lewtun's picture
lewtun HF staff
Upload eval_results/HuggingFaceH4/mistral-7b-kto/v1.0/bbh/results_2024-03-26T09-30-21.406885.json with huggingface_hub
02008c0 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": 1526145.70482935,
"end_time": 1526414.705946317,
"total_evaluation_time_secondes": "269.0011169668287",
"model_name": "HuggingFaceH4/mistral-7b-kto",
"model_sha": "ba517352d0ccbfbbb40cb6c11b66286784ea857a",
"model_dtype": "torch.bfloat16",
"model_size": "13.99 GB",
"config": null
},
"results": {
"harness|bbh:causal_judgment|3": {
"em": 0.5508021390374331,
"em_stderr": 0.0364720501817238,
"qem": 0.5508021390374331,
"qem_stderr": 0.0364720501817238,
"pem": 0.5668449197860963,
"pem_stderr": 0.03633267411102586,
"pqem": 0.5668449197860963,
"pqem_stderr": 0.03633267411102586,
"perfect_em": 0.5508021390374331,
"perfect_em_stderr": 0.0364720501817238
},
"harness|bbh:date_understanding|3": {
"em": 0.48,
"em_stderr": 0.031660853408495185,
"qem": 0.48,
"qem_stderr": 0.031660853408495185,
"pem": 0.48,
"pem_stderr": 0.031660853408495185,
"pqem": 0.568,
"pqem_stderr": 0.03139181076542941,
"perfect_em": 0.48,
"perfect_em_stderr": 0.031660853408495185
},
"harness|bbh:disambiguation_qa|3": {
"em": 0.22,
"em_stderr": 0.02625179282460584,
"qem": 0.22,
"qem_stderr": 0.02625179282460584,
"pem": 0.58,
"pem_stderr": 0.03127799950463661,
"pqem": 0.716,
"pqem_stderr": 0.028576958730437408,
"perfect_em": 0.22,
"perfect_em_stderr": 0.02625179282460584
},
"harness|bbh:geometric_shapes|3": {
"em": 0.188,
"em_stderr": 0.024760377727750502,
"qem": 0.188,
"qem_stderr": 0.024760377727750502,
"pem": 0.188,
"pem_stderr": 0.024760377727750502,
"pqem": 0.188,
"pqem_stderr": 0.024760377727750502,
"perfect_em": 0.188,
"perfect_em_stderr": 0.024760377727750502
},
"harness|bbh:logical_deduction_five_objects|3": {
"em": 0.304,
"em_stderr": 0.029150213374159673,
"qem": 0.304,
"qem_stderr": 0.029150213374159673,
"pem": 0.324,
"pem_stderr": 0.02965829492454557,
"pqem": 0.476,
"pqem_stderr": 0.03164968895968782,
"perfect_em": 0.304,
"perfect_em_stderr": 0.029150213374159673
},
"harness|bbh:logical_deduction_seven_objects|3": {
"em": 0.28,
"em_stderr": 0.02845414827783232,
"qem": 0.28,
"qem_stderr": 0.02845414827783232,
"pem": 0.292,
"pem_stderr": 0.02881432040220564,
"pqem": 0.42,
"pqem_stderr": 0.03127799950463661,
"perfect_em": 0.28,
"perfect_em_stderr": 0.02845414827783232
},
"harness|bbh:logical_deduction_three_objects|3": {
"em": 0.472,
"em_stderr": 0.0316364895315444,
"qem": 0.472,
"qem_stderr": 0.0316364895315444,
"pem": 0.48,
"pem_stderr": 0.031660853408495185,
"pqem": 0.752,
"pqem_stderr": 0.027367497504863555,
"perfect_em": 0.472,
"perfect_em_stderr": 0.0316364895315444
},
"harness|bbh:movie_recommendation|3": {
"em": 0.3895582329317269,
"em_stderr": 0.030965812059094804,
"qem": 0.3895582329317269,
"qem_stderr": 0.030965812059094804,
"pem": 0.4819277108433735,
"pem_stderr": 0.03172928536632067,
"pqem": 0.606425702811245,
"pqem_stderr": 0.031022466480549557,
"perfect_em": 0.3895582329317269,
"perfect_em_stderr": 0.030965812059094804
},
"harness|bbh:navigate|3": {
"em": 0.604,
"em_stderr": 0.030993197854577846,
"qem": 0.604,
"qem_stderr": 0.030993197854577846,
"pem": 0.604,
"pem_stderr": 0.030993197854577846,
"pqem": 0.604,
"pqem_stderr": 0.030993197854577846,
"perfect_em": 0.604,
"perfect_em_stderr": 0.030993197854577846
},
"harness|bbh:reasoning_about_colored_objects|3": {
"em": 0.356,
"em_stderr": 0.03034368065715321,
"qem": 0.356,
"qem_stderr": 0.03034368065715321,
"pem": 0.356,
"pem_stderr": 0.03034368065715321,
"pqem": 0.516,
"pqem_stderr": 0.03166998503010742,
"perfect_em": 0.356,
"perfect_em_stderr": 0.03034368065715321
},
"harness|bbh:ruin_names|3": {
"em": 0.2620967741935484,
"em_stderr": 0.02798221349117912,
"qem": 0.2620967741935484,
"qem_stderr": 0.02798221349117912,
"pem": 0.2701612903225806,
"pem_stderr": 0.02825377818838202,
"pqem": 0.46774193548387094,
"pqem_stderr": 0.03174795841398569,
"perfect_em": 0.2620967741935484,
"perfect_em_stderr": 0.02798221349117912
},
"harness|bbh:salient_translation_error_detection|3": {
"em": 0.268,
"em_stderr": 0.02806876238252669,
"qem": 0.268,
"qem_stderr": 0.02806876238252669,
"pem": 0.268,
"pem_stderr": 0.02806876238252669,
"pqem": 0.408,
"pqem_stderr": 0.031145209846548495,
"perfect_em": 0.268,
"perfect_em_stderr": 0.02806876238252669
},
"harness|bbh:snarks|3": {
"em": 0.3707865168539326,
"em_stderr": 0.03630566062020186,
"qem": 0.3707865168539326,
"qem_stderr": 0.03630566062020186,
"pem": 0.46629213483146065,
"pem_stderr": 0.03749680060368987,
"pqem": 0.6685393258426966,
"pqem_stderr": 0.03538285323537675,
"perfect_em": 0.3707865168539326,
"perfect_em_stderr": 0.03630566062020186
},
"harness|bbh:sports_understanding|3": {
"em": 0.316,
"em_stderr": 0.02946265759857866,
"qem": 0.316,
"qem_stderr": 0.02946265759857866,
"pem": 0.788,
"pem_stderr": 0.02590188469054116,
"pqem": 0.788,
"pqem_stderr": 0.02590188469054116,
"perfect_em": 0.316,
"perfect_em_stderr": 0.02946265759857866
},
"harness|bbh:temporal_sequences|3": {
"em": 0.136,
"em_stderr": 0.021723342617052062,
"qem": 0.136,
"qem_stderr": 0.021723342617052062,
"pem": 0.136,
"pem_stderr": 0.021723342617052062,
"pqem": 0.416,
"pqem_stderr": 0.03123585623701457,
"perfect_em": 0.136,
"perfect_em_stderr": 0.021723342617052062
},
"harness|bbh:tracking_shuffled_objects_five_objects|3": {
"em": 0.176,
"em_stderr": 0.02413349752545712,
"qem": 0.176,
"qem_stderr": 0.02413349752545712,
"pem": 0.18,
"pem_stderr": 0.024346890650293537,
"pqem": 0.38,
"pqem_stderr": 0.03076011604262603,
"perfect_em": 0.176,
"perfect_em_stderr": 0.02413349752545712
},
"harness|bbh:tracking_shuffled_objects_seven_objects|3": {
"em": 0.124,
"em_stderr": 0.02088638225867326,
"qem": 0.124,
"qem_stderr": 0.02088638225867326,
"pem": 0.124,
"pem_stderr": 0.02088638225867326,
"pqem": 0.268,
"pqem_stderr": 0.028068762382526695,
"perfect_em": 0.124,
"perfect_em_stderr": 0.02088638225867326
},
"harness|bbh:tracking_shuffled_objects_three_objects|3": {
"em": 0.316,
"em_stderr": 0.029462657598578683,
"qem": 0.316,
"qem_stderr": 0.029462657598578683,
"pem": 0.32,
"pem_stderr": 0.029561724955241044,
"pqem": 0.636,
"pqem_stderr": 0.030491555220405555,
"perfect_em": 0.316,
"perfect_em_stderr": 0.029462657598578683
},
"harness|bbh:_average|3": {
"em": 0.32295798127870223,
"em_stderr": 0.028817432777176948,
"qem": 0.32295798127870223,
"qem_stderr": 0.028817432777176948,
"pem": 0.38362366976575063,
"pem_stderr": 0.029081727983978106,
"pqem": 0.5247528824402172,
"pqem_stderr": 0.030543158485449497,
"perfect_em": 0.32295798127870223,
"perfect_em_stderr": 0.028817432777176948
}
},
"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": "fa8168f39a475fb0",
"hash_input_tokens": "787f75e06fd43c0d",
"hash_cont_tokens": "a9897ca7ae85c12e"
},
"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": "2cceeea606638d49",
"hash_input_tokens": "10c13d6fb8af7c22",
"hash_cont_tokens": "cabbca449b68ce86"
},
"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": "d8f1ba70c22ae578",
"hash_input_tokens": "c21a88707f480cab",
"hash_cont_tokens": "7d3f1881dc220111"
},
"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": "52a60ed1d0113b8b",
"hash_input_tokens": "10e113b2cf3fa584",
"hash_cont_tokens": "f8197622419ea005"
},
"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": "253aa9791c941909",
"hash_input_tokens": "0bc166cab0aed76a",
"hash_cont_tokens": "181ad1ad6ac183d1"
},
"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": "aa6117f601cd268e",
"hash_input_tokens": "ab99c78b48e3a0bb",
"hash_cont_tokens": "7f2da1aa476b95fa"
},
"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": "1892b050bc7848a4",
"hash_input_tokens": "a720b56aa7c52551",
"hash_cont_tokens": "52a6f1161a9a264a"
},
"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": "8e00606ed3407167",
"hash_input_tokens": "c825ab1c99245a17",
"hash_cont_tokens": "e16524bf716d503d"
},
"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": "8d50c5baf1df7aef",
"hash_input_tokens": "f234e6b28ea1fa49",
"hash_cont_tokens": "8efb02fb07bb7bba"
},
"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": "3d2441a21c12a960",
"hash_input_tokens": "f3b577892955aa84",
"hash_cont_tokens": "9d5dfa1f34a04d9c"
},
"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": "ba95caa786f313b1",
"hash_input_tokens": "9954b30d4205604a",
"hash_cont_tokens": "8c6615983accdd0e"
},
"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": "a8512d174e1cab8f",
"hash_input_tokens": "3e738df24b7eddf8",
"hash_cont_tokens": "6f387929f2f41a99"
},
"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": "ff91d81466b9041f",
"hash_input_tokens": "21388b09e13d0208",
"hash_cont_tokens": "896c8e1a238b7eb4"
},
"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": "a59324d9eb37e0f5",
"hash_input_tokens": "0ad41bb8d2290a5b",
"hash_cont_tokens": "d96237b2ab880bb1"
},
"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": "1b3971192bf481e7",
"hash_input_tokens": "3051b60940ccceab",
"hash_cont_tokens": "15933169b4c72b92"
},
"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": "7ef4567d2fcf5094",
"hash_input_tokens": "b841310ee5531238",
"hash_cont_tokens": "edde026ca7e7988f"
},
"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": "196a0f8712857624",
"hash_input_tokens": "3e738df24b7eddf8",
"hash_cont_tokens": "9a02c83e701bca54"
},
"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": "592a03f0518f17b6",
"hash_input_tokens": "19e0ef1dd5ae9d33",
"hash_cont_tokens": "3c5aafea9626475c"
},
"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": "0d80ce968d89d4ef",
"hash_input_tokens": "72bda1e7aeb34786",
"hash_cont_tokens": "1eec0370c759faa6"
},
"truncated": 4362,
"non_truncated": 0,
"padded": 0,
"non_padded": 4362,
"num_truncated_few_shots": 0
}
}