<!-- 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. -->
t5-base-finetuned-es-to-maq
This model is a fine-tuned version of t5-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.5592
- Bleu: 0.1256
- Gen Len: 19.0
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: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|---|---|---|---|---|---|
| No log | 1.0 | 199 | 2.1563 | 0.0531 | 19.0 |
| No log | 2.0 | 398 | 1.8696 | 0.0492 | 19.0 |
| 2.4958 | 3.0 | 597 | 1.7541 | 0.0568 | 19.0 |
| 2.4958 | 4.0 | 796 | 1.6838 | 0.0874 | 19.0 |
| 2.4958 | 5.0 | 995 | 1.6383 | 0.0975 | 19.0 |
| 1.8903 | 6.0 | 1194 | 1.6066 | 0.1037 | 19.0 |
| 1.8903 | 7.0 | 1393 | 1.5854 | 0.122 | 19.0 |
| 1.7725 | 8.0 | 1592 | 1.5696 | 0.1192 | 19.0 |
| 1.7725 | 9.0 | 1791 | 1.5624 | 0.1241 | 19.0 |
| 1.7725 | 10.0 | 1990 | 1.5592 | 0.1256 | 19.0 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.0+cu118
- Datasets 2.11.0
- Tokenizers 0.13.3
