distilbert-base-spanish-uncased-finetuned-amazon
This model is a fine-tuned version of dccuchile/distilbert-base-spanish-uncased on the amazon_reviews_multi dataset. It achieves the following results on the evaluation set:
- Loss: 3.5344
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: 64
- eval_batch_size: 64
- 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 |
|---|---|---|---|
| 3.6909 | 1.0 | 44 | 3.7628 |
| 3.6793 | 2.0 | 88 | 3.6399 |
| 3.6719 | 3.0 | 132 | 3.6293 |
| 3.6393 | 4.0 | 176 | 3.5817 |
| 3.5905 | 5.0 | 220 | 3.6311 |
| 3.5413 | 6.0 | 264 | 3.5839 |
| 3.5402 | 7.0 | 308 | 3.5679 |
| 3.5335 | 8.0 | 352 | 3.5656 |
| 3.5339 | 9.0 | 396 | 3.6040 |
| 3.5239 | 10.0 | 440 | 3.5724 |
Framework versions
- Transformers 4.27.3
- Pytorch 1.13.1+cu116
- Datasets 2.10.1
- Tokenizers 0.13.2