lewtun's picture
lewtun HF staff
Upload eval_results/mistralai/Mixtral-8x7B-Instruct-v0.1/main/bbh/results_2024-03-28T14-24-16.417420.json with huggingface_hub
75df6a5 verified
raw
history blame
33.1 kB
{
"config_general": {
"lighteval_sha": "?",
"num_fewshot_seeds": 1,
"override_batch_size": 1,
"max_samples": null,
"job_id": "",
"start_time": 1227818.26736698,
"end_time": 1230138.972465043,
"total_evaluation_time_secondes": "2320.7050980629865",
"model_name": "mistralai/Mixtral-8x7B-Instruct-v0.1",
"model_sha": "1e637f2d7cb0a9d6fb1922f305cb784995190a83",
"model_dtype": "torch.bfloat16",
"model_size": "87.49 GB",
"config": null
},
"results": {
"harness|bbh:causal_judgment|3": {
"em": 0.26737967914438504,
"em_stderr": 0.032452428900352305,
"qem": 0.2994652406417112,
"qem_stderr": 0.033583935154759645,
"pem": 0.6470588235294118,
"pem_stderr": 0.03504019983419237,
"pqem": 0.6470588235294118,
"pqem_stderr": 0.03504019983419237,
"perfect_em": 0.26737967914438504,
"perfect_em_stderr": 0.032452428900352305
},
"harness|bbh:date_understanding|3": {
"em": 0.0,
"em_stderr": 0.0,
"qem": 0.2,
"qem_stderr": 0.02534897002097908,
"pem": 0.216,
"pem_stderr": 0.02607865766373272,
"pqem": 0.64,
"pqem_stderr": 0.03041876402517499,
"perfect_em": 0.0,
"perfect_em_stderr": 0.0
},
"harness|bbh:disambiguation_qa|3": {
"em": 0.016,
"em_stderr": 0.00795166118887434,
"qem": 0.156,
"qem_stderr": 0.022995023034068755,
"pem": 0.22,
"pem_stderr": 0.026251792824605834,
"pqem": 0.74,
"pqem_stderr": 0.027797315752644308,
"perfect_em": 0.016,
"perfect_em_stderr": 0.00795166118887434
},
"harness|bbh:geometric_shapes|3": {
"em": 0.0,
"em_stderr": 0.0,
"qem": 0.308,
"qem_stderr": 0.029256928606501864,
"pem": 0.008,
"pem_stderr": 0.005645483676690174,
"pqem": 0.368,
"pqem_stderr": 0.03056207062099316,
"perfect_em": 0.0,
"perfect_em_stderr": 0.0
},
"harness|bbh:logical_deduction_five_objects|3": {
"em": 0.02,
"em_stderr": 0.008872139507342683,
"qem": 0.284,
"qem_stderr": 0.02857695873043741,
"pem": 0.056,
"pem_stderr": 0.014570697336899599,
"pqem": 0.448,
"pqem_stderr": 0.03151438761115355,
"perfect_em": 0.02,
"perfect_em_stderr": 0.008872139507342683
},
"harness|bbh:logical_deduction_seven_objects|3": {
"em": 0.0,
"em_stderr": 0.0,
"qem": 0.304,
"qem_stderr": 0.029150213374159677,
"pem": 0.0,
"pem_stderr": 0.0,
"pqem": 0.452,
"pqem_stderr": 0.03153986449255662,
"perfect_em": 0.0,
"perfect_em_stderr": 0.0
},
"harness|bbh:logical_deduction_three_objects|3": {
"em": 0.036,
"em_stderr": 0.011805655169278133,
"qem": 0.428,
"qem_stderr": 0.031355968923772626,
"pem": 0.072,
"pem_stderr": 0.016381005750490108,
"pqem": 0.632,
"pqem_stderr": 0.030562070620993163,
"perfect_em": 0.036,
"perfect_em_stderr": 0.011805655169278133
},
"harness|bbh:movie_recommendation|3": {
"em": 0.0,
"em_stderr": 0.0,
"qem": 0.4779116465863454,
"qem_stderr": 0.03171903523348456,
"pem": 0.14457831325301204,
"pem_stderr": 0.022331395571821913,
"pqem": 0.7751004016064257,
"pqem_stderr": 0.02651230458673727,
"perfect_em": 0.0,
"perfect_em_stderr": 0.0
},
"harness|bbh:navigate|3": {
"em": 0.224,
"em_stderr": 0.02642136168734791,
"qem": 0.224,
"qem_stderr": 0.02642136168734791,
"pem": 0.648,
"pem_stderr": 0.030266288057359925,
"pqem": 0.648,
"pqem_stderr": 0.030266288057359925,
"perfect_em": 0.224,
"perfect_em_stderr": 0.02642136168734791
},
"harness|bbh:reasoning_about_colored_objects|3": {
"em": 0.18,
"em_stderr": 0.024346890650293548,
"qem": 0.5,
"qem_stderr": 0.031686212526223896,
"pem": 0.232,
"pem_stderr": 0.02675007037486516,
"pqem": 0.62,
"pqem_stderr": 0.030760116042626046,
"perfect_em": 0.18,
"perfect_em_stderr": 0.024346890650293548
},
"harness|bbh:ruin_names|3": {
"em": 0.0,
"em_stderr": 0.0,
"qem": 0.4475806451612903,
"qem_stderr": 0.03163891746142309,
"pem": 0.016129032258064516,
"pem_stderr": 0.008015391715832133,
"pqem": 0.6048387096774194,
"pqem_stderr": 0.03110702726972493,
"perfect_em": 0.0,
"perfect_em_stderr": 0.0
},
"harness|bbh:salient_translation_error_detection|3": {
"em": 0.0,
"em_stderr": 0.0,
"qem": 0.328,
"qem_stderr": 0.02975239182447538,
"pem": 0.012,
"pem_stderr": 0.0069003230236943,
"pqem": 0.564,
"pqem_stderr": 0.03142556706028129,
"perfect_em": 0.0,
"perfect_em_stderr": 0.0
},
"harness|bbh:snarks|3": {
"em": 0.0,
"em_stderr": 0.0,
"qem": 0.6348314606741573,
"qem_stderr": 0.03619005678691266,
"pem": 0.0,
"pem_stderr": 0.0,
"pqem": 0.7584269662921348,
"pqem_stderr": 0.0321732161383325,
"perfect_em": 0.0,
"perfect_em_stderr": 0.0
},
"harness|bbh:sports_understanding|3": {
"em": 0.216,
"em_stderr": 0.026078657663732727,
"qem": 0.22,
"qem_stderr": 0.02625179282460584,
"pem": 0.72,
"pem_stderr": 0.02845414827783232,
"pqem": 0.72,
"pqem_stderr": 0.02845414827783232,
"perfect_em": 0.216,
"perfect_em_stderr": 0.026078657663732727
},
"harness|bbh:temporal_sequences|3": {
"em": 0.016,
"em_stderr": 0.007951661188874328,
"qem": 0.36,
"qem_stderr": 0.030418764025174974,
"pem": 0.116,
"pem_stderr": 0.02029342980308387,
"pqem": 0.716,
"pqem_stderr": 0.028576958730437398,
"perfect_em": 0.016,
"perfect_em_stderr": 0.007951661188874328
},
"harness|bbh:tracking_shuffled_objects_five_objects|3": {
"em": 0.044,
"em_stderr": 0.012997373846574964,
"qem": 0.148,
"qem_stderr": 0.022503547243806144,
"pem": 0.08,
"pem_stderr": 0.017192507941462983,
"pqem": 0.356,
"pqem_stderr": 0.03034368065715322,
"perfect_em": 0.044,
"perfect_em_stderr": 0.012997373846574964
},
"harness|bbh:tracking_shuffled_objects_seven_objects|3": {
"em": 0.08,
"em_stderr": 0.01719250794146297,
"qem": 0.144,
"qem_stderr": 0.022249407735450203,
"pem": 0.144,
"pem_stderr": 0.022249407735450207,
"pqem": 0.34,
"pqem_stderr": 0.030020073605457907,
"perfect_em": 0.08,
"perfect_em_stderr": 0.01719250794146297
},
"harness|bbh:tracking_shuffled_objects_three_objects|3": {
"em": 0.088,
"em_stderr": 0.017953084777052892,
"qem": 0.208,
"qem_stderr": 0.02572139890141639,
"pem": 0.184,
"pem_stderr": 0.02455581299422256,
"pqem": 0.556,
"pqem_stderr": 0.031486849425545735,
"perfect_em": 0.088,
"perfect_em_stderr": 0.017953084777052892
},
"harness|bbh:_average|3": {
"em": 0.06596553773024362,
"em_stderr": 0.010779079028954822,
"qem": 0.31509938850352803,
"qem_stderr": 0.028601160227500002,
"pem": 0.1953203427244716,
"pem_stderr": 0.018387589587902008,
"pqem": 0.5880791611725217,
"pqem_stderr": 0.03047560571162204,
"perfect_em": 0.06596553773024362,
"perfect_em_stderr": 0.010779079028954822
}
},
"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": "c3f54a56ef8b0c84",
"hash_input_tokens": "7e5e423a80ecc1ce",
"hash_cont_tokens": "ea7329191884f89a"
},
"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": "c70878aae99812bd",
"hash_input_tokens": "6e0f2d719a606df2",
"hash_cont_tokens": "168747abf2ed1172"
},
"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": "27580dbe8f42357e",
"hash_input_tokens": "28c4ba12a22d1cd2",
"hash_cont_tokens": "ea97fd2b4e8339e1"
},
"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": "c1efb1382b3d5f26",
"hash_input_tokens": "f6262983a77b3c15",
"hash_cont_tokens": "27b384bb46462abe"
},
"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": "841180f101f6ed2f",
"hash_input_tokens": "4ae5c84ac47f9c00",
"hash_cont_tokens": "7ee9208c42f0f391"
},
"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": "d4ea65028e06515a",
"hash_input_tokens": "d12c34ec49852722",
"hash_cont_tokens": "3ea6682edd9ab88c"
},
"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": "e45ba419a02569cb",
"hash_input_tokens": "539d01f4b2e6a62e",
"hash_cont_tokens": "20fdf72b7bdf66c8"
},
"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": "e7f9f6227ef6d091",
"hash_input_tokens": "ccf15e0353520262",
"hash_cont_tokens": "2c887402efd4ba5c"
},
"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": "363cbc26d2694856",
"hash_input_tokens": "6f26d91169f0f9e7",
"hash_cont_tokens": "f534d356569141cc"
},
"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": "e2c5ea75faa663be",
"hash_input_tokens": "9bc9fca7f0afa719",
"hash_cont_tokens": "6e10e99577f43f65"
},
"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": "39c98a33af277e05",
"hash_input_tokens": "8fc43170201dbcbe",
"hash_cont_tokens": "13fad13af65299fa"
},
"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": "61c199869236d1d0",
"hash_input_tokens": "ebfefff744f0c7a3",
"hash_cont_tokens": "cc08b8755b81929c"
},
"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": "70b02bc8db0a7a32",
"hash_input_tokens": "bae40895da8c14d5",
"hash_cont_tokens": "0320bef36bbf541f"
},
"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": "6a6bb045bbf84268",
"hash_input_tokens": "f8b065aed222d461",
"hash_cont_tokens": "5d577240f3fac015"
},
"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": "95ddd530c1a01713",
"hash_input_tokens": "fe324a3e155b8686",
"hash_cont_tokens": "e993b67463ec16da"
},
"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": "343105b81cd88d67",
"hash_input_tokens": "3aa53f00d4db548e",
"hash_cont_tokens": "9a61bd1425845d55"
},
"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": "4b07759d13b7ab32",
"hash_input_tokens": "5a5a60741cae444d",
"hash_cont_tokens": "f8acae0c3d9c3a40"
},
"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": "95a2d1f682b8e98c",
"hash_input_tokens": "667b9bc0a831893c",
"hash_cont_tokens": "13cc9c9f9aa887ea"
},
"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": "cc928e928ada6335",
"hash_input_tokens": "fa03e97b7a0db38d",
"hash_cont_tokens": "4e1a33fb6e15f9bc"
},
"truncated": 4362,
"non_truncated": 0,
"padded": 0,
"non_padded": 4362,
"num_truncated_few_shots": 0
}
}