metadata
license: apache-2.0
tags:
- generated_from_keras_callback
model-index:
- name: mt5-small-finetuned-test-class2
results: []
mt5-small-finetuned-test-class2
This model is a fine-tuned version of google/mt5-small on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 2.3668
- Validation Loss: 1.9101
- Epoch: 7
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': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 5.6e-05, 'decay_steps': 44464, '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, 'weight_decay_rate': 0.01}
- training_precision: mixed_float16
Training results
| Train Loss | Validation Loss | Epoch |
|---|---|---|
| 4.4693 | 2.3874 | 0 |
| 3.0670 | 2.1557 | 1 |
| 2.7416 | 2.0547 | 2 |
| 2.5824 | 2.0089 | 3 |
| 2.4922 | 1.9654 | 4 |
| 2.4299 | 1.9344 | 5 |
| 2.3906 | 1.9255 | 6 |
| 2.3668 | 1.9101 | 7 |
Framework versions
- Transformers 4.24.0
- TensorFlow 2.9.2
- Datasets 2.7.1
- Tokenizers 0.13.2