BERT_ep6_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: 0.0943
- Precision: 0.8387
- Recall: 0.8727
- F1: 0.8554
- Accuracy: 0.9748
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: 6
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
No log | 1.0 | 467 | 0.0925 | 0.7979 | 0.8341 | 0.8156 | 0.9701 |
0.1097 | 2.0 | 934 | 0.0869 | 0.8285 | 0.8621 | 0.8450 | 0.9730 |
0.0748 | 3.0 | 1401 | 0.0894 | 0.8233 | 0.8770 | 0.8493 | 0.9737 |
0.06 | 4.0 | 1868 | 0.0917 | 0.8240 | 0.8784 | 0.8503 | 0.9735 |
0.0467 | 5.0 | 2335 | 0.0922 | 0.8315 | 0.8748 | 0.8526 | 0.9744 |
0.0442 | 6.0 | 2802 | 0.0943 | 0.8387 | 0.8727 | 0.8554 | 0.9748 |
Framework versions
- Transformers 4.27.4
- Pytorch 1.13.1+cu116
- Datasets 2.11.0
- Tokenizers 0.13.2
- Downloads last month
- 3
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.