{ "config_general": { "lighteval_sha": "?", "num_fewshot_seeds": 1, "override_batch_size": 4, "max_samples": null, "job_id": "", "start_time": 3443526.402672711, "end_time": 3444264.072926939, "total_evaluation_time_secondes": "737.670254228171", "model_name": "HuggingFaceH4/mistral-7b-ift", "model_sha": "b646a0c8e93bc953d2eb9f8a23591751f02d456e", "model_dtype": "torch.bfloat16", "model_size": "13.99 GB", "config": null }, "results": { "custom|ifeval|0": { "prompt_level_strict_acc": 0.48613678373382624, "prompt_level_strict_acc_stderr": 0.02150830206785605, "inst_level_strict_acc": 0.5995203836930456, "inst_level_strict_acc_stderr": 0.0005211886973389416, "prompt_level_loose_acc": 0.5157116451016636, "prompt_level_loose_acc_stderr": 0.021505948540061586, "inst_level_loose_acc": 0.6270983213429256, "inst_level_loose_acc_stderr": 0.0005055707652150286 } }, "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": "46932ca113ba6b0c", "hash_input_tokens": "8b2e0300fbfb70bc", "hash_cont_tokens": "c3b71852f667a55b" }, "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": "8ed52f7b74eb0590", "hash_input_tokens": "9f4b7e9e7ff95d4a", "hash_cont_tokens": "124d4e1d5f6c854f" }, "truncated": 0, "non_truncated": 541, "padded": 0, "non_padded": 541, "num_truncated_few_shots": 0 } }