open-r1-eval-leaderboard / eval_results /Qwen /Qwen1.5-7B-Chat /main /bbh /results_2024-03-28T13-49-45.748302.json
lewtun's picture
lewtun HF staff
Upload eval_results/Qwen/Qwen1.5-7B-Chat/main/bbh/results_2024-03-28T13-49-45.748302.json with huggingface_hub
0b07157 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": 2069217.71399371,
"end_time": 2069504.513928286,
"total_evaluation_time_secondes": "286.7999345760327",
"model_name": "Qwen/Qwen1.5-7B-Chat",
"model_sha": "a2662f4bc1afe913a91cd49f794d229a8c28f97e",
"model_dtype": "torch.bfloat16",
"model_size": "14.88 GB",
"config": null
},
"results": {
"harness|bbh:causal_judgment|3": {
"em": 0.5240641711229946,
"em_stderr": 0.03661929361528703,
"qem": 0.5240641711229946,
"qem_stderr": 0.03661929361528703,
"pem": 0.5240641711229946,
"pem_stderr": 0.03661929361528703,
"pqem": 0.5240641711229946,
"pqem_stderr": 0.03661929361528703,
"perfect_em": 0.5240641711229946,
"perfect_em_stderr": 0.03661929361528703
},
"harness|bbh:date_understanding|3": {
"em": 0.176,
"em_stderr": 0.024133497525457116,
"qem": 0.176,
"qem_stderr": 0.024133497525457116,
"pem": 0.22,
"pem_stderr": 0.026251792824605845,
"pqem": 0.4,
"pqem_stderr": 0.031046021028253247,
"perfect_em": 0.176,
"perfect_em_stderr": 0.024133497525457116
},
"harness|bbh:disambiguation_qa|3": {
"em": 0.404,
"em_stderr": 0.031096688184825295,
"qem": 0.404,
"qem_stderr": 0.031096688184825295,
"pem": 0.484,
"pem_stderr": 0.03166998503010742,
"pqem": 0.776,
"pqem_stderr": 0.0264213616873479,
"perfect_em": 0.404,
"perfect_em_stderr": 0.031096688184825295
},
"harness|bbh:geometric_shapes|3": {
"em": 0.232,
"em_stderr": 0.02675007037486516,
"qem": 0.232,
"qem_stderr": 0.02675007037486516,
"pem": 0.252,
"pem_stderr": 0.027513851933031352,
"pqem": 0.252,
"pqem_stderr": 0.027513851933031352,
"perfect_em": 0.232,
"perfect_em_stderr": 0.02675007037486516
},
"harness|bbh:logical_deduction_five_objects|3": {
"em": 0.38,
"em_stderr": 0.030760116042626046,
"qem": 0.38,
"qem_stderr": 0.030760116042626046,
"pem": 0.436,
"pem_stderr": 0.03142556706028128,
"pqem": 0.572,
"pqem_stderr": 0.0313559689237726,
"perfect_em": 0.38,
"perfect_em_stderr": 0.030760116042626046
},
"harness|bbh:logical_deduction_seven_objects|3": {
"em": 0.284,
"em_stderr": 0.028576958730437405,
"qem": 0.284,
"qem_stderr": 0.028576958730437405,
"pem": 0.38,
"pem_stderr": 0.03076011604262603,
"pqem": 0.488,
"pqem_stderr": 0.03167708558254709,
"perfect_em": 0.284,
"perfect_em_stderr": 0.028576958730437405
},
"harness|bbh:logical_deduction_three_objects|3": {
"em": 0.476,
"em_stderr": 0.03164968895968782,
"qem": 0.476,
"qem_stderr": 0.03164968895968782,
"pem": 0.52,
"pem_stderr": 0.03166085340849519,
"pqem": 0.756,
"pqem_stderr": 0.027217995464553182,
"perfect_em": 0.476,
"perfect_em_stderr": 0.03164968895968782
},
"harness|bbh:movie_recommendation|3": {
"em": 0.3092369477911647,
"em_stderr": 0.02934839790043843,
"qem": 0.3092369477911647,
"qem_stderr": 0.02934839790043843,
"pem": 0.5863453815261044,
"pem_stderr": 0.031273022170585044,
"pqem": 0.678714859437751,
"pqem_stderr": 0.029652625884384973,
"perfect_em": 0.3092369477911647,
"perfect_em_stderr": 0.02934839790043843
},
"harness|bbh:navigate|3": {
"em": 0.6,
"em_stderr": 0.03104602102825325,
"qem": 0.6,
"qem_stderr": 0.03104602102825325,
"pem": 0.6,
"pem_stderr": 0.03104602102825325,
"pqem": 0.6,
"pqem_stderr": 0.03104602102825325,
"perfect_em": 0.6,
"perfect_em_stderr": 0.03104602102825325
},
"harness|bbh:reasoning_about_colored_objects|3": {
"em": 0.128,
"em_stderr": 0.021172081336336506,
"qem": 0.128,
"qem_stderr": 0.021172081336336506,
"pem": 0.304,
"pem_stderr": 0.029150213374159677,
"pqem": 0.428,
"pqem_stderr": 0.03135596892377261,
"perfect_em": 0.128,
"perfect_em_stderr": 0.021172081336336506
},
"harness|bbh:ruin_names|3": {
"em": 0.3709677419354839,
"em_stderr": 0.030736616282226906,
"qem": 0.3709677419354839,
"qem_stderr": 0.030736616282226906,
"pem": 0.40725806451612906,
"pem_stderr": 0.03126217550035507,
"pqem": 0.5685483870967742,
"pqem_stderr": 0.03151383724269122,
"perfect_em": 0.3709677419354839,
"perfect_em_stderr": 0.030736616282226906
},
"harness|bbh:salient_translation_error_detection|3": {
"em": 0.412,
"em_stderr": 0.031191596026022894,
"qem": 0.412,
"qem_stderr": 0.031191596026022894,
"pem": 0.412,
"pem_stderr": 0.031191596026022894,
"pqem": 0.536,
"pqem_stderr": 0.03160397514522374,
"perfect_em": 0.412,
"perfect_em_stderr": 0.031191596026022894
},
"harness|bbh:snarks|3": {
"em": 0.5561797752808989,
"em_stderr": 0.03734431584194243,
"qem": 0.5561797752808989,
"qem_stderr": 0.03734431584194243,
"pem": 0.5561797752808989,
"pem_stderr": 0.03734431584194243,
"pqem": 0.7134831460674157,
"pqem_stderr": 0.033984455265461594,
"perfect_em": 0.5561797752808989,
"perfect_em_stderr": 0.03734431584194243
},
"harness|bbh:sports_understanding|3": {
"em": 0.548,
"em_stderr": 0.03153986449255663,
"qem": 0.548,
"qem_stderr": 0.03153986449255663,
"pem": 0.56,
"pem_stderr": 0.031457244522235625,
"pqem": 0.56,
"pqem_stderr": 0.031457244522235625,
"perfect_em": 0.548,
"perfect_em_stderr": 0.03153986449255663
},
"harness|bbh:temporal_sequences|3": {
"em": 0.284,
"em_stderr": 0.028576958730437394,
"qem": 0.284,
"qem_stderr": 0.028576958730437394,
"pem": 0.44,
"pem_stderr": 0.031457244522235715,
"pqem": 0.604,
"pqem_stderr": 0.030993197854577853,
"perfect_em": 0.284,
"perfect_em_stderr": 0.028576958730437394
},
"harness|bbh:tracking_shuffled_objects_five_objects|3": {
"em": 0.064,
"em_stderr": 0.015510587134374155,
"qem": 0.064,
"qem_stderr": 0.015510587134374155,
"pem": 0.156,
"pem_stderr": 0.022995023034068755,
"pqem": 0.348,
"pqem_stderr": 0.03018656846451171,
"perfect_em": 0.064,
"perfect_em_stderr": 0.015510587134374155
},
"harness|bbh:tracking_shuffled_objects_seven_objects|3": {
"em": 0.104,
"em_stderr": 0.019345100974843897,
"qem": 0.104,
"qem_stderr": 0.019345100974843897,
"pem": 0.124,
"pem_stderr": 0.02088638225867326,
"pqem": 0.26,
"pqem_stderr": 0.027797315752644304,
"perfect_em": 0.104,
"perfect_em_stderr": 0.019345100974843897
},
"harness|bbh:tracking_shuffled_objects_three_objects|3": {
"em": 0.172,
"em_stderr": 0.023915513944486218,
"qem": 0.172,
"qem_stderr": 0.023915513944486218,
"pem": 0.352,
"pem_stderr": 0.03026628805735993,
"pqem": 0.664,
"pqem_stderr": 0.029933259094191516,
"perfect_em": 0.172,
"perfect_em_stderr": 0.023915513944486218
},
"harness|bbh:_average|3": {
"em": 0.33469159089614126,
"em_stderr": 0.028295187062505816,
"qem": 0.33469159089614126,
"qem_stderr": 0.028295187062505816,
"pem": 0.40632485513589595,
"pem_stderr": 0.03023505479168477,
"pqem": 0.5404894757624965,
"pqem_stderr": 0.03063200263404116,
"perfect_em": 0.33469159089614126,
"perfect_em_stderr": 0.028295187062505816
}
},
"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": "3b4e0e3575a9fe46"
},
"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": "e8ae17ee5b188129"
},
"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": "e3bf43a8ea23285a"
},
"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": "45151dea1e2e71f3"
},
"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": "c51b8361a6f4e6bd"
},
"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": "ca75dd49f4c8d505"
},
"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": "14d8d9e3f4729056"
},
"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": "4e32ce157b48f24a"
},
"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": "28c75cb68920c5e5"
},
"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": "e2b9bda947d0d72f"
},
"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": "650e93e42a6b12c3"
},
"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": "c7cb581edecb36c5"
},
"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": "96ff555916e57fb2"
},
"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": "819d7bf2bc094710"
},
"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": "16010037e6da1d04"
},
"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": "2eb386173e7fff58"
},
"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": "405575bc8e10ea9d"
},
"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": "b178ec6cb27af027"
},
"truncated": 4362,
"non_truncated": 0,
"padded": 0,
"non_padded": 4362,
"num_truncated_few_shots": 0
}
}