open-r1-eval-leaderboard / eval_results /Qwen /Qwen1.5-72B-Chat /main /bbh /results_2024-03-18T20-40-36.554904.json
lewtun's picture
lewtun HF staff
Upload eval_results/Qwen/Qwen1.5-72B-Chat/main/bbh/results_2024-03-18T20-40-36.554904.json with huggingface_hub
af53d82 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": 895778.173710304,
"end_time": 897081.949710843,
"total_evaluation_time_secondes": "1303.7760005390737",
"model_name": "Qwen/Qwen1.5-72B-Chat",
"model_sha": "1a6ccc1215278f962c794b1848c710c29ef4053d",
"model_dtype": "torch.bfloat16",
"model_size": "135.9 GB",
"config": null
},
"results": {
"harness|bbh:causal_judgment|3": {
"em": 0.6149732620320856,
"em_stderr": 0.03567936280544673,
"qem": 0.6149732620320856,
"qem_stderr": 0.03567936280544673,
"pem": 0.6149732620320856,
"pem_stderr": 0.03567936280544673,
"pqem": 0.6149732620320856,
"pqem_stderr": 0.03567936280544673,
"perfect_em": 0.6149732620320856,
"perfect_em_stderr": 0.03567936280544673
},
"harness|bbh:date_understanding|3": {
"em": 0.576,
"em_stderr": 0.03131803437491614,
"qem": 0.576,
"qem_stderr": 0.03131803437491614,
"pem": 0.576,
"pem_stderr": 0.03131803437491614,
"pqem": 0.676,
"pqem_stderr": 0.02965829492454558,
"perfect_em": 0.576,
"perfect_em_stderr": 0.03131803437491614
},
"harness|bbh:disambiguation_qa|3": {
"em": 0.664,
"em_stderr": 0.02993325909419152,
"qem": 0.664,
"qem_stderr": 0.02993325909419152,
"pem": 0.664,
"pem_stderr": 0.02993325909419152,
"pqem": 0.78,
"pqem_stderr": 0.026251792824605828,
"perfect_em": 0.664,
"perfect_em_stderr": 0.02993325909419152
},
"harness|bbh:geometric_shapes|3": {
"em": 0.388,
"em_stderr": 0.03088103874899392,
"qem": 0.388,
"qem_stderr": 0.03088103874899392,
"pem": 0.388,
"pem_stderr": 0.03088103874899392,
"pqem": 0.388,
"pqem_stderr": 0.03088103874899392,
"perfect_em": 0.388,
"perfect_em_stderr": 0.03088103874899392
},
"harness|bbh:logical_deduction_five_objects|3": {
"em": 0.556,
"em_stderr": 0.03148684942554574,
"qem": 0.556,
"qem_stderr": 0.03148684942554574,
"pem": 0.556,
"pem_stderr": 0.03148684942554574,
"pqem": 0.644,
"pqem_stderr": 0.030343680657153215,
"perfect_em": 0.556,
"perfect_em_stderr": 0.03148684942554574
},
"harness|bbh:logical_deduction_seven_objects|3": {
"em": 0.488,
"em_stderr": 0.03167708558254708,
"qem": 0.488,
"qem_stderr": 0.03167708558254708,
"pem": 0.488,
"pem_stderr": 0.03167708558254708,
"pqem": 0.568,
"pqem_stderr": 0.0313918107654294,
"perfect_em": 0.488,
"perfect_em_stderr": 0.03167708558254708
},
"harness|bbh:logical_deduction_three_objects|3": {
"em": 0.772,
"em_stderr": 0.02658743248726847,
"qem": 0.772,
"qem_stderr": 0.02658743248726847,
"pem": 0.772,
"pem_stderr": 0.02658743248726847,
"pqem": 0.848,
"pqem_stderr": 0.02275202449176547,
"perfect_em": 0.772,
"perfect_em_stderr": 0.02658743248726847
},
"harness|bbh:movie_recommendation|3": {
"em": 0.8393574297188755,
"em_stderr": 0.023317283401377554,
"qem": 0.8393574297188755,
"qem_stderr": 0.023317283401377554,
"pem": 0.8433734939759037,
"pem_stderr": 0.023078988107708014,
"pqem": 0.8875502008032129,
"pqem_stderr": 0.02006087930418837,
"perfect_em": 0.8393574297188755,
"perfect_em_stderr": 0.023317283401377554
},
"harness|bbh:navigate|3": {
"em": 0.6,
"em_stderr": 0.031046021028253247,
"qem": 0.6,
"qem_stderr": 0.031046021028253247,
"pem": 0.6,
"pem_stderr": 0.031046021028253247,
"pqem": 0.6,
"pqem_stderr": 0.031046021028253247,
"perfect_em": 0.6,
"perfect_em_stderr": 0.031046021028253247
},
"harness|bbh:reasoning_about_colored_objects|3": {
"em": 0.664,
"em_stderr": 0.029933259094191516,
"qem": 0.664,
"qem_stderr": 0.029933259094191516,
"pem": 0.664,
"pem_stderr": 0.029933259094191516,
"pqem": 0.716,
"pqem_stderr": 0.028576958730437394,
"perfect_em": 0.664,
"perfect_em_stderr": 0.029933259094191516
},
"harness|bbh:ruin_names|3": {
"em": 0.8145161290322581,
"em_stderr": 0.024731726954093584,
"qem": 0.8145161290322581,
"qem_stderr": 0.024731726954093584,
"pem": 0.8145161290322581,
"pem_stderr": 0.024731726954093584,
"pqem": 0.875,
"pqem_stderr": 0.021043140573169826,
"perfect_em": 0.8145161290322581,
"perfect_em_stderr": 0.024731726954093584
},
"harness|bbh:salient_translation_error_detection|3": {
"em": 0.592,
"em_stderr": 0.0311452098465485,
"qem": 0.592,
"qem_stderr": 0.0311452098465485,
"pem": 0.592,
"pem_stderr": 0.0311452098465485,
"pqem": 0.688,
"pqem_stderr": 0.029361067575219817,
"perfect_em": 0.592,
"perfect_em_stderr": 0.0311452098465485
},
"harness|bbh:snarks|3": {
"em": 0.8595505617977528,
"em_stderr": 0.026116145785378953,
"qem": 0.8595505617977528,
"qem_stderr": 0.026116145785378953,
"pem": 0.8595505617977528,
"pem_stderr": 0.026116145785378953,
"pqem": 0.9044943820224719,
"pqem_stderr": 0.022091782723697606,
"perfect_em": 0.8595505617977528,
"perfect_em_stderr": 0.026116145785378953
},
"harness|bbh:sports_understanding|3": {
"em": 0.864,
"em_stderr": 0.02172334261705205,
"qem": 0.864,
"qem_stderr": 0.02172334261705205,
"pem": 0.864,
"pem_stderr": 0.02172334261705205,
"pqem": 0.864,
"pqem_stderr": 0.02172334261705205,
"perfect_em": 0.864,
"perfect_em_stderr": 0.02172334261705205
},
"harness|bbh:temporal_sequences|3": {
"em": 0.596,
"em_stderr": 0.031096688184825295,
"qem": 0.596,
"qem_stderr": 0.031096688184825295,
"pem": 0.596,
"pem_stderr": 0.031096688184825295,
"pqem": 0.744,
"pqem_stderr": 0.02765710871820491,
"perfect_em": 0.596,
"perfect_em_stderr": 0.031096688184825295
},
"harness|bbh:tracking_shuffled_objects_five_objects|3": {
"em": 0.24,
"em_stderr": 0.027065293652239007,
"qem": 0.24,
"qem_stderr": 0.027065293652239007,
"pem": 0.24,
"pem_stderr": 0.027065293652239007,
"pqem": 0.396,
"pqem_stderr": 0.030993197854577853,
"perfect_em": 0.24,
"perfect_em_stderr": 0.027065293652239007
},
"harness|bbh:tracking_shuffled_objects_seven_objects|3": {
"em": 0.216,
"em_stderr": 0.02607865766373272,
"qem": 0.216,
"qem_stderr": 0.02607865766373272,
"pem": 0.216,
"pem_stderr": 0.02607865766373272,
"pqem": 0.336,
"pqem_stderr": 0.029933259094191512,
"perfect_em": 0.216,
"perfect_em_stderr": 0.02607865766373272
},
"harness|bbh:tracking_shuffled_objects_three_objects|3": {
"em": 0.264,
"em_stderr": 0.027934518957690908,
"qem": 0.264,
"qem_stderr": 0.027934518957690908,
"pem": 0.264,
"pem_stderr": 0.027934518957690908,
"pqem": 0.556,
"pqem_stderr": 0.03148684942554574,
"perfect_em": 0.264,
"perfect_em_stderr": 0.027934518957690908
},
"harness|bbh:_average|3": {
"em": 0.5893554101433873,
"em_stderr": 0.02876395609468295,
"qem": 0.5893554101433873,
"qem_stderr": 0.02876395609468295,
"pem": 0.5895785248243333,
"pem_stderr": 0.028750717467256864,
"pqem": 0.6714454358254317,
"pqem_stderr": 0.02782953404791547,
"perfect_em": 0.5893554101433873,
"perfect_em_stderr": 0.02876395609468295
}
},
"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": "e93d8d76d4dddd8d"
},
"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": "8c6d71b9a9c752bb"
},
"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": "7db54489d9d427f8"
},
"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": "db89ed479d075689"
},
"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": "1f4919dffa3a134c"
},
"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": "ff391bdb10cfe252"
},
"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": "96770fd477911169"
},
"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": "c65ea0feb714d001"
},
"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": "397518cdac8ba301"
},
"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": "c9511762801670a8"
},
"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": "3b0acadb3bb8f058"
},
"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": "eb8a1f488e70e53c"
},
"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": "9a1668d8c3b79a7a"
},
"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": "46b51525fc124f66"
},
"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": "1977d5de1ecb2dfc"
},
"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": "ce9cfa52d8c85406"
},
"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": "700a13bfc0ce35fc"
},
"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": "e4bffb2467fc2a79"
},
"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": "84a9b5a4627ad8f3"
},
"truncated": 4362,
"non_truncated": 0,
"padded": 0,
"non_padded": 4362,
"num_truncated_few_shots": 0
}
}