metadata
license: apache-2.0
base_model: vgaraujov/t5-base-spanish
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: symptom_extraction
results: []
symptom_extraction
This model is a fine-tuned version of vgaraujov/t5-base-spanish on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1424
- Rouge1: 0.3849
- Rouge2: 0.3231
- Rougel: 0.3816
- Rougelsum: 0.3814
- Gen Len: 19.0
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| 0.2061 | 1.0 | 640 | 0.1686 | 0.3824 | 0.3166 | 0.3784 | 0.3782 | 19.0 |
| 0.195 | 2.0 | 1280 | 0.1515 | 0.3841 | 0.3204 | 0.3803 | 0.3801 | 19.0 |
| 0.2035 | 3.0 | 1920 | 0.1448 | 0.3851 | 0.3226 | 0.3817 | 0.3815 | 19.0 |
| 0.1784 | 4.0 | 2560 | 0.1424 | 0.3849 | 0.3231 | 0.3816 | 0.3814 | 19.0 |
Framework versions
- Transformers 4.38.1
- Pytorch 2.1.0+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2