<!-- 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. -->
BeardedJohn/bert-finetuned-joint_intent_slots_ubb_endava
This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 5.1282
- Train Output 1 Loss: 0.2030
- Train Output 2 Loss: 4.9252
- Train Output 1 Accuracy: 0.9719
- Train Output 2 Accuracy: 0.6116
- Validation Loss: 4.7179
- Validation Output 1 Loss: 0.0092
- Validation Output 2 Loss: 4.7087
- Validation Output 1 Accuracy: 0.9978
- Validation Output 2 Accuracy: 0.9997
- Epoch: 0
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', 'learning_rate': 3e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
- training_precision: float32
Training results
Train Loss | Train Output 1 Loss | Train Output 2 Loss | Train Output 1 Accuracy | Train Output 2 Accuracy | Validation Loss | Validation Output 1 Loss | Validation Output 2 Loss | Validation Output 1 Accuracy | Validation Output 2 Accuracy | Epoch |
---|---|---|---|---|---|---|---|---|---|---|
5.1282 | 0.2030 | 4.9252 | 0.9719 | 0.6116 | 4.7179 | 0.0092 | 4.7087 | 0.9978 | 0.9997 | 0 |
Framework versions
- Transformers 4.25.1
- TensorFlow 2.9.2
- Tokenizers 0.13.2