[2024-07-15 08:06:57,661] [INFO] [real_accelerator.py:191:get_accelerator] Setting ds_accelerator to cuda (auto detect)
07/15/2024 08:06:59 - INFO - llmtuner.data.template - Add <|im_end|>,<|endoftext|> to stop words.
07/15/2024 08:06:59 - INFO - llmtuner.model.patcher - Using KV cache for faster generation.
07/15/2024 08:07:00 - INFO - llmtuner.model.adapter - Fine-tuning method: LoRA
07/15/2024 08:07:03 - INFO - llmtuner.model.adapter - Merged 1 adapter(s).
07/15/2024 08:07:03 - INFO - llmtuner.model.adapter - Loaded adapter(s): /ML-A100/team/mm/eamon/self_instruction/seed_ppl/qwen4B_models/qwen_4B_d0_iter1_model
07/15/2024 08:07:03 - INFO - llmtuner.model.loader - all params: 3950369280