{ "config_general": { "lighteval_sha": "?", "num_fewshot_seeds": 1, "override_batch_size": 4, "max_samples": null, "job_id": "", "start_time": 1189727.731472392, "end_time": 1190263.645667073, "total_evaluation_time_secondes": "535.9141946809832", "model_name": "HuggingFaceH4/qwen-1.5-1.8b-dpo", "model_sha": "c9be03ba1ac690aff6b78bc52ef87f574f553020", "model_dtype": "torch.bfloat16", "model_size": "3.79 GB", "config": null }, "results": { "custom|ifeval|0": { "prompt_level_strict_acc": 0.19593345656192238, "prompt_level_strict_acc_stderr": 0.01708061155345544, "inst_level_strict_acc": 0.3249400479616307, "inst_level_strict_acc_stderr": 0.0004810850886803311, "prompt_level_loose_acc": 0.21256931608133087, "prompt_level_loose_acc_stderr": 0.017605954482106626, "inst_level_loose_acc": 0.34532374100719426, "inst_level_loose_acc_stderr": 0.00048674963584420294 } }, "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": "7ea7bf2a8edba8f4", "hash_input_tokens": "406f216e2e739d61", "hash_cont_tokens": "8f845a82ed683f12" }, "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": "45f8422f6ad2da79", "hash_input_tokens": "7be1d930c9579e40", "hash_cont_tokens": "f491de112ec511a1" }, "truncated": 0, "non_truncated": 541, "padded": 0, "non_padded": 541, "num_truncated_few_shots": 0 } }