mt5-small-finetuned-8epochs-opus_books-en-to-it
This model is a fine-tuned version of google/mt5-small on the opus_books dataset. It achieves the following results on the evaluation set:
- Loss: 2.7220
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: 2e-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 |
|---|---|---|---|
| 4.1572 | 1.0 | 3638 | 3.1652 |
| 3.7846 | 2.0 | 7276 | 2.9708 |
| 3.6056 | 3.0 | 10914 | 2.8673 |
| 3.4722 | 4.0 | 14552 | 2.8067 |
| 3.4006 | 5.0 | 18190 | 2.7665 |
| 3.344 | 6.0 | 21828 | 2.7414 |
| 3.3131 | 7.0 | 25466 | 2.7268 |
| 3.3251 | 8.0 | 29104 | 2.7220 |
Framework versions
- Transformers 4.23.1
- Pytorch 1.12.1+cu113
- Datasets 2.6.1
- Tokenizers 0.13.1