metadata
license: apache-2.0
tags:
- generated_from_keras_callback
model-index:
- name: langtext
results: []
langtext
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: 0.8401
- Train End Logits Accuracy: 0.7623
- Train Start Logits Accuracy: 0.7233
- Validation Loss: 1.1410
- Validation End Logits Accuracy: 0.7038
- Validation Start Logits Accuracy: 0.6658
- 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': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 8298, '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 | Train End Logits Accuracy | Train Start Logits Accuracy | Validation Loss | Validation End Logits Accuracy | Validation Start Logits Accuracy | Epoch |
|---|---|---|---|---|---|---|
| 1.4137 | 0.6275 | 0.5859 | 1.1749 | 0.6833 | 0.6521 | 0 |
| 1.0061 | 0.7229 | 0.6830 | 1.1409 | 0.6976 | 0.6616 | 1 |
| 0.8401 | 0.7623 | 0.7233 | 1.1410 | 0.7038 | 0.6658 | 2 |
Framework versions
- Transformers 4.20.1
- TensorFlow 2.6.4
- Datasets 2.1.0
- Tokenizers 0.12.1