metadata
license: mit
tags:
- generated_from_keras_callback
model-index:
- name: jonaskoenig/topic_classification_04
results: []
jonaskoenig/topic_classification_04
This model is a fine-tuned version of microsoft/xtremedistil-l6-h256-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 0.8707
- Train Sparse Categorical Accuracy: 0.7120
- Epoch: 6
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 | Epoch |
|---|---|---|
| 1.0735 | 0.6503 | 0 |
| 0.9742 | 0.6799 | 1 |
| 0.9424 | 0.6900 | 2 |
| 0.9199 | 0.6970 | 3 |
| 0.9016 | 0.7026 | 4 |
| 0.8853 | 0.7073 | 5 |
| 0.8707 | 0.7120 | 6 |
Framework versions
- Transformers 4.20.1
- TensorFlow 2.9.1
- Datasets 2.3.2
- Tokenizers 0.12.1