The following hyperparameters were used during training:
- learning_rate: 5e-5
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
- mixed_precision_training: Native AMP
- warmup_ratio: 0.1
- weight_decay=1e-2
Training results
| Training Loss | Epoch | Validation Loss | F1 | F1 Macro |
|---|---|---|---|---|
| 0.902700 | 1.0 | 0.704850 | 0.740065 | 0.749341 |
| 0.531000 | 2.0 | 0.689495 | 0.777677 | 0.786924 |
| 0.375200 | 3.0 | 0.585254 | 0.809506 | 0.816099 |
