metadata
license: apache-2.0
base_model: t5-base
tags:
- generated_from_keras_callback
model-index:
- name: CapitainData/dyu-fr-t5-base_v3
results: []
CapitainData/dyu-fr-t5-base_v3
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: 2.3570
- Validation Loss: 2.4646
- Epoch: 11
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 |
|---|---|---|
| 3.3233 | 2.8819 | 0 |
| 3.0679 | 2.7736 | 1 |
| 2.9557 | 2.7031 | 2 |
| 2.8537 | 2.6517 | 3 |
| 2.7672 | 2.6141 | 4 |
| 2.6959 | 2.5790 | 5 |
| 2.6234 | 2.5559 | 6 |
| 2.5663 | 2.5288 | 7 |
| 2.5025 | 2.5099 | 8 |
| 2.4535 | 2.4976 | 9 |
| 2.3996 | 2.4791 | 10 |
| 2.3570 | 2.4646 | 11 |
Framework versions
- Transformers 4.38.2
- TensorFlow 2.16.1
- Datasets 2.18.0
- Tokenizers 0.15.2