| [2024-07-13 16:35:24,404] [INFO] [real_accelerator.py:191:get_accelerator] Setting ds_accelerator to cuda (auto detect) | |
| 07/13/2024 16:35:26 - INFO - llmtuner.data.template - Add <|im_end|>,<|endoftext|> to stop words. | |
| 07/13/2024 16:35:26 - INFO - llmtuner.model.patcher - Using KV cache for faster generation. | |
| 07/13/2024 16:35:29 - INFO - llmtuner.model.adapter - Fine-tuning method: LoRA | |
| 07/13/2024 16:35:58 - INFO - llmtuner.model.adapter - Merged 1 adapter(s). | |
| 07/13/2024 16:35:58 - INFO - llmtuner.model.adapter - Loaded adapter(s): /ML-A100/team/mm/eamon/self_instruction/seed_ppl/qwen32B_models/qwen_32B_d0_iter1_model | |
| 07/13/2024 16:35:58 - INFO - llmtuner.model.loader - all params: 32512218112 | |