<!-- 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_ep6_lr1
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: 0.1352
- Precision: 0.8654
- Recall: 0.8689
- F1: 0.8671
- Accuracy: 0.9759
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-05
- 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: 6
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
No log | 1.0 | 467 | 0.1009 | 0.7821 | 0.8764 | 0.8266 | 0.9665 |
0.1009 | 2.0 | 934 | 0.0870 | 0.8476 | 0.8643 | 0.8559 | 0.9740 |
0.0521 | 3.0 | 1401 | 0.1020 | 0.8789 | 0.8497 | 0.8641 | 0.9746 |
0.0327 | 4.0 | 1868 | 0.1236 | 0.8707 | 0.8649 | 0.8678 | 0.9752 |
0.0175 | 5.0 | 2335 | 0.1290 | 0.8669 | 0.8700 | 0.8685 | 0.9759 |
0.0109 | 6.0 | 2802 | 0.1352 | 0.8654 | 0.8689 | 0.8671 | 0.9759 |
Framework versions
- Transformers 4.27.4
- Pytorch 1.13.1+cu116
- Datasets 2.11.0
- Tokenizers 0.13.2