lewtun's picture
lewtun HF staff
Upload eval_results/kaist-ai/mistral-orpo-capybara-7k/main/agieval/results_2024-03-28T19-15-57.458335.json with huggingface_hub
50c6800 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": 682534.90399004,
"end_time": 682845.604085676,
"total_evaluation_time_secondes": "310.70009563607164",
"model_name": "kaist-ai/mistral-orpo-capybara-7k",
"model_sha": "24c1172060658a1923c9b454796857e2cc59fbeb",
"model_dtype": "torch.bfloat16",
"model_size": "13.99 GB",
"config": null
},
"results": {
"lighteval|agieval:aqua-rat|0": {
"acc": 0.2637795275590551,
"acc_stderr": 0.027705387412897232,
"acc_norm": 0.27165354330708663,
"acc_norm_stderr": 0.02796510358714041
},
"lighteval|agieval:gaokao-biology|0": {
"acc": 0.18571428571428572,
"acc_stderr": 0.026899110619750644,
"acc_norm": 0.29523809523809524,
"acc_norm_stderr": 0.03155253554505398
},
"lighteval|agieval:gaokao-chemistry|0": {
"acc": 0.20772946859903382,
"acc_stderr": 0.028265208679953954,
"acc_norm": 0.25120772946859904,
"acc_norm_stderr": 0.030217850292985314
},
"lighteval|agieval:gaokao-chinese|0": {
"acc": 0.2682926829268293,
"acc_stderr": 0.02830675402312185,
"acc_norm": 0.23577235772357724,
"acc_norm_stderr": 0.027119068752977947
},
"lighteval|agieval:gaokao-english|0": {
"acc": 0.6372549019607843,
"acc_stderr": 0.0275300784471103,
"acc_norm": 0.6078431372549019,
"acc_norm_stderr": 0.027956046165424523
},
"lighteval|agieval:gaokao-geography|0": {
"acc": 0.36180904522613067,
"acc_stderr": 0.034149349640988196,
"acc_norm": 0.38190954773869346,
"acc_norm_stderr": 0.03452817946540989
},
"lighteval|agieval:gaokao-history|0": {
"acc": 0.3276595744680851,
"acc_stderr": 0.030683020843231,
"acc_norm": 0.2936170212765957,
"acc_norm_stderr": 0.02977164271249123
},
"lighteval|agieval:gaokao-mathqa|0": {
"acc": 0.245014245014245,
"acc_stderr": 0.022989579301087353,
"acc_norm": 0.25071225071225073,
"acc_norm_stderr": 0.0231674413196653
},
"lighteval|agieval:gaokao-physics|0": {
"acc": 0.31,
"acc_stderr": 0.032785276754349606,
"acc_norm": 0.33,
"acc_norm_stderr": 0.03333249580187338
},
"lighteval|agieval:logiqa-en|0": {
"acc": 0.3348694316436252,
"acc_stderr": 0.018511198082586826,
"acc_norm": 0.35023041474654376,
"acc_norm_stderr": 0.01871112673222122
},
"lighteval|agieval:logiqa-zh|0": {
"acc": 0.31643625192012287,
"acc_stderr": 0.018242146904305322,
"acc_norm": 0.3533026113671275,
"acc_norm_stderr": 0.018748533323899707
},
"lighteval|agieval:lsat-ar|0": {
"acc": 0.23043478260869565,
"acc_stderr": 0.02782780752227616,
"acc_norm": 0.21304347826086956,
"acc_norm_stderr": 0.02705775438993618
},
"lighteval|agieval:lsat-lr|0": {
"acc": 0.3607843137254902,
"acc_stderr": 0.021285734668630495,
"acc_norm": 0.3254901960784314,
"acc_norm_stderr": 0.02076845539181952
},
"lighteval|agieval:lsat-rc|0": {
"acc": 0.44981412639405205,
"acc_stderr": 0.030388122316939672,
"acc_norm": 0.36059479553903345,
"acc_norm_stderr": 0.029331239329958934
},
"lighteval|agieval:sat-en|0": {
"acc": 0.6116504854368932,
"acc_stderr": 0.034039730667423974,
"acc_norm": 0.4854368932038835,
"acc_norm_stderr": 0.03490669905098905
},
"lighteval|agieval:sat-en-without-passage|0": {
"acc": 0.4320388349514563,
"acc_stderr": 0.0345974255383149,
"acc_norm": 0.3446601941747573,
"acc_norm_stderr": 0.0331934128585908
},
"lighteval|agieval:sat-math|0": {
"acc": 0.37272727272727274,
"acc_stderr": 0.0326739568483895,
"acc_norm": 0.2590909090909091,
"acc_norm_stderr": 0.029606460630040733
},
"lighteval|agieval:_average|0": {
"acc": 0.3480005429927092,
"acc_stderr": 0.028051758133609234,
"acc_norm": 0.32998842206949147,
"acc_norm_stderr": 0.028113767373557537
},
"all": {
"acc": 0.3480005429927092,
"acc_stderr": 0.028051758133609234,
"acc_norm": 0.32998842206949147,
"acc_norm_stderr": 0.028113767373557537
}
},
"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": "8b913655a6fea4ab",
"hash_input_tokens": "293a61e5163aa27e",
"hash_cont_tokens": "a12c4ac8996ba11d"
},
"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": "c7078ace868f7ee8",
"hash_input_tokens": "4abbc3b98bca27c3",
"hash_cont_tokens": "22b786cf7aa6d1a9"
},
"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": "bd066d6d8c807f39",
"hash_input_tokens": "3d9728247bf04ac3",
"hash_cont_tokens": "318562bcb4103fc4"
},
"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": "3f53e9dd34c43d52",
"hash_input_tokens": "f2a1d4c848527f86",
"hash_cont_tokens": "7b177add04591cdb"
},
"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": "59104cb8623f69e5",
"hash_input_tokens": "ff82bcaabb6cde43",
"hash_cont_tokens": "c9ca0addab2a9327"
},
"truncated": 0,
"non_truncated": 306,
"padded": 1224,
"non_padded": 0,
"effective_few_shots": 0.0,
"num_truncated_few_shots": 0
},
"lighteval|agieval:gaokao-geography|0": {
"hashes": {
"hash_examples": "ec3a021e37650e7d",
"hash_full_prompts": "d2456e0377df1973",
"hash_input_tokens": "b6593d42d60f9e65",
"hash_cont_tokens": "e1bc87e81807da78"
},
"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": "faea8f291d9a0cd5",
"hash_input_tokens": "ffa388f05b4bfadf",
"hash_cont_tokens": "b3c6c60f59b08db4"
},
"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": "de899bfeaaa61154",
"hash_input_tokens": "1e826e8ae60c9cf4",
"hash_cont_tokens": "5d69ebf8391bf298"
},
"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": "08008e0300283edc",
"hash_input_tokens": "0a4cddbeea3c31fa",
"hash_cont_tokens": "93b4c52fa838ace2"
},
"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": "3405fd262d4b2d28",
"hash_input_tokens": "8672a68d080ba1fb",
"hash_cont_tokens": "2624c1243afac3f2"
},
"truncated": 0,
"non_truncated": 651,
"padded": 2604,
"non_padded": 0,
"effective_few_shots": 0.0,
"num_truncated_few_shots": 0
},
"lighteval|agieval:logiqa-zh|0": {
"hashes": {
"hash_examples": "620d6888b6012ea5",
"hash_full_prompts": "ac19dc4eaa56f5e0",
"hash_input_tokens": "24c3bd34df395ee2",
"hash_cont_tokens": "725ca2b921b6f8fe"
},
"truncated": 0,
"non_truncated": 651,
"padded": 2603,
"non_padded": 1,
"effective_few_shots": 0.0,
"num_truncated_few_shots": 0
},
"lighteval|agieval:lsat-ar|0": {
"hashes": {
"hash_examples": "627c8f5ccd5da209",
"hash_full_prompts": "9aed992c4bfa8dd7",
"hash_input_tokens": "042173fcbbb85776",
"hash_cont_tokens": "23c097e1d431f2b8"
},
"truncated": 0,
"non_truncated": 230,
"padded": 1137,
"non_padded": 13,
"effective_few_shots": 0.0,
"num_truncated_few_shots": 0
},
"lighteval|agieval:lsat-lr|0": {
"hashes": {
"hash_examples": "794641c86de172f5",
"hash_full_prompts": "6a36e90325996129",
"hash_input_tokens": "58c268b8b0f3c5c4",
"hash_cont_tokens": "b555f4319746d815"
},
"truncated": 0,
"non_truncated": 510,
"padded": 2532,
"non_padded": 18,
"effective_few_shots": 0.0,
"num_truncated_few_shots": 0
},
"lighteval|agieval:lsat-rc|0": {
"hashes": {
"hash_examples": "35981ed917ea01cf",
"hash_full_prompts": "15f0f342f9572c41",
"hash_input_tokens": "1eaa7331cf1a555e",
"hash_cont_tokens": "8c1c4fc8c9cabd97"
},
"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": "163217fd603b9352",
"hash_input_tokens": "e1e9417c28fa0db0",
"hash_cont_tokens": "4837f17aae6c95e0"
},
"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": "bdd4c7065b87de8a",
"hash_input_tokens": "70bcab139ba874e5",
"hash_cont_tokens": "4837f17aae6c95e0"
},
"truncated": 0,
"non_truncated": 206,
"padded": 817,
"non_padded": 4,
"effective_few_shots": 0.0,
"num_truncated_few_shots": 0
},
"lighteval|agieval:sat-math|0": {
"hashes": {
"hash_examples": "01db7291603fc1a0",
"hash_full_prompts": "63ca65b2f0baebb5",
"hash_input_tokens": "e242b0a44e256fbb",
"hash_cont_tokens": "d959ef83452da9fe"
},
"truncated": 0,
"non_truncated": 220,
"padded": 877,
"non_padded": 3,
"effective_few_shots": 0.0,
"num_truncated_few_shots": 0
}
},
"summary_general": {
"hashes": {
"hash_examples": "da3af66181f18ddf",
"hash_full_prompts": "f7c298d03686fa0e",
"hash_input_tokens": "84e02a40c0a714da",
"hash_cont_tokens": "b3bace8c3199f6d8"
},
"truncated": 0,
"non_truncated": 5151,
"padded": 21823,
"non_padded": 41,
"num_truncated_few_shots": 0
}
}