open-r1-eval-leaderboard / eval_results /databricks /dbrx-base /main /agieval /results_2024-03-30T21-38-32.137846.json
lewtun's picture
lewtun HF staff
Upload eval_results/databricks/dbrx-base/main/agieval/results_2024-03-30T21-38-32.137846.json with huggingface_hub
0426020 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": 1422585.581207942,
"end_time": 1428994.705335767,
"total_evaluation_time_secondes": "6409.124127825024",
"model_name": "databricks/dbrx-base",
"model_sha": "4e1f4c3e5452762b62b8cf3c2eee863c52da7903",
"model_dtype": "torch.bfloat16",
"model_size": "245.12 GB",
"config": null
},
"results": {
"lighteval|agieval:aqua-rat|0": {
"acc": 0.2677165354330709,
"acc_stderr": 0.02783664886644535,
"acc_norm": 0.2440944881889764,
"acc_norm_stderr": 0.027005516126961032
},
"lighteval|agieval:gaokao-biology|0": {
"acc": 0.3523809523809524,
"acc_stderr": 0.03304401999334817,
"acc_norm": 0.4095238095238095,
"acc_norm_stderr": 0.03401477718256436
},
"lighteval|agieval:gaokao-chemistry|0": {
"acc": 0.3188405797101449,
"acc_stderr": 0.03246964709878484,
"acc_norm": 0.30917874396135264,
"acc_norm_stderr": 0.03219986494000449
},
"lighteval|agieval:gaokao-chinese|0": {
"acc": 0.33739837398373984,
"acc_stderr": 0.030207494084156634,
"acc_norm": 0.33739837398373984,
"acc_norm_stderr": 0.03020749408415664
},
"lighteval|agieval:gaokao-english|0": {
"acc": 0.7222222222222222,
"acc_stderr": 0.02564686309713791,
"acc_norm": 0.7516339869281046,
"acc_norm_stderr": 0.02473998135511359
},
"lighteval|agieval:gaokao-geography|0": {
"acc": 0.5829145728643216,
"acc_stderr": 0.035041474244182344,
"acc_norm": 0.592964824120603,
"acc_norm_stderr": 0.03491385802519052
},
"lighteval|agieval:gaokao-history|0": {
"acc": 0.6468085106382979,
"acc_stderr": 0.031245325202761926,
"acc_norm": 0.5957446808510638,
"acc_norm_stderr": 0.03208115750788684
},
"lighteval|agieval:gaokao-mathqa|0": {
"acc": 0.2905982905982906,
"acc_stderr": 0.024269376594479995,
"acc_norm": 0.2934472934472934,
"acc_norm_stderr": 0.024339032696810918
},
"lighteval|agieval:gaokao-physics|0": {
"acc": 0.42,
"acc_stderr": 0.034987434930487206,
"acc_norm": 0.395,
"acc_norm_stderr": 0.03465370682892271
},
"lighteval|agieval:logiqa-en|0": {
"acc": 0.36251920122887865,
"acc_stderr": 0.01885568797958507,
"acc_norm": 0.36251920122887865,
"acc_norm_stderr": 0.01885568797958506
},
"lighteval|agieval:logiqa-zh|0": {
"acc": 0.35176651305683565,
"acc_stderr": 0.01872993627442735,
"acc_norm": 0.3563748079877112,
"acc_norm_stderr": 0.01878509246182
},
"lighteval|agieval:lsat-ar|0": {
"acc": 0.21739130434782608,
"acc_stderr": 0.02725685083881996,
"acc_norm": 0.19130434782608696,
"acc_norm_stderr": 0.025991852462828483
},
"lighteval|agieval:lsat-lr|0": {
"acc": 0.5490196078431373,
"acc_stderr": 0.022055345548930266,
"acc_norm": 0.43529411764705883,
"acc_norm_stderr": 0.02197574787518572
},
"lighteval|agieval:lsat-rc|0": {
"acc": 0.6877323420074349,
"acc_stderr": 0.02830778120469435,
"acc_norm": 0.5427509293680297,
"acc_norm_stderr": 0.03043051529856916
},
"lighteval|agieval:sat-en|0": {
"acc": 0.8009708737864077,
"acc_stderr": 0.02788622643950503,
"acc_norm": 0.7330097087378641,
"acc_norm_stderr": 0.030897665523458163
},
"lighteval|agieval:sat-en-without-passage|0": {
"acc": 0.5388349514563107,
"acc_stderr": 0.03481602144131183,
"acc_norm": 0.41262135922330095,
"acc_norm_stderr": 0.03438412659410014
},
"lighteval|agieval:sat-math|0": {
"acc": 0.4681818181818182,
"acc_stderr": 0.03371838809107288,
"acc_norm": 0.39090909090909093,
"acc_norm_stderr": 0.03297288034347065
},
"lighteval|agieval:_average|0": {
"acc": 0.46560568527880525,
"acc_stderr": 0.028610265995890068,
"acc_norm": 0.4325746919960567,
"acc_norm_stderr": 0.02873229160509579
},
"all": {
"acc": 0.46560568527880525,
"acc_stderr": 0.028610265995890068,
"acc_norm": 0.4325746919960567,
"acc_norm_stderr": 0.02873229160509579
}
},
"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": "f09607f69e5b7525",
"hash_input_tokens": "5e845ed6a5a59a8b",
"hash_cont_tokens": "13c4460922661f6d"
},
"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": "f262eaf4a72db963",
"hash_input_tokens": "15e32c0bb9018595",
"hash_cont_tokens": "f7ca0af9c4bb24f3"
},
"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": "47f2e649f58d9da5",
"hash_input_tokens": "79e0c48ebebf97e6",
"hash_cont_tokens": "fabcd867b980328e"
},
"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": "1010b21fde4726ab",
"hash_input_tokens": "4d94735847efad72",
"hash_cont_tokens": "7758ed9477088621"
},
"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": "4864e492a350ae93",
"hash_input_tokens": "4a838d8e9a91fe62",
"hash_cont_tokens": "7c77a755a025b7d3"
},
"truncated": 0,
"non_truncated": 306,
"padded": 1218,
"non_padded": 6,
"effective_few_shots": 0.0,
"num_truncated_few_shots": 0
},
"lighteval|agieval:gaokao-geography|0": {
"hashes": {
"hash_examples": "ec3a021e37650e7d",
"hash_full_prompts": "ec3a021e37650e7d",
"hash_input_tokens": "9c9a81cac8b66719",
"hash_cont_tokens": "4ad67a82d321a083"
},
"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": "b3fad1596f1ae1f9",
"hash_input_tokens": "06e991bbc67fe0ad",
"hash_cont_tokens": "5773d3e5394a127f"
},
"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": "1d1088556861b0b0",
"hash_input_tokens": "cc5894dcbd8929a6",
"hash_cont_tokens": "074ce57bdfb21a5b"
},
"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": "eb05f035c7bfca2f",
"hash_input_tokens": "85a92d12f41170d5",
"hash_cont_tokens": "f8182436964f9017"
},
"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": "0a688a45f69c21e0",
"hash_input_tokens": "aa01c09fda59aef4",
"hash_cont_tokens": "86626d7a51d9ba03"
},
"truncated": 0,
"non_truncated": 651,
"padded": 2599,
"non_padded": 5,
"effective_few_shots": 0.0,
"num_truncated_few_shots": 0
},
"lighteval|agieval:logiqa-zh|0": {
"hashes": {
"hash_examples": "620d6888b6012ea5",
"hash_full_prompts": "620d6888b6012ea5",
"hash_input_tokens": "1695856d2ea03235",
"hash_cont_tokens": "5c235458a89a73e9"
},
"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": "627c8f5ccd5da209",
"hash_input_tokens": "d8a2fef5ce117c68",
"hash_cont_tokens": "76a773001205abb5"
},
"truncated": 0,
"non_truncated": 230,
"padded": 1147,
"non_padded": 3,
"effective_few_shots": 0.0,
"num_truncated_few_shots": 0
},
"lighteval|agieval:lsat-lr|0": {
"hashes": {
"hash_examples": "794641c86de172f5",
"hash_full_prompts": "794641c86de172f5",
"hash_input_tokens": "e738982173c1244d",
"hash_cont_tokens": "04ee8888f6032d56"
},
"truncated": 0,
"non_truncated": 510,
"padded": 2519,
"non_padded": 31,
"effective_few_shots": 0.0,
"num_truncated_few_shots": 0
},
"lighteval|agieval:lsat-rc|0": {
"hashes": {
"hash_examples": "35981ed917ea01cf",
"hash_full_prompts": "35981ed917ea01cf",
"hash_input_tokens": "db2fbdf3c4b6aad0",
"hash_cont_tokens": "d07111c2a7dfec96"
},
"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": "041c39c646536a1e",
"hash_input_tokens": "7431fc1d02cbfbeb",
"hash_cont_tokens": "9e81a3554c11cb1d"
},
"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": "e4d9284367dff68f",
"hash_input_tokens": "3d8ef71036a52557",
"hash_cont_tokens": "9e81a3554c11cb1d"
},
"truncated": 0,
"non_truncated": 206,
"padded": 819,
"non_padded": 2,
"effective_few_shots": 0.0,
"num_truncated_few_shots": 0
},
"lighteval|agieval:sat-math|0": {
"hashes": {
"hash_examples": "01db7291603fc1a0",
"hash_full_prompts": "01db7291603fc1a0",
"hash_input_tokens": "82caa2d74dee3221",
"hash_cont_tokens": "b61900fe25c4c91d"
},
"truncated": 0,
"non_truncated": 220,
"padded": 878,
"non_padded": 2,
"effective_few_shots": 0.0,
"num_truncated_few_shots": 0
}
},
"summary_general": {
"hashes": {
"hash_examples": "da3af66181f18ddf",
"hash_full_prompts": "da3af66181f18ddf",
"hash_input_tokens": "513e4104fbe52ac3",
"hash_cont_tokens": "0f1f5acaf948f318"
},
"truncated": 0,
"non_truncated": 5151,
"padded": 21801,
"non_padded": 63,
"num_truncated_few_shots": 0
}
}