roberta-base
This model was trained from scratch on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 1.0016
- Accuracy: 0.8
- Precision: 0.8169
- Recall: 0.8
- F1: 0.7923
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: 6.75e-05
- train_batch_size: 20
- eval_batch_size: 20
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 7
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|---|
| No log | 1.0 | 5 | 0.6820 | 0.5333 | 0.2844 | 0.5333 | 0.3710 |
| No log | 2.0 | 10 | 0.6334 | 0.5333 | 0.2844 | 0.5333 | 0.3710 |
| No log | 3.0 | 15 | 0.5110 | 0.7333 | 0.7556 | 0.7333 | 0.7310 |
| No log | 4.0 | 20 | 0.4460 | 0.8 | 0.8071 | 0.8 | 0.8 |
| No log | 5.0 | 25 | 0.4716 | 0.8667 | 0.8667 | 0.8667 | 0.8667 |
| No log | 6.0 | 30 | 0.4568 | 0.9 | 0.9014 | 0.9 | 0.8997 |
| No log | 7.0 | 35 | 0.4533 | 0.9 | 0.9014 | 0.9 | 0.8997 |
Framework versions
- Transformers 4.51.3
- Pytorch 2.6.0+cu124
- Datasets 3.5.0
- Tokenizers 0.21.1
