metadata
license: mit
tags:
- generated_from_trainer
model-index:
- name: paraphraser-spanish-t5-small
results: []
paraphraser-spanish-t5-small
This model is a fine-tuned version of flax-community/spanish-t5-small on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.0804
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: 3
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.8574 | 0.37 | 2000 | 1.1683 |
| 0.7908 | 0.73 | 4000 | 1.1285 |
| 0.7447 | 1.37 | 6000 | 1.1043 |
| 0.7224 | 1.83 | 8000 | 1.0900 |
| 0.6863 | 2.29 | 10000 | 1.0811 |
| 0.6765 | 2.75 | 12000 | 1.0851 |
Framework versions
- Transformers 4.18.0
- Pytorch 1.11.0+cu113
- Datasets 2.1.0
- Tokenizers 0.12.1