<!-- 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. -->
roberta-cpt-medical-ner
This model is a fine-tuned version of silpakanneganti/roberta-cpt-medical-ner on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.8502
- Precision: 0.0342
- Recall: 0.1849
- F1: 0.0577
- Accuracy: 0.1849
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: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
No log | 1.0 | 25 | 0.8394 | 0.0342 | 0.1849 | 0.0577 | 0.1849 |
No log | 2.0 | 50 | 0.8356 | 0.0342 | 0.1849 | 0.0577 | 0.1849 |
No log | 3.0 | 75 | 0.8381 | 0.0342 | 0.1849 | 0.0577 | 0.1849 |
No log | 4.0 | 100 | 0.8406 | 0.0342 | 0.1849 | 0.0577 | 0.1849 |
No log | 5.0 | 125 | 0.8426 | 0.0342 | 0.1849 | 0.0577 | 0.1849 |
No log | 6.0 | 150 | 0.8432 | 0.0342 | 0.1849 | 0.0577 | 0.1849 |
No log | 7.0 | 175 | 0.8431 | 0.0342 | 0.1849 | 0.0577 | 0.1849 |
No log | 8.0 | 200 | 0.8461 | 0.0342 | 0.1849 | 0.0577 | 0.1849 |
No log | 9.0 | 225 | 0.8497 | 0.0342 | 0.1849 | 0.0577 | 0.1849 |
No log | 10.0 | 250 | 0.8502 | 0.0342 | 0.1849 | 0.0577 | 0.1849 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu117
- Datasets 2.12.0
- Tokenizers 0.12.1