{ "config_general": { "lighteval_sha": "?", "num_fewshot_seeds": 1, "override_batch_size": 4, "max_samples": null, "job_id": "", "start_time": 680463.287952653, "end_time": 681325.649658282, "total_evaluation_time_secondes": "862.3617056290386", "model_name": "HuggingFaceH4/zephyr-7b-gemma-v0.1", "model_sha": "19186e70e5679c47aaef473ae2fd56e20765088d", "model_dtype": "torch.bfloat16", "model_size": "15.91 GB", "config": null }, "results": { "custom|ifeval|0": { "prompt_level_strict_acc": 0.26247689463955637, "prompt_level_strict_acc_stderr": 0.018933742876044622, "inst_level_strict_acc": 0.39448441247002397, "inst_level_strict_acc_stderr": 0.0005019966290557219, "prompt_level_loose_acc": 0.2809611829944547, "prompt_level_loose_acc_stderr": 0.019342047683777005, "inst_level_loose_acc": 0.41007194244604317, "inst_level_loose_acc_stderr": 0.00050375270527348 } }, "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": "dffcf9a3b5dd7b3d", "hash_input_tokens": "697d713cee490081", "hash_cont_tokens": "51a1983caaa17d4d" }, "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": "74abf332fe1a119c", "hash_input_tokens": "369e8568d4bc5b04", "hash_cont_tokens": "407f8961ecb36033" }, "truncated": 0, "non_truncated": 541, "padded": 0, "non_padded": 541, "num_truncated_few_shots": 0 } }