|
--- |
|
license: apache-2.0 |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: bert-medical-ner |
|
results: [] |
|
--- |
|
|
|
<!-- 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-medical-ner |
|
|
|
This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.3752 |
|
- Precision: 0.7403 |
|
- Recall: 0.6800 |
|
- F1: 0.7089 |
|
- Accuracy: 0.9401 |
|
|
|
## 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 | 63 | 0.3364 | 0.6802 | 0.6433 | 0.6612 | 0.9325 | |
|
| No log | 2.0 | 126 | 0.3434 | 0.6759 | 0.6789 | 0.6774 | 0.9331 | |
|
| No log | 3.0 | 189 | 0.3381 | 0.7297 | 0.6851 | 0.7067 | 0.9389 | |
|
| No log | 4.0 | 252 | 0.3470 | 0.6788 | 0.6942 | 0.6864 | 0.9333 | |
|
| No log | 5.0 | 315 | 0.3668 | 0.7392 | 0.6761 | 0.7062 | 0.9380 | |
|
| No log | 6.0 | 378 | 0.3722 | 0.7565 | 0.6710 | 0.7112 | 0.9416 | |
|
| No log | 7.0 | 441 | 0.3669 | 0.7253 | 0.6806 | 0.7022 | 0.9386 | |
|
| 0.0633 | 8.0 | 504 | 0.3673 | 0.7250 | 0.6914 | 0.7078 | 0.9404 | |
|
| 0.0633 | 9.0 | 567 | 0.3789 | 0.7456 | 0.6744 | 0.7082 | 0.9405 | |
|
| 0.0633 | 10.0 | 630 | 0.3752 | 0.7403 | 0.6800 | 0.7089 | 0.9401 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.29.2 |
|
- Pytorch 2.0.1+cu117 |
|
- Datasets 2.12.0 |
|
- Tokenizers 0.13.3 |
|
|
