--- license: apache-2.0 tags: - generated_from_keras_callback model-index: - name: Apache20Classic_Train_Balance_DATA_ratio_4 results: [] --- # Apache20Classic_Train_Balance_DATA_ratio_4 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: 0.3728 - Train Accuracy: 0.8276 - Validation Loss: 0.4573 - Validation Accuracy: 0.7953 - 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': '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': False, '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 | |:----------:|:--------------:|:---------------:|:-------------------:|:-----:| | 0.4955 | 0.8009 | 0.4557 | 0.7930 | 0 | | 0.4392 | 0.8060 | 0.4709 | 0.8047 | 1 | | 0.3728 | 0.8276 | 0.4573 | 0.7953 | 2 | ### Framework versions - Transformers 4.29.2 - TensorFlow 2.12.0 - Datasets 2.12.0 - Tokenizers 0.13.3