<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
mt5-small-finetuned-summary-en-fr-finetuned-summary-en-fr
This model is a fine-tuned version of thekenken/mt5-small-finetuned-summary-en-fr on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.2663
- Rouge1: 0.226
- Rouge2: 0.0761
- Rougel: 0.1868
- Rougelsum: 0.1867
- Gen Len: 18.9787
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:
- learning_rate: 3.6e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| 2.4654 | 1.0 | 74615 | 2.3755 | 0.2166 | 0.0691 | 0.1789 | 0.1789 | 18.9725 |
| 2.3603 | 2.0 | 149230 | 2.3189 | 0.2222 | 0.0728 | 0.1835 | 0.1836 | 18.9777 |
| 2.3052 | 3.0 | 223845 | 2.2922 | 0.2246 | 0.0749 | 0.1854 | 0.1854 | 18.9823 |
| 2.272 | 4.0 | 298460 | 2.2733 | 0.2252 | 0.0757 | 0.1861 | 0.1861 | 18.9801 |
| 2.2532 | 5.0 | 373075 | 2.2663 | 0.226 | 0.0761 | 0.1868 | 0.1867 | 18.9787 |
Framework versions
- Transformers 4.34.1
- Pytorch 2.0.0
- Datasets 2.14.5
- Tokenizers 0.14.1
