metadata
license: mit
base_model: gpt2-large
tags:
- generated_from_keras_callback
model-index:
- name: enhanced_turkishReviews-generativeAI
results: []
enhanced_turkishReviews-generativeAI
This model is a fine-tuned version of gpt2-large on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 9.7770
- Validation Loss: 9.7482
- Epoch: 9
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: {'inner_optimizer': {'module': 'transformers.optimization_tf', 'class_name': 'AdamWeightDecay', 'config': {'name': 'AdamWeightDecay', 'learning_rate': {'module': 'transformers.optimization_tf', 'class_name': 'WarmUp', 'config': {'initial_learning_rate': 5e-07, 'decay_schedule_fn': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 5e-07, 'decay_steps': -293, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'warmup_steps': 1000, 'power': 1.0, 'name': None}, 'registered_name': 'WarmUp'}, 'decay': 0.0, 'beta_1': 0.8999999761581421, 'beta_2': 0.9990000128746033, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.09}, 'registered_name': 'AdamWeightDecay'}, 'dynamic': True, 'initial_scale': 32768.0, 'dynamic_growth_steps': 2000}
- training_precision: mixed_float16
Training results
| Train Loss | Validation Loss | Epoch |
|---|---|---|
| 10.1112 | 9.8654 | 0 |
| 9.8034 | 9.7482 | 1 |
| 9.7773 | 9.7482 | 2 |
| 9.7774 | 9.7482 | 3 |
| 9.7772 | 9.7482 | 4 |
| 9.7770 | 9.7482 | 5 |
| 9.7770 | 9.7482 | 6 |
| 9.7774 | 9.7482 | 7 |
| 9.7776 | 9.7482 | 8 |
| 9.7770 | 9.7482 | 9 |
Framework versions
- Transformers 4.35.2
- TensorFlow 2.14.0
- Datasets 2.15.0
- Tokenizers 0.15.0