|
|
--- |
|
|
library_name: transformers |
|
|
license: apache-2.0 |
|
|
base_model: google-bert/bert-base-uncased |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
datasets: |
|
|
- biobert_json |
|
|
metrics: |
|
|
- precision |
|
|
- recall |
|
|
- f1 |
|
|
- accuracy |
|
|
model-index: |
|
|
- name: bert-base-uncased-finetuned-ner |
|
|
results: |
|
|
- task: |
|
|
name: Token Classification |
|
|
type: token-classification |
|
|
dataset: |
|
|
name: biobert_json |
|
|
type: biobert_json |
|
|
config: Biobert_json |
|
|
split: validation |
|
|
args: Biobert_json |
|
|
metrics: |
|
|
- name: Precision |
|
|
type: precision |
|
|
value: 0.942891335567257 |
|
|
- name: Recall |
|
|
type: recall |
|
|
value: 0.9658232813572619 |
|
|
- name: F1 |
|
|
type: f1 |
|
|
value: 0.9542195523689565 |
|
|
- name: Accuracy |
|
|
type: accuracy |
|
|
value: 0.9763595874355369 |
|
|
--- |
|
|
|
|
|
<!-- 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-base-uncased-finetuned-ner |
|
|
|
|
|
This model is a fine-tuned version of [google-bert/bert-base-uncased](https://huggingface.co/google-bert/bert-base-uncased) on the biobert_json dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 0.1204 |
|
|
- Precision: 0.9429 |
|
|
- Recall: 0.9658 |
|
|
- F1: 0.9542 |
|
|
- Accuracy: 0.9764 |
|
|
|
|
|
## 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: 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: 10 |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | |
|
|
|:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:| |
|
|
| 0.1823 | 1.0 | 1224 | 0.1059 | 0.9301 | 0.9628 | 0.9462 | 0.9731 | |
|
|
| 0.1142 | 2.0 | 2448 | 0.1163 | 0.9203 | 0.9717 | 0.9453 | 0.9698 | |
|
|
| 0.0812 | 3.0 | 3672 | 0.1000 | 0.9427 | 0.9705 | 0.9564 | 0.9773 | |
|
|
| 0.0603 | 4.0 | 4896 | 0.0970 | 0.9424 | 0.9717 | 0.9568 | 0.9773 | |
|
|
| 0.0516 | 5.0 | 6120 | 0.1018 | 0.9416 | 0.9720 | 0.9566 | 0.9772 | |
|
|
| 0.0418 | 6.0 | 7344 | 0.1044 | 0.9446 | 0.9704 | 0.9574 | 0.9778 | |
|
|
| 0.0361 | 7.0 | 8568 | 0.1070 | 0.9422 | 0.9725 | 0.9571 | 0.9775 | |
|
|
| 0.0296 | 8.0 | 9792 | 0.1166 | 0.9438 | 0.9708 | 0.9571 | 0.9776 | |
|
|
| 0.0242 | 9.0 | 11016 | 0.1174 | 0.9437 | 0.9671 | 0.9553 | 0.9767 | |
|
|
| 0.0231 | 10.0 | 12240 | 0.1204 | 0.9429 | 0.9658 | 0.9542 | 0.9764 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.45.1 |
|
|
- Pytorch 2.4.0 |
|
|
- Datasets 3.0.1 |
|
|
- Tokenizers 0.20.0 |
|
|
|
