svenbl80/roberta-base-finetuned-new-mnli-run-2
This model is a fine-tuned version of roberta-base on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 0.0256
- Validation Loss: 0.7289
- Train Accuracy: 0.8643
- Epoch: 9
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:
- optimizer: {'name': 'Adam', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 245430, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
- training_precision: float32
Training results
Train Loss | Validation Loss | Train Accuracy | Epoch |
---|---|---|---|
0.4540 | 0.4007 | 0.8488 | 0 |
0.3282 | 0.3756 | 0.8566 | 1 |
0.2444 | 0.4087 | 0.8586 | 2 |
0.1789 | 0.4880 | 0.8573 | 3 |
0.1291 | 0.4915 | 0.8621 | 4 |
0.0926 | 0.5759 | 0.8641 | 5 |
0.0665 | 0.5938 | 0.8643 | 6 |
0.0482 | 0.6515 | 0.8632 | 7 |
0.0345 | 0.7010 | 0.8637 | 8 |
0.0256 | 0.7289 | 0.8643 | 9 |
Framework versions
- Transformers 4.28.0
- TensorFlow 2.9.1
- Datasets 2.15.0
- Tokenizers 0.13.3
- Downloads last month
- 5