Training hyperparameters
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 |
|---|---|---|---|---|
| 1.238700 | 1.0 | 1.135360 | 0.238667 | 0.106812 |
| 1.084500 | 2.0 | 1.103713 | 0.234572 | 0.105525 |
| 1.009300 | 3.0 | 1.099275 | 0.290353 | 0.162856 |
| 0.929300 | 4.0 | 1.159663 | 0.334926 | 0.208453 |
- Downloads last month
- 0
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.