EmoraBert3 / README.md
Q317's picture
Training in progress epoch 4
bf621fe
---
license: mit
base_model: wonrax/phobert-base-vietnamese-sentiment
tags:
- generated_from_keras_callback
model-index:
- name: Q317/EmoraBert3
results: []
---
<!-- 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. -->
# Q317/EmoraBert3
This model is a fine-tuned version of [wonrax/phobert-base-vietnamese-sentiment](https://huggingface.co/wonrax/phobert-base-vietnamese-sentiment) on an unknown dataset.
It achieves the following results on the evaluation set:
- Train Loss: 0.2932
- Validation Loss: 0.8787
- Train Accuracy: 0.7133
- 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: {'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': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 100590, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
- training_precision: float32
### Training results
| Train Loss | Validation Loss | Train Accuracy | Epoch |
|:----------:|:---------------:|:--------------:|:-----:|
| 0.8163 | 0.7328 | 0.6839 | 0 |
| 0.6475 | 0.6971 | 0.7038 | 1 |
| 0.5167 | 0.7402 | 0.7131 | 2 |
| 0.3987 | 0.8218 | 0.7087 | 3 |
| 0.2932 | 0.8787 | 0.7133 | 4 |
### Framework versions
- Transformers 4.33.1
- TensorFlow 2.13.0
- Datasets 2.14.5
- Tokenizers 0.13.3