{ "config_general": { "lighteval_sha": "?", "num_fewshot_seeds": 1, "override_batch_size": 4, "max_samples": null, "job_id": "", "start_time": 406815.641391649, "end_time": 407676.317755509, "total_evaluation_time_secondes": "860.6763638599659", "model_name": "HuggingFaceH4/starcoder2-15b-dpo", "model_sha": "47b2dd7e0effeca0a37c0efb5fe09f2b50745c20", "model_dtype": "torch.bfloat16", "model_size": "30.04 GB", "config": null }, "results": { "custom|ifeval|0": { "prompt_level_strict_acc": 0.2828096118299446, "prompt_level_strict_acc_stderr": 0.01938060959589276, "inst_level_strict_acc": 0.42326139088729015, "inst_level_strict_acc_stderr": 0.0005122130513016085, "prompt_level_loose_acc": 0.29944547134935307, "prompt_level_loose_acc_stderr": 0.019709834029672916, "inst_level_loose_acc": 0.43884892086330934, "inst_level_loose_acc_stderr": 0.0005095536627210149 } }, "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": "7ea7bf2a8edba8f4", "hash_input_tokens": "dc4c9014dffc6917", "hash_cont_tokens": "ce608c76b2f75aa7" }, "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": "45f8422f6ad2da79", "hash_input_tokens": "5d5e6158af678a01", "hash_cont_tokens": "f90ceed4053b75ab" }, "truncated": 0, "non_truncated": 541, "padded": 0, "non_padded": 541, "num_truncated_few_shots": 0 } }