{ "config_general": { "lighteval_sha": "?", "num_fewshot_seeds": 1, "override_batch_size": 1, "max_samples": null, "job_id": "", "start_time": 1467500.567268427, "end_time": 1467697.843720951, "total_evaluation_time_secondes": "197.27645252388902", "model_name": "HuggingFaceH4/mistral-7b-ift", "model_sha": "c611133be4aeaac5cf03e723fdc682a46dbebb51", "model_dtype": "torch.bfloat16", "model_size": "13.99 GB", "config": null }, "results": { "harness|bbh:causal_judgment|3": { "em": 0.5561497326203209, "em_stderr": 0.03642987131924728, "qem": 0.5561497326203209, "qem_stderr": 0.03642987131924728, "pem": 0.5561497326203209, "pem_stderr": 0.03642987131924728, "pqem": 0.5561497326203209, "pqem_stderr": 0.03642987131924728, "perfect_em": 0.5561497326203209, "perfect_em_stderr": 0.03642987131924728 }, "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": 0.572, "pqem_stderr": 0.031355968923772605, "perfect_em": 0.48, "perfect_em_stderr": 0.031660853408495185 }, "harness|bbh:disambiguation_qa|3": { "em": 0.596, "em_stderr": 0.031096688184825295, "qem": 0.596, "qem_stderr": 0.031096688184825295, "pem": 0.596, "pem_stderr": 0.031096688184825295, "pqem": 0.728, "pqem_stderr": 0.02820008829630998, "perfect_em": 0.596, "perfect_em_stderr": 0.031096688184825295 }, "harness|bbh:geometric_shapes|3": { "em": 0.2, "em_stderr": 0.025348970020979078, "qem": 0.2, "qem_stderr": 0.025348970020979078, "pem": 0.2, "pem_stderr": 0.025348970020979078, "pqem": 0.2, "pqem_stderr": 0.025348970020979078, "perfect_em": 0.2, "perfect_em_stderr": 0.025348970020979078 }, "harness|bbh:logical_deduction_five_objects|3": { "em": 0.352, "em_stderr": 0.030266288057359942, "qem": 0.352, "qem_stderr": 0.030266288057359942, "pem": 0.352, "pem_stderr": 0.030266288057359942, "pqem": 0.484, "pqem_stderr": 0.03166998503010742, "perfect_em": 0.352, "perfect_em_stderr": 0.030266288057359942 }, "harness|bbh:logical_deduction_seven_objects|3": { "em": 0.284, "em_stderr": 0.028576958730437408, "qem": 0.284, "qem_stderr": 0.028576958730437408, "pem": 0.284, "pem_stderr": 0.028576958730437408, "pqem": 0.4, "pqem_stderr": 0.031046021028253237, "perfect_em": 0.284, "perfect_em_stderr": 0.028576958730437408 }, "harness|bbh:logical_deduction_three_objects|3": { "em": 0.5, "em_stderr": 0.031686212526223896, "qem": 0.5, "qem_stderr": 0.031686212526223896, "pem": 0.5, "pem_stderr": 0.031686212526223896, "pqem": 0.756, "pqem_stderr": 0.027217995464553182, "perfect_em": 0.5, "perfect_em_stderr": 0.031686212526223896 }, "harness|bbh:movie_recommendation|3": { "em": 0.5582329317269076, "em_stderr": 0.031533963107802196, "qem": 0.5582329317269076, "qem_stderr": 0.031533963107802196, "pem": 0.5582329317269076, "pem_stderr": 0.031533963107802196, "pqem": 0.6626506024096386, "pqem_stderr": 0.030023161860939146, "perfect_em": 0.5582329317269076, "perfect_em_stderr": 0.031533963107802196 }, "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": 0.348, "em_stderr": 0.0301865684645117, "qem": 0.348, "qem_stderr": 0.0301865684645117, "pem": 0.356, "pem_stderr": 0.030343680657153215, "pqem": 0.512, "pqem_stderr": 0.03167708558254708, "perfect_em": 0.348, "perfect_em_stderr": 0.0301865684645117 }, "harness|bbh:ruin_names|3": { "em": 0.3185483870967742, "em_stderr": 0.029645360812643396, "qem": 0.3185483870967742, "qem_stderr": 0.029645360812643396, "pem": 0.3185483870967742, "pem_stderr": 0.029645360812643396, "pqem": 0.45564516129032256, "pqem_stderr": 0.03168881131061097, "perfect_em": 0.3185483870967742, "perfect_em_stderr": 0.029645360812643396 }, "harness|bbh:salient_translation_error_detection|3": { "em": 0.352, "em_stderr": 0.030266288057359942, "qem": 0.352, "qem_stderr": 0.030266288057359942, "pem": 0.352, "pem_stderr": 0.030266288057359942, "pqem": 0.492, "pqem_stderr": 0.031682156431413803, "perfect_em": 0.352, "perfect_em_stderr": 0.030266288057359942 }, "harness|bbh:snarks|3": { "em": 0.5224719101123596, "em_stderr": 0.037544325084871946, "qem": 0.5224719101123596, "qem_stderr": 0.037544325084871946, "pem": 0.5224719101123596, "pem_stderr": 0.037544325084871946, "pqem": 0.6966292134831461, "pqem_stderr": 0.03455421944400099, "perfect_em": 0.5224719101123596, "perfect_em_stderr": 0.037544325084871946 }, "harness|bbh:sports_understanding|3": { "em": 0.78, "em_stderr": 0.026251792824605824, "qem": 0.78, "qem_stderr": 0.026251792824605824, "pem": 0.78, "pem_stderr": 0.026251792824605824, "pqem": 0.78, "pqem_stderr": 0.026251792824605824, "perfect_em": 0.78, "perfect_em_stderr": 0.026251792824605824 }, "harness|bbh:temporal_sequences|3": { "em": 0.156, "em_stderr": 0.022995023034068744, "qem": 0.156, "qem_stderr": 0.022995023034068744, "pem": 0.156, "pem_stderr": 0.022995023034068744, "pqem": 0.436, "pqem_stderr": 0.03142556706028128, "perfect_em": 0.156, "perfect_em_stderr": 0.022995023034068744 }, "harness|bbh:tracking_shuffled_objects_five_objects|3": { "em": 0.192, "em_stderr": 0.024960691989172015, "qem": 0.192, "qem_stderr": 0.024960691989172015, "pem": 0.192, "pem_stderr": 0.024960691989172015, "pqem": 0.392, "pqem_stderr": 0.030938207620401195, "perfect_em": 0.192, "perfect_em_stderr": 0.024960691989172015 }, "harness|bbh:tracking_shuffled_objects_seven_objects|3": { "em": 0.12, "em_stderr": 0.02059360059683997, "qem": 0.12, "qem_stderr": 0.02059360059683997, "pem": 0.12, "pem_stderr": 0.02059360059683997, "pqem": 0.264, "pqem_stderr": 0.02793451895769091, "perfect_em": 0.12, "perfect_em_stderr": 0.02059360059683997 }, "harness|bbh:tracking_shuffled_objects_three_objects|3": { "em": 0.348, "em_stderr": 0.030186568464511686, "qem": 0.348, "qem_stderr": 0.030186568464511686, "pem": 0.348, "pem_stderr": 0.030186568464511686, "pqem": 0.664, "pqem_stderr": 0.029933259094191516, "perfect_em": 0.348, "perfect_em_stderr": 0.030186568464511686 }, "harness|bbh:_average|3": { "em": 0.40374460897535347, "em_stderr": 0.029456845696585188, "qem": 0.40374460897535347, "qem_stderr": 0.029456845696585188, "pem": 0.40418905341979783, "pem_stderr": 0.029465574151731937, "pqem": 0.5363930394335238, "pqem_stderr": 0.03046504878469352, "perfect_em": 0.40374460897535347, "perfect_em_stderr": 0.029456845696585188 } }, "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": [ "", "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": [ "", "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": [ "", "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": [ "", "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": [ "", "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": [ "", "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": [ "", "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": [ "", "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": [ "", "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": [ "", "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": [ "", "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": [ "", "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": [ "", "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": [ "", "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": [ "", "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": [ "", "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": [ "", "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": [ "", "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": "e4c253a8681bf364" }, "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": "0ed430d5278b416c" }, "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": "7b7794fcb91031e2" }, "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": "01cecc5dff38dd91" }, "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": "9d26dd290bafa8fe" }, "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": "9048cc3f73ab92fb" }, "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": "daac20c5618ed703" }, "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": "00faebfddd3ad134" }, "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": "62c3fdb3d1eb28de" }, "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": "dcb665080b66ff23" }, "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": "a88425b4cd016660" }, "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": "1ff03589170a9c22" }, "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": "a0e9d30060362261" }, "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": "2dd1a0bbe88c59fc" }, "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": "ad6342524c809638" }, "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": "8bfa64af5bd5d43e" }, "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": "62b9c4a2a02ea0a6" }, "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": "8bf730633382d68c" }, "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": "2d6caa036b5ecdf8" }, "truncated": 4362, "non_truncated": 0, "padded": 0, "non_padded": 4362, "num_truncated_few_shots": 0 } }