metadata
base_model: MMG/bert-base-spanish-wwm-cased-finetuned-spa-squad2-es-finetuned-sqac
tags:
- generated_from_trainer
model-index:
- name: uda_rules_qa
results: []
uda_rules_qa
This model is a fine-tuned version of MMG/bert-base-spanish-wwm-cased-finetuned-spa-squad2-es-finetuned-sqac on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.8326
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: 8
- eval_batch_size: 8
- 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 |
|---|---|---|---|
| 3.5008 | 1.0 | 22 | 1.6862 |
| 1.1372 | 2.0 | 44 | 1.1231 |
| 0.7131 | 3.0 | 66 | 0.8089 |
| 0.4438 | 4.0 | 88 | 0.8190 |
| 0.3027 | 5.0 | 110 | 0.9009 |
| 0.182 | 6.0 | 132 | 0.8840 |
| 0.1399 | 7.0 | 154 | 0.7756 |
| 0.105 | 8.0 | 176 | 0.7858 |
| 0.0742 | 9.0 | 198 | 0.8326 |
| 0.0637 | 10.0 | 220 | 0.8326 |
Framework versions
- Transformers 4.36.2
- Pytorch 2.1.2+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0