|
--- |
|
license: apache-2.0 |
|
base_model: google/electra-small-discriminator |
|
tags: |
|
- generated_from_keras_callback |
|
model-index: |
|
- name: nguyennghia0902/electra-small-discriminator_0.0001_32_15e |
|
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. --> |
|
|
|
# nguyennghia0902/electra-small-discriminator_0.0001_32_15e |
|
|
|
This model is a fine-tuned version of [google/electra-small-discriminator](https://huggingface.co/google/electra-small-discriminator) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Train Loss: 0.5958 |
|
- Train End Logits Accuracy: 0.8298 |
|
- Train Start Logits Accuracy: 0.8077 |
|
- Validation Loss: 0.2565 |
|
- Validation End Logits Accuracy: 0.9243 |
|
- Validation Start Logits Accuracy: 0.9233 |
|
- Epoch: 14 |
|
|
|
## 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': 0.0001, 'decay_steps': 23445, '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 | Train End Logits Accuracy | Train Start Logits Accuracy | Validation Loss | Validation End Logits Accuracy | Validation Start Logits Accuracy | Epoch | |
|
|:----------:|:-------------------------:|:---------------------------:|:---------------:|:------------------------------:|:--------------------------------:|:-----:| |
|
| 3.0253 | 0.3302 | 0.2968 | 2.2414 | 0.4704 | 0.4533 | 0 | |
|
| 2.3162 | 0.4597 | 0.4260 | 1.8267 | 0.5511 | 0.5364 | 1 | |
|
| 2.0285 | 0.5160 | 0.4813 | 1.5472 | 0.6109 | 0.5994 | 2 | |
|
| 1.8125 | 0.5587 | 0.5287 | 1.2995 | 0.6688 | 0.6512 | 3 | |
|
| 1.6192 | 0.5963 | 0.5677 | 1.0973 | 0.7105 | 0.7030 | 4 | |
|
| 1.4482 | 0.6341 | 0.6066 | 0.8998 | 0.7637 | 0.7547 | 5 | |
|
| 1.2931 | 0.6694 | 0.6423 | 0.7622 | 0.7920 | 0.7916 | 6 | |
|
| 1.1518 | 0.6980 | 0.6741 | 0.6412 | 0.8260 | 0.8197 | 7 | |
|
| 1.0351 | 0.7240 | 0.7025 | 0.5316 | 0.8518 | 0.8531 | 8 | |
|
| 0.9269 | 0.7488 | 0.7270 | 0.4671 | 0.8701 | 0.8700 | 9 | |
|
| 0.8354 | 0.7714 | 0.7489 | 0.3836 | 0.8910 | 0.8896 | 10 | |
|
| 0.7520 | 0.7904 | 0.7699 | 0.3342 | 0.9048 | 0.9021 | 11 | |
|
| 0.6869 | 0.8056 | 0.7848 | 0.2983 | 0.9134 | 0.9118 | 12 | |
|
| 0.6320 | 0.8209 | 0.7994 | 0.2667 | 0.9223 | 0.9205 | 13 | |
|
| 0.5958 | 0.8298 | 0.8077 | 0.2565 | 0.9243 | 0.9233 | 14 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.39.3 |
|
- TensorFlow 2.15.0 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.2 |
|
|
