vnktrmnb/bert-base-multilingual-cased-FT-TyDiQA-GoldP_BL
This model is a fine-tuned version of bert-base-multilingual-cased on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 0.5214
- Train End Logits Accuracy: 0.8427
- Train Start Logits Accuracy: 0.8833
- Validation Loss: 0.4515
- Validation End Logits Accuracy: 0.8686
- Validation Start Logits Accuracy: 0.9149
- Epoch: 2
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': 1359, '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 | Train End Logits Accuracy | Train Start Logits Accuracy | Validation Loss | Validation End Logits Accuracy | Validation Start Logits Accuracy | Epoch |
|---|---|---|---|---|---|---|
| 1.4868 | 0.6326 | 0.6700 | 0.5422 | 0.8338 | 0.8956 | 0 |
| 0.7301 | 0.7886 | 0.8328 | 0.4645 | 0.8595 | 0.9046 | 1 |
| 0.5214 | 0.8427 | 0.8833 | 0.4515 | 0.8686 | 0.9149 | 2 |
Framework versions
- Transformers 4.32.0
- TensorFlow 2.12.0
- Datasets 2.14.4
- Tokenizers 0.13.3