open-r1-eval-leaderboard / eval_results /Qwen /Qwen1.5-4B-Chat /main /bbh /results_2024-03-18T20-20-24.322898.json
lewtun's picture
lewtun HF staff
Upload eval_results/Qwen/Qwen1.5-4B-Chat/main/bbh/results_2024-03-18T20-20-24.322898.json with huggingface_hub
1b733bf 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": 1050074.883104552,
"end_time": 1050273.266616125,
"total_evaluation_time_secondes": "198.38351157284342",
"model_name": "Qwen/Qwen1.5-4B-Chat",
"model_sha": "ef715c26c82dd2d04634101d5fb9855ff3f45bc9",
"model_dtype": "torch.bfloat16",
"model_size": "7.98 GB",
"config": null
},
"results": {
"harness|bbh:causal_judgment|3": {
"em": 0.5775401069518716,
"em_stderr": 0.036218240207533565,
"qem": 0.5775401069518716,
"qem_stderr": 0.036218240207533565,
"pem": 0.5775401069518716,
"pem_stderr": 0.036218240207533565,
"pqem": 0.5775401069518716,
"pqem_stderr": 0.036218240207533565,
"perfect_em": 0.5775401069518716,
"perfect_em_stderr": 0.036218240207533565
},
"harness|bbh:date_understanding|3": {
"em": 0.436,
"em_stderr": 0.03142556706028128,
"qem": 0.436,
"qem_stderr": 0.03142556706028128,
"pem": 0.436,
"pem_stderr": 0.03142556706028128,
"pqem": 0.556,
"pqem_stderr": 0.03148684942554575,
"perfect_em": 0.436,
"perfect_em_stderr": 0.03142556706028128
},
"harness|bbh:disambiguation_qa|3": {
"em": 0.632,
"em_stderr": 0.030562070620993163,
"qem": 0.632,
"qem_stderr": 0.030562070620993163,
"pem": 0.632,
"pem_stderr": 0.030562070620993163,
"pqem": 0.66,
"pqem_stderr": 0.03002007360545791,
"perfect_em": 0.632,
"perfect_em_stderr": 0.030562070620993163
},
"harness|bbh:geometric_shapes|3": {
"em": 0.368,
"em_stderr": 0.030562070620993163,
"qem": 0.368,
"qem_stderr": 0.030562070620993163,
"pem": 0.368,
"pem_stderr": 0.030562070620993163,
"pqem": 0.368,
"pqem_stderr": 0.030562070620993163,
"perfect_em": 0.368,
"perfect_em_stderr": 0.030562070620993163
},
"harness|bbh:logical_deduction_five_objects|3": {
"em": 0.376,
"em_stderr": 0.030696336267394583,
"qem": 0.376,
"qem_stderr": 0.030696336267394583,
"pem": 0.376,
"pem_stderr": 0.030696336267394583,
"pqem": 0.512,
"pqem_stderr": 0.03167708558254709,
"perfect_em": 0.376,
"perfect_em_stderr": 0.030696336267394583
},
"harness|bbh:logical_deduction_seven_objects|3": {
"em": 0.38,
"em_stderr": 0.030760116042626035,
"qem": 0.38,
"qem_stderr": 0.030760116042626035,
"pem": 0.38,
"pem_stderr": 0.030760116042626035,
"pqem": 0.488,
"pqem_stderr": 0.03167708558254709,
"perfect_em": 0.38,
"perfect_em_stderr": 0.030760116042626035
},
"harness|bbh:logical_deduction_three_objects|3": {
"em": 0.424,
"em_stderr": 0.03131803437491615,
"qem": 0.424,
"qem_stderr": 0.03131803437491615,
"pem": 0.424,
"pem_stderr": 0.03131803437491615,
"pqem": 0.648,
"pqem_stderr": 0.030266288057359942,
"perfect_em": 0.424,
"perfect_em_stderr": 0.03131803437491615
},
"harness|bbh:movie_recommendation|3": {
"em": 0.4819277108433735,
"em_stderr": 0.03172928536632067,
"qem": 0.4819277108433735,
"qem_stderr": 0.03172928536632067,
"pem": 0.4819277108433735,
"pem_stderr": 0.03172928536632067,
"pqem": 0.6385542168674698,
"pqem_stderr": 0.03050665772049054,
"perfect_em": 0.4819277108433735,
"perfect_em_stderr": 0.03172928536632067
},
"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": 0.372,
"em_stderr": 0.030630325944558317,
"qem": 0.396,
"qem_stderr": 0.030993197854577853,
"pem": 0.372,
"pem_stderr": 0.030630325944558317,
"pqem": 0.508,
"pqem_stderr": 0.0316821564314138,
"perfect_em": 0.372,
"perfect_em_stderr": 0.030630325944558317
},
"harness|bbh:ruin_names|3": {
"em": 0.22983870967741934,
"em_stderr": 0.026770344128192625,
"qem": 0.22983870967741934,
"qem_stderr": 0.026770344128192625,
"pem": 0.22983870967741934,
"pem_stderr": 0.026770344128192625,
"pqem": 0.4274193548387097,
"pqem_stderr": 0.031477261888285146,
"perfect_em": 0.22983870967741934,
"perfect_em_stderr": 0.026770344128192625
},
"harness|bbh:salient_translation_error_detection|3": {
"em": 0.256,
"em_stderr": 0.0276571087182049,
"qem": 0.256,
"qem_stderr": 0.0276571087182049,
"pem": 0.256,
"pem_stderr": 0.0276571087182049,
"pqem": 0.388,
"pqem_stderr": 0.030881038748993922,
"perfect_em": 0.256,
"perfect_em_stderr": 0.0276571087182049
},
"harness|bbh:snarks|3": {
"em": 0.651685393258427,
"em_stderr": 0.035811144737534335,
"qem": 0.651685393258427,
"qem_stderr": 0.035811144737534335,
"pem": 0.651685393258427,
"pem_stderr": 0.035811144737534335,
"pqem": 0.8370786516853933,
"pqem_stderr": 0.02775782910660748,
"perfect_em": 0.651685393258427,
"perfect_em_stderr": 0.035811144737534335
},
"harness|bbh:sports_understanding|3": {
"em": 0.684,
"em_stderr": 0.029462657598578683,
"qem": 0.684,
"qem_stderr": 0.029462657598578683,
"pem": 0.684,
"pem_stderr": 0.029462657598578683,
"pqem": 0.684,
"pqem_stderr": 0.029462657598578683,
"perfect_em": 0.684,
"perfect_em_stderr": 0.029462657598578683
},
"harness|bbh:temporal_sequences|3": {
"em": 0.108,
"em_stderr": 0.019669559381568745,
"qem": 0.108,
"qem_stderr": 0.019669559381568745,
"pem": 0.108,
"pem_stderr": 0.019669559381568745,
"pqem": 0.392,
"pqem_stderr": 0.0309382076204012,
"perfect_em": 0.108,
"perfect_em_stderr": 0.019669559381568745
},
"harness|bbh:tracking_shuffled_objects_five_objects|3": {
"em": 0.132,
"em_stderr": 0.021450980824038107,
"qem": 0.132,
"qem_stderr": 0.021450980824038107,
"pem": 0.132,
"pem_stderr": 0.021450980824038107,
"pqem": 0.316,
"pqem_stderr": 0.029462657598578693,
"perfect_em": 0.132,
"perfect_em_stderr": 0.021450980824038107
},
"harness|bbh:tracking_shuffled_objects_seven_objects|3": {
"em": 0.116,
"em_stderr": 0.020293429803083855,
"qem": 0.116,
"qem_stderr": 0.020293429803083855,
"pem": 0.116,
"pem_stderr": 0.020293429803083855,
"pqem": 0.24,
"pqem_stderr": 0.027065293652239007,
"perfect_em": 0.116,
"perfect_em_stderr": 0.020293429803083855
},
"harness|bbh:tracking_shuffled_objects_three_objects|3": {
"em": 0.296,
"em_stderr": 0.028928939388379614,
"qem": 0.296,
"qem_stderr": 0.028928939388379614,
"pem": 0.296,
"pem_stderr": 0.028928939388379614,
"pqem": 0.6,
"pqem_stderr": 0.031046021028253254,
"perfect_em": 0.296,
"perfect_em_stderr": 0.028928939388379614
},
"harness|bbh:_average|3": {
"em": 0.39561066226283836,
"em_stderr": 0.029166235117413952,
"qem": 0.3969439955961717,
"qem_stderr": 0.02918639466797059,
"pem": 0.39561066226283836,
"pem_stderr": 0.029166235117413952,
"pqem": 0.5244773516857469,
"pqem_stderr": 0.030735194194671085,
"perfect_em": 0.39561066226283836,
"perfect_em_stderr": 0.029166235117413952
}
},
"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": "9c35405c70fbe3d7"
},
"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": "120761f6c3f44303"
},
"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": "0ed83d6c1a142638"
},
"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": "f51d9b28b207c446"
},
"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": "1d58cfef59ce072f"
},
"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": "a62643cff254b5b7"
},
"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": "601753724cc523b9"
},
"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": "7173d31f9686926b"
},
"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": "a1021fcbc080cc09"
},
"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": "f7bc1973e2c0d8ec"
},
"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": "5b55ac1cb97b47f5"
},
"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": "20287bbc87726773"
},
"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": "c5ab07c8679b1c3e"
},
"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": "1a157d3cf9cc3c9a"
},
"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": "c20becad71ebce6f"
},
"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": "35ea25ceeb3a07b2"
},
"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": "07fa40ebe832c82e"
},
"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": "ac04b579ad1bf082"
},
"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": "b12b9a2bac014e42"
},
"truncated": 4362,
"non_truncated": 0,
"padded": 0,
"non_padded": 4362,
"num_truncated_few_shots": 0
}
}