<!-- 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_ep9_lr3
This model is a fine-tuned version of ajtamayoh/NER_EHR_Spanish_model_Mulitlingual_BERT on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0904
- Precision: 0.7736
- Recall: 0.8277
- F1: 0.7997
- Accuracy: 0.9699
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: 5e-07
- 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: 9
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 467 | 0.1271 | 0.6992 | 0.7545 | 0.7258 | 0.9582 |
| 0.1807 | 2.0 | 934 | 0.1061 | 0.7236 | 0.7831 | 0.7521 | 0.9638 |
| 0.126 | 3.0 | 1401 | 0.0988 | 0.7443 | 0.8029 | 0.7725 | 0.9663 |
| 0.113 | 4.0 | 1868 | 0.0954 | 0.7534 | 0.8183 | 0.7845 | 0.9677 |
| 0.1072 | 5.0 | 2335 | 0.0927 | 0.7634 | 0.8164 | 0.7890 | 0.9688 |
| 0.1014 | 6.0 | 2802 | 0.0918 | 0.7700 | 0.8255 | 0.7968 | 0.9694 |
| 0.0982 | 7.0 | 3269 | 0.0910 | 0.7726 | 0.8277 | 0.7992 | 0.9696 |
| 0.0977 | 8.0 | 3736 | 0.0905 | 0.7739 | 0.8282 | 0.8002 | 0.9698 |
| 0.0938 | 9.0 | 4203 | 0.0904 | 0.7736 | 0.8277 | 0.7997 | 0.9699 |
Framework versions
- Transformers 4.27.4
- Pytorch 2.0.0+cu118
- Datasets 2.11.0
- Tokenizers 0.13.3
