<!-- 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. -->
MarcoLYH/bert-base-uncased-finetuned-v2
This model is a fine-tuned version of csarron/bert-base-uncased-squad-v1 on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 0.6988
- Train End Logits Accuracy: 0.8958
- Train Start Logits Accuracy: 0.7917
- Validation Loss: 0.5760
- Validation End Logits Accuracy: 0.8500
- Validation Start Logits Accuracy: 0.8500
- 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': {'class_name': 'WarmUp', 'config': {'initial_learning_rate': 1e-05, 'decay_schedule_fn': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 1e-05, 'decay_steps': 27, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'passive_serialization': True}, 'warmup_steps': 3, 'power': 1.0, '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 |
---|---|---|---|---|---|---|
1.9477 | 0.4375 | 0.5417 | 1.3534 | 0.6000 | 0.7000 | 0 |
1.7097 | 0.4583 | 0.5208 | 1.0429 | 0.7000 | 0.7000 | 1 |
1.3797 | 0.6875 | 0.5833 | 0.8816 | 0.75 | 0.7000 | 2 |
1.1394 | 0.625 | 0.6875 | 0.7849 | 0.75 | 0.7000 | 3 |
1.0558 | 0.6875 | 0.625 | 0.7057 | 0.8000 | 0.7000 | 4 |
0.8213 | 0.8542 | 0.8125 | 0.6496 | 0.8500 | 0.75 | 5 |
0.8661 | 0.8125 | 0.7292 | 0.6152 | 0.8500 | 0.8000 | 6 |
0.7864 | 0.8542 | 0.7917 | 0.5948 | 0.8500 | 0.8500 | 7 |
0.8933 | 0.8333 | 0.75 | 0.5822 | 0.8500 | 0.8500 | 8 |
0.6988 | 0.8958 | 0.7917 | 0.5760 | 0.8500 | 0.8500 | 9 |
Framework versions
- Transformers 4.30.1
- TensorFlow 2.12.0
- Datasets 2.12.0
- Tokenizers 0.13.3