<!-- 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. -->
my_awesome_opus_books_model_df
This model is a fine-tuned version of t5-small on the opus_books dataset. It achieves the following results on the evaluation set:
- Loss: 3.2250
- Bleu: 1.7828
- Gen Len: 16.9721
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
Training results
Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
---|---|---|---|---|---|
3.5639 | 1.0 | 4674 | 3.2830 | 1.5733 | 16.9662 |
3.4771 | 2.0 | 9348 | 3.2250 | 1.7828 | 16.9721 |
Framework versions
- Transformers 4.17.0
- Pytorch 1.8.1+cu111
- Datasets 2.13.0
- Tokenizers 0.11.6