metadata
license: apache-2.0
base_model: distilbert-base-cased
tags:
- generated_from_keras_callback
model-index:
- name: LongRiver/transformer_QAVi
results: []
LongRiver/transformer_QAVi
This model is a fine-tuned version of distilbert-base-cased on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 0.1280
- Train End Logits Accuracy: 0.9610
- Train Start Logits Accuracy: 0.9485
- Validation Loss: 2.0278
- Validation End Logits Accuracy: 0.6900
- Validation Start Logits Accuracy: 0.6542
- Epoch: 9
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': 55450, '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 | Train End Logits Accuracy | Train Start Logits Accuracy | Validation Loss | Validation End Logits Accuracy | Validation Start Logits Accuracy | Epoch |
|---|---|---|---|---|---|---|
| 1.6102 | 0.5808 | 0.5465 | 1.1787 | 0.6799 | 0.6465 | 0 |
| 0.9934 | 0.7242 | 0.6859 | 1.1191 | 0.6984 | 0.6676 | 1 |
| 0.7428 | 0.7852 | 0.7468 | 1.1470 | 0.6996 | 0.6693 | 2 |
| 0.5627 | 0.8317 | 0.7975 | 1.2633 | 0.6977 | 0.6624 | 3 |
| 0.4244 | 0.8709 | 0.8396 | 1.4117 | 0.6933 | 0.6589 | 4 |
| 0.3229 | 0.9013 | 0.8736 | 1.5396 | 0.6870 | 0.6575 | 5 |
| 0.2478 | 0.9239 | 0.9009 | 1.7142 | 0.6880 | 0.6573 | 6 |
| 0.1909 | 0.9398 | 0.9243 | 1.8694 | 0.6893 | 0.6543 | 7 |
| 0.1526 | 0.9528 | 0.9388 | 1.9620 | 0.6867 | 0.6516 | 8 |
| 0.1280 | 0.9610 | 0.9485 | 2.0278 | 0.6900 | 0.6542 | 9 |
Framework versions
- Transformers 4.39.3
- TensorFlow 2.15.0
- Datasets 2.18.0
- Tokenizers 0.15.2