<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
bert-finetuned-ner-clinical-BETO-1-uncased
This model is a fine-tuned version of dccuchile/bert-base-spanish-wwm-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.5376
- Precision: 0.7341
- Recall: 0.7772
- F1: 0.7550
- Accuracy: 0.9177
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: 12
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
0.4682 | 1.0 | 502 | 0.3263 | 0.6124 | 0.7344 | 0.6678 | 0.8939 |
0.2443 | 2.0 | 1004 | 0.2778 | 0.6809 | 0.7519 | 0.7147 | 0.9122 |
0.1728 | 3.0 | 1506 | 0.2898 | 0.7011 | 0.7481 | 0.7238 | 0.9155 |
0.1277 | 4.0 | 2008 | 0.3182 | 0.6970 | 0.7640 | 0.7290 | 0.9118 |
0.0928 | 5.0 | 2510 | 0.3578 | 0.6975 | 0.7667 | 0.7305 | 0.9128 |
0.0699 | 6.0 | 3012 | 0.3931 | 0.7058 | 0.7794 | 0.7407 | 0.9102 |
0.0538 | 7.0 | 3514 | 0.4213 | 0.7225 | 0.7574 | 0.7395 | 0.9140 |
0.0413 | 8.0 | 4016 | 0.4387 | 0.7143 | 0.7821 | 0.7467 | 0.9147 |
0.033 | 9.0 | 4518 | 0.4997 | 0.7184 | 0.7728 | 0.7446 | 0.9147 |
0.0265 | 10.0 | 5020 | 0.5056 | 0.7180 | 0.7728 | 0.7444 | 0.9152 |
0.0225 | 11.0 | 5522 | 0.5237 | 0.7250 | 0.7728 | 0.7481 | 0.9164 |
0.0176 | 12.0 | 6024 | 0.5376 | 0.7341 | 0.7772 | 0.7550 | 0.9177 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3