<!-- 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. -->
Najia/t5-base-finetuned-urdu
This model is a fine-tuned version of t5-base on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 0.0701
- Validation Loss: 0.0538
- 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': 3000, '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 |
---|---|---|
0.1270 | 0.1669 | 0 |
0.0896 | 0.0654 | 1 |
0.0829 | 0.0598 | 2 |
0.0781 | 0.0511 | 3 |
0.0749 | 0.0534 | 4 |
0.0733 | 0.0533 | 5 |
0.0711 | 0.0515 | 6 |
0.0701 | 0.0538 | 7 |
Framework versions
- Transformers 4.29.0
- TensorFlow 2.12.0
- Datasets 2.12.0
- Tokenizers 0.13.3