[2024-07-16 23:27:04,861] [INFO] [real_accelerator.py:191:get_accelerator] Setting ds_accelerator to cuda (auto detect)
07/16/2024 23:27:07 - INFO - llmtuner.data.template - Add <|im_end|>,<|endoftext|> to stop words.
07/16/2024 23:27:07 - INFO - llmtuner.model.patcher - Using KV cache for faster generation.
07/16/2024 23:27:12 - INFO - llmtuner.model.adapter - Fine-tuning method: LoRA
07/16/2024 23:28:09 - INFO - llmtuner.model.adapter - Merged 1 adapter(s).
07/16/2024 23:28:09 - INFO - llmtuner.model.adapter - Loaded adapter(s): /ML-A100/team/mm/eamon/self_instruction/seed_ppl/qwen72B_models/qwen_72B_d5_iter6_model
07/16/2024 23:28:09 - INFO - llmtuner.model.loader - all params: 72287920128