lewtun's picture
lewtun HF staff
Upload eval_results/NousResearch/Hermes-2-Pro-Mistral-7B/main/agieval/results_2024-03-28T19-46-49.792931.json with huggingface_hub
4d8d0e1 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": 1251891.597231437,
"end_time": 1252194.99353289,
"total_evaluation_time_secondes": "303.3963014530018",
"model_name": "NousResearch/Hermes-2-Pro-Mistral-7B",
"model_sha": "4d50786bb33ce7c31697932a0ebe01fd8a373a4a",
"model_dtype": "torch.bfloat16",
"model_size": "13.99 GB",
"config": null
},
"results": {
"lighteval|agieval:aqua-rat|0": {
"acc": 0.2559055118110236,
"acc_stderr": 0.027434282297895834,
"acc_norm": 0.24803149606299213,
"acc_norm_stderr": 0.027151447091181707
},
"lighteval|agieval:gaokao-biology|0": {
"acc": 0.37142857142857144,
"acc_stderr": 0.03342272296374861,
"acc_norm": 0.32857142857142857,
"acc_norm_stderr": 0.03248939796876843
},
"lighteval|agieval:gaokao-chemistry|0": {
"acc": 0.2995169082125604,
"acc_stderr": 0.03191360682406663,
"acc_norm": 0.30434782608695654,
"acc_norm_stderr": 0.03205882236563528
},
"lighteval|agieval:gaokao-chinese|0": {
"acc": 0.35772357723577236,
"acc_stderr": 0.03062328176107229,
"acc_norm": 0.33739837398373984,
"acc_norm_stderr": 0.03020749408415665
},
"lighteval|agieval:gaokao-english|0": {
"acc": 0.7418300653594772,
"acc_stderr": 0.02505850331695815,
"acc_norm": 0.7352941176470589,
"acc_norm_stderr": 0.025261691219729494
},
"lighteval|agieval:gaokao-geography|0": {
"acc": 0.4472361809045226,
"acc_stderr": 0.035335047084973224,
"acc_norm": 0.45226130653266333,
"acc_norm_stderr": 0.03537112167025914
},
"lighteval|agieval:gaokao-history|0": {
"acc": 0.4425531914893617,
"acc_stderr": 0.032469569197899575,
"acc_norm": 0.41702127659574467,
"acc_norm_stderr": 0.03223276266711712
},
"lighteval|agieval:gaokao-mathqa|0": {
"acc": 0.24786324786324787,
"acc_stderr": 0.023079184079532435,
"acc_norm": 0.2621082621082621,
"acc_norm_stderr": 0.023507294979756403
},
"lighteval|agieval:gaokao-physics|0": {
"acc": 0.34,
"acc_stderr": 0.033580324461725736,
"acc_norm": 0.35,
"acc_norm_stderr": 0.0338114785302567
},
"lighteval|agieval:logiqa-en|0": {
"acc": 0.41781874039938555,
"acc_stderr": 0.019344895592714094,
"acc_norm": 0.4116743471582181,
"acc_norm_stderr": 0.019303191408121433
},
"lighteval|agieval:logiqa-zh|0": {
"acc": 0.3932411674347158,
"acc_stderr": 0.019159354078934838,
"acc_norm": 0.4039938556067588,
"acc_norm_stderr": 0.019246690834000654
},
"lighteval|agieval:lsat-ar|0": {
"acc": 0.2608695652173913,
"acc_stderr": 0.029017133559381264,
"acc_norm": 0.21739130434782608,
"acc_norm_stderr": 0.02725685083881996
},
"lighteval|agieval:lsat-lr|0": {
"acc": 0.5862745098039216,
"acc_stderr": 0.02182969935625459,
"acc_norm": 0.5117647058823529,
"acc_norm_stderr": 0.022155974669311143
},
"lighteval|agieval:lsat-rc|0": {
"acc": 0.6431226765799256,
"acc_stderr": 0.029264357329058684,
"acc_norm": 0.5390334572490706,
"acc_norm_stderr": 0.030449149512372407
},
"lighteval|agieval:sat-en|0": {
"acc": 0.7669902912621359,
"acc_stderr": 0.029526026912337848,
"acc_norm": 0.7135922330097088,
"acc_norm_stderr": 0.031574793744217594
},
"lighteval|agieval:sat-en-without-passage|0": {
"acc": 0.47572815533980584,
"acc_stderr": 0.034880344423561846,
"acc_norm": 0.38349514563106796,
"acc_norm_stderr": 0.0339602794458664
},
"lighteval|agieval:sat-math|0": {
"acc": 0.37272727272727274,
"acc_stderr": 0.03267395684838951,
"acc_norm": 0.3181818181818182,
"acc_norm_stderr": 0.03147385294171885
},
"lighteval|agieval:_average|0": {
"acc": 0.4365193901805348,
"acc_stderr": 0.028741899416970893,
"acc_norm": 0.4078918208620981,
"acc_norm_stderr": 0.028677193763017014
},
"all": {
"acc": 0.4365193901805348,
"acc_stderr": 0.028741899416970893,
"acc_norm": 0.4078918208620981,
"acc_norm_stderr": 0.028677193763017014
}
},
"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": "f0af1499da980246",
"hash_input_tokens": "01586a40d59a3028",
"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": "4027de4b1cdd1c67",
"hash_input_tokens": "3356b55c1770d4be",
"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": "39de31ab927f9675",
"hash_input_tokens": "be1a2c35ca21a256",
"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": "3b4313f1bd85fd2e",
"hash_input_tokens": "b9a6f600f1a44225",
"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": "547863254a606496",
"hash_input_tokens": "b485aadfee63f77a",
"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": "0a7cffbf555ab29e",
"hash_input_tokens": "5bf408915575d7cb",
"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": "b8aca4146c3435af",
"hash_input_tokens": "469990442dc541ac",
"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": "1441e196c635c040",
"hash_input_tokens": "388782ae768ee70a",
"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": "be15722274b1466d",
"hash_input_tokens": "6b2a1c4c5dd03798",
"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": "ca179e67bdc726a6",
"hash_input_tokens": "88b9eb8dd84c5f92",
"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": "55e305ed89c6e580",
"hash_input_tokens": "cdf0a9b880d48886",
"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": "59e010e22954d5b7",
"hash_input_tokens": "7a5e560985b7a87a",
"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": "efc3c1a3a1586d3e",
"hash_input_tokens": "ea471d0cc4d212d8",
"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": "b80e2b86e1eb0cea",
"hash_input_tokens": "698fdaec9f62ef4b",
"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": "4eb610121b313521",
"hash_input_tokens": "21ba0f545d8e5547",
"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": "532ea18906ff2f4e",
"hash_input_tokens": "5b22e8182489bfd3",
"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": "1422fad2e0cca51f",
"hash_input_tokens": "d158847b7d653fa6",
"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": "e89209d4ce68d63a",
"hash_input_tokens": "61b07fdce46e8b55",
"hash_cont_tokens": "b3bace8c3199f6d8"
},
"truncated": 0,
"non_truncated": 5151,
"padded": 21823,
"non_padded": 41,
"num_truncated_few_shots": 0
}
}