{ "config_general": { "lighteval_sha": "?", "num_fewshot_seeds": 1, "override_batch_size": 4, "max_samples": null, "job_id": "", "start_time": 1970888.213890348, "end_time": 1994849.647908654, "total_evaluation_time_secondes": "23961.43401830597", "model_name": "codellama/CodeLlama-70b-Instruct-hf", "model_sha": "b256b38c05ffdc3cb99f1a60211ee877d803cf5f", "model_dtype": "torch.bfloat16", "model_size": "128.64 GB", "config": null }, "results": { "custom|ifeval|0": { "prompt_level_strict_acc": 0.2902033271719039, "prompt_level_strict_acc_stderr": 0.019530856691222523, "inst_level_strict_acc": 0.434052757793765, "inst_level_strict_acc_stderr": 0.0005064804253948305, "prompt_level_loose_acc": 0.36414048059149723, "prompt_level_loose_acc_stderr": 0.02070704795859199, "inst_level_loose_acc": 0.49160671462829736, "inst_level_loose_acc_stderr": 0.0005319082260807404 } }, "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": "ac9c7a319a28a49c", "hash_input_tokens": "293299dd5a357664", "hash_cont_tokens": "32c35de97bdb740e" }, "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": "e81546dd645864e0", "hash_input_tokens": "18412135b31119b5", "hash_cont_tokens": "e36d9633e35f162d" }, "truncated": 0, "non_truncated": 541, "padded": 0, "non_padded": 541, "num_truncated_few_shots": 0 } }