open-r1-eval-leaderboard / eval_results /Qwen /Qwen1.5-0.5B-Chat /main /bbh /results_2024-03-18T19-43-00.075213.json
lewtun's picture
lewtun HF staff
Upload eval_results/Qwen/Qwen1.5-0.5B-Chat/main/bbh/results_2024-03-18T19-43-00.075213.json with huggingface_hub
7add925 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": 1047853.482597071,
"end_time": 1048029.018555961,
"total_evaluation_time_secondes": "175.53595888998825",
"model_name": "Qwen/Qwen1.5-0.5B-Chat",
"model_sha": "6c705984bb8b5591dd4e1a9e66e1a127965fd08d",
"model_dtype": "torch.bfloat16",
"model_size": "1.05 GB",
"config": null
},
"results": {
"harness|bbh:causal_judgment|3": {
"em": 0.45454545454545453,
"em_stderr": 0.036509969495568145,
"qem": 0.45454545454545453,
"qem_stderr": 0.036509969495568145,
"pem": 0.45454545454545453,
"pem_stderr": 0.036509969495568145,
"pqem": 0.45454545454545453,
"pqem_stderr": 0.036509969495568145,
"perfect_em": 0.45454545454545453,
"perfect_em_stderr": 0.036509969495568145
},
"harness|bbh:date_understanding|3": {
"em": 0.116,
"em_stderr": 0.020293429803083837,
"qem": 0.116,
"qem_stderr": 0.020293429803083837,
"pem": 0.164,
"pem_stderr": 0.023465261002076757,
"pqem": 0.356,
"pqem_stderr": 0.030343680657153215,
"perfect_em": 0.116,
"perfect_em_stderr": 0.020293429803083837
},
"harness|bbh:disambiguation_qa|3": {
"em": 0.388,
"em_stderr": 0.030881038748993922,
"qem": 0.388,
"qem_stderr": 0.030881038748993922,
"pem": 0.388,
"pem_stderr": 0.030881038748993922,
"pqem": 0.7,
"pqem_stderr": 0.02904089347757585,
"perfect_em": 0.388,
"perfect_em_stderr": 0.030881038748993922
},
"harness|bbh:geometric_shapes|3": {
"em": 0.176,
"em_stderr": 0.024133497525457116,
"qem": 0.176,
"qem_stderr": 0.024133497525457116,
"pem": 0.176,
"pem_stderr": 0.024133497525457116,
"pqem": 0.176,
"pqem_stderr": 0.024133497525457116,
"perfect_em": 0.176,
"perfect_em_stderr": 0.024133497525457116
},
"harness|bbh:logical_deduction_five_objects|3": {
"em": 0.176,
"em_stderr": 0.024133497525457116,
"qem": 0.176,
"qem_stderr": 0.024133497525457116,
"pem": 0.176,
"pem_stderr": 0.024133497525457116,
"pqem": 0.368,
"pqem_stderr": 0.030562070620993163,
"perfect_em": 0.176,
"perfect_em_stderr": 0.024133497525457116
},
"harness|bbh:logical_deduction_seven_objects|3": {
"em": 0.132,
"em_stderr": 0.021450980824038107,
"qem": 0.132,
"qem_stderr": 0.021450980824038107,
"pem": 0.132,
"pem_stderr": 0.021450980824038107,
"pqem": 0.28,
"pqem_stderr": 0.028454148277832332,
"perfect_em": 0.132,
"perfect_em_stderr": 0.021450980824038107
},
"harness|bbh:logical_deduction_three_objects|3": {
"em": 0.344,
"em_stderr": 0.03010450339231639,
"qem": 0.344,
"qem_stderr": 0.03010450339231639,
"pem": 0.344,
"pem_stderr": 0.03010450339231639,
"pqem": 0.656,
"pqem_stderr": 0.03010450339231639,
"perfect_em": 0.344,
"perfect_em_stderr": 0.03010450339231639
},
"harness|bbh:movie_recommendation|3": {
"em": 0.30522088353413657,
"em_stderr": 0.029241837556221117,
"qem": 0.30522088353413657,
"qem_stderr": 0.029241837556221117,
"pem": 0.3654618473895582,
"pem_stderr": 0.030579054441446426,
"pqem": 0.5903614457831325,
"pqem_stderr": 0.03122723745928603,
"perfect_em": 0.30522088353413657,
"perfect_em_stderr": 0.029241837556221117
},
"harness|bbh:navigate|3": {
"em": 0.424,
"em_stderr": 0.03131803437491615,
"qem": 0.424,
"qem_stderr": 0.03131803437491615,
"pem": 0.424,
"pem_stderr": 0.03131803437491615,
"pqem": 0.424,
"pqem_stderr": 0.03131803437491615,
"perfect_em": 0.424,
"perfect_em_stderr": 0.03131803437491615
},
"harness|bbh:reasoning_about_colored_objects|3": {
"em": 0.148,
"em_stderr": 0.022503547243806144,
"qem": 0.148,
"qem_stderr": 0.022503547243806144,
"pem": 0.148,
"pem_stderr": 0.022503547243806144,
"pqem": 0.32,
"pqem_stderr": 0.02956172495524104,
"perfect_em": 0.148,
"perfect_em_stderr": 0.022503547243806144
},
"harness|bbh:ruin_names|3": {
"em": 0.27419354838709675,
"em_stderr": 0.028385108031064067,
"qem": 0.27419354838709675,
"qem_stderr": 0.028385108031064067,
"pem": 0.2782258064516129,
"pem_stderr": 0.028513524532740565,
"pqem": 0.5645161290322581,
"pqem_stderr": 0.031548283738756754,
"perfect_em": 0.27419354838709675,
"perfect_em_stderr": 0.028385108031064067
},
"harness|bbh:salient_translation_error_detection|3": {
"em": 0.224,
"em_stderr": 0.026421361687347905,
"qem": 0.224,
"qem_stderr": 0.026421361687347905,
"pem": 0.224,
"pem_stderr": 0.026421361687347905,
"pqem": 0.364,
"pqem_stderr": 0.03049155522040556,
"perfect_em": 0.224,
"perfect_em_stderr": 0.026421361687347905
},
"harness|bbh:snarks|3": {
"em": 0.48314606741573035,
"em_stderr": 0.037560944447344806,
"qem": 0.48314606741573035,
"qem_stderr": 0.037560944447344806,
"pem": 0.48314606741573035,
"pem_stderr": 0.037560944447344806,
"pqem": 0.702247191011236,
"pqem_stderr": 0.03437053607199152,
"perfect_em": 0.48314606741573035,
"perfect_em_stderr": 0.037560944447344806
},
"harness|bbh:sports_understanding|3": {
"em": 0.468,
"em_stderr": 0.03162125257572551,
"qem": 0.468,
"qem_stderr": 0.03162125257572551,
"pem": 0.468,
"pem_stderr": 0.03162125257572551,
"pqem": 0.468,
"pqem_stderr": 0.03162125257572551,
"perfect_em": 0.468,
"perfect_em_stderr": 0.03162125257572551
},
"harness|bbh:temporal_sequences|3": {
"em": 0.264,
"em_stderr": 0.02793451895769091,
"qem": 0.264,
"qem_stderr": 0.02793451895769091,
"pem": 0.264,
"pem_stderr": 0.02793451895769091,
"pqem": 0.548,
"pqem_stderr": 0.03153986449255663,
"perfect_em": 0.264,
"perfect_em_stderr": 0.02793451895769091
},
"harness|bbh:tracking_shuffled_objects_five_objects|3": {
"em": 0.196,
"em_stderr": 0.02515685731325594,
"qem": 0.196,
"qem_stderr": 0.02515685731325594,
"pem": 0.216,
"pem_stderr": 0.02607865766373274,
"pqem": 0.416,
"pqem_stderr": 0.031235856237014577,
"perfect_em": 0.196,
"perfect_em_stderr": 0.02515685731325594
},
"harness|bbh:tracking_shuffled_objects_seven_objects|3": {
"em": 0.136,
"em_stderr": 0.021723342617052062,
"qem": 0.136,
"qem_stderr": 0.021723342617052062,
"pem": 0.144,
"pem_stderr": 0.022249407735450217,
"pqem": 0.288,
"pqem_stderr": 0.028697004587398205,
"perfect_em": 0.136,
"perfect_em_stderr": 0.021723342617052062
},
"harness|bbh:tracking_shuffled_objects_three_objects|3": {
"em": 0.332,
"em_stderr": 0.02984403904746589,
"qem": 0.332,
"qem_stderr": 0.02984403904746589,
"pem": 0.352,
"pem_stderr": 0.030266288057359928,
"pqem": 0.668,
"pqem_stderr": 0.029844039047465912,
"perfect_em": 0.332,
"perfect_em_stderr": 0.02984403904746589
},
"harness|bbh:_average|3": {
"em": 0.2800614418823566,
"em_stderr": 0.02773432006482251,
"qem": 0.2800614418823566,
"qem_stderr": 0.02773432006482251,
"pem": 0.28896550976679763,
"pem_stderr": 0.028095852235081605,
"pqem": 0.46353723446511563,
"pqem_stderr": 0.03058911956709189,
"perfect_em": 0.2800614418823566,
"perfect_em_stderr": 0.02773432006482251
}
},
"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": "2b1c252616552565"
},
"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": "6bc80b0ca66464e7"
},
"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": "eb6214a3fd3cb167"
},
"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": "31edbe902bbed74b"
},
"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": "958ce48a7b35c33a"
},
"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": "b8a3547024ba00da"
},
"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": "8b76b4d4ed2635c1"
},
"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": "0ce9ab06e6d45f53"
},
"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": "4c1c1d085fa4b5e8"
},
"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": "bd0e5dbe9dc6b564"
},
"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": "41c70c002212ae1d"
},
"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": "6f5bea4e5dafeb02"
},
"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": "2ad77d2d56c85ba8"
},
"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": "47b63407c2dc4c1e"
},
"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": "ec9978fbd9924f4c"
},
"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": "ac5fa8cffb972c8e"
},
"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": "8736eeb6db7cd358"
},
"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": "81f84fcc367a02ea"
},
"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": "a6844dce5b8e19e8"
},
"truncated": 4362,
"non_truncated": 0,
"padded": 0,
"non_padded": 4362,
"num_truncated_few_shots": 0
}
}