|
--- |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- i2b22014 |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: electramed-small-deid2014-ner-v4 |
|
results: |
|
- task: |
|
name: Token Classification |
|
type: token-classification |
|
dataset: |
|
name: i2b22014 |
|
type: i2b22014 |
|
config: i2b22014-deid |
|
split: train |
|
args: i2b22014-deid |
|
metrics: |
|
- name: Precision |
|
type: precision |
|
value: 0.7571112095702259 |
|
- name: Recall |
|
type: recall |
|
value: 0.7853663020498207 |
|
- name: F1 |
|
type: f1 |
|
value: 0.770979967514889 |
|
- name: Accuracy |
|
type: accuracy |
|
value: 0.9906153616114308 |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# electramed-small-deid2014-ner-v4 |
|
|
|
This model is a fine-tuned version of [giacomomiolo/electramed_small_scivocab](https://huggingface.co/giacomomiolo/electramed_small_scivocab) on the i2b22014 dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.0362 |
|
- Precision: 0.7571 |
|
- Recall: 0.7854 |
|
- F1: 0.7710 |
|
- Accuracy: 0.9906 |
|
|
|
## 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: 16 |
|
- eval_batch_size: 16 |
|
- 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 | |
|
|:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:| |
|
| 0.0143 | 1.0 | 1838 | 0.1451 | 0.3136 | 0.3463 | 0.3291 | 0.9700 | |
|
| 0.0033 | 2.0 | 3676 | 0.0940 | 0.4293 | 0.4861 | 0.4559 | 0.9758 | |
|
| 0.0014 | 3.0 | 5514 | 0.0725 | 0.4906 | 0.5766 | 0.5301 | 0.9799 | |
|
| 0.0007 | 4.0 | 7352 | 0.0568 | 0.6824 | 0.7022 | 0.6921 | 0.9860 | |
|
| 0.0112 | 5.0 | 9190 | 0.0497 | 0.6966 | 0.7400 | 0.7177 | 0.9870 | |
|
| 0.0002 | 6.0 | 11028 | 0.0442 | 0.7126 | 0.7549 | 0.7332 | 0.9878 | |
|
| 0.0002 | 7.0 | 12866 | 0.0404 | 0.7581 | 0.7591 | 0.7586 | 0.9896 | |
|
| 0.0002 | 8.0 | 14704 | 0.0376 | 0.7540 | 0.7804 | 0.7670 | 0.9904 | |
|
| 0.0002 | 9.0 | 16542 | 0.0367 | 0.7548 | 0.7825 | 0.7684 | 0.9905 | |
|
| 0.0001 | 10.0 | 18380 | 0.0362 | 0.7571 | 0.7854 | 0.7710 | 0.9906 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.22.1 |
|
- Pytorch 1.12.1+cu113 |
|
- Datasets 2.5.1 |
|
- Tokenizers 0.12.1 |
|
|
