paraphraser-spanish-mt5-small
This model is a fine-tuned version of google/mt5-small on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.4586
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 |
---|---|---|---|
3.5365 | 0.07 | 2000 | 1.7577 |
2.5821 | 0.14 | 4000 | 1.6885 |
2.3485 | 0.21 | 6000 | 1.6532 |
2.2427 | 0.28 | 8000 | 1.5780 |
2.1358 | 0.35 | 10000 | 1.5455 |
2.0808 | 0.42 | 12000 | 1.5185 |
2.0139 | 0.5 | 14000 | 1.5130 |
1.9883 | 0.57 | 16000 | 1.5012 |
1.969 | 0.64 | 18000 | 1.4911 |
1.9697 | 0.71 | 20000 | 1.4706 |
1.9552 | 0.78 | 22000 | 1.4653 |
1.9264 | 0.85 | 24000 | 1.4669 |
1.932 | 0.92 | 26000 | 1.4569 |
1.9256 | 0.99 | 28000 | 1.4586 |
Framework versions
- Transformers 4.26.0
- Pytorch 1.13.1+cu116
- Datasets 2.9.0
- Tokenizers 0.13.2
- Downloads last month
- 18
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.