lewtun's picture
lewtun HF staff
Upload eval_results/databricks/dbrx-instruct/main/agieval/results_2024-03-30T15-19-26.415183.json with huggingface_hub
e5995a8 verified
raw
history blame
25.9 kB
{
"config_general": {
"lighteval_sha": "?",
"num_fewshot_seeds": 1,
"override_batch_size": 1,
"max_samples": null,
"job_id": "",
"start_time": 1449028.270326239,
"end_time": 1455742.868291307,
"total_evaluation_time_secondes": "6714.597965067951",
"model_name": "databricks/dbrx-instruct",
"model_sha": "3b5d968eab47b0cb5b075fd984612b63f92841c2",
"model_dtype": "torch.bfloat16",
"model_size": "245.12 GB",
"config": null
},
"results": {
"lighteval|agieval:aqua-rat|0": {
"acc": 0.25196850393700787,
"acc_stderr": 0.027294353392553605,
"acc_norm": 0.25984251968503935,
"acc_norm_stderr": 0.02757127913961099
},
"lighteval|agieval:gaokao-biology|0": {
"acc": 0.41904761904761906,
"acc_stderr": 0.03412941259257987,
"acc_norm": 0.41904761904761906,
"acc_norm_stderr": 0.034129412592579865
},
"lighteval|agieval:gaokao-chemistry|0": {
"acc": 0.40096618357487923,
"acc_stderr": 0.03414647938499206,
"acc_norm": 0.3526570048309179,
"acc_norm_stderr": 0.033289699402134686
},
"lighteval|agieval:gaokao-chinese|0": {
"acc": 0.3943089430894309,
"acc_stderr": 0.03122200953730326,
"acc_norm": 0.4065040650406504,
"acc_norm_stderr": 0.03138038579815636
},
"lighteval|agieval:gaokao-english|0": {
"acc": 0.6176470588235294,
"acc_stderr": 0.027826109307283697,
"acc_norm": 0.5751633986928104,
"acc_norm_stderr": 0.02830457667314111
},
"lighteval|agieval:gaokao-geography|0": {
"acc": 0.6030150753768844,
"acc_stderr": 0.03477110537378156,
"acc_norm": 0.592964824120603,
"acc_norm_stderr": 0.03491385802519052
},
"lighteval|agieval:gaokao-history|0": {
"acc": 0.6042553191489362,
"acc_stderr": 0.031967586978353627,
"acc_norm": 0.5446808510638298,
"acc_norm_stderr": 0.03255525359340356
},
"lighteval|agieval:gaokao-mathqa|0": {
"acc": 0.2849002849002849,
"acc_stderr": 0.024126577672411744,
"acc_norm": 0.2792022792022792,
"acc_norm_stderr": 0.02397906029914625
},
"lighteval|agieval:gaokao-physics|0": {
"acc": 0.46,
"acc_stderr": 0.03533045720097817,
"acc_norm": 0.445,
"acc_norm_stderr": 0.0352289710609046
},
"lighteval|agieval:logiqa-en|0": {
"acc": 0.3210445468509985,
"acc_stderr": 0.01831245670147613,
"acc_norm": 0.34715821812596004,
"acc_norm_stderr": 0.018672867593776798
},
"lighteval|agieval:logiqa-zh|0": {
"acc": 0.40860215053763443,
"acc_stderr": 0.019281175878347604,
"acc_norm": 0.42242703533026116,
"acc_norm_stderr": 0.01937414753071922
},
"lighteval|agieval:lsat-ar|0": {
"acc": 0.20869565217391303,
"acc_stderr": 0.026854108265439658,
"acc_norm": 0.20869565217391303,
"acc_norm_stderr": 0.026854108265439658
},
"lighteval|agieval:lsat-lr|0": {
"acc": 0.48823529411764705,
"acc_stderr": 0.022155974669311143,
"acc_norm": 0.3843137254901961,
"acc_norm_stderr": 0.021560746452830175
},
"lighteval|agieval:lsat-rc|0": {
"acc": 0.6133828996282528,
"acc_stderr": 0.029746711725453,
"acc_norm": 0.46096654275092935,
"acc_norm_stderr": 0.030449149512372414
},
"lighteval|agieval:sat-en|0": {
"acc": 0.7378640776699029,
"acc_stderr": 0.03071669765614076,
"acc_norm": 0.5922330097087378,
"acc_norm_stderr": 0.034322222902602624
},
"lighteval|agieval:sat-en-without-passage|0": {
"acc": 0.46601941747572817,
"acc_stderr": 0.03484077510347999,
"acc_norm": 0.3786407766990291,
"acc_norm_stderr": 0.033877248925062636
},
"lighteval|agieval:sat-math|0": {
"acc": 0.44545454545454544,
"acc_stderr": 0.03358522134954388,
"acc_norm": 0.32727272727272727,
"acc_norm_stderr": 0.0317067966768602
},
"lighteval|agieval:_average|0": {
"acc": 0.4544357395180702,
"acc_stderr": 0.029194541928789987,
"acc_norm": 0.41157472054326494,
"acc_norm_stderr": 0.029304104967290103
},
"all": {
"acc": 0.4544357395180702,
"acc_stderr": 0.029194541928789987,
"acc_norm": 0.41157472054326494,
"acc_norm_stderr": 0.029304104967290103
}
},
"versions": {
"lighteval|agieval:aqua-rat|0": 0,
"lighteval|agieval:gaokao-biology|0": 0,
"lighteval|agieval:gaokao-chemistry|0": 0,
"lighteval|agieval:gaokao-chinese|0": 0,
"lighteval|agieval:gaokao-english|0": 0,
"lighteval|agieval:gaokao-geography|0": 0,
"lighteval|agieval:gaokao-history|0": 0,
"lighteval|agieval:gaokao-mathqa|0": 0,
"lighteval|agieval:gaokao-physics|0": 0,
"lighteval|agieval:logiqa-en|0": 0,
"lighteval|agieval:logiqa-zh|0": 0,
"lighteval|agieval:lsat-ar|0": 0,
"lighteval|agieval:lsat-lr|0": 0,
"lighteval|agieval:lsat-rc|0": 0,
"lighteval|agieval:sat-en|0": 0,
"lighteval|agieval:sat-en-without-passage|0": 0,
"lighteval|agieval:sat-math|0": 0
},
"config_tasks": {
"lighteval|agieval:aqua-rat": {
"name": "agieval:aqua-rat",
"prompt_function": "agieval",
"hf_repo": "dmayhem93/agieval-aqua-rat",
"hf_subset": "default",
"metric": [
"loglikelihood_acc",
"loglikelihood_acc_norm_nospace"
],
"hf_avail_splits": [
"test"
],
"evaluation_splits": [
"test"
],
"few_shots_split": null,
"few_shots_select": "random_sampling",
"generation_size": 1,
"stop_sequence": null,
"output_regex": null,
"frozen": false,
"suite": [
"lighteval"
],
"original_num_docs": 254,
"effective_num_docs": 254,
"trust_dataset": true,
"must_remove_duplicate_docs": null
},
"lighteval|agieval:gaokao-biology": {
"name": "agieval:gaokao-biology",
"prompt_function": "agieval",
"hf_repo": "dmayhem93/agieval-gaokao-biology",
"hf_subset": "default",
"metric": [
"loglikelihood_acc",
"loglikelihood_acc_norm_nospace"
],
"hf_avail_splits": [
"test"
],
"evaluation_splits": [
"test"
],
"few_shots_split": null,
"few_shots_select": "random_sampling",
"generation_size": 1,
"stop_sequence": null,
"output_regex": null,
"frozen": false,
"suite": [
"lighteval"
],
"original_num_docs": 210,
"effective_num_docs": 210,
"trust_dataset": true,
"must_remove_duplicate_docs": null
},
"lighteval|agieval:gaokao-chemistry": {
"name": "agieval:gaokao-chemistry",
"prompt_function": "agieval",
"hf_repo": "dmayhem93/agieval-gaokao-chemistry",
"hf_subset": "default",
"metric": [
"loglikelihood_acc",
"loglikelihood_acc_norm_nospace"
],
"hf_avail_splits": [
"test"
],
"evaluation_splits": [
"test"
],
"few_shots_split": null,
"few_shots_select": "random_sampling",
"generation_size": 1,
"stop_sequence": null,
"output_regex": null,
"frozen": false,
"suite": [
"lighteval"
],
"original_num_docs": 207,
"effective_num_docs": 207,
"trust_dataset": true,
"must_remove_duplicate_docs": null
},
"lighteval|agieval:gaokao-chinese": {
"name": "agieval:gaokao-chinese",
"prompt_function": "agieval",
"hf_repo": "dmayhem93/agieval-gaokao-chinese",
"hf_subset": "default",
"metric": [
"loglikelihood_acc",
"loglikelihood_acc_norm_nospace"
],
"hf_avail_splits": [
"test"
],
"evaluation_splits": [
"test"
],
"few_shots_split": null,
"few_shots_select": "random_sampling",
"generation_size": 1,
"stop_sequence": null,
"output_regex": null,
"frozen": false,
"suite": [
"lighteval"
],
"original_num_docs": 246,
"effective_num_docs": 246,
"trust_dataset": true,
"must_remove_duplicate_docs": null
},
"lighteval|agieval:gaokao-english": {
"name": "agieval:gaokao-english",
"prompt_function": "agieval",
"hf_repo": "dmayhem93/agieval-gaokao-english",
"hf_subset": "default",
"metric": [
"loglikelihood_acc",
"loglikelihood_acc_norm_nospace"
],
"hf_avail_splits": [
"test"
],
"evaluation_splits": [
"test"
],
"few_shots_split": null,
"few_shots_select": "random_sampling",
"generation_size": 1,
"stop_sequence": null,
"output_regex": null,
"frozen": false,
"suite": [
"lighteval"
],
"original_num_docs": 306,
"effective_num_docs": 306,
"trust_dataset": true,
"must_remove_duplicate_docs": null
},
"lighteval|agieval:gaokao-geography": {
"name": "agieval:gaokao-geography",
"prompt_function": "agieval",
"hf_repo": "dmayhem93/agieval-gaokao-geography",
"hf_subset": "default",
"metric": [
"loglikelihood_acc",
"loglikelihood_acc_norm_nospace"
],
"hf_avail_splits": [
"test"
],
"evaluation_splits": [
"test"
],
"few_shots_split": null,
"few_shots_select": "random_sampling",
"generation_size": 1,
"stop_sequence": null,
"output_regex": null,
"frozen": false,
"suite": [
"lighteval"
],
"original_num_docs": 199,
"effective_num_docs": 199,
"trust_dataset": true,
"must_remove_duplicate_docs": null
},
"lighteval|agieval:gaokao-history": {
"name": "agieval:gaokao-history",
"prompt_function": "agieval",
"hf_repo": "dmayhem93/agieval-gaokao-history",
"hf_subset": "default",
"metric": [
"loglikelihood_acc",
"loglikelihood_acc_norm_nospace"
],
"hf_avail_splits": [
"test"
],
"evaluation_splits": [
"test"
],
"few_shots_split": null,
"few_shots_select": "random_sampling",
"generation_size": 1,
"stop_sequence": null,
"output_regex": null,
"frozen": false,
"suite": [
"lighteval"
],
"original_num_docs": 235,
"effective_num_docs": 235,
"trust_dataset": true,
"must_remove_duplicate_docs": null
},
"lighteval|agieval:gaokao-mathqa": {
"name": "agieval:gaokao-mathqa",
"prompt_function": "agieval",
"hf_repo": "dmayhem93/agieval-gaokao-mathqa",
"hf_subset": "default",
"metric": [
"loglikelihood_acc",
"loglikelihood_acc_norm_nospace"
],
"hf_avail_splits": [
"test"
],
"evaluation_splits": [
"test"
],
"few_shots_split": null,
"few_shots_select": "random_sampling",
"generation_size": 1,
"stop_sequence": null,
"output_regex": null,
"frozen": false,
"suite": [
"lighteval"
],
"original_num_docs": 351,
"effective_num_docs": 351,
"trust_dataset": true,
"must_remove_duplicate_docs": null
},
"lighteval|agieval:gaokao-physics": {
"name": "agieval:gaokao-physics",
"prompt_function": "agieval",
"hf_repo": "dmayhem93/agieval-gaokao-physics",
"hf_subset": "default",
"metric": [
"loglikelihood_acc",
"loglikelihood_acc_norm_nospace"
],
"hf_avail_splits": [
"test"
],
"evaluation_splits": [
"test"
],
"few_shots_split": null,
"few_shots_select": "random_sampling",
"generation_size": 1,
"stop_sequence": null,
"output_regex": null,
"frozen": false,
"suite": [
"lighteval"
],
"original_num_docs": 200,
"effective_num_docs": 200,
"trust_dataset": true,
"must_remove_duplicate_docs": null
},
"lighteval|agieval:logiqa-en": {
"name": "agieval:logiqa-en",
"prompt_function": "agieval",
"hf_repo": "dmayhem93/agieval-logiqa-en",
"hf_subset": "default",
"metric": [
"loglikelihood_acc",
"loglikelihood_acc_norm_nospace"
],
"hf_avail_splits": [
"test"
],
"evaluation_splits": [
"test"
],
"few_shots_split": null,
"few_shots_select": "random_sampling",
"generation_size": 1,
"stop_sequence": null,
"output_regex": null,
"frozen": false,
"suite": [
"lighteval"
],
"original_num_docs": 651,
"effective_num_docs": 651,
"trust_dataset": true,
"must_remove_duplicate_docs": null
},
"lighteval|agieval:logiqa-zh": {
"name": "agieval:logiqa-zh",
"prompt_function": "agieval",
"hf_repo": "dmayhem93/agieval-logiqa-zh",
"hf_subset": "default",
"metric": [
"loglikelihood_acc",
"loglikelihood_acc_norm_nospace"
],
"hf_avail_splits": [
"test"
],
"evaluation_splits": [
"test"
],
"few_shots_split": null,
"few_shots_select": "random_sampling",
"generation_size": 1,
"stop_sequence": null,
"output_regex": null,
"frozen": false,
"suite": [
"lighteval"
],
"original_num_docs": 651,
"effective_num_docs": 651,
"trust_dataset": true,
"must_remove_duplicate_docs": null
},
"lighteval|agieval:lsat-ar": {
"name": "agieval:lsat-ar",
"prompt_function": "agieval",
"hf_repo": "dmayhem93/agieval-lsat-ar",
"hf_subset": "default",
"metric": [
"loglikelihood_acc",
"loglikelihood_acc_norm_nospace"
],
"hf_avail_splits": [
"test"
],
"evaluation_splits": [
"test"
],
"few_shots_split": null,
"few_shots_select": "random_sampling",
"generation_size": 1,
"stop_sequence": null,
"output_regex": null,
"frozen": false,
"suite": [
"lighteval"
],
"original_num_docs": 230,
"effective_num_docs": 230,
"trust_dataset": true,
"must_remove_duplicate_docs": null
},
"lighteval|agieval:lsat-lr": {
"name": "agieval:lsat-lr",
"prompt_function": "agieval",
"hf_repo": "dmayhem93/agieval-lsat-lr",
"hf_subset": "default",
"metric": [
"loglikelihood_acc",
"loglikelihood_acc_norm_nospace"
],
"hf_avail_splits": [
"test"
],
"evaluation_splits": [
"test"
],
"few_shots_split": null,
"few_shots_select": "random_sampling",
"generation_size": 1,
"stop_sequence": null,
"output_regex": null,
"frozen": false,
"suite": [
"lighteval"
],
"original_num_docs": 510,
"effective_num_docs": 510,
"trust_dataset": true,
"must_remove_duplicate_docs": null
},
"lighteval|agieval:lsat-rc": {
"name": "agieval:lsat-rc",
"prompt_function": "agieval",
"hf_repo": "dmayhem93/agieval-lsat-rc",
"hf_subset": "default",
"metric": [
"loglikelihood_acc",
"loglikelihood_acc_norm_nospace"
],
"hf_avail_splits": [
"test"
],
"evaluation_splits": [
"test"
],
"few_shots_split": null,
"few_shots_select": "random_sampling",
"generation_size": 1,
"stop_sequence": null,
"output_regex": null,
"frozen": false,
"suite": [
"lighteval"
],
"original_num_docs": 269,
"effective_num_docs": 269,
"trust_dataset": true,
"must_remove_duplicate_docs": null
},
"lighteval|agieval:sat-en": {
"name": "agieval:sat-en",
"prompt_function": "agieval",
"hf_repo": "dmayhem93/agieval-sat-en",
"hf_subset": "default",
"metric": [
"loglikelihood_acc",
"loglikelihood_acc_norm_nospace"
],
"hf_avail_splits": [
"test"
],
"evaluation_splits": [
"test"
],
"few_shots_split": null,
"few_shots_select": "random_sampling",
"generation_size": 1,
"stop_sequence": null,
"output_regex": null,
"frozen": false,
"suite": [
"lighteval"
],
"original_num_docs": 206,
"effective_num_docs": 206,
"trust_dataset": true,
"must_remove_duplicate_docs": null
},
"lighteval|agieval:sat-en-without-passage": {
"name": "agieval:sat-en-without-passage",
"prompt_function": "agieval",
"hf_repo": "dmayhem93/agieval-sat-en-without-passage",
"hf_subset": "default",
"metric": [
"loglikelihood_acc",
"loglikelihood_acc_norm_nospace"
],
"hf_avail_splits": [
"test"
],
"evaluation_splits": [
"test"
],
"few_shots_split": null,
"few_shots_select": "random_sampling",
"generation_size": 1,
"stop_sequence": null,
"output_regex": null,
"frozen": false,
"suite": [
"lighteval"
],
"original_num_docs": 206,
"effective_num_docs": 206,
"trust_dataset": true,
"must_remove_duplicate_docs": null
},
"lighteval|agieval:sat-math": {
"name": "agieval:sat-math",
"prompt_function": "agieval",
"hf_repo": "dmayhem93/agieval-sat-math",
"hf_subset": "default",
"metric": [
"loglikelihood_acc",
"loglikelihood_acc_norm_nospace"
],
"hf_avail_splits": [
"test"
],
"evaluation_splits": [
"test"
],
"few_shots_split": null,
"few_shots_select": "random_sampling",
"generation_size": 1,
"stop_sequence": null,
"output_regex": null,
"frozen": false,
"suite": [
"lighteval"
],
"original_num_docs": 220,
"effective_num_docs": 220,
"trust_dataset": true,
"must_remove_duplicate_docs": null
}
},
"summary_tasks": {
"lighteval|agieval:aqua-rat|0": {
"hashes": {
"hash_examples": "f09607f69e5b7525",
"hash_full_prompts": "2dd019f2a9629d3c",
"hash_input_tokens": "c7a095b065d480b0",
"hash_cont_tokens": "9a4c5828e6dabe2e"
},
"truncated": 0,
"non_truncated": 254,
"padded": 1270,
"non_padded": 0,
"effective_few_shots": 0.0,
"num_truncated_few_shots": 0
},
"lighteval|agieval:gaokao-biology|0": {
"hashes": {
"hash_examples": "f262eaf4a72db963",
"hash_full_prompts": "9936cbf7a5bc399f",
"hash_input_tokens": "28166e19ba7194ee",
"hash_cont_tokens": "5dc07709ee2eda10"
},
"truncated": 0,
"non_truncated": 210,
"padded": 840,
"non_padded": 0,
"effective_few_shots": 0.0,
"num_truncated_few_shots": 0
},
"lighteval|agieval:gaokao-chemistry|0": {
"hashes": {
"hash_examples": "47f2e649f58d9da5",
"hash_full_prompts": "679f06a0d708b514",
"hash_input_tokens": "abfd6d291af87b20",
"hash_cont_tokens": "c02c0b3f0938184c"
},
"truncated": 0,
"non_truncated": 207,
"padded": 831,
"non_padded": 0,
"effective_few_shots": 0.0,
"num_truncated_few_shots": 0
},
"lighteval|agieval:gaokao-chinese|0": {
"hashes": {
"hash_examples": "1010b21fde4726ab",
"hash_full_prompts": "3c905587787709a8",
"hash_input_tokens": "f800795cf9f4a078",
"hash_cont_tokens": "885b3626dcebb080"
},
"truncated": 0,
"non_truncated": 246,
"padded": 982,
"non_padded": 2,
"effective_few_shots": 0.0,
"num_truncated_few_shots": 0
},
"lighteval|agieval:gaokao-english|0": {
"hashes": {
"hash_examples": "4864e492a350ae93",
"hash_full_prompts": "72fe2d636b6f6622",
"hash_input_tokens": "179f671d7cc3b7cc",
"hash_cont_tokens": "2262620ff400b608"
},
"truncated": 0,
"non_truncated": 306,
"padded": 1218,
"non_padded": 6,
"effective_few_shots": 0.0,
"num_truncated_few_shots": 0
},
"lighteval|agieval:gaokao-geography|0": {
"hashes": {
"hash_examples": "ec3a021e37650e7d",
"hash_full_prompts": "60a42fb81acf5a1e",
"hash_input_tokens": "55a30b8466c26129",
"hash_cont_tokens": "480a5c8f86827df4"
},
"truncated": 0,
"non_truncated": 199,
"padded": 796,
"non_padded": 0,
"effective_few_shots": 0.0,
"num_truncated_few_shots": 0
},
"lighteval|agieval:gaokao-history|0": {
"hashes": {
"hash_examples": "b3fad1596f1ae1f9",
"hash_full_prompts": "2c8875804d162da8",
"hash_input_tokens": "5cdba09c199f23cf",
"hash_cont_tokens": "e1608c6dd5f55267"
},
"truncated": 0,
"non_truncated": 235,
"padded": 940,
"non_padded": 0,
"effective_few_shots": 0.0,
"num_truncated_few_shots": 0
},
"lighteval|agieval:gaokao-mathqa|0": {
"hashes": {
"hash_examples": "1d1088556861b0b0",
"hash_full_prompts": "c1a6433c211e92a1",
"hash_input_tokens": "814594787313230d",
"hash_cont_tokens": "e8cd9aaeeec6a5d4"
},
"truncated": 0,
"non_truncated": 351,
"padded": 1404,
"non_padded": 0,
"effective_few_shots": 0.0,
"num_truncated_few_shots": 0
},
"lighteval|agieval:gaokao-physics|0": {
"hashes": {
"hash_examples": "eb05f035c7bfca2f",
"hash_full_prompts": "4ba90cfb06e848e8",
"hash_input_tokens": "a96955e66f7210d8",
"hash_cont_tokens": "b89267e9f865c6b3"
},
"truncated": 0,
"non_truncated": 200,
"padded": 800,
"non_padded": 0,
"effective_few_shots": 0.0,
"num_truncated_few_shots": 0
},
"lighteval|agieval:logiqa-en|0": {
"hashes": {
"hash_examples": "0a688a45f69c21e0",
"hash_full_prompts": "d66246a3e0fde055",
"hash_input_tokens": "cb9639b768095552",
"hash_cont_tokens": "2c45f086a39c57b8"
},
"truncated": 0,
"non_truncated": 651,
"padded": 2599,
"non_padded": 5,
"effective_few_shots": 0.0,
"num_truncated_few_shots": 0
},
"lighteval|agieval:logiqa-zh|0": {
"hashes": {
"hash_examples": "620d6888b6012ea5",
"hash_full_prompts": "12bef01e6e2bb3bb",
"hash_input_tokens": "fb10f8f201d221fc",
"hash_cont_tokens": "528f93b95cf11c45"
},
"truncated": 0,
"non_truncated": 651,
"padded": 2592,
"non_padded": 12,
"effective_few_shots": 0.0,
"num_truncated_few_shots": 0
},
"lighteval|agieval:lsat-ar|0": {
"hashes": {
"hash_examples": "627c8f5ccd5da209",
"hash_full_prompts": "2f70fdd969d5131c",
"hash_input_tokens": "ff96b15c8e322081",
"hash_cont_tokens": "a04649158245218b"
},
"truncated": 0,
"non_truncated": 230,
"padded": 1147,
"non_padded": 3,
"effective_few_shots": 0.0,
"num_truncated_few_shots": 0
},
"lighteval|agieval:lsat-lr|0": {
"hashes": {
"hash_examples": "794641c86de172f5",
"hash_full_prompts": "19fa02ffa4cfbbe3",
"hash_input_tokens": "1ac160b68dbd4f42",
"hash_cont_tokens": "1020f1117c8bf340"
},
"truncated": 0,
"non_truncated": 510,
"padded": 2519,
"non_padded": 31,
"effective_few_shots": 0.0,
"num_truncated_few_shots": 0
},
"lighteval|agieval:lsat-rc|0": {
"hashes": {
"hash_examples": "35981ed917ea01cf",
"hash_full_prompts": "37f03609dd5027c5",
"hash_input_tokens": "71655332fea694a0",
"hash_cont_tokens": "cb10bf65326d313e"
},
"truncated": 0,
"non_truncated": 269,
"padded": 1345,
"non_padded": 0,
"effective_few_shots": 0.0,
"num_truncated_few_shots": 0
},
"lighteval|agieval:sat-en|0": {
"hashes": {
"hash_examples": "041c39c646536a1e",
"hash_full_prompts": "10014752d3b89e2d",
"hash_input_tokens": "1086a441056617a9",
"hash_cont_tokens": "b2eb0cb9fcf03bef"
},
"truncated": 0,
"non_truncated": 206,
"padded": 821,
"non_padded": 0,
"effective_few_shots": 0.0,
"num_truncated_few_shots": 0
},
"lighteval|agieval:sat-en-without-passage|0": {
"hashes": {
"hash_examples": "e4d9284367dff68f",
"hash_full_prompts": "048ea6811dd85fb5",
"hash_input_tokens": "8b8d347811731c48",
"hash_cont_tokens": "b2eb0cb9fcf03bef"
},
"truncated": 0,
"non_truncated": 206,
"padded": 819,
"non_padded": 2,
"effective_few_shots": 0.0,
"num_truncated_few_shots": 0
},
"lighteval|agieval:sat-math|0": {
"hashes": {
"hash_examples": "01db7291603fc1a0",
"hash_full_prompts": "eff3065f8ae8d936",
"hash_input_tokens": "b4d4bd8a36ef96a7",
"hash_cont_tokens": "20524d21001d25a6"
},
"truncated": 0,
"non_truncated": 220,
"padded": 878,
"non_padded": 2,
"effective_few_shots": 0.0,
"num_truncated_few_shots": 0
}
},
"summary_general": {
"hashes": {
"hash_examples": "da3af66181f18ddf",
"hash_full_prompts": "99f646ddb87a6ed9",
"hash_input_tokens": "7e5cae6af0c269dd",
"hash_cont_tokens": "748ca081a3836593"
},
"truncated": 0,
"non_truncated": 5151,
"padded": 21801,
"non_padded": 63,
"num_truncated_few_shots": 0
}
}