--- license: apache-2.0 base_model: distilbert/distilbert-base-uncased tags: - generated_from_keras_callback model-index: - name: PlasmicZ/SIH3 results: [] --- # PlasmicZ/SIH3 This model is a fine-tuned version of [distilbert/distilbert-base-uncased](https://huggingface.co/distilbert/distilbert-base-uncased) on an unknown dataset. It achieves the following results on the evaluation set: - Train Loss: 3.1868 - Validation Loss: 3.1679 - Train Accuracy: 0.6194 - Epoch: 14 ## 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': None, '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': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 450, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False} - training_precision: float32 ### Training results | Train Loss | Validation Loss | Train Accuracy | Epoch | |:----------:|:---------------:|:--------------:|:-----:| | 3.6966 | 3.6944 | 0.0139 | 0 | | 3.6920 | 3.6912 | 0.0278 | 1 | | 3.6463 | 3.5387 | 0.3056 | 2 | | 3.4074 | 3.2592 | 0.5667 | 3 | | 3.2234 | 3.1679 | 0.6194 | 4 | | 3.1902 | 3.1679 | 0.6194 | 5 | | 3.1887 | 3.1679 | 0.6194 | 6 | | 3.1907 | 3.1679 | 0.6194 | 7 | | 3.1893 | 3.1679 | 0.6194 | 8 | | 3.1843 | 3.1679 | 0.6194 | 9 | | 3.1894 | 3.1679 | 0.6194 | 10 | | 3.1893 | 3.1679 | 0.6194 | 11 | | 3.1881 | 3.1679 | 0.6194 | 12 | | 3.1935 | 3.1679 | 0.6194 | 13 | | 3.1868 | 3.1679 | 0.6194 | 14 | ### Framework versions - Transformers 4.42.4 - TensorFlow 2.17.0 - Datasets 2.21.0 - Tokenizers 0.19.1