---
license: apache-2.0
base_model: google/electra-small-discriminator
tags:
- generated_from_keras_callback
model-index:
- name: nguyennghia0902/electra-small-discriminator_5e-05_32
  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_5e-05_32

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: 1.4462
- Train End Logits Accuracy: 0.6364
- Train Start Logits Accuracy: 0.6099
- Validation Loss: 1.1013
- Validation End Logits Accuracy: 0.7152
- Validation Start Logits Accuracy: 0.7045
- Epoch: 9
- {'name': 'nguyennghia0902/electra-small-discriminator_5e-05_32',
  'lnr': 5e-05,
  'epoch': 10,
  'batch_size': 32,
  'time': 14496.06916427612,
  'accuracy': 0.6114793047392773,
  'f1_score': 0.7343828320758286}

## 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': 5e-05, 'decay_steps': 15630, '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 |
|:----------:|:-------------------------:|:---------------------------:|:---------------:|:------------------------------:|:--------------------------------:|:-----:|
| 3.1881     | 0.3010                    | 0.2689                      | 2.5228          | 0.4049                         | 0.3836                           | 0     |
| 2.5007     | 0.4217                    | 0.3882                      | 2.0728          | 0.5036                         | 0.4895                           | 1     |
| 2.2043     | 0.4835                    | 0.4496                      | 1.8175          | 0.5578                         | 0.5406                           | 2     |
| 2.0197     | 0.5187                    | 0.4879                      | 1.6380          | 0.5947                         | 0.5795                           | 3     |
| 1.8749     | 0.5476                    | 0.5157                      | 1.4806          | 0.6256                         | 0.6152                           | 4     |
| 1.7536     | 0.5717                    | 0.5421                      | 1.3605          | 0.6524                         | 0.6404                           | 5     |
| 1.6484     | 0.5931                    | 0.5631                      | 1.2566          | 0.6796                         | 0.6667                           | 6     |
| 1.5646     | 0.6133                    | 0.5839                      | 1.1845          | 0.6976                         | 0.6855                           | 7     |
| 1.4907     | 0.6288                    | 0.5993                      | 1.1223          | 0.7084                         | 0.6998                           | 8     |
| 1.4462     | 0.6364                    | 0.6099                      | 1.1013          | 0.7152                         | 0.7045                           | 9     |


### Framework versions

- Transformers 4.39.3
- TensorFlow 2.15.0
- Datasets 2.18.0
- Tokenizers 0.15.2