{ "config_general": { "lighteval_sha": "?", "num_fewshot_seeds": 1, "override_batch_size": 4, "max_samples": null, "job_id": "", "start_time": 175257.708535006, "end_time": 186107.383512892, "total_evaluation_time_secondes": "10849.674977885996", "model_name": "abhishek/autotrain-mixtral-8x7b-orpo-v2", "model_sha": "dcc2c4efe12c26fc1ec211f68cc139d61de5ce84", "model_dtype": "torch.bfloat16", "model_size": "87.49 GB", "config": null }, "results": { "extended|ifeval|0": { "prompt_level_strict_acc": 0.3567467652495379, "prompt_level_strict_acc_stderr": 0.020614562936479914, "inst_level_strict_acc": 0.47601918465227816, "inst_level_strict_acc_stderr": 0.0005065496192489137, "prompt_level_loose_acc": 0.43253234750462105, "prompt_level_loose_acc_stderr": 0.02131979239817807, "inst_level_loose_acc": 0.5443645083932853, "inst_level_loose_acc_stderr": 0.0005360949430588119 }, "all": { "prompt_level_strict_acc": 0.3567467652495379, "prompt_level_strict_acc_stderr": 0.020614562936479914, "inst_level_strict_acc": 0.47601918465227816, "inst_level_strict_acc_stderr": 0.0005065496192489137, "prompt_level_loose_acc": 0.43253234750462105, "prompt_level_loose_acc_stderr": 0.02131979239817807, "inst_level_loose_acc": 0.5443645083932853, "inst_level_loose_acc_stderr": 0.0005360949430588119 } }, "versions": { "extended|ifeval|0": 0 }, "config_tasks": { "extended|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": [ "extended" ], "original_num_docs": 541, "effective_num_docs": 541, "trust_dataset": null, "must_remove_duplicate_docs": null } }, "summary_tasks": { "extended|ifeval|0": { "hashes": { "hash_examples": "e99cbf567588d7c6", "hash_full_prompts": "7ea7bf2a8edba8f4", "hash_input_tokens": "d47b7c7e5ff179c6", "hash_cont_tokens": "ddfa5f22570bf01d" }, "truncated": 541, "non_truncated": 0, "padded": 123, "non_padded": 418, "effective_few_shots": 0.0, "num_truncated_few_shots": 0 } }, "summary_general": { "hashes": { "hash_examples": "ea046ab2c6fc5928", "hash_full_prompts": "45f8422f6ad2da79", "hash_input_tokens": "7f002d5843c6bae7", "hash_cont_tokens": "c17d667172ebd9ee" }, "truncated": 541, "non_truncated": 0, "padded": 123, "non_padded": 418, "num_truncated_few_shots": 0 } }