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: 3.0628
- Rouge1: 18.2745
- Rouge2: 8.9341
- Rougel: 17.7329
- Rougelsum: 17.7032
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: 16
- eval_batch_size: 16
- 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 |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 605 | 3.4162 | 12.6112 | 3.9985 | 12.1247 | 12.1926 |
| 12.8350 | 2.0 | 1210 | 3.2325 | 15.6049 | 7.2111 | 15.1154 | 15.1009 |
| 12.8350 | 3.0 | 1815 | 3.1578 | 16.1457 | 7.752 | 15.5819 | 15.5884 |
| 7.4935 | 4.0 | 2420 | 3.1299 | 17.0489 | 8.5235 | 16.4449 | 16.3916 |
| 7.4935 | 5.0 | 3025 | 3.0825 | 17.0426 | 8.604 | 16.5451 | 16.4277 |
| 6.9901 | 6.0 | 3630 | 3.0688 | 18.1609 | 9.0247 | 17.5536 | 17.5264 |
| 6.9901 | 7.0 | 4235 | 3.0658 | 18.2162 | 8.9419 | 17.6511 | 17.5678 |
| 6.7831 | 8.0 | 4840 | 3.0628 | 18.2745 | 8.9341 | 17.7329 | 17.7032 |
Framework versions
- Transformers 5.16.1
- Pytorch 2.11.0+cu128
- Datasets 3.6.0
- Tokenizers 0.23.1