<!-- 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. -->
Horovod_Tweet_Sentiment_1k_5eps
This model is a fine-tuned version of bert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 0.5216092
- Train Accuracy: 0.784375
- Validation Loss: 0.92405033
- Validation Accuracy: 0.4875
- Epoch: 4
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', 'clipnorm': 1.0, 'learning_rate': 0.0003, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
- training_precision: float32
Training results
| Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch |
|---|---|---|---|---|
| 0.7129049 | 0.50937504 | 0.7314203 | 0.490625 | 0 |
| 0.73165804 | 0.47343752 | 0.6929074 | 0.484375 | 1 |
| 0.6827939 | 0.55 | 0.6864271 | 0.50625 | 2 |
| 0.66076773 | 0.5578125 | 0.60817575 | 0.69687504 | 3 |
| 0.5216092 | 0.784375 | 0.92405033 | 0.4875 | 4 |
Framework versions
- Transformers 4.17.0
- TensorFlow 2.6.0
- Tokenizers 0.11.6
