lewtun's picture
lewtun HF staff
Upload eval_results/NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO/main/bbh/results_2024-03-18T20-39-32.747348.json with huggingface_hub
d30acf6 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": 2106314.171046321,
"end_time": 2107521.942727167,
"total_evaluation_time_secondes": "1207.7716808463447",
"model_name": "NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO",
"model_sha": "707b6e3251d114cc3d326e6a2bcff1449110aedf",
"model_dtype": "torch.bfloat16",
"model_size": "87.49 GB",
"config": null
},
"results": {
"harness|bbh:causal_judgment|3": {
"em": 0.6684491978609626,
"em_stderr": 0.034518568148016175,
"qem": 0.6684491978609626,
"qem_stderr": 0.034518568148016175,
"pem": 0.6684491978609626,
"pem_stderr": 0.034518568148016175,
"pqem": 0.6684491978609626,
"pqem_stderr": 0.034518568148016175,
"perfect_em": 0.6684491978609626,
"perfect_em_stderr": 0.034518568148016175
},
"harness|bbh:date_understanding|3": {
"em": 0.536,
"em_stderr": 0.03160397514522374,
"qem": 0.536,
"qem_stderr": 0.03160397514522374,
"pem": 0.536,
"pem_stderr": 0.03160397514522374,
"pqem": 0.624,
"pqem_stderr": 0.030696336267394594,
"perfect_em": 0.536,
"perfect_em_stderr": 0.03160397514522374
},
"harness|bbh:disambiguation_qa|3": {
"em": 0.632,
"em_stderr": 0.030562070620993167,
"qem": 0.632,
"qem_stderr": 0.030562070620993167,
"pem": 0.684,
"pem_stderr": 0.029462657598578666,
"pqem": 0.728,
"pqem_stderr": 0.028200088296309985,
"perfect_em": 0.632,
"perfect_em_stderr": 0.030562070620993167
},
"harness|bbh:geometric_shapes|3": {
"em": 0.196,
"em_stderr": 0.025156857313255898,
"qem": 0.196,
"qem_stderr": 0.025156857313255898,
"pem": 0.38,
"pem_stderr": 0.03076011604262604,
"pqem": 0.38,
"pqem_stderr": 0.03076011604262604,
"perfect_em": 0.196,
"perfect_em_stderr": 0.025156857313255898
},
"harness|bbh:logical_deduction_five_objects|3": {
"em": 0.536,
"em_stderr": 0.031603975145223735,
"qem": 0.536,
"qem_stderr": 0.031603975145223735,
"pem": 0.536,
"pem_stderr": 0.031603975145223735,
"pqem": 0.592,
"pqem_stderr": 0.0311452098465485,
"perfect_em": 0.536,
"perfect_em_stderr": 0.031603975145223735
},
"harness|bbh:logical_deduction_seven_objects|3": {
"em": 0.524,
"em_stderr": 0.031649688959687824,
"qem": 0.524,
"qem_stderr": 0.031649688959687824,
"pem": 0.524,
"pem_stderr": 0.031649688959687824,
"pqem": 0.552,
"pqem_stderr": 0.03151438761115351,
"perfect_em": 0.524,
"perfect_em_stderr": 0.031649688959687824
},
"harness|bbh:logical_deduction_three_objects|3": {
"em": 0.708,
"em_stderr": 0.028814320402205655,
"qem": 0.708,
"qem_stderr": 0.028814320402205655,
"pem": 0.712,
"pem_stderr": 0.02869700458739821,
"pqem": 0.824,
"pqem_stderr": 0.02413349752545711,
"perfect_em": 0.708,
"perfect_em_stderr": 0.028814320402205655
},
"harness|bbh:movie_recommendation|3": {
"em": 0.7951807228915663,
"em_stderr": 0.025626688837598215,
"qem": 0.7951807228915663,
"qem_stderr": 0.025626688837598215,
"pem": 0.8554216867469879,
"pem_stderr": 0.02233139557182192,
"pqem": 0.8875502008032129,
"pqem_stderr": 0.020060879304188376,
"perfect_em": 0.7951807228915663,
"perfect_em_stderr": 0.025626688837598215
},
"harness|bbh:navigate|3": {
"em": 0.684,
"em_stderr": 0.02946265759857867,
"qem": 0.684,
"qem_stderr": 0.02946265759857867,
"pem": 0.684,
"pem_stderr": 0.02946265759857867,
"pqem": 0.684,
"pqem_stderr": 0.02946265759857867,
"perfect_em": 0.684,
"perfect_em_stderr": 0.02946265759857867
},
"harness|bbh:reasoning_about_colored_objects|3": {
"em": 0.604,
"em_stderr": 0.03099319785457785,
"qem": 0.604,
"qem_stderr": 0.03099319785457785,
"pem": 0.628,
"pem_stderr": 0.030630325944558317,
"pqem": 0.696,
"pqem_stderr": 0.029150213374159673,
"perfect_em": 0.604,
"perfect_em_stderr": 0.03099319785457785
},
"harness|bbh:ruin_names|3": {
"em": 0.657258064516129,
"em_stderr": 0.030199733298058248,
"qem": 0.657258064516129,
"qem_stderr": 0.030199733298058248,
"pem": 0.657258064516129,
"pem_stderr": 0.030199733298058248,
"pqem": 0.7903225806451613,
"pqem_stderr": 0.025901776404740794,
"perfect_em": 0.657258064516129,
"perfect_em_stderr": 0.030199733298058248
},
"harness|bbh:salient_translation_error_detection|3": {
"em": 0.492,
"em_stderr": 0.031682156431413803,
"qem": 0.492,
"qem_stderr": 0.031682156431413803,
"pem": 0.5,
"pem_stderr": 0.031686212526223896,
"pqem": 0.62,
"pqem_stderr": 0.030760116042626046,
"perfect_em": 0.492,
"perfect_em_stderr": 0.031682156431413803
},
"harness|bbh:snarks|3": {
"em": 0.7696629213483146,
"em_stderr": 0.03164794946543343,
"qem": 0.7696629213483146,
"qem_stderr": 0.03164794946543343,
"pem": 0.7752808988764045,
"pem_stderr": 0.03137349512125098,
"pqem": 0.8089887640449438,
"pqem_stderr": 0.029547046053276616,
"perfect_em": 0.7696629213483146,
"perfect_em_stderr": 0.03164794946543343
},
"harness|bbh:sports_understanding|3": {
"em": 0.656,
"em_stderr": 0.03010450339231639,
"qem": 0.656,
"qem_stderr": 0.03010450339231639,
"pem": 0.728,
"pem_stderr": 0.02820008829631,
"pqem": 0.728,
"pqem_stderr": 0.02820008829631,
"perfect_em": 0.656,
"perfect_em_stderr": 0.03010450339231639
},
"harness|bbh:temporal_sequences|3": {
"em": 0.712,
"em_stderr": 0.02869700458739821,
"qem": 0.712,
"qem_stderr": 0.02869700458739821,
"pem": 0.716,
"pem_stderr": 0.0285769587304374,
"pqem": 0.78,
"pqem_stderr": 0.026251792824605824,
"perfect_em": 0.712,
"perfect_em_stderr": 0.02869700458739821
},
"harness|bbh:tracking_shuffled_objects_five_objects|3": {
"em": 0.216,
"em_stderr": 0.02607865766373272,
"qem": 0.216,
"qem_stderr": 0.02607865766373272,
"pem": 0.216,
"pem_stderr": 0.02607865766373272,
"pqem": 0.368,
"pqem_stderr": 0.03056207062099316,
"perfect_em": 0.216,
"perfect_em_stderr": 0.02607865766373272
},
"harness|bbh:tracking_shuffled_objects_seven_objects|3": {
"em": 0.24,
"em_stderr": 0.027065293652239003,
"qem": 0.24,
"qem_stderr": 0.027065293652239003,
"pem": 0.24,
"pem_stderr": 0.027065293652239003,
"pqem": 0.34,
"pqem_stderr": 0.030020073605457904,
"perfect_em": 0.24,
"perfect_em_stderr": 0.027065293652239003
},
"harness|bbh:tracking_shuffled_objects_three_objects|3": {
"em": 0.292,
"em_stderr": 0.028814320402205638,
"qem": 0.292,
"qem_stderr": 0.028814320402205638,
"pem": 0.292,
"pem_stderr": 0.028814320402205638,
"pqem": 0.576,
"pqem_stderr": 0.03131803437491614,
"perfect_em": 0.292,
"perfect_em_stderr": 0.028814320402205638
},
"harness|bbh:_average|3": {
"em": 0.5510306059231651,
"em_stderr": 0.02968231216211991,
"qem": 0.5510306059231651,
"qem_stderr": 0.02968231216211991,
"pem": 0.5740227693333602,
"pem_stderr": 0.029595284690676182,
"pqem": 0.6470728190752378,
"pqem_stderr": 0.029011275124297724,
"perfect_em": 0.5510306059231651,
"perfect_em_stderr": 0.02968231216211991
}
},
"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": "7303fa1d0fe0b29a",
"hash_input_tokens": "94e6ca97dc7a8d65",
"hash_cont_tokens": "c1fd192768c0e57e"
},
"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": "69e60d10afa5a6f1",
"hash_input_tokens": "56c1b1dfb318cc75",
"hash_cont_tokens": "07e69cb17d2c8831"
},
"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": "ae0a8fd428f9aee3",
"hash_input_tokens": "bc3e442621b75177",
"hash_cont_tokens": "b0bec51398a8ab33"
},
"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": "76633257f67207f9",
"hash_input_tokens": "18d576df2960751d",
"hash_cont_tokens": "e45ae98082e3f8e4"
},
"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": "3c96645848786efd",
"hash_input_tokens": "36a60b866a1bf813",
"hash_cont_tokens": "d0fd54910c263084"
},
"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": "185c5851c101ee66",
"hash_input_tokens": "c1e2e1d71455bb49",
"hash_cont_tokens": "be34a7e0cad54ac6"
},
"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": "8ba2d94357e589d0",
"hash_input_tokens": "70f1b3c78b924815",
"hash_cont_tokens": "9809821397c70a07"
},
"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": "a411e216d0f5f626",
"hash_input_tokens": "d671ce3b88ee45cd",
"hash_cont_tokens": "bb2b8b6208282129"
},
"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": "ebb3084ecc78a46a",
"hash_input_tokens": "51743c1fef4a5482",
"hash_cont_tokens": "be308b10012c18c5"
},
"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": "38328d016a4ebef3",
"hash_input_tokens": "6897c18acd616cb9",
"hash_cont_tokens": "41e24bff8937bc90"
},
"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": "9c7d0493c37182d6",
"hash_input_tokens": "4d618e950c8d013d",
"hash_cont_tokens": "af8b825ca94f816b"
},
"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": "edccd4061b168b78",
"hash_input_tokens": "fcdd25281b1eba05",
"hash_cont_tokens": "23b483e6c7f2007c"
},
"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": "31cafd95ab850a44",
"hash_input_tokens": "16886c991ce348c1",
"hash_cont_tokens": "f03d63eceacec321"
},
"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": "3d46581e9bbec2d0",
"hash_input_tokens": "117a2d8c0e6cb894",
"hash_cont_tokens": "ffeb0de5394f482b"
},
"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": "4a54db144a5dd222",
"hash_input_tokens": "70740a88f84e4a13",
"hash_cont_tokens": "e734dc7f2a09b368"
},
"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": "e3079106787cc311",
"hash_input_tokens": "c8d7203b8c369cb8",
"hash_cont_tokens": "4906a9453f52f313"
},
"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": "6364e5b860590ec8",
"hash_input_tokens": "beb0b08cec3d048f",
"hash_cont_tokens": "ea591550a02af892"
},
"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": "01aef56c4d1fe9fe",
"hash_input_tokens": "9642e09abf045647",
"hash_cont_tokens": "423b3e314913c518"
},
"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": "1cbeab0a00117cb8",
"hash_input_tokens": "2a35e6d8f7c2fc79",
"hash_cont_tokens": "7c03f3b4f9d962b4"
},
"truncated": 4362,
"non_truncated": 0,
"padded": 0,
"non_padded": 4362,
"num_truncated_few_shots": 0
}
}