| [2024-07-15 10:10:22,449] [INFO] [real_accelerator.py:191:get_accelerator] Setting ds_accelerator to cuda (auto detect) | |
| 07/15/2024 10:10:24 - INFO - llmtuner.data.template - Add <|im_end|>,<|endoftext|> to stop words. | |
| 07/15/2024 10:10:24 - INFO - llmtuner.model.patcher - Using KV cache for faster generation. | |
| 07/15/2024 10:10:25 - INFO - llmtuner.model.adapter - Fine-tuning method: LoRA | |
| 07/15/2024 10:10:28 - INFO - llmtuner.model.adapter - Merged 1 adapter(s). | |
| 07/15/2024 10:10:28 - INFO - llmtuner.model.adapter - Loaded adapter(s): /ML-A100/team/mm/eamon/self_instruction/seed_ppl/qwen4B_models/qwen_4B_d1_iter2_model | |
| 07/15/2024 10:10:28 - INFO - llmtuner.model.loader - all params: 3950369280 | |