my_awesome_opus_books_model
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: 1.6037
- Bleu: 5.7884
- Gen Len: 17.5934
Model description
HuggingFace T5-small tutorial, en-fr translate model.
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 |
|---|---|---|---|---|---|
| 1.8398 | 1.0 | 6355 | 1.6266 | 5.604 | 17.6036 |
| 1.8127 | 2.0 | 12710 | 1.6037 | 5.7884 | 17.5934 |
Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu117
- Datasets 2.14.5
- Tokenizers 0.13.3
- Downloads last month
- 3
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for Alexle/T5-small-en-fr
Base model
google-t5/t5-smallDataset used to train Alexle/T5-small-en-fr
Evaluation results
- Bleu on opus_booksself-reported5.788