Qwen3-8B-Base-OpenThoughts3Math-SFT-step250-lr5e-6

Qwen3-8B-Base -- OpenThoughts3 math SFT, step 250

Intermediate checkpoint (step 250 of a planned 2000), bf16 weights only. Not yet evaluated.

Every assistant message in the data is a <think>...</think> trace ending in \boxed{}, and the model is trained to reproduce that. It uses a plain ChatML template with no thinking logic -- Qwen3's own template strips <think> from all but the last assistant turn, which would have removed the reasoning from the training targets. No enable_thinking flag applies.

A turn ends with <|im_end|> (151645); config.json and generation_config.json both say so. Qwen3-8B-Base's stock generation_config.json says 151643 instead, which yields a model that never terminates under vLLM. Generate with max_new_tokens around 16384.