[2024-07-13 20:00:21,001] [INFO] [real_accelerator.py:191:get_accelerator] Setting ds_accelerator to cuda (auto detect)
07/13/2024 20:00:23 - INFO - llmtuner.data.template - Add <|im_end|>,<|endoftext|> to stop words.
07/13/2024 20:00:23 - INFO - llmtuner.model.patcher - Using KV cache for faster generation.
07/13/2024 20:00:25 - INFO - llmtuner.model.adapter - Fine-tuning method: LoRA
07/13/2024 20:00:53 - INFO - llmtuner.model.adapter - Merged 1 adapter(s).
07/13/2024 20:00:53 - INFO - llmtuner.model.adapter - Loaded adapter(s): /ML-A100/team/mm/eamon/self_instruction/seed_ppl/qwen32B_models/qwen_32B_d1_iter2_model
07/13/2024 20:00:53 - INFO - llmtuner.model.loader - all params: 32512218112