lewtun's picture
lewtun HF staff
Upload eval_results/deepseek-ai/deepseek-llm-67b-chat/main/agieval/results_2024-03-28T17-11-01.242076.json with huggingface_hub
02352db 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": 2077820.830040582,
"end_time": 2080750.614670217,
"total_evaluation_time_secondes": "2929.784629635047",
"model_name": "deepseek-ai/deepseek-llm-67b-chat",
"model_sha": "79648bef7658bb824e4630740f6e1484c1b0620b",
"model_dtype": "torch.bfloat16",
"model_size": "125.77 GB",
"config": null
},
"results": {
"lighteval|agieval:aqua-rat|0": {
"acc": 0.3188976377952756,
"acc_stderr": 0.029300267397764652,
"acc_norm": 0.2874015748031496,
"acc_norm_stderr": 0.028451603010183634
},
"lighteval|agieval:gaokao-biology|0": {
"acc": 0.5857142857142857,
"acc_stderr": 0.034073735217849545,
"acc_norm": 0.5428571428571428,
"acc_norm_stderr": 0.034458439380315835
},
"lighteval|agieval:gaokao-chemistry|0": {
"acc": 0.4251207729468599,
"acc_stderr": 0.034443784322092386,
"acc_norm": 0.34782608695652173,
"acc_norm_stderr": 0.03318403378139901
},
"lighteval|agieval:gaokao-chinese|0": {
"acc": 0.5975609756097561,
"acc_stderr": 0.03132983555771989,
"acc_norm": 0.5487804878048781,
"acc_norm_stderr": 0.031791441795983734
},
"lighteval|agieval:gaokao-english|0": {
"acc": 0.696078431372549,
"acc_stderr": 0.026336613469046633,
"acc_norm": 0.6633986928104575,
"acc_norm_stderr": 0.027057974624494382
},
"lighteval|agieval:gaokao-geography|0": {
"acc": 0.7336683417085427,
"acc_stderr": 0.03141439434617944,
"acc_norm": 0.7085427135678392,
"acc_norm_stderr": 0.03229519279811605
},
"lighteval|agieval:gaokao-history|0": {
"acc": 0.7574468085106383,
"acc_stderr": 0.02802022627120022,
"acc_norm": 0.6638297872340425,
"acc_norm_stderr": 0.030881618520676942
},
"lighteval|agieval:gaokao-mathqa|0": {
"acc": 0.2934472934472934,
"acc_stderr": 0.02433903269681092,
"acc_norm": 0.2962962962962963,
"acc_norm_stderr": 0.024407539882901112
},
"lighteval|agieval:gaokao-physics|0": {
"acc": 0.56,
"acc_stderr": 0.03518793763172071,
"acc_norm": 0.47,
"acc_norm_stderr": 0.03538020341900046
},
"lighteval|agieval:logiqa-en|0": {
"acc": 0.43010752688172044,
"acc_stderr": 0.01941906447090713,
"acc_norm": 0.4039938556067588,
"acc_norm_stderr": 0.019246690834000654
},
"lighteval|agieval:logiqa-zh|0": {
"acc": 0.5422427035330261,
"acc_stderr": 0.019541496438967652,
"acc_norm": 0.445468509984639,
"acc_norm_stderr": 0.01949462713343998
},
"lighteval|agieval:lsat-ar|0": {
"acc": 0.25217391304347825,
"acc_stderr": 0.028696745294493377,
"acc_norm": 0.21739130434782608,
"acc_norm_stderr": 0.02725685083881996
},
"lighteval|agieval:lsat-lr|0": {
"acc": 0.5705882352941176,
"acc_stderr": 0.02194014455513715,
"acc_norm": 0.44901960784313727,
"acc_norm_stderr": 0.022046610724356357
},
"lighteval|agieval:lsat-rc|0": {
"acc": 0.6356877323420075,
"acc_stderr": 0.029396215063241374,
"acc_norm": 0.4758364312267658,
"acc_norm_stderr": 0.030506674211283072
},
"lighteval|agieval:sat-en|0": {
"acc": 0.7912621359223301,
"acc_stderr": 0.028384671935185526,
"acc_norm": 0.6941747572815534,
"acc_norm_stderr": 0.032180600400244896
},
"lighteval|agieval:sat-en-without-passage|0": {
"acc": 0.4854368932038835,
"acc_stderr": 0.03490669905098905,
"acc_norm": 0.3155339805825243,
"acc_norm_stderr": 0.03245802450146824
},
"lighteval|agieval:sat-math|0": {
"acc": 0.42272727272727273,
"acc_stderr": 0.033380942640935336,
"acc_norm": 0.35,
"acc_norm_stderr": 0.032230618755899304
},
"lighteval|agieval:_average|0": {
"acc": 0.5351859388266493,
"acc_stderr": 0.02883010625648476,
"acc_norm": 0.4635500723060901,
"acc_norm_stderr": 0.029019337918387268
},
"all": {
"acc": 0.5351859388266493,
"acc_stderr": 0.02883010625648476,
"acc_norm": 0.4635500723060901,
"acc_norm_stderr": 0.029019337918387268
}
},
"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": "0e5e32a970e390ea",
"hash_input_tokens": "77a739a63819e008",
"hash_cont_tokens": "2cad1f93cd377428"
},
"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": "229fc17c14965d1c",
"hash_input_tokens": "abdc458e17f2ba7a",
"hash_cont_tokens": "decb1b6a4f846fdb"
},
"truncated": 0,
"non_truncated": 210,
"padded": 833,
"non_padded": 7,
"effective_few_shots": 0.0,
"num_truncated_few_shots": 0
},
"lighteval|agieval:gaokao-chemistry|0": {
"hashes": {
"hash_examples": "47f2e649f58d9da5",
"hash_full_prompts": "a1662423763cd50a",
"hash_input_tokens": "b30dc42a725e0381",
"hash_cont_tokens": "55034b0104261709"
},
"truncated": 0,
"non_truncated": 207,
"padded": 826,
"non_padded": 5,
"effective_few_shots": 0.0,
"num_truncated_few_shots": 0
},
"lighteval|agieval:gaokao-chinese|0": {
"hashes": {
"hash_examples": "1010b21fde4726ab",
"hash_full_prompts": "849f250b06540d96",
"hash_input_tokens": "efa18c51ae25e7dc",
"hash_cont_tokens": "ed6245bf0174f812"
},
"truncated": 0,
"non_truncated": 246,
"padded": 981,
"non_padded": 3,
"effective_few_shots": 0.0,
"num_truncated_few_shots": 0
},
"lighteval|agieval:gaokao-english|0": {
"hashes": {
"hash_examples": "4864e492a350ae93",
"hash_full_prompts": "8ae18cea7c33973f",
"hash_input_tokens": "ccc2862769a768f0",
"hash_cont_tokens": "ef0d21bb5e92ad27"
},
"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": "9281a6eef7c0ff74",
"hash_input_tokens": "3d03a6deb16b00ae",
"hash_cont_tokens": "a3f1aa75c1c0f518"
},
"truncated": 0,
"non_truncated": 199,
"padded": 791,
"non_padded": 5,
"effective_few_shots": 0.0,
"num_truncated_few_shots": 0
},
"lighteval|agieval:gaokao-history|0": {
"hashes": {
"hash_examples": "b3fad1596f1ae1f9",
"hash_full_prompts": "d6df287dca759a9e",
"hash_input_tokens": "af0c96864f4164fa",
"hash_cont_tokens": "24b37966ac3f0820"
},
"truncated": 0,
"non_truncated": 235,
"padded": 930,
"non_padded": 10,
"effective_few_shots": 0.0,
"num_truncated_few_shots": 0
},
"lighteval|agieval:gaokao-mathqa|0": {
"hashes": {
"hash_examples": "1d1088556861b0b0",
"hash_full_prompts": "849410cb9a4101a4",
"hash_input_tokens": "37500c8ac391ff93",
"hash_cont_tokens": "3fd46a253d4f64f0"
},
"truncated": 0,
"non_truncated": 351,
"padded": 1403,
"non_padded": 1,
"effective_few_shots": 0.0,
"num_truncated_few_shots": 0
},
"lighteval|agieval:gaokao-physics|0": {
"hashes": {
"hash_examples": "eb05f035c7bfca2f",
"hash_full_prompts": "ec6493a6dd766f44",
"hash_input_tokens": "9aa42e2ae8a705a3",
"hash_cont_tokens": "38fcd2b335c3fb40"
},
"truncated": 0,
"non_truncated": 200,
"padded": 797,
"non_padded": 3,
"effective_few_shots": 0.0,
"num_truncated_few_shots": 0
},
"lighteval|agieval:logiqa-en|0": {
"hashes": {
"hash_examples": "0a688a45f69c21e0",
"hash_full_prompts": "7fe2e6fedb447416",
"hash_input_tokens": "1f3460a64b7f60f1",
"hash_cont_tokens": "8bc0af2414f69ab8"
},
"truncated": 0,
"non_truncated": 651,
"padded": 2602,
"non_padded": 2,
"effective_few_shots": 0.0,
"num_truncated_few_shots": 0
},
"lighteval|agieval:logiqa-zh|0": {
"hashes": {
"hash_examples": "620d6888b6012ea5",
"hash_full_prompts": "df88541b270818dc",
"hash_input_tokens": "2927a5683d83a326",
"hash_cont_tokens": "74ef8ea01dcec4c7"
},
"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": "c65582c7eb7e71b3",
"hash_input_tokens": "4c412bfd912649cb",
"hash_cont_tokens": "dec54f05f564f9d4"
},
"truncated": 0,
"non_truncated": 230,
"padded": 1149,
"non_padded": 1,
"effective_few_shots": 0.0,
"num_truncated_few_shots": 0
},
"lighteval|agieval:lsat-lr|0": {
"hashes": {
"hash_examples": "794641c86de172f5",
"hash_full_prompts": "033f31969f6927c6",
"hash_input_tokens": "df058f1fd4548e45",
"hash_cont_tokens": "9c4ce131b925f840"
},
"truncated": 0,
"non_truncated": 510,
"padded": 2539,
"non_padded": 11,
"effective_few_shots": 0.0,
"num_truncated_few_shots": 0
},
"lighteval|agieval:lsat-rc|0": {
"hashes": {
"hash_examples": "35981ed917ea01cf",
"hash_full_prompts": "594ea1493ac00038",
"hash_input_tokens": "3dbe9d992702e035",
"hash_cont_tokens": "ee975d9e9167fa6f"
},
"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": "6459686d0db60d98",
"hash_input_tokens": "2601f7afb0f6edda",
"hash_cont_tokens": "87912bae8bee15a6"
},
"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": "3111aa1c817d5f73",
"hash_input_tokens": "f2bed14fba7f44a1",
"hash_cont_tokens": "87912bae8bee15a6"
},
"truncated": 0,
"non_truncated": 206,
"padded": 812,
"non_padded": 9,
"effective_few_shots": 0.0,
"num_truncated_few_shots": 0
},
"lighteval|agieval:sat-math|0": {
"hashes": {
"hash_examples": "01db7291603fc1a0",
"hash_full_prompts": "854368f14f99baee",
"hash_input_tokens": "0242f0472c553cfc",
"hash_cont_tokens": "d54c758fcae21262"
},
"truncated": 0,
"non_truncated": 220,
"padded": 872,
"non_padded": 8,
"effective_few_shots": 0.0,
"num_truncated_few_shots": 0
}
},
"summary_general": {
"hashes": {
"hash_examples": "da3af66181f18ddf",
"hash_full_prompts": "0399ef5bbb34ed90",
"hash_input_tokens": "77cd14086f902b7e",
"hash_cont_tokens": "11392dba3393fe7f"
},
"truncated": 0,
"non_truncated": 5151,
"padded": 21787,
"non_padded": 77,
"num_truncated_few_shots": 0
}
}