open-r1-eval-leaderboard
/
eval_results
/abhishek
/autotrain-llama3-70b-orpo-v1
/main
/winogrande
/results_2024-05-03T07-44-18.999816.json
{ | |
"config_general": { | |
"lighteval_sha": "?", | |
"num_fewshot_seeds": 1, | |
"override_batch_size": 4, | |
"max_samples": null, | |
"job_id": "", | |
"start_time": 293245.717943439, | |
"end_time": 296195.95324294, | |
"total_evaluation_time_secondes": "2950.235299500986", | |
"model_name": "abhishek/autotrain-llama3-70b-orpo-v1", | |
"model_sha": "053236c6846cc561c1503ba05e2b28c94855a432", | |
"model_dtype": "torch.float16", | |
"model_size": "131.73 GB", | |
"config": null | |
}, | |
"results": { | |
"leaderboard|winogrande|5": { | |
"acc": 0.8263614838200474, | |
"acc_stderr": 0.010646116480330996 | |
}, | |
"all": { | |
"acc": 0.8263614838200474, | |
"acc_stderr": 0.010646116480330996 | |
} | |
}, | |
"versions": { | |
"leaderboard|winogrande|5": 0 | |
}, | |
"config_tasks": { | |
"leaderboard|winogrande": { | |
"name": "winogrande", | |
"prompt_function": "winogrande", | |
"hf_repo": "winogrande", | |
"hf_subset": "winogrande_xl", | |
"metric": [ | |
"loglikelihood_acc" | |
], | |
"hf_avail_splits": [ | |
"train", | |
"test", | |
"validation" | |
], | |
"evaluation_splits": [ | |
"validation" | |
], | |
"few_shots_split": null, | |
"few_shots_select": "random_sampling", | |
"generation_size": -1, | |
"stop_sequence": [ | |
"\n" | |
], | |
"output_regex": null, | |
"frozen": false, | |
"suite": [ | |
"leaderboard" | |
], | |
"original_num_docs": 1267, | |
"effective_num_docs": 1267, | |
"trust_dataset": true, | |
"must_remove_duplicate_docs": null | |
} | |
}, | |
"summary_tasks": { | |
"leaderboard|winogrande|5": { | |
"hashes": { | |
"hash_examples": "087d5d1a1afd4c7b", | |
"hash_full_prompts": "29e044bcf40d6a6d", | |
"hash_input_tokens": "959564e102714b28", | |
"hash_cont_tokens": "81127b8a36b7a00f" | |
}, | |
"truncated": 0, | |
"non_truncated": 1267, | |
"padded": 2364, | |
"non_padded": 170, | |
"effective_few_shots": 5.0, | |
"num_truncated_few_shots": 0 | |
} | |
}, | |
"summary_general": { | |
"hashes": { | |
"hash_examples": "b9a49975cc41fab7", | |
"hash_full_prompts": "2f908b2b9b5ec583", | |
"hash_input_tokens": "03ee21d0107089ef", | |
"hash_cont_tokens": "1b54e36ca1d6e0d5" | |
}, | |
"truncated": 0, | |
"non_truncated": 1267, | |
"padded": 2364, | |
"non_padded": 170, | |
"num_truncated_few_shots": 0 | |
} | |
} |