cansen88/PromptGenerator_32_topic_finetuned

1---2license: mit3tags:4- generated_from_keras_callback5model-index:6- name: PromptGenerator_32_topic_finetuned7  results: []8---9 10<!-- This model card has been generated automatically according to the information Keras had access to. You should11probably proofread and complete it, then remove this comment. -->12 13# PromptGenerator_32_topic_finetuned14 15This model is a fine-tuned version of [kmkarakaya/turkishReviews-ds](https://huggingface.co/kmkarakaya/turkishReviews-ds) on an unknown dataset.16It achieves the following results on the evaluation set:17- Train Loss: 0.056918- Train Sparse Categorical Accuracy: 1.019- Validation Loss: 0.078720- Validation Sparse Categorical Accuracy: 1.021- Epoch: 422 23## Model description24 25More information needed26 27## Intended uses & limitations28 29More information needed30 31## Training and evaluation data32 33More information needed34 35## Training procedure36 37### Training hyperparameters38 39The following hyperparameters were used during training:40- optimizer: {'name': 'Adam', 'learning_rate': 5e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}41- training_precision: float3242 43### Training results44 45| Train Loss | Train Sparse Categorical Accuracy | Validation Loss | Validation Sparse Categorical Accuracy | Epoch |46|:----------:|:---------------------------------:|:---------------:|:--------------------------------------:|:-----:|47| 1.7185     | 0.7860                            | 0.5569          | 0.9868                                 | 0     |48| 0.4711     | 0.9958                            | 0.2097          | 0.9995                                 | 1     |49| 0.2016     | 1.0000                            | 0.1197          | 0.9999                                 | 2     |50| 0.1014     | 1.0                               | 0.0903          | 0.9999                                 | 3     |51| 0.0569     | 1.0                               | 0.0787          | 1.0                                    | 4     |52 53 54### Framework versions55 56- Transformers 4.21.157- TensorFlow 2.8.258- Datasets 2.4.059- Tokenizers 0.12.160