{ "config_general": { "lighteval_sha": "?", "num_fewshot_seeds": 1, "override_batch_size": 4, "max_samples": null, "job_id": "", "start_time": 5784652.511086358, "end_time": 5786009.090706546, "total_evaluation_time_secondes": "1356.5796201881021", "model_name": "codellama/CodeLlama-13b-Instruct-hf", "model_sha": "e9066d1322d2aba257d935c3e30e1ca483b84d1f", "model_dtype": "torch.bfloat16", "model_size": "24.59 GB", "config": null }, "results": { "custom|ifeval|0": { "prompt_level_strict_acc": 0.38817005545286504, "prompt_level_strict_acc_stderr": 0.02097150021579478, "inst_level_strict_acc": 0.5071942446043165, "inst_level_strict_acc_stderr": 0.0005353112894017984, "prompt_level_loose_acc": 0.4343807763401109, "prompt_level_loose_acc_stderr": 0.021330473657564724, "inst_level_loose_acc": 0.5539568345323741, "inst_level_loose_acc_stderr": 0.0005315680771827647 } }, "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": "65ce6f78dff49b9b", "hash_input_tokens": "948a776e66685f18", "hash_cont_tokens": "f7560c2b66958a1b" }, "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": "d0f34a7fe2118466", "hash_input_tokens": "a33aa38cc652a8a9", "hash_cont_tokens": "6ca6f9cfb7c78cdd" }, "truncated": 0, "non_truncated": 541, "padded": 0, "non_padded": 541, "num_truncated_few_shots": 0 } }