<!-- 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. -->
nominal-groups-recognition-beto-clinical-wl-es
This model is a fine-tuned version of plncmm/beto-clinical-wl-es on the bastianchinchon/spanish_nominal_groups_conll2003 dataset. It achieves the following results on the evaluation set:
- Loss: 0.2338
- Body Part Precision: 0.7894
- Body Part Recall: 0.8257
- Body Part F1: 0.8071
- Body Part Number: 413
- Disease Precision: 0.7790
- Disease Recall: 0.8133
- Disease F1: 0.7958
- Disease Number: 975
- Family Member Precision: 0.8286
- Family Member Recall: 0.9667
- Family Member F1: 0.8923
- Family Member Number: 30
- Medication Precision: 0.8913
- Medication Recall: 0.8817
- Medication F1: 0.8865
- Medication Number: 93
- Procedure Precision: 0.7130
- Procedure Recall: 0.7910
- Procedure F1: 0.75
- Procedure Number: 311
- Overall Precision: 0.7758
- Overall Recall: 0.8183
- Overall F1: 0.7965
- Overall Accuracy: 0.9382
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: 13
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Body Part Precision | Body Part Recall | Body Part F1 | Body Part Number | Disease Precision | Disease Recall | Disease F1 | Disease Number | Family Member Precision | Family Member Recall | Family Member F1 | Family Member Number | Medication Precision | Medication Recall | Medication F1 | Medication Number | Procedure Precision | Procedure Recall | Procedure F1 | Procedure Number | Overall Precision | Overall Recall | Overall F1 | Overall Accuracy |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0.2998 | 1.0 | 1004 | 0.2127 | 0.7460 | 0.7893 | 0.7671 | 413 | 0.7612 | 0.7815 | 0.7713 | 975 | 0.9062 | 0.9667 | 0.9355 | 30 | 0.8462 | 0.8280 | 0.8370 | 93 | 0.6583 | 0.7556 | 0.7036 | 311 | 0.7450 | 0.7843 | 0.7642 | 0.9331 |
| 0.1566 | 2.0 | 2008 | 0.2278 | 0.7780 | 0.8232 | 0.8 | 413 | 0.7847 | 0.8 | 0.7923 | 975 | 0.8529 | 0.9667 | 0.9062 | 30 | 0.8710 | 0.8710 | 0.8710 | 93 | 0.7346 | 0.7653 | 0.7496 | 311 | 0.7800 | 0.8057 | 0.7927 | 0.9367 |
| 0.1089 | 3.0 | 3012 | 0.2338 | 0.7894 | 0.8257 | 0.8071 | 413 | 0.7790 | 0.8133 | 0.7958 | 975 | 0.8286 | 0.9667 | 0.8923 | 30 | 0.8913 | 0.8817 | 0.8865 | 93 | 0.7130 | 0.7910 | 0.75 | 311 | 0.7758 | 0.8183 | 0.7965 | 0.9382 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
