<!-- 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. -->
letingliu/my_awesome_model3
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: 0.5057
- Validation Loss: 0.4900
- Train Accuracy: 0.9245
- Epoch: 18
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': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 30, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, '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 |
---|---|---|---|
0.6850 | 0.6546 | 0.7170 | 0 |
0.6449 | 0.6103 | 0.7547 | 1 |
0.5989 | 0.5549 | 0.8774 | 2 |
0.5506 | 0.5088 | 0.9151 | 3 |
0.5059 | 0.4900 | 0.9245 | 4 |
0.4885 | 0.4900 | 0.9245 | 5 |
0.4939 | 0.4900 | 0.9245 | 6 |
0.4969 | 0.4900 | 0.9245 | 7 |
0.4993 | 0.4900 | 0.9245 | 8 |
0.4951 | 0.4900 | 0.9245 | 9 |
0.5035 | 0.4900 | 0.9245 | 10 |
0.5064 | 0.4900 | 0.9245 | 11 |
0.5022 | 0.4900 | 0.9245 | 12 |
0.5111 | 0.4900 | 0.9245 | 13 |
0.5057 | 0.4900 | 0.9245 | 14 |
0.4979 | 0.4900 | 0.9245 | 15 |
0.5110 | 0.4900 | 0.9245 | 16 |
0.5080 | 0.4900 | 0.9245 | 17 |
0.5057 | 0.4900 | 0.9245 | 18 |
Framework versions
- Transformers 4.26.1
- TensorFlow 2.11.0
- Datasets 2.10.0
- Tokenizers 0.13.2