2026-07-23:22:12:13 WARNING [config.evaluate_config:287] --limit SHOULD ONLY BE USED FOR TESTING. REAL METRICS SHOULD NOT BE COMPUTED USING LIMIT. 2026-07-23:22:12:20 INFO [_cli.run:388] Selected Tasks: ['mmlu_pro', 'gpqa_diamond_cot_zeroshot', 'minerva_math500', 'ifeval', 'gsm8k_cot_zeroshot'] 2026-07-23:22:12:22 INFO [evaluator:214] Setting random seed to 0 | Setting numpy seed to 1234 | Setting torch manual seed to 1234 | Setting fewshot manual seed to 1234 2026-07-23:22:12:22 WARNING [evaluator:226] generation_kwargs: {'max_gen_toks': 1280} specified through cli, these settings will update set parameters in yaml tasks. Ensure 'do_sample=True' for non-greedy decoding! 2026-07-23:22:12:22 INFO [evaluator:239] Initializing local-chat-completions model, with arguments: {'model': 'student', 'base_url': 'http://127.0.0.1:8399/v1/chat/completions', 'num_concurrent': 32, 'tokenized_requests': False, 'max_retries': 3} 2026-07-23:22:12:22 INFO [models.api_models:179] Using max length 2048 - 1 2026-07-23:22:12:22 INFO [models.api_models:200] Using tokenizer None Map: 0%| | 0/198 [00:00'], 'do_sample': False, 'temperature': 0.0, 'max_gen_toks': 1280} 2026-07-23:22:12:36 INFO [evaluator:314] minerva_math500: Using gen_kwargs: {'until': ['Problem:'], 'do_sample': False, 'temperature': 0.0, 'max_gen_toks': 1280} 2026-07-23:22:12:36 INFO [evaluator:314] ifeval: Using gen_kwargs: {'until': [], 'do_sample': False, 'temperature': 0.0, 'max_gen_toks': 1280} 2026-07-23:22:12:36 INFO [evaluator:314] gsm8k_cot_zeroshot: Using gen_kwargs: {'until': ['Q:', '', '<|im_end|>'], 'do_sample': False, 'max_gen_toks': 1280} 2026-07-23:22:12:36 INFO [api.task:312] Building contexts for mmlu_pro_biology on rank 0... 0%| | 0/10 [00:00