metadata
license: mit
base_model: indolem/indobert-base-uncased
tags:
- generated_from_keras_callback
model-index:
- name: damand2061/pfsa-id-med-indobert-lem
results: []
damand2061/pfsa-id-med-indobert-lem
This model is a fine-tuned version of indolem/indobert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 0.1033
- Validation Loss: 0.2546
- Validation F1: 0.8649
- Validation Accuracy: 0.9290
- Epoch: 4
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': {'module': 'transformers.optimization_tf', 'class_name': 'AdamWeightDecay', 'config': {'name': 'AdamWeightDecay', 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 1e-05, 'decay_steps': 19220, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'decay': 0.0, 'beta_1': 0.8999999761581421, 'beta_2': 0.9990000128746033, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}, 'registered_name': 'AdamWeightDecay'}, 'dynamic': True, 'initial_scale': 32768.0, 'dynamic_growth_steps': 2000}
- training_precision: mixed_float16
Training results
| Train Loss | Validation Loss | Validation F1 | Validation Accuracy | Epoch |
|---|---|---|---|---|
| 0.3412 | 0.2362 | 0.7881 | 0.9230 | 0 |
| 0.2070 | 0.2131 | 0.8448 | 0.9301 | 1 |
| 0.1615 | 0.2377 | 0.8529 | 0.9254 | 2 |
| 0.1288 | 0.2406 | 0.8623 | 0.9285 | 3 |
| 0.1033 | 0.2546 | 0.8649 | 0.9290 | 4 |
Framework versions
- Transformers 4.44.0
- TensorFlow 2.16.1
- Datasets 2.21.0
- Tokenizers 0.19.1