<!-- 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. -->
ayshi/basic_distil
This model is a fine-tuned version of ayshi/basic_distil on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 0.0114
- Validation Loss: 1.0035
- Train Accuracy: 0.7911
- Epoch: 19
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': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 640, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
- training_precision: float32
Training results
| Train Loss | Validation Loss | Train Accuracy | Epoch |
|---|---|---|---|
| 0.3282 | 0.7966 | 0.7644 | 0 |
| 0.2163 | 0.8219 | 0.7778 | 1 |
| 0.1323 | 0.8099 | 0.7778 | 2 |
| 0.0933 | 0.8337 | 0.7956 | 3 |
| 0.0619 | 0.9082 | 0.7689 | 4 |
| 0.0461 | 0.9380 | 0.7778 | 5 |
| 0.0495 | 0.9502 | 0.7556 | 6 |
| 0.0301 | 0.9445 | 0.7733 | 7 |
| 0.0249 | 0.9578 | 0.8 | 8 |
| 0.0209 | 0.9663 | 0.7911 | 9 |
| 0.0200 | 0.9828 | 0.7778 | 10 |
| 0.0159 | 0.9987 | 0.7689 | 11 |
| 0.0163 | 1.0120 | 0.7689 | 12 |
| 0.0142 | 1.0020 | 0.7956 | 13 |
| 0.0153 | 1.0270 | 0.7911 | 14 |
| 0.0142 | 1.0159 | 0.7822 | 15 |
| 0.0130 | 1.0049 | 0.7911 | 16 |
| 0.0129 | 1.0085 | 0.7956 | 17 |
| 0.0099 | 1.0033 | 0.7911 | 18 |
| 0.0114 | 1.0035 | 0.7911 | 19 |
Framework versions
- Transformers 4.34.0
- TensorFlow 2.13.0
- Datasets 2.14.5
- Tokenizers 0.14.1
