metadata
license: apache-2.0
tags:
- generated_from_keras_callback
base_model: google/mt5-base
model-index:
- name: bic-fil-mt5b
results: []
bic-fil-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: 0.4212
- Validation Loss: 2.6637
- 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 |
|---|---|---|
| 6.4138 | 5.0392 | 0 |
| 4.7105 | 3.8096 | 1 |
| 3.7780 | 3.2907 | 2 |
| 3.2925 | 3.0002 | 3 |
| 2.9407 | 2.8001 | 4 |
| 2.6372 | 2.6142 | 5 |
| 2.3310 | 2.4768 | 6 |
| 2.1052 | 2.2808 | 7 |
| 1.8424 | 2.2372 | 8 |
| 1.6298 | 2.2036 | 9 |
| 1.4416 | 2.1891 | 10 |
| 1.2660 | 2.1835 | 11 |
| 1.1067 | 2.2480 | 12 |
| 0.9585 | 2.2821 | 13 |
| 0.8516 | 2.3494 | 14 |
| 0.7260 | 2.4127 | 15 |
| 0.6270 | 2.5566 | 16 |
| 0.5473 | 2.5503 | 17 |
| 0.4718 | 2.6471 | 18 |
| 0.4212 | 2.6637 | 19 |
Framework versions
- Transformers 4.37.2
- TensorFlow 2.15.0
- Datasets 2.17.0
- Tokenizers 0.15.2