{ "config_general": { "lighteval_sha": "?", "num_fewshot_seeds": 1, "override_batch_size": 1, "max_samples": null, "job_id": "", "start_time": 789438.649623106, "end_time": 789850.759707724, "total_evaluation_time_secondes": "412.1100846179761", "model_name": "HuggingFaceH4/Qwen1.5-1.8B-Chat-odpo", "model_sha": "3f268359edf3bea5beb998cef7a2bff5b0720e94", "model_dtype": "torch.bfloat16", "model_size": "3.8 GB", "config": null }, "results": { "leaderboard|hellaswag|10": { "acc": 0.4576777534355706, "acc_stderr": 0.0049718741597776965, "acc_norm": 0.5821549492133041, "acc_norm_stderr": 0.004921964133874023 } }, "versions": { "leaderboard|hellaswag|10": 0 }, "config_tasks": { "leaderboard|hellaswag": { "name": "hellaswag", "prompt_function": "hellaswag_harness", "hf_repo": "hellaswag", "hf_subset": "default", "metric": [ "loglikelihood_acc", "loglikelihood_acc_norm" ], "hf_avail_splits": [ "train", "test", "validation" ], "evaluation_splits": [ "validation" ], "few_shots_split": null, "few_shots_select": "random_sampling_from_train", "generation_size": -1, "stop_sequence": [ "\n" ], "output_regex": null, "frozen": false, "suite": [ "leaderboard" ], "original_num_docs": 10042, "effective_num_docs": 10042, "trust_dataset": true } }, "summary_tasks": { "leaderboard|hellaswag|10": { "hashes": { "hash_examples": "31985c805c3a737e", "hash_full_prompts": "693f4478cad5e6ae", "hash_input_tokens": "74bfcf67a650cc23", "hash_cont_tokens": "3a21ed80a4a7585d" }, "truncated": 0, "non_truncated": 10042, "padded": 39979, "non_padded": 189, "effective_few_shots": 10.0, "num_truncated_few_shots": 0 } }, "summary_general": { "hashes": { "hash_examples": "63bc2cf8bae03fbc", "hash_full_prompts": "3be43840a0fc57a3", "hash_input_tokens": "5ae15d6c23138d3e", "hash_cont_tokens": "b7bfbb64b00158d2" }, "truncated": 0, "non_truncated": 10042, "padded": 39979, "non_padded": 189, "num_truncated_few_shots": 0 } }