<!-- 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. -->
cakiki/distilbert-base-uncased-finetuned-tweet-sentiment
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: 0.1025
- Train Sparse Categorical Accuracy: 0.9511
- Validation Loss: 0.1455
- Validation Sparse Categorical Accuracy: 0.9365
- Epoch: 2
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': 5e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
- training_precision: float32
Training results
| Train Loss | Train Sparse Categorical Accuracy | Validation Loss | Validation Sparse Categorical Accuracy | Epoch |
|---|---|---|---|---|
| 0.5409 | 0.8158 | 0.2115 | 0.9265 | 0 |
| 0.1442 | 0.9373 | 0.1411 | 0.9380 | 1 |
| 0.1025 | 0.9511 | 0.1455 | 0.9365 | 2 |
Framework versions
- Transformers 4.18.0
- TensorFlow 2.9.0-rc0
- Datasets 2.1.0
- Tokenizers 0.12.1
