<!-- 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-amazon-en-es
This model is a fine-tuned version of google/mt5-small on the amazon_reviews_multi dataset (https://huggingface.co/datasets/amazon_reviews_multi), with a filter applied to reviews about books.
The filter_books function is used to filter examples in the data and returns only those that belong to the "book" or "digital ebook purchase" category.
It achieves the following results on the evaluation set:
- Loss: 3.0270
- Rouge1: 16.8614
- Rouge2: 8.3352
- Rougel: 16.5595
- Rougelsum: 16.5755
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 |
|---|---|---|---|---|---|---|---|
| 7.376 | 1.0 | 1209 | 3.3114 | 13.6834 | 5.4759 | 13.2778 | 13.3315 |
| 3.9197 | 2.0 | 2418 | 3.1662 | 15.4107 | 7.396 | 15.0443 | 15.0493 |
| 3.5954 | 3.0 | 3627 | 3.0844 | 15.4126 | 7.2537 | 15.0816 | 15.1281 |
| 3.4243 | 4.0 | 4836 | 3.0384 | 15.9869 | 7.7568 | 15.7054 | 15.6149 |
| 3.3145 | 5.0 | 6045 | 3.0512 | 17.3119 | 8.412 | 16.8461 | 16.7631 |
| 3.2597 | 6.0 | 7254 | 3.0237 | 16.7165 | 7.9706 | 16.4276 | 16.3935 |
| 3.2094 | 7.0 | 8463 | 3.0308 | 17.4737 | 8.7048 | 17.0836 | 17.0624 |
| 3.1886 | 8.0 | 9672 | 3.0270 | 16.8614 | 8.3352 | 16.5595 | 16.5755 |
Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cpu
- Datasets 2.14.5
- Tokenizers 0.13.3
