open-r1-eval-leaderboard
/
eval_results
/abhishek
/autotrain-mixtral-8x7b-orpo-v1
/main
/winogrande
/results_2024-05-01T17-41-08.262432.json
{ | |
"config_general": { | |
"lighteval_sha": "?", | |
"num_fewshot_seeds": 1, | |
"override_batch_size": 4, | |
"max_samples": null, | |
"job_id": "", | |
"start_time": 77686.102001593, | |
"end_time": 79985.516959794, | |
"total_evaluation_time_secondes": "2299.4149582009995", | |
"model_name": "abhishek/autotrain-mixtral-8x7b-orpo-v1", | |
"model_sha": "a8be37cf01ad767a0c71e0ba3af29c0b3ebcb559", | |
"model_dtype": "torch.bfloat16", | |
"model_size": "87.49 GB", | |
"config": null | |
}, | |
"results": { | |
"leaderboard|winogrande|5": { | |
"acc": 0.7821625887924231, | |
"acc_stderr": 0.011601066079939324 | |
}, | |
"all": { | |
"acc": 0.7821625887924231, | |
"acc_stderr": 0.011601066079939324 | |
} | |
}, | |
"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": "3eb9a6f4227aee6f", | |
"hash_cont_tokens": "54383825542e097b" | |
}, | |
"truncated": 0, | |
"non_truncated": 1267, | |
"padded": 2403, | |
"non_padded": 131, | |
"effective_few_shots": 5.0, | |
"num_truncated_few_shots": 0 | |
} | |
}, | |
"summary_general": { | |
"hashes": { | |
"hash_examples": "b9a49975cc41fab7", | |
"hash_full_prompts": "2f908b2b9b5ec583", | |
"hash_input_tokens": "db7ee210efecf1fd", | |
"hash_cont_tokens": "99f29aedfb31c4b2" | |
}, | |
"truncated": 0, | |
"non_truncated": 1267, | |
"padded": 2403, | |
"non_padded": 131, | |
"num_truncated_few_shots": 0 | |
} | |
} |