basakdemirok/bert-base-turkish-cased-sentiment_v01
This model is a fine-tuned version of dbmdz/bert-base-turkish-cased on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 0.0184
- Validation Loss: 0.3156
- Train F1: 0.9306
- 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': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 3920, '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 F1 | Epoch |
---|---|---|---|
0.2342 | 0.2100 | 0.9271 | 0 |
0.0820 | 0.2595 | 0.9245 | 1 |
0.0343 | 0.3048 | 0.9341 | 2 |
0.0184 | 0.3156 | 0.9306 | 3 |
Framework versions
- Transformers 4.41.2
- TensorFlow 2.13.1
- Datasets 2.4.0
- Tokenizers 0.19.1
- Downloads last month
- 8
Model tree for basakdemirok/bert-base-turkish-cased-sentiment_v01
Base model
dbmdz/bert-base-turkish-cased