2026-08-08:18:17:39 INFO [_cli.run:388] Selected Tasks: ['humaneval', 'mbpp'] 2026-08-08:18:17:40 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 2026-08-08:18:17:40 INFO [evaluator:239] Initializing local-completions model, with arguments: {'model': 'student', 'base_url': 'http://127.0.0.1:8451/v1/completions', 'tokenizer': 'outputs/release/healed/release-offpolicy-general-keep25/step0150', 'num_concurrent': 48, 'tokenized_requests': False, 'max_retries': 3} 2026-08-08:18:17:40 INFO [models.openai_completions:42] Remote tokenizer not supported. Using huggingface tokenizer backend. 2026-08-08:18:17:40 INFO [models.api_models:179] Using max length 2048 - 1 2026-08-08:18:17:40 INFO [models.api_models:200] Using tokenizer huggingface 2026-08-08:18:17:47 INFO [evaluator_utils:446] Selected tasks: 2026-08-08:18:17:47 INFO [evaluator_utils:480] Task: humaneval (humaneval/humaneval.yaml) 2026-08-08:18:17:47 INFO [evaluator_utils:480] Task: mbpp (mbpp/mbpp.yaml) 2026-08-08:18:17:47 INFO [evaluator:314] humaneval: Using gen_kwargs: {'until': ['\nclass', '\ndef', '\n#', '\nif', '\nprint'], 'max_gen_toks': 1024, 'do_sample': False} 2026-08-08:18:17:47 INFO [evaluator:314] mbpp: Using gen_kwargs: {'until': ['[DONE]'], 'do_sample': False} 2026-08-08:18:17:47 INFO [api.task:312] Building contexts for humaneval on rank 0... 0%| | 0/164 [00:00