metadata
license: apache-2.0
base_model: bert-base-uncased
tags:
- generated_from_keras_callback
model-index:
- name: BenjaminKUL/IDP_chat_intent
results: []
BenjaminKUL/IDP_chat_intent
This model is a fine-tuned version of bert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 0.1623
- Train Accuracy: 0.9658
- Validation Loss: 4.8680
- Validation Accuracy: 0.0092
- Epoch: 5
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': 1e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
- training_precision: float32
Training results
| Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch |
|---|---|---|---|---|
| 1.6630 | 0.4900 | 2.3887 | 0.0414 | 0 |
| 0.9443 | 0.8153 | 2.9321 | 0.0077 | 1 |
| 0.5060 | 0.9155 | 3.6382 | 0.0046 | 2 |
| 0.2954 | 0.9512 | 4.1146 | 0.0077 | 3 |
| 0.2028 | 0.9643 | 4.5732 | 0.0031 | 4 |
| 0.1623 | 0.9658 | 4.8680 | 0.0092 | 5 |
Framework versions
- Transformers 4.37.2
- TensorFlow 2.9.0
- Datasets 2.14.4
- Tokenizers 0.15.1