svenbl80/roberta-base-finetuned-new-mnli-run-1
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: 0.0248
- Validation Loss: 0.7357
- Train Accuracy: 0.8661
- 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 |
---|---|---|---|
0.4558 | 0.3972 | 0.8495 | 0 |
0.3309 | 0.3834 | 0.8520 | 1 |
0.2465 | 0.4150 | 0.8627 | 2 |
0.1784 | 0.4412 | 0.8670 | 3 |
0.1288 | 0.4816 | 0.8626 | 4 |
0.0926 | 0.5470 | 0.8647 | 5 |
0.0666 | 0.5634 | 0.8669 | 6 |
0.0477 | 0.6574 | 0.8648 | 7 |
0.0345 | 0.6919 | 0.8641 | 8 |
0.0248 | 0.7357 | 0.8661 | 9 |
Framework versions
- Transformers 4.28.0
- TensorFlow 2.9.1
- Datasets 2.15.0
- Tokenizers 0.13.3
- Downloads last month
- 5
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.