--- license: apache-2.0 tags: - generated_from_keras_callback model-index: - name: mt5-small-finetuned-amazon-en results: [] --- # mt5-small-finetuned-amazon-en This model is a fine-tuned version of [google/mt5-small](https://huggingface.co./google/mt5-small) on an unknown dataset. It achieves the following results on the evaluation set: - Train Loss: 4.7061 - Validation Loss: 2.9222 - Epoch: 7 ## 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': 'PolynomialDecay', 'config': {'initial_learning_rate': 5.6e-05, 'decay_steps': 4088, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, '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: mixed_float16 ### Training results | Train Loss | Validation Loss | Epoch | |:----------:|:---------------:|:-----:| | 11.5921 | 4.9298 | 0 | | 7.0246 | 3.8648 | 1 | | 5.9216 | 3.3448 | 2 | | 5.4516 | 3.1383 | 3 | | 5.1038 | 3.0219 | 4 | | 4.9252 | 2.9631 | 5 | | 4.7894 | 2.9329 | 6 | | 4.7061 | 2.9222 | 7 | ### Framework versions - Transformers 4.29.2 - TensorFlow 2.12.0 - Datasets 2.12.0 - Tokenizers 0.13.3