<!-- This model card has been generated automatically according to the information Keras had access to. You should probably proofread and complete it, then remove this comment. -->
distilbert_oscarth_0020
This model is a fine-tuned version of distilbert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 1.4909
- Validation Loss: 1.4161
- Epoch: 19
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': 'AdamWeightDecay', 'learning_rate': 2e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.01}
- training_precision: float32
Training results
| Train Loss | Validation Loss | Epoch |
|---|---|---|
| 4.1327 | 2.9983 | 0 |
| 2.7813 | 2.4562 | 1 |
| 2.4194 | 2.2066 | 2 |
| 2.2231 | 2.0562 | 3 |
| 2.0894 | 1.9450 | 4 |
| 1.9905 | 1.8621 | 5 |
| 1.9148 | 1.7941 | 6 |
| 1.8508 | 1.7363 | 7 |
| 1.7976 | 1.6909 | 8 |
| 1.7509 | 1.6488 | 9 |
| 1.7126 | 1.6124 | 10 |
| 1.6764 | 1.5835 | 11 |
| 1.6450 | 1.5521 | 12 |
| 1.6175 | 1.5282 | 13 |
| 1.5919 | 1.5045 | 14 |
| 1.5679 | 1.4833 | 15 |
| 1.5476 | 1.4627 | 16 |
| 1.5271 | 1.4498 | 17 |
| 1.5098 | 1.4270 | 18 |
| 1.4909 | 1.4161 | 19 |
Framework versions
- Transformers 4.20.1
- TensorFlow 2.8.2
- Datasets 2.3.2
- Tokenizers 0.12.1
