metadata
license: apache-2.0
base_model: t5-small
tags:
- generated_from_keras_callback
model-index:
- name: tarsssss/eng-jagoy-t5-001
results: []
tarsssss/eng-jagoy-t5-001
This model is a fine-tuned version of t5-small on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 6.4250
- Validation Loss: 6.2436
- Epoch: 12
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': 2e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.01}
- training_precision: float32
Training results
| Train Loss | Validation Loss | Epoch |
|---|---|---|
| 7.8603 | 7.4105 | 0 |
| 7.3775 | 7.1273 | 1 |
| 7.1632 | 6.9598 | 2 |
| 7.0228 | 6.8372 | 3 |
| 6.9085 | 6.7335 | 4 |
| 6.8226 | 6.6458 | 5 |
| 6.7451 | 6.5671 | 6 |
| 6.6785 | 6.5022 | 7 |
| 6.6254 | 6.4409 | 8 |
| 6.5606 | 6.3842 | 9 |
| 6.5163 | 6.3361 | 10 |
| 6.4682 | 6.2908 | 11 |
| 6.4250 | 6.2436 | 12 |
Framework versions
- Transformers 4.33.2
- TensorFlow 2.10.0
- Datasets 2.15.0
- Tokenizers 0.13.3