mt5-small-finetuned-amazon-en-es
This model is a fine-tuned version of google/mt5-small on the None dataset. It achieves the following results on the evaluation set:
- Loss: 3.0235
- Rouge1: 17.3723
- Rouge2: 8.6788
- Rougel: 16.972
- Rougelsum: 16.8066
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: 5.6e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 8
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
|---|---|---|---|---|---|---|---|
| 3.6769 | 1.0 | 1209 | 3.2281 | 17.5299 | 9.3163 | 16.9743 | 16.9047 |
| 3.6541 | 2.0 | 2418 | 3.1183 | 16.9243 | 8.1519 | 16.4871 | 16.3384 |
| 3.4432 | 3.0 | 3627 | 3.0908 | 16.7411 | 8.5955 | 16.1601 | 15.9917 |
| 3.3225 | 4.0 | 4836 | 3.0774 | 16.3278 | 8.0157 | 15.7674 | 15.7251 |
| 3.2248 | 5.0 | 6045 | 3.0427 | 16.458 | 8.3155 | 16.1506 | 15.9907 |
| 3.17 | 6.0 | 7254 | 3.0316 | 16.8247 | 8.3449 | 16.4588 | 16.3216 |
| 3.1417 | 7.0 | 8463 | 3.0229 | 17.2503 | 8.814 | 16.818 | 16.6599 |
| 3.1189 | 8.0 | 9672 | 3.0235 | 17.3723 | 8.6788 | 16.972 | 16.8066 |
Framework versions
- Transformers 4.57.6
- Pytorch 2.11.0+cu128
- Datasets 3.6.0
- Tokenizers 0.22.2