metadata
license: apache-2.0
base_model: google/mt5-base
tags:
- generated_from_keras_callback
model-index:
- name: fil-bic-mt5b
results: []
fil-bic-mt5b
This model is a fine-tuned version of google/mt5-base on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 1.6869
- Validation Loss: 2.1368
- Epoch: 9
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': 0.001, '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 |
|---|---|---|
| 6.4314 | 5.5917 | 0 |
| 5.3928 | 4.4267 | 1 |
| 4.1407 | 3.3539 | 2 |
| 3.3195 | 2.9488 | 3 |
| 2.8989 | 2.6887 | 4 |
| 2.5563 | 2.4716 | 5 |
| 2.3243 | 2.3927 | 6 |
| 2.0852 | 2.2162 | 7 |
| 1.8621 | 2.1450 | 8 |
| 1.6869 | 2.1368 | 9 |
Framework versions
- Transformers 4.37.2
- TensorFlow 2.15.0
- Datasets 2.17.0
- Tokenizers 0.15.2