<!-- 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. -->
tyavika/QAModel_Distilbert_b16_20_3e5
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: 0.4271
- Train End Logits Accuracy: 0.8747
- Train Start Logits Accuracy: 0.8628
- Validation Loss: 1.7887
- Validation End Logits Accuracy: 0.6175
- Validation Start Logits Accuracy: 0.5786
- 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: {'inner_optimizer': {'class_name': 'Custom>Adam', 'config': {'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': 3e-05, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}}, 'dynamic': True, 'initial_scale': 32768.0, 'dynamic_growth_steps': 2000}
- training_precision: mixed_float16
Training results
Train Loss | Train End Logits Accuracy | Train Start Logits Accuracy | Validation Loss | Validation End Logits Accuracy | Validation Start Logits Accuracy | Epoch |
---|---|---|---|---|---|---|
2.2867 | 0.4392 | 0.4104 | 1.5112 | 0.6056 | 0.5722 | 0 |
1.1957 | 0.6764 | 0.6470 | 1.4029 | 0.6343 | 0.5930 | 1 |
0.7345 | 0.7904 | 0.7696 | 1.5582 | 0.6177 | 0.5801 | 2 |
0.4271 | 0.8747 | 0.8628 | 1.7887 | 0.6175 | 0.5786 | 3 |
Framework versions
- Transformers 4.30.2
- TensorFlow 2.12.0
- Datasets 2.13.1
- Tokenizers 0.13.3