| --- |
| license: mit |
| tags: |
| - generated_from_keras_callback |
| model-index: |
| - name: GCopoulos/deberta-base-finetuned-answer_pol |
| 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. --> |
|
|
| # GCopoulos/deberta-base-finetuned-answer_pol |
| |
| This model is a fine-tuned version of [microsoft/deberta-base](https://huggingface.co/microsoft/deberta-base) on an unknown dataset. |
| It achieves the following results on the evaluation set: |
| - Train Loss: 0.0755 |
| - Validation Loss: 0.6949 |
| - Train F1: 0.8489 |
| - Epoch: 2 |
| |
| ## 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': 'AdamWeightDecay', 'learning_rate': {'class_name': 'WarmUp', 'config': {'initial_learning_rate': 7e-05, 'decay_schedule_fn': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 7e-05, 'decay_steps': 653, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, '__passive_serialization__': True}, 'warmup_steps': 10, 'power': 1.0, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01} |
| - training_precision: float32 |
| |
| ### Training results |
| |
| | Train Loss | Validation Loss | Train F1 | Epoch | |
| |:----------:|:---------------:|:--------:|:-----:| |
| | 0.5343 | 0.6051 | 0.8389 | 0 | |
| | 0.1790 | 0.7237 | 0.8194 | 1 | |
| | 0.0755 | 0.6949 | 0.8489 | 2 | |
| |
| |
| ### Framework versions |
| |
| - Transformers 4.30.0 |
| - TensorFlow 2.12.0 |
| - Datasets 2.12.0 |
| - Tokenizers 0.13.3 |
| |
