lewtun's picture
lewtun HF staff
Upload eval_results/kaist-ai/mistral-orpo-alpha/main/agieval/results_2024-03-28T19-14-46.723246.json with huggingface_hub
2a949e8 verified
raw
history blame
25.8 kB
{
"config_general": {
"lighteval_sha": "?",
"num_fewshot_seeds": 1,
"override_batch_size": 1,
"max_samples": null,
"job_id": "",
"start_time": 1626308.847028699,
"end_time": 1626593.843652943,
"total_evaluation_time_secondes": "284.99662424391136",
"model_name": "kaist-ai/mistral-orpo-alpha",
"model_sha": "fe1724b77567a2a3579e74240a69a66622191735",
"model_dtype": "torch.bfloat16",
"model_size": "13.99 GB",
"config": null
},
"results": {
"lighteval|agieval:aqua-rat|0": {
"acc": 0.23228346456692914,
"acc_stderr": 0.026549071327684932,
"acc_norm": 0.24015748031496062,
"acc_norm_stderr": 0.026856511194355212
},
"lighteval|agieval:gaokao-biology|0": {
"acc": 0.3238095238095238,
"acc_stderr": 0.03236727895404352,
"acc_norm": 0.32857142857142857,
"acc_norm_stderr": 0.03248939796876844
},
"lighteval|agieval:gaokao-chemistry|0": {
"acc": 0.2946859903381642,
"acc_stderr": 0.03176416108295297,
"acc_norm": 0.28019323671497587,
"acc_norm_stderr": 0.031289827964521094
},
"lighteval|agieval:gaokao-chinese|0": {
"acc": 0.2682926829268293,
"acc_stderr": 0.028306754023121848,
"acc_norm": 0.2601626016260163,
"acc_norm_stderr": 0.028028995361669366
},
"lighteval|agieval:gaokao-english|0": {
"acc": 0.6993464052287581,
"acc_stderr": 0.026256053835718968,
"acc_norm": 0.6437908496732027,
"acc_norm_stderr": 0.02742047766262924
},
"lighteval|agieval:gaokao-geography|0": {
"acc": 0.4723618090452261,
"acc_stderr": 0.035479125346565575,
"acc_norm": 0.45226130653266333,
"acc_norm_stderr": 0.03537112167025914
},
"lighteval|agieval:gaokao-history|0": {
"acc": 0.4085106382978723,
"acc_stderr": 0.03213418026701576,
"acc_norm": 0.37446808510638296,
"acc_norm_stderr": 0.03163910665367291
},
"lighteval|agieval:gaokao-mathqa|0": {
"acc": 0.2535612535612536,
"acc_stderr": 0.023254366364417835,
"acc_norm": 0.23646723646723647,
"acc_norm_stderr": 0.022712519049117575
},
"lighteval|agieval:gaokao-physics|0": {
"acc": 0.32,
"acc_stderr": 0.03306761764450865,
"acc_norm": 0.355,
"acc_norm_stderr": 0.033920910080708536
},
"lighteval|agieval:logiqa-en|0": {
"acc": 0.3456221198156682,
"acc_stderr": 0.018653416684754197,
"acc_norm": 0.3486943164362519,
"acc_norm_stderr": 0.018692104055797923
},
"lighteval|agieval:logiqa-zh|0": {
"acc": 0.3241167434715822,
"acc_stderr": 0.01835819163513243,
"acc_norm": 0.35023041474654376,
"acc_norm_stderr": 0.018711126732221216
},
"lighteval|agieval:lsat-ar|0": {
"acc": 0.1782608695652174,
"acc_stderr": 0.025291655246273914,
"acc_norm": 0.17391304347826086,
"acc_norm_stderr": 0.025047317386049713
},
"lighteval|agieval:lsat-lr|0": {
"acc": 0.403921568627451,
"acc_stderr": 0.021749102234028657,
"acc_norm": 0.34901960784313724,
"acc_norm_stderr": 0.021127590746109415
},
"lighteval|agieval:lsat-rc|0": {
"acc": 0.5092936802973977,
"acc_stderr": 0.030537084593525398,
"acc_norm": 0.3680297397769517,
"acc_norm_stderr": 0.029459297142360175
},
"lighteval|agieval:sat-en|0": {
"acc": 0.6504854368932039,
"acc_stderr": 0.03330232052876045,
"acc_norm": 0.5339805825242718,
"acc_norm_stderr": 0.03484077510348
},
"lighteval|agieval:sat-en-without-passage|0": {
"acc": 0.4174757281553398,
"acc_stderr": 0.03444258173919335,
"acc_norm": 0.3640776699029126,
"acc_norm_stderr": 0.03360641055142782
},
"lighteval|agieval:sat-math|0": {
"acc": 0.35,
"acc_stderr": 0.03223061875589932,
"acc_norm": 0.30454545454545456,
"acc_norm_stderr": 0.03109842385860254
},
"lighteval|agieval:_average|0": {
"acc": 0.3795310538000245,
"acc_stderr": 0.0284555047213881,
"acc_norm": 0.3507978267212148,
"acc_norm_stderr": 0.028371289010691192
},
"all": {
"acc": 0.3795310538000245,
"acc_stderr": 0.0284555047213881,
"acc_norm": 0.3507978267212148,
"acc_norm_stderr": 0.028371289010691192
}
},
"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
}
}