svenbl80/albert-base-v2-finetuned-mnli
This model is a fine-tuned version of albert-base-v2 on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 0.2712
- Validation Loss: 0.4705
- Train Accuracy: 0.8264
- Epoch: 3
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': 736290, '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 |
---|---|---|---|
0.5312 | 0.4792 | 0.8117 | 0 |
0.4204 | 0.4335 | 0.8344 | 1 |
0.3465 | 0.4351 | 0.8317 | 2 |
0.2712 | 0.4705 | 0.8264 | 3 |
Framework versions
- Transformers 4.28.0
- TensorFlow 2.7.0
- Datasets 2.3.2
- Tokenizers 0.12.1
- Downloads last month
- 0