metadata
license: mit
tags:
- generated_from_keras_callback
model-index:
- name: soumya13/GPT2_CleanDesc_MAKE_v1.4
results: []
soumya13/GPT2_CleanDesc_MAKE_v1.4
This model is a fine-tuned version of gpt2 on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 0.0635
- Validation Loss: 0.0017
- Train Accuracy: 1.0
- Epoch: 6
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': 4560, '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 |
|---|---|---|---|
| 2.1210 | 0.7138 | 0.8974 | 0 |
| 0.5720 | 0.3016 | 0.8974 | 1 |
| 0.2713 | 0.0579 | 1.0 | 2 |
| 0.1361 | 0.0190 | 1.0 | 3 |
| 0.0969 | 0.0049 | 1.0 | 4 |
| 0.0698 | 0.0024 | 1.0 | 5 |
| 0.0635 | 0.0017 | 1.0 | 6 |
Framework versions
- Transformers 4.28.1
- TensorFlow 2.12.0
- Datasets 2.12.0
- Tokenizers 0.13.3