|
--- |
|
license: apache-2.0 |
|
base_model: google/electra-small-discriminator |
|
tags: |
|
- generated_from_keras_callback |
|
model-index: |
|
- name: textming_proj01_electra |
|
results: [] |
|
language: |
|
- vi |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# textming_proj01_electra |
|
|
|
This model is a fine-tuned version of [google/electra-small-discriminator](https://huggingface.co/google/electra-small-discriminator) on [Vietnamese dataset - Kaggle](https://www.kaggle.com/datasets/duyminhnguyentran/csc15105). |
|
It achieves the following results on the evaluation set: |
|
- Train Loss: 0.4494 |
|
- Train Accuracy: 0.7976 |
|
- Validation Loss: 0.5521 |
|
- Validation Accuracy: 0.7456 |
|
- Epoch: 5 |
|
- Batch size: 32 |
|
|
|
## Model description |
|
This model is fine-tuned by 19120600@student.hcmus.edu.vn in [Kaggle](https://www.kaggle.com/code/nguynnghabi/training-electra) |
|
|
|
## Training procedure |
|
|
|
### Training hyperparameters |
|
|
|
The following hyperparameters were used during training: |
|
- optimizer: {'name': 'Adam', 'learning_rate': 5e-05, 'epsilon': 1e-08} |
|
- training_precision: float32 |
|
|
|
### Training results |
|
|
|
| Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch | |
|
|:----------:|:--------------:|:---------------:|:-------------------:|:-----:| |
|
| 0.5951 | 0.6936 | 0.5818 | 0.6966 | 1 | |
|
| 0.5484 | 0.7291 | 0.5681 | 0.7054 | 2 | |
|
| 0.5119 | 0.7543 | 0.5284 | 0.7423 | 3 | |
|
| 0.4769 | 0.7800 | 0.5306 | 0.7432 | 4 | |
|
| 0.4494 | 0.7976 | 0.5521 | 0.7456 | 5 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.39.3 |
|
- TensorFlow 2.15.0 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.2 |