lewtun's picture
lewtun HF staff
Upload eval_results/meta-llama/Llama-2-13b-chat-hf/main/agieval/results_2024-03-28T16-53-48.762881.json with huggingface_hub
5f452f9 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": 8646774.98843263,
"end_time": 8647277.082037227,
"total_evaluation_time_secondes": "502.0936045963317",
"model_name": "meta-llama/Llama-2-13b-chat-hf",
"model_sha": "29655417e51232f4f2b9b5d3e1418e5a9b04e80e",
"model_dtype": "torch.bfloat16",
"model_size": "24.32 GB",
"config": null
},
"results": {
"lighteval|agieval:aqua-rat|0": {
"acc": 0.2047244094488189,
"acc_stderr": 0.02536783354473852,
"acc_norm": 0.2047244094488189,
"acc_norm_stderr": 0.02536783354473853
},
"lighteval|agieval:gaokao-biology|0": {
"acc": 0.28095238095238095,
"acc_stderr": 0.03109009446934462,
"acc_norm": 0.3142857142857143,
"acc_norm_stderr": 0.03211151353994384
},
"lighteval|agieval:gaokao-chemistry|0": {
"acc": 0.30917874396135264,
"acc_stderr": 0.03219986494000449,
"acc_norm": 0.2560386473429952,
"acc_norm_stderr": 0.03040845392239327
},
"lighteval|agieval:gaokao-chinese|0": {
"acc": 0.1991869918699187,
"acc_stderr": 0.025516024108089824,
"acc_norm": 0.21138211382113822,
"acc_norm_stderr": 0.02608461238305184
},
"lighteval|agieval:gaokao-english|0": {
"acc": 0.5490196078431373,
"acc_stderr": 0.02849199358617156,
"acc_norm": 0.4477124183006536,
"acc_norm_stderr": 0.028472938478033522
},
"lighteval|agieval:gaokao-geography|0": {
"acc": 0.3316582914572864,
"acc_stderr": 0.03345893526874066,
"acc_norm": 0.3015075376884422,
"acc_norm_stderr": 0.03261349587454653
},
"lighteval|agieval:gaokao-history|0": {
"acc": 0.33191489361702126,
"acc_stderr": 0.03078373675774565,
"acc_norm": 0.28936170212765955,
"acc_norm_stderr": 0.02964400657700962
},
"lighteval|agieval:gaokao-mathqa|0": {
"acc": 0.2706552706552707,
"acc_stderr": 0.023748744034266786,
"acc_norm": 0.2706552706552707,
"acc_norm_stderr": 0.023748744034266786
},
"lighteval|agieval:gaokao-physics|0": {
"acc": 0.27,
"acc_stderr": 0.03147145152843339,
"acc_norm": 0.315,
"acc_norm_stderr": 0.032928657464464904
},
"lighteval|agieval:logiqa-en|0": {
"acc": 0.3563748079877112,
"acc_stderr": 0.01878509246182,
"acc_norm": 0.3210445468509985,
"acc_norm_stderr": 0.01831245670147612
},
"lighteval|agieval:logiqa-zh|0": {
"acc": 0.26574500768049153,
"acc_stderr": 0.017326040808935687,
"acc_norm": 0.3333333333333333,
"acc_norm_stderr": 0.018490006540841045
},
"lighteval|agieval:lsat-ar|0": {
"acc": 0.21739130434782608,
"acc_stderr": 0.027256850838819964,
"acc_norm": 0.22608695652173913,
"acc_norm_stderr": 0.027641785707241334
},
"lighteval|agieval:lsat-lr|0": {
"acc": 0.3568627450980392,
"acc_stderr": 0.02123457379560983,
"acc_norm": 0.28823529411764703,
"acc_norm_stderr": 0.02007626467805952
},
"lighteval|agieval:lsat-rc|0": {
"acc": 0.4200743494423792,
"acc_stderr": 0.030149620080212006,
"acc_norm": 0.31226765799256506,
"acc_norm_stderr": 0.02830778120469435
},
"lighteval|agieval:sat-en|0": {
"acc": 0.6019417475728155,
"acc_stderr": 0.03418799390613399,
"acc_norm": 0.4077669902912621,
"acc_norm_stderr": 0.03432222290260263
},
"lighteval|agieval:sat-en-without-passage|0": {
"acc": 0.3640776699029126,
"acc_stderr": 0.03360641055142781,
"acc_norm": 0.25728155339805825,
"acc_norm_stderr": 0.030530892446123826
},
"lighteval|agieval:sat-math|0": {
"acc": 0.2863636363636364,
"acc_stderr": 0.030547478139694613,
"acc_norm": 0.2636363636363636,
"acc_norm_stderr": 0.02977328576472747
},
"lighteval|agieval:_average|0": {
"acc": 0.3303601093059411,
"acc_stderr": 0.027954278754128786,
"acc_norm": 0.2953129711654506,
"acc_norm_stderr": 0.0275785265743656
},
"all": {
"acc": 0.3303601093059411,
"acc_stderr": 0.027954278754128786,
"acc_norm": 0.2953129711654506,
"acc_norm_stderr": 0.0275785265743656
}
},
"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": "3861b27efd5a6170",
"hash_input_tokens": "b81ddf32d9e36b1f",
"hash_cont_tokens": "d68d99aa7aafcf10"
},
"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": "1ef14dcf5933ff33",
"hash_input_tokens": "0e02a46ea2b2e076",
"hash_cont_tokens": "fb818e5d1e6cfaf9"
},
"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": "324a4d07d3b7de40",
"hash_input_tokens": "ab927b5975095914",
"hash_cont_tokens": "cae820a904612b14"
},
"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": "938611fd6ecdbf4e",
"hash_input_tokens": "72d5df618421255b",
"hash_cont_tokens": "4f99bcd4d0795887"
},
"truncated": 0,
"non_truncated": 246,
"padded": 979,
"non_padded": 5,
"effective_few_shots": 0.0,
"num_truncated_few_shots": 0
},
"lighteval|agieval:gaokao-english|0": {
"hashes": {
"hash_examples": "4864e492a350ae93",
"hash_full_prompts": "2cff929f74eb0813",
"hash_input_tokens": "364e98db90c628be",
"hash_cont_tokens": "8b0fdf9d99f09625"
},
"truncated": 0,
"non_truncated": 306,
"padded": 1217,
"non_padded": 7,
"effective_few_shots": 0.0,
"num_truncated_few_shots": 0
},
"lighteval|agieval:gaokao-geography|0": {
"hashes": {
"hash_examples": "ec3a021e37650e7d",
"hash_full_prompts": "79c20e1e52638229",
"hash_input_tokens": "fb6db8d803e25b33",
"hash_cont_tokens": "0144954f291c77ff"
},
"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": "541c270a0bbab3fd",
"hash_input_tokens": "4461fd574f259120",
"hash_cont_tokens": "f7f0c87190e11336"
},
"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": "6002200193304ad6",
"hash_input_tokens": "e6fb6d8930aa10fa",
"hash_cont_tokens": "1c92bd434c8ca7cf"
},
"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": "7b606fe0e48d1136",
"hash_input_tokens": "1c39aecbf26045ac",
"hash_cont_tokens": "2c78afa11a936dc4"
},
"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": "70df665a01ea64f7",
"hash_input_tokens": "61f22bb8a98d5e05",
"hash_cont_tokens": "1c7594dbf0a0a533"
},
"truncated": 0,
"non_truncated": 651,
"padded": 2588,
"non_padded": 16,
"effective_few_shots": 0.0,
"num_truncated_few_shots": 0
},
"lighteval|agieval:logiqa-zh|0": {
"hashes": {
"hash_examples": "620d6888b6012ea5",
"hash_full_prompts": "79066930a44b0f7e",
"hash_input_tokens": "2fe19dd623007024",
"hash_cont_tokens": "16ad57705a79dec4"
},
"truncated": 0,
"non_truncated": 651,
"padded": 2585,
"non_padded": 19,
"effective_few_shots": 0.0,
"num_truncated_few_shots": 0
},
"lighteval|agieval:lsat-ar|0": {
"hashes": {
"hash_examples": "627c8f5ccd5da209",
"hash_full_prompts": "254286f37d4a76ce",
"hash_input_tokens": "dcb768476dabfd30",
"hash_cont_tokens": "32e72f9ac5e990db"
},
"truncated": 0,
"non_truncated": 230,
"padded": 1139,
"non_padded": 11,
"effective_few_shots": 0.0,
"num_truncated_few_shots": 0
},
"lighteval|agieval:lsat-lr|0": {
"hashes": {
"hash_examples": "794641c86de172f5",
"hash_full_prompts": "cf1badbb8c42f6a8",
"hash_input_tokens": "f46eacac0dc8f43d",
"hash_cont_tokens": "f59d4751382d6cd2"
},
"truncated": 0,
"non_truncated": 510,
"padded": 2527,
"non_padded": 23,
"effective_few_shots": 0.0,
"num_truncated_few_shots": 0
},
"lighteval|agieval:lsat-rc|0": {
"hashes": {
"hash_examples": "35981ed917ea01cf",
"hash_full_prompts": "5fbc2eae9474469b",
"hash_input_tokens": "29375d042cf27c7e",
"hash_cont_tokens": "3e5cd22ff2929a47"
},
"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": "171c266251542e36",
"hash_input_tokens": "1ad83cc18fd43db0",
"hash_cont_tokens": "3bc244ff75c1a591"
},
"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": "66bc76f2704c6ca7",
"hash_input_tokens": "afd505d4ceeeaa45",
"hash_cont_tokens": "3bc244ff75c1a591"
},
"truncated": 0,
"non_truncated": 206,
"padded": 821,
"non_padded": 0,
"effective_few_shots": 0.0,
"num_truncated_few_shots": 0
},
"lighteval|agieval:sat-math|0": {
"hashes": {
"hash_examples": "01db7291603fc1a0",
"hash_full_prompts": "6016bbecd8642dbe",
"hash_input_tokens": "86192e0452c1707e",
"hash_cont_tokens": "5175b61accc0c5d1"
},
"truncated": 0,
"non_truncated": 220,
"padded": 879,
"non_padded": 1,
"effective_few_shots": 0.0,
"num_truncated_few_shots": 0
}
},
"summary_general": {
"hashes": {
"hash_examples": "da3af66181f18ddf",
"hash_full_prompts": "3554a21b6b69cbf8",
"hash_input_tokens": "4abd38d6a674e0cd",
"hash_cont_tokens": "0fc139d3b2070461"
},
"truncated": 0,
"non_truncated": 5151,
"padded": 21782,
"non_padded": 82,
"num_truncated_few_shots": 0
}
}