paraphraser-spanish-t5-base
This model is a fine-tuned version of milyiyo/paraphraser-spanish-t5-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.7572
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: 10
- eval_batch_size: 10
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 1
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.1212 | 0.07 | 2000 | 0.8120 |
| 1.2263 | 0.14 | 4000 | 0.7773 |
| 1.1976 | 0.21 | 6000 | 0.7745 |
| 1.1828 | 0.28 | 8000 | 0.7675 |
| 1.1399 | 0.35 | 10000 | 0.7668 |
| 1.1378 | 0.42 | 12000 | 0.7651 |
| 1.1035 | 0.5 | 14000 | 0.7644 |
| 1.0923 | 0.57 | 16000 | 0.7633 |
| 1.0924 | 0.64 | 18000 | 0.7594 |
| 1.0943 | 0.71 | 20000 | 0.7578 |
| 1.0872 | 0.78 | 22000 | 0.7575 |
| 1.0755 | 0.85 | 24000 | 0.7599 |
| 1.0806 | 0.92 | 26000 | 0.7558 |
| 1.079 | 0.99 | 28000 | 0.7572 |
Framework versions
- Transformers 4.24.0
- Pytorch 1.12.1+cu113
- Datasets 2.7.0
- Tokenizers 0.13.2