open-r1-eval-leaderboard
/
eval_results
/alignment-handbook
/zephyr-2b-gemma-dpo-v1
/main
/ifeval
/results_2024-03-05T08-32-16.063626.json
{ | |
"config_general": { | |
"lighteval_sha": "?", | |
"num_fewshot_seeds": 1, | |
"override_batch_size": 4, | |
"max_samples": null, | |
"job_id": "", | |
"start_time": 2116458.485149511, | |
"end_time": 2117098.72181407, | |
"total_evaluation_time_secondes": "640.2366645587608", | |
"model_name": "alignment-handbook/zephyr-2b-gemma-dpo-v1", | |
"model_sha": "ac25a047a4550623bd94295d5e7ead1bcd5fc831", | |
"model_dtype": "torch.bfloat16", | |
"model_size": "4.68 GB", | |
"config": null | |
}, | |
"results": { | |
"custom|ifeval|0": { | |
"prompt_level_strict_acc": 0.2255083179297597, | |
"prompt_level_strict_acc_stderr": 0.0179842686644956, | |
"inst_level_strict_acc": 0.36930455635491605, | |
"inst_level_strict_acc_stderr": 0.0004957477481426761, | |
"prompt_level_loose_acc": 0.23290203327171904, | |
"prompt_level_loose_acc_stderr": 0.018189266074091773, | |
"inst_level_loose_acc": 0.3776978417266187, | |
"inst_level_loose_acc_stderr": 0.0005043819490094154 | |
} | |
}, | |
"versions": { | |
"custom|ifeval|0": 0 | |
}, | |
"config_tasks": { | |
"custom|ifeval": { | |
"name": "ifeval", | |
"prompt_function": "ifeval_prompt", | |
"hf_repo": "wis-k/instruction-following-eval", | |
"hf_subset": "default", | |
"metric": [ | |
"ifeval_metric" | |
], | |
"hf_avail_splits": [ | |
"train" | |
], | |
"evaluation_splits": [ | |
"train" | |
], | |
"few_shots_split": "train", | |
"few_shots_select": "random_sampling", | |
"generation_size": 1280, | |
"stop_sequence": [], | |
"output_regex": null, | |
"frozen": false, | |
"suite": [ | |
"custom" | |
], | |
"original_num_docs": 541, | |
"effective_num_docs": 541 | |
} | |
}, | |
"summary_tasks": { | |
"custom|ifeval|0": { | |
"hashes": { | |
"hash_examples": "e99cbf567588d7c6", | |
"hash_full_prompts": "dffcf9a3b5dd7b3d", | |
"hash_input_tokens": "697d713cee490081", | |
"hash_cont_tokens": "35c5135106f25ca3" | |
}, | |
"truncated": 0, | |
"non_truncated": 541, | |
"padded": 0, | |
"non_padded": 541, | |
"effective_few_shots": 0.0, | |
"num_truncated_few_shots": 0 | |
} | |
}, | |
"summary_general": { | |
"hashes": { | |
"hash_examples": "ea046ab2c6fc5928", | |
"hash_full_prompts": "74abf332fe1a119c", | |
"hash_input_tokens": "369e8568d4bc5b04", | |
"hash_cont_tokens": "a635c9b8adcb142f" | |
}, | |
"truncated": 0, | |
"non_truncated": 541, | |
"padded": 0, | |
"non_padded": 541, | |
"num_truncated_few_shots": 0 | |
} | |
} |