| Model: gpt_LinearDiTStudent2 | |
| Optimizer: adamw, LR: 2e-05 | |
| Best Val Loss: 1.0569, Test Loss: 1.0260 | |
| Epoch 1: Train Loss: 7146.0399, Val Loss: 5.1513 | |
| Epoch 2: Train Loss: 2.6326, Val Loss: 1.4842 | |
| Epoch 3: Train Loss: 1.4425, Val Loss: 1.2182 | |
| Epoch 4: Train Loss: 1.2817, Val Loss: 1.1668 | |
| Epoch 5: Train Loss: 1.1631, Val Loss: 1.1296 | |
| Epoch 6: Train Loss: 1.0963, Val Loss: 1.0863 | |
| Epoch 7: Train Loss: 1.2146, Val Loss: 1.0793 | |
| Epoch 8: Train Loss: 1.0522, Val Loss: 1.0756 | |
| Epoch 9: Train Loss: 1.0450, Val Loss: 1.0707 | |
| Epoch 10: Train Loss: 1.1127, Val Loss: 1.0760 | |
| Epoch 11: Train Loss: 1.0296, Val Loss: 1.0569 | |
| Epoch 12: Train Loss: 1.0260, Val Loss: 1.0654 | |
| Epoch 13: Train Loss: 1.0236, Val Loss: 1.0681 | |
| Epoch 14: Train Loss: 1.0223, Val Loss: 1.0661 | |
| Epoch 15: Train Loss: 1.0216, Val Loss: 1.0714 | |
| Final Test Loss: 1.0260 |