baseline_roberta-base_epoch3_batch4_lr2e-05_w0.01
This model is a fine-tuned version of roberta-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.4562
- Accuracy: 0.8988
- F1: 0.8636
- Precision: 0.8675
- Recall: 0.8597
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|---|---|---|---|---|---|---|---|
| 0.6109 | 1.0 | 788 | 0.6462 | 0.8343 | 0.7306 | 0.9266 | 0.6030 |
| 0.4597 | 2.0 | 1576 | 0.4432 | 0.8899 | 0.8596 | 0.8189 | 0.9045 |
| 0.3418 | 3.0 | 2364 | 0.4562 | 0.8988 | 0.8636 | 0.8675 | 0.8597 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.3
- Tokenizers 0.13.3