{ "config_general": { "lighteval_sha": "?", "num_fewshot_seeds": 1, "override_batch_size": 4, "max_samples": null, "job_id": "", "start_time": 23288.638250584, "end_time": 34586.574863959, "total_evaluation_time_secondes": "11297.936613375", "model_name": "abhishek/autotrain-llama3-70b-orpo-v1", "model_sha": "053236c6846cc561c1503ba05e2b28c94855a432", "model_dtype": "torch.float16", "model_size": "131.73 GB", "config": null }, "results": { "extended|ifeval|0": { "prompt_level_strict_acc": 0.4879852125693161, "prompt_level_strict_acc_stderr": 0.0215103611934391, "inst_level_strict_acc": 0.617505995203837, "inst_level_strict_acc_stderr": 0.0005195895575057764, "prompt_level_loose_acc": 0.5693160813308688, "prompt_level_loose_acc_stderr": 0.021308808857898928, "inst_level_loose_acc": 0.6870503597122302, "inst_level_loose_acc_stderr": 0.0004997429710027276 }, "all": { "prompt_level_strict_acc": 0.4879852125693161, "prompt_level_strict_acc_stderr": 0.0215103611934391, "inst_level_strict_acc": 0.617505995203837, "inst_level_strict_acc_stderr": 0.0005195895575057764, "prompt_level_loose_acc": 0.5693160813308688, "prompt_level_loose_acc_stderr": 0.021308808857898928, "inst_level_loose_acc": 0.6870503597122302, "inst_level_loose_acc_stderr": 0.0004997429710027276 } }, "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": "16c7deaf8d8cfab4", "hash_cont_tokens": "4b479691f3ccd4e6" }, "truncated": 541, "non_truncated": 0, "padded": 115, "non_padded": 426, "effective_few_shots": 0.0, "num_truncated_few_shots": 0 } }, "summary_general": { "hashes": { "hash_examples": "ea046ab2c6fc5928", "hash_full_prompts": "45f8422f6ad2da79", "hash_input_tokens": "91a30a216e4e8fc8", "hash_cont_tokens": "0d7e2fc431561e24" }, "truncated": 541, "non_truncated": 0, "padded": 115, "non_padded": 426, "num_truncated_few_shots": 0 } }