lewtun's picture
lewtun HF staff
Upload eval_results/openchat/openchat-3.5-0106/main/agieval/results_2024-03-28T16-28-08.688920.json with huggingface_hub
a9251bd 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": 1616328.065043648,
"end_time": 1616595.808001383,
"total_evaluation_time_secondes": "267.7429577349685",
"model_name": "openchat/openchat-3.5-0106",
"model_sha": "9619fb7d2a8e25fa6b0633c0f57f7f4aa79b45c4",
"model_dtype": "torch.bfloat16",
"model_size": "13.61 GB",
"config": null
},
"results": {
"lighteval|agieval:aqua-rat|0": {
"acc": 0.2795275590551181,
"acc_stderr": 0.02821374533845074,
"acc_norm": 0.2795275590551181,
"acc_norm_stderr": 0.02821374533845074
},
"lighteval|agieval:gaokao-biology|0": {
"acc": 0.4,
"acc_stderr": 0.03388694968349424,
"acc_norm": 0.40476190476190477,
"acc_norm_stderr": 0.03395252139627751
},
"lighteval|agieval:gaokao-chemistry|0": {
"acc": 0.2898550724637681,
"acc_stderr": 0.03161042514455282,
"acc_norm": 0.30917874396135264,
"acc_norm_stderr": 0.03219986494000449
},
"lighteval|agieval:gaokao-chinese|0": {
"acc": 0.3252032520325203,
"acc_stderr": 0.029928220038850473,
"acc_norm": 0.3333333333333333,
"acc_norm_stderr": 0.030116930096841722
},
"lighteval|agieval:gaokao-english|0": {
"acc": 0.6895424836601307,
"acc_stderr": 0.02649303322514589,
"acc_norm": 0.6797385620915033,
"acc_norm_stderr": 0.02671611838015684
},
"lighteval|agieval:gaokao-geography|0": {
"acc": 0.49748743718592964,
"acc_stderr": 0.03553300407972604,
"acc_norm": 0.49748743718592964,
"acc_norm_stderr": 0.03553300407972604
},
"lighteval|agieval:gaokao-history|0": {
"acc": 0.46808510638297873,
"acc_stderr": 0.03261936918467382,
"acc_norm": 0.4723404255319149,
"acc_norm_stderr": 0.03263597118409769
},
"lighteval|agieval:gaokao-mathqa|0": {
"acc": 0.2962962962962963,
"acc_stderr": 0.02440753988290111,
"acc_norm": 0.2905982905982906,
"acc_norm_stderr": 0.02426937659448
},
"lighteval|agieval:gaokao-physics|0": {
"acc": 0.37,
"acc_stderr": 0.03422508997679329,
"acc_norm": 0.39,
"acc_norm_stderr": 0.03457567623250012
},
"lighteval|agieval:logiqa-en|0": {
"acc": 0.38402457757296465,
"acc_stderr": 0.019076755948732343,
"acc_norm": 0.3763440860215054,
"acc_norm_stderr": 0.019002397214689486
},
"lighteval|agieval:logiqa-zh|0": {
"acc": 0.37327188940092165,
"acc_stderr": 0.018971232715472068,
"acc_norm": 0.3763440860215054,
"acc_norm_stderr": 0.01900239721468949
},
"lighteval|agieval:lsat-ar|0": {
"acc": 0.18695652173913044,
"acc_stderr": 0.025763772398512335,
"acc_norm": 0.1782608695652174,
"acc_norm_stderr": 0.025291655246273914
},
"lighteval|agieval:lsat-lr|0": {
"acc": 0.5352941176470588,
"acc_stderr": 0.02210682784673137,
"acc_norm": 0.515686274509804,
"acc_norm_stderr": 0.022151201291314516
},
"lighteval|agieval:lsat-rc|0": {
"acc": 0.5799256505576208,
"acc_stderr": 0.030149620080212002,
"acc_norm": 0.5390334572490706,
"acc_norm_stderr": 0.030449149512372407
},
"lighteval|agieval:sat-en|0": {
"acc": 0.7961165048543689,
"acc_stderr": 0.028138595623668775,
"acc_norm": 0.7718446601941747,
"acc_norm_stderr": 0.029309157873241714
},
"lighteval|agieval:sat-en-without-passage|0": {
"acc": 0.4320388349514563,
"acc_stderr": 0.0345974255383149,
"acc_norm": 0.41262135922330095,
"acc_norm_stderr": 0.03438412659410013
},
"lighteval|agieval:sat-math|0": {
"acc": 0.35,
"acc_stderr": 0.032230618755899304,
"acc_norm": 0.3,
"acc_norm_stderr": 0.03096617686426667
},
"lighteval|agieval:_average|0": {
"acc": 0.4266838414000154,
"acc_stderr": 0.028703072086007732,
"acc_norm": 0.4192412381943485,
"acc_norm_stderr": 0.028751145297263737
},
"all": {
"acc": 0.4266838414000154,
"acc_stderr": 0.028703072086007732,
"acc_norm": 0.4192412381943485,
"acc_norm_stderr": 0.028751145297263737
}
},
"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": "c885824d200848ff",
"hash_input_tokens": "bbc9473dbbe6f16c",
"hash_cont_tokens": "7c2bcf33ed1e5ae3"
},
"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": "a57b68a06f7c5dad",
"hash_input_tokens": "ca1fe44a4eaeed8d",
"hash_cont_tokens": "b3febf85776696e1"
},
"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": "77b311499beca56b",
"hash_input_tokens": "43896e11a60e81d3",
"hash_cont_tokens": "711fb41221b6515e"
},
"truncated": 0,
"non_truncated": 207,
"padded": 830,
"non_padded": 1,
"effective_few_shots": 0.0,
"num_truncated_few_shots": 0
},
"lighteval|agieval:gaokao-chinese|0": {
"hashes": {
"hash_examples": "1010b21fde4726ab",
"hash_full_prompts": "765b83dc3fe58e0e",
"hash_input_tokens": "c2e6ac114faa28b7",
"hash_cont_tokens": "393b1820b8f4534f"
},
"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": "2d90914067cbddb2",
"hash_input_tokens": "19ee1ddb098e0782",
"hash_cont_tokens": "dd72ceb1d7224598"
},
"truncated": 0,
"non_truncated": 306,
"padded": 1222,
"non_padded": 2,
"effective_few_shots": 0.0,
"num_truncated_few_shots": 0
},
"lighteval|agieval:gaokao-geography|0": {
"hashes": {
"hash_examples": "ec3a021e37650e7d",
"hash_full_prompts": "26abf6b8b06b03fd",
"hash_input_tokens": "9c63079da9deb525",
"hash_cont_tokens": "e06462bcee629ea8"
},
"truncated": 0,
"non_truncated": 199,
"padded": 794,
"non_padded": 2,
"effective_few_shots": 0.0,
"num_truncated_few_shots": 0
},
"lighteval|agieval:gaokao-history|0": {
"hashes": {
"hash_examples": "b3fad1596f1ae1f9",
"hash_full_prompts": "d22e901442960499",
"hash_input_tokens": "cd1d7e17c8e3016d",
"hash_cont_tokens": "87cce58a4ec6cfd8"
},
"truncated": 0,
"non_truncated": 235,
"padded": 935,
"non_padded": 5,
"effective_few_shots": 0.0,
"num_truncated_few_shots": 0
},
"lighteval|agieval:gaokao-mathqa|0": {
"hashes": {
"hash_examples": "1d1088556861b0b0",
"hash_full_prompts": "8f130ed7923a2e96",
"hash_input_tokens": "d4e27a91afe699a4",
"hash_cont_tokens": "771402d59229cbae"
},
"truncated": 0,
"non_truncated": 351,
"padded": 1401,
"non_padded": 3,
"effective_few_shots": 0.0,
"num_truncated_few_shots": 0
},
"lighteval|agieval:gaokao-physics|0": {
"hashes": {
"hash_examples": "eb05f035c7bfca2f",
"hash_full_prompts": "04c26f6aa4512fa0",
"hash_input_tokens": "c571bd43f31938ce",
"hash_cont_tokens": "f1574dddbe4231e1"
},
"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": "1e7fa6f1e62bea8b",
"hash_input_tokens": "c349474caa787f2c",
"hash_cont_tokens": "106c1564fdd5ff8e"
},
"truncated": 0,
"non_truncated": 651,
"padded": 2597,
"non_padded": 7,
"effective_few_shots": 0.0,
"num_truncated_few_shots": 0
},
"lighteval|agieval:logiqa-zh|0": {
"hashes": {
"hash_examples": "620d6888b6012ea5",
"hash_full_prompts": "f5e4b12f2be2730a",
"hash_input_tokens": "7443875e78dae670",
"hash_cont_tokens": "22d3640f03c44bb0"
},
"truncated": 0,
"non_truncated": 651,
"padded": 2581,
"non_padded": 23,
"effective_few_shots": 0.0,
"num_truncated_few_shots": 0
},
"lighteval|agieval:lsat-ar|0": {
"hashes": {
"hash_examples": "627c8f5ccd5da209",
"hash_full_prompts": "93f01bfefd21f036",
"hash_input_tokens": "cd6e0cee27c3c3e4",
"hash_cont_tokens": "9e13af9ad8f5f78e"
},
"truncated": 0,
"non_truncated": 230,
"padded": 1140,
"non_padded": 10,
"effective_few_shots": 0.0,
"num_truncated_few_shots": 0
},
"lighteval|agieval:lsat-lr|0": {
"hashes": {
"hash_examples": "794641c86de172f5",
"hash_full_prompts": "8e81a99c7521258c",
"hash_input_tokens": "09e76ba415ce4540",
"hash_cont_tokens": "86333847359ceee5"
},
"truncated": 0,
"non_truncated": 510,
"padded": 2525,
"non_padded": 25,
"effective_few_shots": 0.0,
"num_truncated_few_shots": 0
},
"lighteval|agieval:lsat-rc|0": {
"hashes": {
"hash_examples": "35981ed917ea01cf",
"hash_full_prompts": "b6e8d1adf72e9fb4",
"hash_input_tokens": "78bda8444d556179",
"hash_cont_tokens": "cb47c6b984067525"
},
"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": "b9081e0a4bf5d97f",
"hash_input_tokens": "16dc5e2c7544b9f1",
"hash_cont_tokens": "cb01422bf828aefe"
},
"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": "f1362aa3ba355eaa",
"hash_input_tokens": "c4236dd09d0088d9",
"hash_cont_tokens": "cb01422bf828aefe"
},
"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": "8dab33ab73deb698",
"hash_input_tokens": "e4d4e2e413144ff5",
"hash_cont_tokens": "0c4980b69a75cb83"
},
"truncated": 0,
"non_truncated": 220,
"padded": 876,
"non_padded": 4,
"effective_few_shots": 0.0,
"num_truncated_few_shots": 0
}
},
"summary_general": {
"hashes": {
"hash_examples": "da3af66181f18ddf",
"hash_full_prompts": "37ef9da1700eed47",
"hash_input_tokens": "3a23d7f630bcf75b",
"hash_cont_tokens": "7f70e41f6e93ac40"
},
"truncated": 0,
"non_truncated": 5151,
"padded": 21772,
"non_padded": 92,
"num_truncated_few_shots": 0
}
}