metadata
license: mit
tags:
- generated_from_keras_callback
base_model: kmkarakaya/turkishReviews-ds
model-index:
- name: PromptGenerator_5_topic_finetuned
results: []
PromptGenerator_5_topic_finetuned
This model is a fine-tuned version of kmkarakaya/turkishReviews-ds on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 1.6861
- Train Sparse Categorical Accuracy: 0.8150
- Validation Loss: 1.9777
- Validation Sparse Categorical Accuracy: 0.7250
- Epoch: 4
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', 'learning_rate': 5e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
- training_precision: float32
Training results
| Train Loss | Train Sparse Categorical Accuracy | Validation Loss | Validation Sparse Categorical Accuracy | Epoch |
|---|---|---|---|---|
| 3.0394 | 0.5171 | 2.7152 | 0.5841 | 0 |
| 2.5336 | 0.6247 | 2.4440 | 0.6318 | 1 |
| 2.2002 | 0.6958 | 2.2557 | 0.6659 | 2 |
| 1.9241 | 0.7608 | 2.1059 | 0.6932 | 3 |
| 1.6861 | 0.8150 | 1.9777 | 0.7250 | 4 |
Framework versions
- Transformers 4.21.1
- TensorFlow 2.8.2
- Datasets 2.4.0
- Tokenizers 0.12.1