BERT_ep7_lr2
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: 0.0921
- Precision: 0.8435
- Recall: 0.8668
- F1: 0.8550
- Accuracy: 0.9757
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-06
- 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: 7
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
No log | 1.0 | 467 | 0.0875 | 0.8131 | 0.8272 | 0.8201 | 0.9712 |
0.1124 | 2.0 | 934 | 0.0855 | 0.8073 | 0.8649 | 0.8351 | 0.9728 |
0.075 | 3.0 | 1401 | 0.0824 | 0.8359 | 0.8579 | 0.8467 | 0.9754 |
0.0603 | 4.0 | 1868 | 0.0835 | 0.8409 | 0.8587 | 0.8497 | 0.9754 |
0.0474 | 5.0 | 2335 | 0.0886 | 0.8428 | 0.8695 | 0.8560 | 0.9755 |
0.0434 | 6.0 | 2802 | 0.0899 | 0.8450 | 0.8682 | 0.8565 | 0.9758 |
0.0391 | 7.0 | 3269 | 0.0921 | 0.8435 | 0.8668 | 0.8550 | 0.9757 |
Framework versions
- Transformers 4.27.3
- Pytorch 1.13.1+cu116
- Datasets 2.10.1
- Tokenizers 0.13.2
- Downloads last month
- 37
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.