--- license: apache-2.0 base_model: bert-base-uncased tags: - generated_from_keras_callback model-index: - name: ashhadahsan/amazon-theme-bert-base-finetuned results: [] --- # ashhadahsan/amazon-theme-bert-base-finetuned This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset. It achieves the following results on the evaluation set: - Train Loss: 0.0142 - Train Accuracy: 0.9923 - Validation Loss: 0.7089 - Validation Accuracy: 0.8797 - Epoch: 16 ## 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': 1.0, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': 3e-05, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False} - training_precision: float32 ### Training results | Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch | |:----------:|:--------------:|:---------------:|:-------------------:|:-----:| | 1.3910 | 0.5974 | 0.8022 | 0.8008 | 0 | | 0.2739 | 0.9554 | 0.6211 | 0.8609 | 1 | | 0.0782 | 0.9885 | 0.5895 | 0.8609 | 2 | | 0.0418 | 0.9913 | 0.5456 | 0.8797 | 3 | | 0.0318 | 0.9908 | 0.5729 | 0.8797 | 4 | | 0.0251 | 0.9906 | 0.5747 | 0.8797 | 5 | | 0.0211 | 0.9913 | 0.5994 | 0.8797 | 6 | | 0.0195 | 0.9906 | 0.6241 | 0.8797 | 7 | | 0.0184 | 0.9911 | 0.6244 | 0.8797 | 8 | | 0.0170 | 0.9904 | 0.6235 | 0.8797 | 9 | | 0.0159 | 0.9913 | 0.6619 | 0.8797 | 10 | | 0.0164 | 0.9913 | 0.6501 | 0.8797 | 11 | | 0.0165 | 0.9911 | 0.6452 | 0.8835 | 12 | | 0.0155 | 0.9908 | 0.6727 | 0.8872 | 13 | | 0.0149 | 0.9904 | 0.6798 | 0.8835 | 14 | | 0.0144 | 0.9906 | 0.6905 | 0.8797 | 15 | | 0.0142 | 0.9923 | 0.7089 | 0.8797 | 16 | ### Framework versions - Transformers 4.31.0 - TensorFlow 2.12.0 - Tokenizers 0.13.3