<!-- 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-bert-base-spanish-wwm-cased
This model is a fine-tuned version of dccuchile/bert-base-spanish-wwm-cased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3247
- Body Part Precision: 0.7066
- Body Part Recall: 0.7288
- Body Part F1: 0.7175
- Body Part Number: 413
- Disease Precision: 0.7316
- Disease Recall: 0.7662
- Disease F1: 0.7485
- Disease Number: 975
- Family Member Precision: 0.8333
- Family Member Recall: 0.8333
- Family Member F1: 0.8333
- Family Member Number: 30
- Medication Precision: 0.8148
- Medication Recall: 0.7097
- Medication F1: 0.7586
- Medication Number: 93
- Procedure Precision: 0.6419
- Procedure Recall: 0.6399
- Procedure F1: 0.6409
- Procedure Number: 311
- Overall Precision: 0.7163
- Overall Recall: 0.7344
- Overall F1: 0.7252
- Overall Accuracy: 0.9201
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: 5
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 |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0.4301 | 1.0 | 1004 | 0.3018 | 0.6054 | 0.7094 | 0.6533 | 413 | 0.6988 | 0.7067 | 0.7027 | 975 | 0.8889 | 0.8 | 0.8421 | 30 | 0.8025 | 0.6989 | 0.7471 | 93 | 0.5795 | 0.4920 | 0.5322 | 311 | 0.6645 | 0.6718 | 0.6681 | 0.9052 |
| 0.2384 | 2.0 | 2008 | 0.2903 | 0.6983 | 0.6949 | 0.6966 | 413 | 0.7402 | 0.7159 | 0.7278 | 975 | 0.8 | 0.8 | 0.8000 | 30 | 0.7283 | 0.7204 | 0.7243 | 93 | 0.6026 | 0.6045 | 0.6035 | 311 | 0.7069 | 0.6937 | 0.7003 | 0.9148 |
| 0.1625 | 3.0 | 3012 | 0.2948 | 0.6653 | 0.7603 | 0.7096 | 413 | 0.7412 | 0.7374 | 0.7393 | 975 | 0.9231 | 0.8 | 0.8571 | 30 | 0.8313 | 0.7419 | 0.7841 | 93 | 0.5789 | 0.6720 | 0.6220 | 311 | 0.6982 | 0.7327 | 0.7151 | 0.9188 |
| 0.1142 | 4.0 | 4016 | 0.3247 | 0.7066 | 0.7288 | 0.7175 | 413 | 0.7316 | 0.7662 | 0.7485 | 975 | 0.8333 | 0.8333 | 0.8333 | 30 | 0.8148 | 0.7097 | 0.7586 | 93 | 0.6419 | 0.6399 | 0.6409 | 311 | 0.7163 | 0.7344 | 0.7252 | 0.9201 |
| 0.0858 | 5.0 | 5020 | 0.3583 | 0.6996 | 0.7554 | 0.7264 | 413 | 0.7451 | 0.7436 | 0.7444 | 975 | 0.8333 | 0.8333 | 0.8333 | 30 | 0.8375 | 0.7204 | 0.7746 | 93 | 0.5976 | 0.6495 | 0.6225 | 311 | 0.7129 | 0.7305 | 0.7216 | 0.9180 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu117
- Datasets 2.13.1
- Tokenizers 0.13.3
