| | Model save | quyanh | Never scanned |
| | Training in progress, step 10050 | quyanh | Never scanned |
| | DPO LoRA checkpoint - step 10000 (eval_loss: 0.6355) | quyanh | Never scanned |
| | DPO LoRA checkpoint - step 9900 (eval_loss: 0.6342) | quyanh | Never scanned |
| | DPO LoRA checkpoint - step 9800 (eval_loss: 0.6355) | quyanh | Aug 15, 2025 |
| | DPO LoRA checkpoint - step 9700 (eval_loss: 0.6356) | quyanh | Never scanned |
| | DPO LoRA checkpoint - step 9600 (eval_loss: 0.6347) | quyanh | Never scanned |
| | DPO LoRA checkpoint - step 9500 (eval_loss: 0.6358) | quyanh | Never scanned |
| | DPO LoRA checkpoint - step 9400 (eval_loss: 0.6343) | quyanh | Never scanned |
| | DPO LoRA checkpoint - step 9300 (eval_loss: 0.6351) | quyanh | Aug 14, 2025 |
| | DPO LoRA checkpoint - step 9200 (eval_loss: 0.6333) | quyanh | Never scanned |
| | DPO LoRA checkpoint - step 9100 (eval_loss: 0.6349) | quyanh | Never scanned |
| | DPO LoRA checkpoint - step 9000 (eval_loss: 0.6345) | quyanh | Never scanned |
| | DPO LoRA checkpoint - step 8900 (eval_loss: 0.6348) | quyanh | Never scanned |
| | DPO LoRA checkpoint - step 8800 (eval_loss: 0.6352) | quyanh | Aug 15, 2025 |
| | DPO LoRA checkpoint - step 8700 (eval_loss: 0.6347) | quyanh | Never scanned |
| | DPO LoRA checkpoint - step 8600 (eval_loss: 0.6351) | quyanh | Never scanned |
| | DPO LoRA checkpoint - step 8500 (eval_loss: 0.6347) | quyanh | Never scanned |
| | DPO LoRA checkpoint - step 8400 (eval_loss: 0.6357) | quyanh | Never scanned |
| | DPO LoRA checkpoint - step 8300 (eval_loss: 0.6353) | quyanh | Never scanned |