---
license: mit
tags:
- generated_from_keras_callback
model-index:
- name: soumya13/GPT2_CleanDesc_MAKE_v1.5
  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. -->

# soumya13/GPT2_CleanDesc_MAKE_v1.5

This model is a fine-tuned version of [gpt2](https://huggingface.co./gpt2) on an unknown dataset.
It achieves the following results on the evaluation set:
- Train Loss: 0.0052
- Validation Loss: 0.0002
- Train Accuracy: 1.0
- Epoch: 24

## 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': False, 'is_legacy_optimizer': False, 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 7600, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, '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 |
|:----------:|:---------------:|:--------------:|:-----:|
| 4.0208     | 1.7346          | 0.3590         | 0     |
| 1.5028     | 0.9649          | 0.6923         | 1     |
| 0.8469     | 0.4756          | 0.9231         | 2     |
| 0.4664     | 0.1764          | 0.9231         | 3     |
| 0.2632     | 0.0836          | 0.9744         | 4     |
| 0.1579     | 0.0488          | 0.9744         | 5     |
| 0.1298     | 0.0250          | 1.0            | 6     |
| 0.0962     | 0.0136          | 1.0            | 7     |
| 0.0498     | 0.0041          | 1.0            | 8     |
| 0.0520     | 0.0022          | 1.0            | 9     |
| 0.0418     | 0.0016          | 1.0            | 10    |
| 0.0403     | 0.0013          | 1.0            | 11    |
| 0.0281     | 0.0009          | 1.0            | 12    |
| 0.0236     | 0.0008          | 1.0            | 13    |
| 0.0150     | 0.0008          | 1.0            | 14    |
| 0.0173     | 0.0007          | 1.0            | 15    |
| 0.0160     | 0.0005          | 1.0            | 16    |
| 0.0302     | 0.0004          | 1.0            | 17    |
| 0.0250     | 0.0003          | 1.0            | 18    |
| 0.0069     | 0.0003          | 1.0            | 19    |
| 0.0241     | 0.0003          | 1.0            | 20    |
| 0.0100     | 0.0003          | 1.0            | 21    |
| 0.0114     | 0.0002          | 1.0            | 22    |
| 0.0172     | 0.0002          | 1.0            | 23    |
| 0.0052     | 0.0002          | 1.0            | 24    |


### Framework versions

- Transformers 4.28.1
- TensorFlow 2.12.0
- Datasets 2.12.0
- Tokenizers 0.13.3