mt5-small-finetuned-amazon-en-es
This model is a fine-tuned version of google/mt5-small on the Amazon Multilingual Reviews dataset. It achieves the following results on the evaluation set:
- Loss: 3.0300
- Rouge1: 17.0969
- Rouge2: 8.1081
- Rougel: 16.7069
- Rougelsum: 16.7227
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: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 8
Training results
Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
---|---|---|---|---|---|---|---|
6.6964 | 1.0 | 1209 | 3.3036 | 13.8775 | 6.0277 | 13.4042 | 13.4677 |
3.9031 | 2.0 | 2418 | 3.1324 | 16.5514 | 8.1488 | 15.8036 | 15.8162 |
3.5802 | 3.0 | 3627 | 3.0846 | 17.9548 | 9.0413 | 17.4648 | 17.3896 |
3.4212 | 4.0 | 4836 | 3.0613 | 18.0845 | 8.6844 | 17.3944 | 17.3103 |
3.3216 | 5.0 | 6045 | 3.0606 | 17.3438 | 8.4715 | 16.9527 | 16.9714 |
3.2427 | 6.0 | 7254 | 3.0392 | 17.3668 | 8.7507 | 17.1243 | 17.0755 |
3.2081 | 7.0 | 8463 | 3.0344 | 17.4993 | 8.6458 | 17.0474 | 16.9892 |
3.1806 | 8.0 | 9672 | 3.0300 | 17.0969 | 8.1081 | 16.7069 | 16.7227 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1
- Datasets 2.10.0
- Tokenizers 0.11.0