| license: apache-2.0 | |
| base_model: t5-small | |
| tags: | |
| - generated_from_keras_callback | |
| model-index: | |
| - name: dyu-fr-t5-small | |
| results: [] | |
| <!-- This model card has been generated automatically according to the information Keras had access to. You should | |
| probably proofread and complete it, then remove this comment. --> | |
| # dyu-fr-t5-small | |
| This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on an unknown dataset. | |
| It achieves the following results on the evaluation set: | |
| - Train Loss: 2.7460 | |
| - Validation Loss: 2.7296 | |
| - Epoch: 24 | |
| ## 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 | | |
| |:----------:|:---------------:|:-----:| | |
| | 3.6901 | 3.2495 | 0 | | |
| | 3.4675 | 3.1435 | 1 | | |
| | 3.3768 | 3.0836 | 2 | | |
| | 3.3150 | 3.0325 | 3 | | |
| | 3.2568 | 2.9926 | 4 | | |
| | 3.2142 | 2.9639 | 5 | | |
| | 3.1743 | 2.9341 | 6 | | |
| | 3.1376 | 2.9166 | 7 | | |
| | 3.1019 | 2.8968 | 8 | | |
| | 3.0716 | 2.8781 | 9 | | |
| | 3.0480 | 2.8647 | 10 | | |
| | 3.0187 | 2.8465 | 11 | | |
| | 2.9931 | 2.8347 | 12 | | |
| | 2.9661 | 2.8247 | 13 | | |
| | 2.9482 | 2.8123 | 14 | | |
| | 2.9176 | 2.7992 | 15 | | |
| | 2.9023 | 2.7922 | 16 | | |
| | 2.8792 | 2.7826 | 17 | | |
| | 2.8600 | 2.7731 | 18 | | |
| | 2.8422 | 2.7683 | 19 | | |
| | 2.8236 | 2.7567 | 20 | | |
| | 2.7979 | 2.7493 | 21 | | |
| | 2.7856 | 2.7438 | 22 | | |
| | 2.7681 | 2.7346 | 23 | | |
| | 2.7460 | 2.7296 | 24 | | |
| ### Framework versions | |
| - Transformers 4.38.2 | |
| - TensorFlow 2.16.1 | |
| - Datasets 2.18.0 | |
| - Tokenizers 0.15.2 | |