<!-- 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. -->
Thangnv/t5
This model is a fine-tuned version of NlpHUST/t5-en-vi-small on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 0.6838
- Train Sparse Categorical Accuracy: 0.8193
- Validation Loss: 0.6798
- Validation Sparse Categorical Accuracy: 0.8227
- Epoch: 3
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', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': 0.001, '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 |
|---|---|---|---|---|
| 0.8162 | 0.7924 | 0.7433 | 0.8094 | 0 |
| 0.7413 | 0.8077 | 0.7142 | 0.8151 | 1 |
| 0.7069 | 0.8147 | 0.6927 | 0.8199 | 2 |
| 0.6838 | 0.8193 | 0.6798 | 0.8227 | 3 |
Framework versions
- Transformers 4.33.2
- TensorFlow 2.13.0
- Datasets 2.14.5
- Tokenizers 0.13.3
