,none": 0.6947409276149815,
|
||||
"acc_stderr,none": 0.006415903230922688
|
||||
},
|
||||
"openbookqa": {
|
||||
"acc,none": 0.276,
|
||||
"acc_stderr,none": 0.02001121929807353,
|
||||
"acc_norm,none": 0.386,
|
||||
"acc_norm_stderr,none": 0.021793529219281165
|
||||
},
|
||||
"piqa": {
|
||||
"acc,none": 0.7622415669205659,
|
||||
"acc_stderr,none": 0.009932525779525485,
|
||||
"acc_norm,none": 0.7704026115342764,
|
||||
"acc_norm_stderr,none": 0.009812682950815187
|
||||
},
|
||||
"sciq": {
|
||||
"acc,none": 0.894,
|
||||
"acc_stderr,none": 0.00973955126578514,
|
||||
"acc_norm,none": 0.83,
|
||||
"acc_norm_stderr,none": 0.011884495834541663
|
||||
},
|
||||
"wikitext": {
|
||||
"word_perplexity,none": 18.198752319892222,
|
||||
"byte_perplexity,none": 1.6133334471336491,
|
||||
"bits_per_byte,none": 0.6900446485426469
|
||||
},
|
||||
"winogrande": {
|
||||
"acc,none": 0.6235201262825573,
|
||||
"acc_stderr,none": 0.013616931960667182
|
||||
}
|
||||
},
|
||||
"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 0x7fed0a7c5120>",
|
||||
"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 0x7fed0a7c5360>",
|
||||
"doc_to_target": "<function doc_to_target at 0x7fed0a7c56c0>",
|
||||
"doc_to_choice": "<function doc_to_choice at 0x7fed0a7c5a20>",
|
||||
"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=lomahony/eleuther-pythia6.9b-hh-dpo",
|
||||
"batch_size": "4",
|
||||
"batch_sizes": [],
|
||||
"device": null,
|
||||
"use_cache": null,
|
||||
"limit": null,
|
||||
"bootstrap_iters": 100000
|
||||
},
|
||||
"git_hash": "d1a44c8"
|
||||
}
|
||||
24
dpo-6.9b-eval-files/dpo-pythia-6.9b-5shot-shelloutput.txt
Normal file
24
dpo-6.9b-eval-files/dpo-pythia-6.9b-5shot-shelloutput.txt
Normal file
@@ -0,0 +1,24 @@
|
||||
bootstrapping for stddev: perplexity
|
||||
hf (pretrained=lomahony/eleuther-pythia6.9b-hh-dpo), limit: None, num_fewshot: 5, batch_size: 4
|
||||
| Task |Version|Filter| Metric | Value | |Stderr|
|
||||
|--------------|-------|------|---------------|------:|---|-----:|
|
||||
|arc_challenge |Yaml |none |acc | 0.3746|± |0.0141|
|
||||
| | |none |acc_norm | 0.4036|± |0.0143|
|
||||
|arc_easy |Yaml |none |acc | 0.7193|± |0.0092|
|
||||
| | |none |acc_norm | 0.7197|± |0.0092|
|
||||
|boolq |Yaml |none |acc | 0.6694|± |0.0082|
|
||||
|hellaswag |Yaml |none |acc | 0.4890|± |0.0050|
|
||||
| | |none |acc_norm | 0.6550|± |0.0047|
|
||||
|lambada_openai|Yaml |none |perplexity | 4.7574|± |0.1175|
|
||||
| | |none |acc | 0.6487|± |0.0067|
|
||||
|openbookqa |Yaml |none |acc | 0.2960|± |0.0204|
|
||||
| | |none |acc_norm | 0.3820|± |0.0218|
|
||||
|piqa |Yaml |none |acc | 0.7726|± |0.0098|
|
||||
| | |none |acc_norm | 0.7704|± |0.0098|
|
||||
|sciq |Yaml |none |acc | 0.9490|± |0.0070|
|
||||
| | |none |acc_norm | 0.9530|± |0.0067|
|
||||
|wikitext |Yaml |none |word_perplexity|18.1988| | |
|
||||
| | |none |byte_perplexity| 1.6133| | |
|
||||
| | |none |bits_per_byte | 0.6900| | |
|
||||
|winogrande |Yaml |none |acc | 0.6235|± |0.0136|
|
||||
|
||||
404
dpo-6.9b-eval-files/dpo-pythia-6.9b-5shot/results.json
Normal file
404
dpo-6.9b-eval-files/dpo-pythia-6.9b-5shot/results.json
Normal file
@@ -0,0 +1,404 @@
|
||||
{
|
||||
"results": {
|
||||
"arc_challenge": {
|
||||
"acc,none": 0.37457337883959047,
|
||||
"acc_stderr,none": 0.01414419347189344,
|
||||
"acc_norm,none": 0.4035836177474403,
|
||||
"acc_norm_stderr,none": 0.014337158914268447
|
||||
},
|
||||
"arc_easy": {
|
||||
"acc,none": 0.7192760942760943,
|
||||
"acc_stderr,none": 0.009220526174711353,
|
||||
"acc_norm,none": 0.7196969696969697,
|
||||
"acc_norm_stderr,none": 0.009216306864088041
|
||||
},
|
||||
"boolq": {
|
||||
"acc,none": 0.6694189602446483,
|
||||
"acc_stderr,none": 0.008227739156121659
|
||||
},
|
||||
"hellaswag": {
|
||||
"acc,none": 0.48904600677155946,
|
||||
"acc_stderr,none": 0.0049885838203099185,
|
||||
"acc_norm,none": 0.6550487950607449,
|
||||
"acc_norm_stderr,none": 0.004743808792037855
|
||||
},
|
||||
"lambada_openai": {
|
||||
"perplexity,none": 4.757413961755731,
|
||||
"perplexity_stderr,none": 0.11748014516027318,
|
||||
"acc,none": 0.6487483019600233,
|
||||
"acc_stderr,none": 0.006650578225573465
|
||||
},
|
||||
"openbookqa": {
|
||||
"acc,none": 0.296,
|
||||
"acc_stderr,none": 0.020435342091896135,
|
||||
"acc_norm,none": 0.382,
|
||||
"acc_norm_stderr,none": 0.021750820591250837
|
||||
},
|
||||
"piqa": {
|
||||
"acc,none": 0.7725788900979326,
|
||||
"acc_stderr,none": 0.009779850767847252,
|
||||
"acc_norm,none": 0.7704026115342764,
|
||||
"acc_norm_stderr,none": 0.009812682950815181
|
||||
},
|
||||
"sciq": {
|
||||
"acc,none": 0.949,
|
||||
"acc_stderr,none": 0.006960420062571422,
|
||||
"acc_norm,none": 0.953,
|
||||
"acc_norm_stderr,none": 0.006695956678163039
|
||||
},
|
||||
"wikitext": {
|
||||
"word_perplexity,none": 18.198752319892222,
|
||||
"byte_perplexity,none": 1.6133334471336491,
|
||||
"bits_per_byte,none": 0.6900446485426469
|
||||
},
|
||||
"winogrande": {
|
||||
"acc,none": 0.6235201262825573,
|
||||
"acc_stderr,none": 0.013616931960667182
|
||||
}
|
||||
},
|
||||
"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 0x7fac47ff5120>",
|
||||
"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 0x7fac47ff5360>",
|
||||
"doc_to_target": "<function doc_to_target at 0x7fac47ff56c0>",
|
||||
"doc_to_choice": "<function doc_to_choice at 0x7fac47ff5a20>",
|
||||
"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-dpo",
|
||||
"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