open-r1-eval-leaderboard / eval_results /Qwen /Qwen1.5-1.8B-Chat /main /bbh /results_2024-03-18T20-11-24.511185.json
lewtun's picture
lewtun HF staff
Upload eval_results/Qwen/Qwen1.5-1.8B-Chat/main/bbh/results_2024-03-18T20-11-24.511185.json with huggingface_hub
754f9ed verified
raw
history blame
33.5 kB
{
"config_general": {
"lighteval_sha": "?",
"num_fewshot_seeds": 1,
"override_batch_size": 1,
"max_samples": null,
"job_id": "",
"start_time": 1049544.406302061,
"end_time": 1049733.454036125,
"total_evaluation_time_secondes": "189.04773406405002",
"model_name": "Qwen/Qwen1.5-1.8B-Chat",
"model_sha": "3aede71902ad578aac72678f9f8b6199ca6ab53b",
"model_dtype": "torch.bfloat16",
"model_size": "3.8 GB",
"config": null
},
"results": {
"harness|bbh:causal_judgment|3": {
"em": 0.5080213903743316,
"em_stderr": 0.03665706061581778,
"qem": 0.5080213903743316,
"qem_stderr": 0.03665706061581778,
"pem": 0.5080213903743316,
"pem_stderr": 0.03665706061581778,
"pqem": 0.5080213903743316,
"pqem_stderr": 0.03665706061581778,
"perfect_em": 0.5080213903743316,
"perfect_em_stderr": 0.03665706061581778
},
"harness|bbh:date_understanding|3": {
"em": 0.24,
"em_stderr": 0.027065293652239007,
"qem": 0.24,
"qem_stderr": 0.027065293652239007,
"pem": 0.38,
"pem_stderr": 0.03076011604262604,
"pqem": 0.568,
"pqem_stderr": 0.031391810765429407,
"perfect_em": 0.24,
"perfect_em_stderr": 0.027065293652239007
},
"harness|bbh:disambiguation_qa|3": {
"em": 0.38,
"em_stderr": 0.030760116042626053,
"qem": 0.38,
"qem_stderr": 0.030760116042626053,
"pem": 0.384,
"pem_stderr": 0.03082167911737537,
"pqem": 0.672,
"pqem_stderr": 0.029752391824475387,
"perfect_em": 0.38,
"perfect_em_stderr": 0.030760116042626053
},
"harness|bbh:geometric_shapes|3": {
"em": 0.088,
"em_stderr": 0.017953084777052913,
"qem": 0.088,
"qem_stderr": 0.017953084777052913,
"pem": 0.088,
"pem_stderr": 0.017953084777052913,
"pqem": 0.088,
"pqem_stderr": 0.017953084777052913,
"perfect_em": 0.088,
"perfect_em_stderr": 0.017953084777052913
},
"harness|bbh:logical_deduction_five_objects|3": {
"em": 0.208,
"em_stderr": 0.025721398901416396,
"qem": 0.208,
"qem_stderr": 0.025721398901416396,
"pem": 0.24,
"pem_stderr": 0.02706529365223901,
"pqem": 0.42,
"pqem_stderr": 0.03127799950463661,
"perfect_em": 0.208,
"perfect_em_stderr": 0.025721398901416396
},
"harness|bbh:logical_deduction_seven_objects|3": {
"em": 0.104,
"em_stderr": 0.01934510097484389,
"qem": 0.104,
"qem_stderr": 0.01934510097484389,
"pem": 0.164,
"pem_stderr": 0.023465261002076764,
"pqem": 0.308,
"pqem_stderr": 0.029256928606501868,
"perfect_em": 0.104,
"perfect_em_stderr": 0.01934510097484389
},
"harness|bbh:logical_deduction_three_objects|3": {
"em": 0.352,
"em_stderr": 0.03026628805735995,
"qem": 0.352,
"qem_stderr": 0.03026628805735995,
"pem": 0.404,
"pem_stderr": 0.03109668818482529,
"pqem": 0.596,
"pqem_stderr": 0.031096688184825295,
"perfect_em": 0.352,
"perfect_em_stderr": 0.03026628805735995
},
"harness|bbh:movie_recommendation|3": {
"em": 0.3855421686746988,
"em_stderr": 0.030906949634000834,
"qem": 0.3855421686746988,
"qem_stderr": 0.030906949634000834,
"pem": 0.4578313253012048,
"pem_stderr": 0.031636914616125444,
"pqem": 0.642570281124498,
"pqem_stderr": 0.030431951782206115,
"perfect_em": 0.3855421686746988,
"perfect_em_stderr": 0.030906949634000834
},
"harness|bbh:navigate|3": {
"em": 0.6,
"em_stderr": 0.031046021028253254,
"qem": 0.6,
"qem_stderr": 0.031046021028253254,
"pem": 0.6,
"pem_stderr": 0.031046021028253254,
"pqem": 0.6,
"pqem_stderr": 0.031046021028253254,
"perfect_em": 0.6,
"perfect_em_stderr": 0.031046021028253254
},
"harness|bbh:reasoning_about_colored_objects|3": {
"em": 0.068,
"em_stderr": 0.015953748410747023,
"qem": 0.068,
"qem_stderr": 0.015953748410747023,
"pem": 0.204,
"pem_stderr": 0.02553712157454818,
"pqem": 0.376,
"pqem_stderr": 0.03069633626739458,
"perfect_em": 0.068,
"perfect_em_stderr": 0.015953748410747023
},
"harness|bbh:ruin_names|3": {
"em": 0.2217741935483871,
"em_stderr": 0.026433814730987774,
"qem": 0.2217741935483871,
"qem_stderr": 0.026433814730987774,
"pem": 0.2217741935483871,
"pem_stderr": 0.026433814730987774,
"pqem": 0.31048387096774194,
"pqem_stderr": 0.029440369763442335,
"perfect_em": 0.2217741935483871,
"perfect_em_stderr": 0.026433814730987774
},
"harness|bbh:salient_translation_error_detection|3": {
"em": 0.184,
"em_stderr": 0.024555812994222558,
"qem": 0.184,
"qem_stderr": 0.024555812994222558,
"pem": 0.216,
"pem_stderr": 0.02607865766373273,
"pqem": 0.356,
"pqem_stderr": 0.030343680657153215,
"perfect_em": 0.184,
"perfect_em_stderr": 0.024555812994222558
},
"harness|bbh:snarks|3": {
"em": 0.4101123595505618,
"em_stderr": 0.036969999449426284,
"qem": 0.4101123595505618,
"qem_stderr": 0.036969999449426284,
"pem": 0.4101123595505618,
"pem_stderr": 0.036969999449426284,
"pqem": 0.7921348314606742,
"pqem_stderr": 0.030500276950436892,
"perfect_em": 0.4101123595505618,
"perfect_em_stderr": 0.036969999449426284
},
"harness|bbh:sports_understanding|3": {
"em": 0.592,
"em_stderr": 0.0311452098465485,
"qem": 0.592,
"qem_stderr": 0.0311452098465485,
"pem": 0.592,
"pem_stderr": 0.0311452098465485,
"pqem": 0.592,
"pqem_stderr": 0.0311452098465485,
"perfect_em": 0.592,
"perfect_em_stderr": 0.0311452098465485
},
"harness|bbh:temporal_sequences|3": {
"em": 0.156,
"em_stderr": 0.022995023034068748,
"qem": 0.156,
"qem_stderr": 0.022995023034068748,
"pem": 0.156,
"pem_stderr": 0.022995023034068748,
"pqem": 0.432,
"pqem_stderr": 0.0313918107654294,
"perfect_em": 0.156,
"perfect_em_stderr": 0.022995023034068748
},
"harness|bbh:tracking_shuffled_objects_five_objects|3": {
"em": 0.036,
"em_stderr": 0.011805655169278133,
"qem": 0.036,
"qem_stderr": 0.011805655169278133,
"pem": 0.176,
"pem_stderr": 0.024133497525457123,
"pqem": 0.376,
"pqem_stderr": 0.030696336267394587,
"perfect_em": 0.036,
"perfect_em_stderr": 0.011805655169278133
},
"harness|bbh:tracking_shuffled_objects_seven_objects|3": {
"em": 0.04,
"em_stderr": 0.012418408411301304,
"qem": 0.04,
"qem_stderr": 0.012418408411301304,
"pem": 0.148,
"pem_stderr": 0.02250354724380614,
"pqem": 0.288,
"pqem_stderr": 0.028697004587398208,
"perfect_em": 0.04,
"perfect_em_stderr": 0.012418408411301304
},
"harness|bbh:tracking_shuffled_objects_three_objects|3": {
"em": 0.192,
"em_stderr": 0.024960691989172,
"qem": 0.192,
"qem_stderr": 0.024960691989172,
"pem": 0.34,
"pem_stderr": 0.030020073605457907,
"pqem": 0.46,
"pqem_stderr": 0.031584653891499004,
"perfect_em": 0.192,
"perfect_em_stderr": 0.024960691989172
},
"harness|bbh:_average|3": {
"em": 0.26474722845266546,
"em_stderr": 0.025386648762186804,
"qem": 0.26474722845266546,
"qem_stderr": 0.025386648762186804,
"pem": 0.3160966260430269,
"pem_stderr": 0.02812883687280141,
"pqem": 0.46584502077373596,
"pqem_stderr": 0.030186645338105295,
"perfect_em": 0.26474722845266546,
"perfect_em_stderr": 0.025386648762186804
}
},
"versions": {
"harness|bbh:causal_judgment|3": 0,
"harness|bbh:date_understanding|3": 0,
"harness|bbh:disambiguation_qa|3": 0,
"harness|bbh:geometric_shapes|3": 0,
"harness|bbh:logical_deduction_five_objects|3": 0,
"harness|bbh:logical_deduction_seven_objects|3": 0,
"harness|bbh:logical_deduction_three_objects|3": 0,
"harness|bbh:movie_recommendation|3": 0,
"harness|bbh:navigate|3": 0,
"harness|bbh:reasoning_about_colored_objects|3": 0,
"harness|bbh:ruin_names|3": 0,
"harness|bbh:salient_translation_error_detection|3": 0,
"harness|bbh:snarks|3": 0,
"harness|bbh:sports_understanding|3": 0,
"harness|bbh:temporal_sequences|3": 0,
"harness|bbh:tracking_shuffled_objects_five_objects|3": 0,
"harness|bbh:tracking_shuffled_objects_seven_objects|3": 0,
"harness|bbh:tracking_shuffled_objects_three_objects|3": 0
},
"config_tasks": {
"harness|bbh:causal_judgment": {
"name": "bbh:causal_judgment",
"prompt_function": "bbh_causal_judgment",
"hf_repo": "lukaemon/bbh",
"hf_subset": "causal_judgement",
"metric": [
"exact_match",
"quasi_exact_match",
"prefix_exact_match",
"prefix_quasi_exact_match",
"perfect_exact_match"
],
"hf_avail_splits": [
"test"
],
"evaluation_splits": [
"test"
],
"few_shots_split": null,
"few_shots_select": null,
"generation_size": 20,
"stop_sequence": [
"</s>",
"Q:",
"\n\n"
],
"output_regex": null,
"frozen": false,
"suite": [
"harness"
],
"original_num_docs": 187,
"effective_num_docs": 187,
"trust_dataset": true,
"must_remove_duplicate_docs": null
},
"harness|bbh:date_understanding": {
"name": "bbh:date_understanding",
"prompt_function": "bbh_date_understanding",
"hf_repo": "lukaemon/bbh",
"hf_subset": "date_understanding",
"metric": [
"exact_match",
"quasi_exact_match",
"prefix_exact_match",
"prefix_quasi_exact_match",
"perfect_exact_match"
],
"hf_avail_splits": [
"test"
],
"evaluation_splits": [
"test"
],
"few_shots_split": null,
"few_shots_select": null,
"generation_size": 20,
"stop_sequence": [
"</s>",
"Q:",
"\n\n"
],
"output_regex": null,
"frozen": false,
"suite": [
"harness"
],
"original_num_docs": 250,
"effective_num_docs": 250,
"trust_dataset": true,
"must_remove_duplicate_docs": null
},
"harness|bbh:disambiguation_qa": {
"name": "bbh:disambiguation_qa",
"prompt_function": "bbh_disambiguation_qa",
"hf_repo": "lukaemon/bbh",
"hf_subset": "disambiguation_qa",
"metric": [
"exact_match",
"quasi_exact_match",
"prefix_exact_match",
"prefix_quasi_exact_match",
"perfect_exact_match"
],
"hf_avail_splits": [
"test"
],
"evaluation_splits": [
"test"
],
"few_shots_split": null,
"few_shots_select": null,
"generation_size": 20,
"stop_sequence": [
"</s>",
"Q:",
"\n\n"
],
"output_regex": null,
"frozen": false,
"suite": [
"harness"
],
"original_num_docs": 250,
"effective_num_docs": 250,
"trust_dataset": true,
"must_remove_duplicate_docs": null
},
"harness|bbh:geometric_shapes": {
"name": "bbh:geometric_shapes",
"prompt_function": "bbh_geometric_shapes",
"hf_repo": "lukaemon/bbh",
"hf_subset": "geometric_shapes",
"metric": [
"exact_match",
"quasi_exact_match",
"prefix_exact_match",
"prefix_quasi_exact_match",
"perfect_exact_match"
],
"hf_avail_splits": [
"test"
],
"evaluation_splits": [
"test"
],
"few_shots_split": null,
"few_shots_select": null,
"generation_size": 20,
"stop_sequence": [
"</s>",
"Q:",
"\n\n"
],
"output_regex": null,
"frozen": false,
"suite": [
"harness"
],
"original_num_docs": 250,
"effective_num_docs": 250,
"trust_dataset": true,
"must_remove_duplicate_docs": null
},
"harness|bbh:logical_deduction_five_objects": {
"name": "bbh:logical_deduction_five_objects",
"prompt_function": "bbh_logical_deduction_five_objects",
"hf_repo": "lukaemon/bbh",
"hf_subset": "logical_deduction_five_objects",
"metric": [
"exact_match",
"quasi_exact_match",
"prefix_exact_match",
"prefix_quasi_exact_match",
"perfect_exact_match"
],
"hf_avail_splits": [
"test"
],
"evaluation_splits": [
"test"
],
"few_shots_split": null,
"few_shots_select": null,
"generation_size": 20,
"stop_sequence": [
"</s>",
"Q:",
"\n\n"
],
"output_regex": null,
"frozen": false,
"suite": [
"harness"
],
"original_num_docs": 250,
"effective_num_docs": 250,
"trust_dataset": true,
"must_remove_duplicate_docs": null
},
"harness|bbh:logical_deduction_seven_objects": {
"name": "bbh:logical_deduction_seven_objects",
"prompt_function": "bbh_logical_deduction_seven_objects",
"hf_repo": "lukaemon/bbh",
"hf_subset": "logical_deduction_seven_objects",
"metric": [
"exact_match",
"quasi_exact_match",
"prefix_exact_match",
"prefix_quasi_exact_match",
"perfect_exact_match"
],
"hf_avail_splits": [
"test"
],
"evaluation_splits": [
"test"
],
"few_shots_split": null,
"few_shots_select": null,
"generation_size": 20,
"stop_sequence": [
"</s>",
"Q:",
"\n\n"
],
"output_regex": null,
"frozen": false,
"suite": [
"harness"
],
"original_num_docs": 250,
"effective_num_docs": 250,
"trust_dataset": true,
"must_remove_duplicate_docs": null
},
"harness|bbh:logical_deduction_three_objects": {
"name": "bbh:logical_deduction_three_objects",
"prompt_function": "bbh_logical_deduction_three_objects",
"hf_repo": "lukaemon/bbh",
"hf_subset": "logical_deduction_three_objects",
"metric": [
"exact_match",
"quasi_exact_match",
"prefix_exact_match",
"prefix_quasi_exact_match",
"perfect_exact_match"
],
"hf_avail_splits": [
"test"
],
"evaluation_splits": [
"test"
],
"few_shots_split": null,
"few_shots_select": null,
"generation_size": 20,
"stop_sequence": [
"</s>",
"Q:",
"\n\n"
],
"output_regex": null,
"frozen": false,
"suite": [
"harness"
],
"original_num_docs": 250,
"effective_num_docs": 250,
"trust_dataset": true,
"must_remove_duplicate_docs": null
},
"harness|bbh:movie_recommendation": {
"name": "bbh:movie_recommendation",
"prompt_function": "bbh_movie_recommendation",
"hf_repo": "lukaemon/bbh",
"hf_subset": "movie_recommendation",
"metric": [
"exact_match",
"quasi_exact_match",
"prefix_exact_match",
"prefix_quasi_exact_match",
"perfect_exact_match"
],
"hf_avail_splits": [
"test"
],
"evaluation_splits": [
"test"
],
"few_shots_split": null,
"few_shots_select": null,
"generation_size": 20,
"stop_sequence": [
"</s>",
"Q:",
"\n\n"
],
"output_regex": null,
"frozen": false,
"suite": [
"harness"
],
"original_num_docs": 249,
"effective_num_docs": 249,
"trust_dataset": true,
"must_remove_duplicate_docs": null
},
"harness|bbh:navigate": {
"name": "bbh:navigate",
"prompt_function": "bbh_navigate",
"hf_repo": "lukaemon/bbh",
"hf_subset": "navigate",
"metric": [
"exact_match",
"quasi_exact_match",
"prefix_exact_match",
"prefix_quasi_exact_match",
"perfect_exact_match"
],
"hf_avail_splits": [
"test"
],
"evaluation_splits": [
"test"
],
"few_shots_split": null,
"few_shots_select": null,
"generation_size": 20,
"stop_sequence": [
"</s>",
"Q:",
"\n\n"
],
"output_regex": null,
"frozen": false,
"suite": [
"harness"
],
"original_num_docs": 250,
"effective_num_docs": 250,
"trust_dataset": true,
"must_remove_duplicate_docs": null
},
"harness|bbh:reasoning_about_colored_objects": {
"name": "bbh:reasoning_about_colored_objects",
"prompt_function": "bbh_reasoning_about_colored_objects",
"hf_repo": "lukaemon/bbh",
"hf_subset": "reasoning_about_colored_objects",
"metric": [
"exact_match",
"quasi_exact_match",
"prefix_exact_match",
"prefix_quasi_exact_match",
"perfect_exact_match"
],
"hf_avail_splits": [
"test"
],
"evaluation_splits": [
"test"
],
"few_shots_split": null,
"few_shots_select": null,
"generation_size": 20,
"stop_sequence": [
"</s>",
"Q:",
"\n\n"
],
"output_regex": null,
"frozen": false,
"suite": [
"harness"
],
"original_num_docs": 250,
"effective_num_docs": 250,
"trust_dataset": true,
"must_remove_duplicate_docs": null
},
"harness|bbh:ruin_names": {
"name": "bbh:ruin_names",
"prompt_function": "bbh_ruin_names",
"hf_repo": "lukaemon/bbh",
"hf_subset": "ruin_names",
"metric": [
"exact_match",
"quasi_exact_match",
"prefix_exact_match",
"prefix_quasi_exact_match",
"perfect_exact_match"
],
"hf_avail_splits": [
"test"
],
"evaluation_splits": [
"test"
],
"few_shots_split": null,
"few_shots_select": null,
"generation_size": 20,
"stop_sequence": [
"</s>",
"Q:",
"\n\n"
],
"output_regex": null,
"frozen": false,
"suite": [
"harness"
],
"original_num_docs": 248,
"effective_num_docs": 248,
"trust_dataset": true,
"must_remove_duplicate_docs": null
},
"harness|bbh:salient_translation_error_detection": {
"name": "bbh:salient_translation_error_detection",
"prompt_function": "bbh_salient_translation_error_detection",
"hf_repo": "lukaemon/bbh",
"hf_subset": "salient_translation_error_detection",
"metric": [
"exact_match",
"quasi_exact_match",
"prefix_exact_match",
"prefix_quasi_exact_match",
"perfect_exact_match"
],
"hf_avail_splits": [
"test"
],
"evaluation_splits": [
"test"
],
"few_shots_split": null,
"few_shots_select": null,
"generation_size": 20,
"stop_sequence": [
"</s>",
"Q:",
"\n\n"
],
"output_regex": null,
"frozen": false,
"suite": [
"harness"
],
"original_num_docs": 250,
"effective_num_docs": 250,
"trust_dataset": true,
"must_remove_duplicate_docs": null
},
"harness|bbh:snarks": {
"name": "bbh:snarks",
"prompt_function": "bbh_snarks",
"hf_repo": "lukaemon/bbh",
"hf_subset": "snarks",
"metric": [
"exact_match",
"quasi_exact_match",
"prefix_exact_match",
"prefix_quasi_exact_match",
"perfect_exact_match"
],
"hf_avail_splits": [
"test"
],
"evaluation_splits": [
"test"
],
"few_shots_split": null,
"few_shots_select": null,
"generation_size": 20,
"stop_sequence": [
"</s>",
"Q:",
"\n\n"
],
"output_regex": null,
"frozen": false,
"suite": [
"harness"
],
"original_num_docs": 178,
"effective_num_docs": 178,
"trust_dataset": true,
"must_remove_duplicate_docs": null
},
"harness|bbh:sports_understanding": {
"name": "bbh:sports_understanding",
"prompt_function": "bbh_sports_understanding",
"hf_repo": "lukaemon/bbh",
"hf_subset": "sports_understanding",
"metric": [
"exact_match",
"quasi_exact_match",
"prefix_exact_match",
"prefix_quasi_exact_match",
"perfect_exact_match"
],
"hf_avail_splits": [
"test"
],
"evaluation_splits": [
"test"
],
"few_shots_split": null,
"few_shots_select": null,
"generation_size": 20,
"stop_sequence": [
"</s>",
"Q:",
"\n\n"
],
"output_regex": null,
"frozen": false,
"suite": [
"harness"
],
"original_num_docs": 250,
"effective_num_docs": 250,
"trust_dataset": true,
"must_remove_duplicate_docs": null
},
"harness|bbh:temporal_sequences": {
"name": "bbh:temporal_sequences",
"prompt_function": "bbh_temporal_sequences",
"hf_repo": "lukaemon/bbh",
"hf_subset": "temporal_sequences",
"metric": [
"exact_match",
"quasi_exact_match",
"prefix_exact_match",
"prefix_quasi_exact_match",
"perfect_exact_match"
],
"hf_avail_splits": [
"test"
],
"evaluation_splits": [
"test"
],
"few_shots_split": null,
"few_shots_select": null,
"generation_size": 20,
"stop_sequence": [
"</s>",
"Q:",
"\n\n"
],
"output_regex": null,
"frozen": false,
"suite": [
"harness"
],
"original_num_docs": 250,
"effective_num_docs": 250,
"trust_dataset": true,
"must_remove_duplicate_docs": null
},
"harness|bbh:tracking_shuffled_objects_five_objects": {
"name": "bbh:tracking_shuffled_objects_five_objects",
"prompt_function": "bbh_tracking_shuffled_objects_five_objects",
"hf_repo": "lukaemon/bbh",
"hf_subset": "tracking_shuffled_objects_five_objects",
"metric": [
"exact_match",
"quasi_exact_match",
"prefix_exact_match",
"prefix_quasi_exact_match",
"perfect_exact_match"
],
"hf_avail_splits": [
"test"
],
"evaluation_splits": [
"test"
],
"few_shots_split": null,
"few_shots_select": null,
"generation_size": 20,
"stop_sequence": [
"</s>",
"Q:",
"\n\n"
],
"output_regex": null,
"frozen": false,
"suite": [
"harness"
],
"original_num_docs": 250,
"effective_num_docs": 250,
"trust_dataset": true,
"must_remove_duplicate_docs": null
},
"harness|bbh:tracking_shuffled_objects_seven_objects": {
"name": "bbh:tracking_shuffled_objects_seven_objects",
"prompt_function": "bbh_tracking_shuffled_objects_seven_objects",
"hf_repo": "lukaemon/bbh",
"hf_subset": "tracking_shuffled_objects_seven_objects",
"metric": [
"exact_match",
"quasi_exact_match",
"prefix_exact_match",
"prefix_quasi_exact_match",
"perfect_exact_match"
],
"hf_avail_splits": [
"test"
],
"evaluation_splits": [
"test"
],
"few_shots_split": null,
"few_shots_select": null,
"generation_size": 20,
"stop_sequence": [
"</s>",
"Q:",
"\n\n"
],
"output_regex": null,
"frozen": false,
"suite": [
"harness"
],
"original_num_docs": 250,
"effective_num_docs": 250,
"trust_dataset": true,
"must_remove_duplicate_docs": null
},
"harness|bbh:tracking_shuffled_objects_three_objects": {
"name": "bbh:tracking_shuffled_objects_three_objects",
"prompt_function": "bbh_tracking_shuffled_objects_three_objects",
"hf_repo": "lukaemon/bbh",
"hf_subset": "tracking_shuffled_objects_three_objects",
"metric": [
"exact_match",
"quasi_exact_match",
"prefix_exact_match",
"prefix_quasi_exact_match",
"perfect_exact_match"
],
"hf_avail_splits": [
"test"
],
"evaluation_splits": [
"test"
],
"few_shots_split": null,
"few_shots_select": null,
"generation_size": 20,
"stop_sequence": [
"</s>",
"Q:",
"\n\n"
],
"output_regex": null,
"frozen": false,
"suite": [
"harness"
],
"original_num_docs": 250,
"effective_num_docs": 250,
"trust_dataset": true,
"must_remove_duplicate_docs": null
}
},
"summary_tasks": {
"harness|bbh:causal_judgment|3": {
"hashes": {
"hash_examples": "63218f5ae055ab2b",
"hash_full_prompts": "148a4c45a8d2b858",
"hash_input_tokens": "41f3903cf7efd5be",
"hash_cont_tokens": "4b1a44e922053996"
},
"truncated": 187,
"non_truncated": 0,
"padded": 0,
"non_padded": 187,
"effective_few_shots": 3.0,
"num_truncated_few_shots": 0
},
"harness|bbh:date_understanding|3": {
"hashes": {
"hash_examples": "f145c7a06def3c8e",
"hash_full_prompts": "e79a3237877b106e",
"hash_input_tokens": "ae3f6744fd7add8b",
"hash_cont_tokens": "db120b243de4b867"
},
"truncated": 250,
"non_truncated": 0,
"padded": 0,
"non_padded": 250,
"effective_few_shots": 3.0,
"num_truncated_few_shots": 0
},
"harness|bbh:disambiguation_qa|3": {
"hashes": {
"hash_examples": "19677fd1773f7eb9",
"hash_full_prompts": "9458fa1926b438bb",
"hash_input_tokens": "a9ea8e42e7ca4f0f",
"hash_cont_tokens": "2cf63241cef67c0f"
},
"truncated": 250,
"non_truncated": 0,
"padded": 0,
"non_padded": 250,
"effective_few_shots": 3.0,
"num_truncated_few_shots": 0
},
"harness|bbh:geometric_shapes|3": {
"hashes": {
"hash_examples": "76c7b11a13cc72a9",
"hash_full_prompts": "78ead1e22de562a8",
"hash_input_tokens": "ded49f2dd58c24f6",
"hash_cont_tokens": "653996ee2697ddd1"
},
"truncated": 250,
"non_truncated": 0,
"padded": 0,
"non_padded": 250,
"effective_few_shots": 3.0,
"num_truncated_few_shots": 0
},
"harness|bbh:logical_deduction_five_objects|3": {
"hashes": {
"hash_examples": "0e958c856332a745",
"hash_full_prompts": "0d7cff0e511b49e7",
"hash_input_tokens": "d16bae7ef2034333",
"hash_cont_tokens": "9f567d45365d04bd"
},
"truncated": 250,
"non_truncated": 0,
"padded": 0,
"non_padded": 250,
"effective_few_shots": 3.0,
"num_truncated_few_shots": 0
},
"harness|bbh:logical_deduction_seven_objects|3": {
"hashes": {
"hash_examples": "ab9de25a5eb40d09",
"hash_full_prompts": "db7b7b19919ef4a7",
"hash_input_tokens": "8b1a10d2204d99c3",
"hash_cont_tokens": "52c8200b9fa5f1de"
},
"truncated": 250,
"non_truncated": 0,
"padded": 0,
"non_padded": 250,
"effective_few_shots": 3.0,
"num_truncated_few_shots": 0
},
"harness|bbh:logical_deduction_three_objects|3": {
"hashes": {
"hash_examples": "3c6bf52517714218",
"hash_full_prompts": "fd6a5580415c1e21",
"hash_input_tokens": "d48e4b55d3c0ab6c",
"hash_cont_tokens": "872cd9ef89295e7c"
},
"truncated": 250,
"non_truncated": 0,
"padded": 0,
"non_padded": 250,
"effective_few_shots": 3.0,
"num_truncated_few_shots": 0
},
"harness|bbh:movie_recommendation|3": {
"hashes": {
"hash_examples": "2d9dc4975935d31a",
"hash_full_prompts": "b7c9fdf1a2ad8106",
"hash_input_tokens": "019f6011d8ebb7b4",
"hash_cont_tokens": "cfe7570976b159dc"
},
"truncated": 249,
"non_truncated": 0,
"padded": 0,
"non_padded": 249,
"effective_few_shots": 3.0,
"num_truncated_few_shots": 0
},
"harness|bbh:navigate|3": {
"hashes": {
"hash_examples": "ba91dcdb9a064255",
"hash_full_prompts": "35aa68650803f91c",
"hash_input_tokens": "fbf7bbc927857899",
"hash_cont_tokens": "6a051a13fb1325c7"
},
"truncated": 250,
"non_truncated": 0,
"padded": 0,
"non_padded": 250,
"effective_few_shots": 3.0,
"num_truncated_few_shots": 0
},
"harness|bbh:reasoning_about_colored_objects|3": {
"hashes": {
"hash_examples": "a6ba328c4c3385d2",
"hash_full_prompts": "954618143d9d5c6d",
"hash_input_tokens": "eab386685d65e6d7",
"hash_cont_tokens": "da90bdfdc8b2a389"
},
"truncated": 250,
"non_truncated": 0,
"padded": 0,
"non_padded": 250,
"effective_few_shots": 3.0,
"num_truncated_few_shots": 0
},
"harness|bbh:ruin_names|3": {
"hashes": {
"hash_examples": "2ef28d5f2d4fdd25",
"hash_full_prompts": "fd807f4380c14312",
"hash_input_tokens": "f17c7a83f10826d5",
"hash_cont_tokens": "df801f8720a5842d"
},
"truncated": 248,
"non_truncated": 0,
"padded": 0,
"non_padded": 248,
"effective_few_shots": 3.0,
"num_truncated_few_shots": 0
},
"harness|bbh:salient_translation_error_detection|3": {
"hashes": {
"hash_examples": "c13f25ec8ffed496",
"hash_full_prompts": "49ab3bc1ed62613f",
"hash_input_tokens": "4ecdc0361737b984",
"hash_cont_tokens": "c393c4b99636afd2"
},
"truncated": 250,
"non_truncated": 0,
"padded": 0,
"non_padded": 250,
"effective_few_shots": 3.0,
"num_truncated_few_shots": 0
},
"harness|bbh:snarks|3": {
"hashes": {
"hash_examples": "5f6db7bff7f6f22e",
"hash_full_prompts": "fa5c1ca26f4a8d48",
"hash_input_tokens": "e0e9ee6065d02980",
"hash_cont_tokens": "6b6260eac154ac76"
},
"truncated": 178,
"non_truncated": 0,
"padded": 0,
"non_padded": 178,
"effective_few_shots": 3.0,
"num_truncated_few_shots": 0
},
"harness|bbh:sports_understanding|3": {
"hashes": {
"hash_examples": "042afbe5d9c1f02d",
"hash_full_prompts": "607b29401b4907ec",
"hash_input_tokens": "e2868a0e92e68765",
"hash_cont_tokens": "07d49088800fc8a1"
},
"truncated": 250,
"non_truncated": 0,
"padded": 0,
"non_padded": 250,
"effective_few_shots": 3.0,
"num_truncated_few_shots": 0
},
"harness|bbh:temporal_sequences|3": {
"hashes": {
"hash_examples": "803a05f352eb6afc",
"hash_full_prompts": "faab4b5e14b9304e",
"hash_input_tokens": "26a0ab6e389383c3",
"hash_cont_tokens": "c20e48a221e722a2"
},
"truncated": 250,
"non_truncated": 0,
"padded": 0,
"non_padded": 250,
"effective_few_shots": 3.0,
"num_truncated_few_shots": 0
},
"harness|bbh:tracking_shuffled_objects_five_objects|3": {
"hashes": {
"hash_examples": "2bbac6db7ab0d527",
"hash_full_prompts": "7e689cfb3916666f",
"hash_input_tokens": "d0e6770bedbf925a",
"hash_cont_tokens": "5fc11d3433371c9d"
},
"truncated": 250,
"non_truncated": 0,
"padded": 0,
"non_padded": 250,
"effective_few_shots": 3.0,
"num_truncated_few_shots": 0
},
"harness|bbh:tracking_shuffled_objects_seven_objects|3": {
"hashes": {
"hash_examples": "845caf093ac2b58c",
"hash_full_prompts": "a80a61e259878fa0",
"hash_input_tokens": "9b1288a55911b79d",
"hash_cont_tokens": "79facbdd2f1c2c40"
},
"truncated": 250,
"non_truncated": 0,
"padded": 0,
"non_padded": 250,
"effective_few_shots": 3.0,
"num_truncated_few_shots": 0
},
"harness|bbh:tracking_shuffled_objects_three_objects|3": {
"hashes": {
"hash_examples": "9004f14d5a32b9a8",
"hash_full_prompts": "fc66cf32f54cd46f",
"hash_input_tokens": "1328545243e4b107",
"hash_cont_tokens": "c127e9f1818fe352"
},
"truncated": 250,
"non_truncated": 0,
"padded": 0,
"non_padded": 250,
"effective_few_shots": 3.0,
"num_truncated_few_shots": 0
}
},
"summary_general": {
"hashes": {
"hash_examples": "4ff1e3dc5703575d",
"hash_full_prompts": "3758756e616fd780",
"hash_input_tokens": "3ee0dfd31c556ab0",
"hash_cont_tokens": "35d93ac2d1cbf93a"
},
"truncated": 4362,
"non_truncated": 0,
"padded": 0,
"non_padded": 4362,
"num_truncated_few_shots": 0
}
}