mt5-small-finetuned-amazon-en-es
This model is a fine-tuned version of google/mt5-small on an cnn_dailymail dataset. It achieves the following results on the evaluation set:
- Loss: 2.9656
- Rouge1: 20.2011
- Rouge2: 7.4122
- Rougel: 17.8564
- Rougelsum: 18.8766
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 |
|---|---|---|---|---|---|---|---|
| 7.3296 | 1.0 | 359 | 3.3443 | 17.157 | 5.0252 | 13.7241 | 15.2096 |
| 3.7963 | 2.0 | 718 | 3.1227 | 19.3565 | 6.4323 | 16.2667 | 17.6293 |
| 3.466 | 3.0 | 1077 | 3.0429 | 20.6042 | 7.4904 | 18.0103 | 18.8393 |
| 3.3056 | 4.0 | 1436 | 2.9962 | 20.0641 | 7.5242 | 17.4293 | 18.251 |
| 3.1929 | 5.0 | 1795 | 3.0064 | 19.9075 | 6.7477 | 17.4271 | 18.1428 |
| 3.1217 | 6.0 | 2154 | 2.9834 | 20.206 | 7.3608 | 18.0178 | 18.8707 |
| 3.0865 | 7.0 | 2513 | 2.9700 | 20.5888 | 7.7139 | 18.2165 | 19.2697 |
| 3.0566 | 8.0 | 2872 | 2.9656 | 20.2011 | 7.4122 | 17.8564 | 18.8766 |
Framework versions
- Transformers 4.56.1
- Pytorch 2.11.0+cu128
- Datasets 3.6.0
- Tokenizers 0.22.2