metadata
license: apache-2.0
tags:
- generated_from_keras_callback
base_model: google/mt5-base
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: 0.2155
- Validation Loss: 2.4691
- Epoch: 19
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 |
|---|---|---|
| 4.8782 | 3.0764 | 0 |
| 3.0550 | 2.4897 | 1 |
| 2.4361 | 2.1678 | 2 |
| 2.0424 | 1.9982 | 3 |
| 1.7454 | 1.8860 | 4 |
| 1.5089 | 1.8502 | 5 |
| 1.3137 | 1.8682 | 6 |
| 1.1487 | 1.8252 | 7 |
| 0.9793 | 1.8486 | 8 |
| 0.8428 | 1.8815 | 9 |
| 0.7107 | 1.9716 | 10 |
| 0.6015 | 2.0271 | 11 |
| 0.5106 | 2.1239 | 12 |
| 0.4392 | 2.2095 | 13 |
| 0.3786 | 2.2045 | 14 |
| 0.3315 | 2.2884 | 15 |
| 0.2882 | 2.3419 | 16 |
| 0.2587 | 2.4029 | 17 |
| 0.2354 | 2.4173 | 18 |
| 0.2155 | 2.4691 | 19 |
Framework versions
- Transformers 4.37.2
- TensorFlow 2.15.0
- Datasets 2.17.0
- Tokenizers 0.15.2