| 2025-06-17 12:44:52,511 - INFO - [main_preprocess] - --- PREPROCESS-PHASE 1: �}�l�ͦ� Rejected �^�� --- | |
| 2025-06-17 12:44:52,511 - INFO - [prepare_datasets] - �q train-reasoning-v2.csv ���J�ƾڶ� | |
| 2025-06-17 12:44:56,454 - INFO - [get_balanced_memory] - We will use 90% of the memory on device 0 for storing the model, and 10% for the buffer to avoid OOM. You can set `max_memory` in to a higher value to use more memory (at your own risk). | |
| 2025-06-17 12:44:58,974 - INFO - [main_preprocess] - �ϥ� map_batch_size = 4 �i��ͦ� | |
| 2025-06-17 14:24:28,082 - INFO - [main_preprocess] - Rejected �^���ͦ������C | |
| 2025-06-17 14:24:28,082 - INFO - [main_preprocess] - ����ͦ��ҫ��� VRAM... | |
| 2025-06-17 14:24:28,082 - INFO - [main_preprocess] - VRAM �w����C | |
| 2025-06-17 14:24:28,082 - INFO - [main_preprocess] - --- PREPROCESS-PHASE 2: �}�l�p����y���� --- | |
| 2025-06-17 14:24:28,082 - INFO - [__init__] - ���J���u���y�ҫ�: google/gemma-2b-it | |
| 2025-06-17 14:24:31,163 - INFO - [get_balanced_memory] - We will use 90% of the memory on device 0 for storing the model, and 10% for the buffer to avoid OOM. You can set `max_memory` in to a higher value to use more memory (at your own risk). | |
| 2025-06-17 15:01:13,102 - INFO - [main_preprocess] - ���y���ƭp�⧹���C | |
| 2025-06-17 15:01:13,102 - INFO - [main_preprocess] - ������y�ҫ��� VRAM... | |
| 2025-06-17 15:01:13,150 - INFO - [main_preprocess] - VRAM �w����C | |
| 2025-06-17 15:01:13,150 - INFO - [main_preprocess] - --- PREPROCESS-PHASE 3: �x�s�w�B�z��������ƶ� --- | |
| 2025-06-17 15:01:13,276 - INFO - [main_preprocess] - ��Ƥw�x�s�� train_preprocessed.jsonl �M eval_preprocessed.jsonl | |
| 2025-06-17 15:01:13,276 - INFO - [main_preprocess] - �w�B�z���������I | |