metadata
tags:
- generated_from_trainer
datasets:
- bc2gm_corpus
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: biobert-base-cased-v1.2-bc2gm-ner
results:
- task:
name: Token Classification
type: token-classification
dataset:
name: bc2gm_corpus
type: bc2gm_corpus
config: bc2gm_corpus
split: train
args: bc2gm_corpus
metrics:
- name: Precision
type: precision
value: 0.7988356059445381
- name: Recall
type: recall
value: 0.8243478260869566
- name: F1
type: f1
value: 0.8113912231559292
- name: Accuracy
type: accuracy
value: 0.9772069842818806
biobert-base-cased-v1.2-bc2gm-ner
This model is a fine-tuned version of dmis-lab/biobert-base-cased-v1.2 on the bc2gm_corpus dataset. It achieves the following results on the evaluation set:
- Loss: 0.1528
- Precision: 0.7988
- Recall: 0.8243
- F1: 0.8114
- Accuracy: 0.9772
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 |
---|---|---|---|---|---|---|---|
0.057 | 1.0 | 782 | 0.0670 | 0.7446 | 0.8051 | 0.7736 | 0.9738 |
0.0586 | 2.0 | 1564 | 0.0689 | 0.7689 | 0.8106 | 0.7892 | 0.9755 |
0.0123 | 3.0 | 2346 | 0.0715 | 0.7846 | 0.8076 | 0.7959 | 0.9750 |
0.0002 | 4.0 | 3128 | 0.0896 | 0.7942 | 0.8199 | 0.8068 | 0.9767 |
0.0004 | 5.0 | 3910 | 0.1119 | 0.7971 | 0.8201 | 0.8084 | 0.9765 |
0.0004 | 6.0 | 4692 | 0.1192 | 0.7966 | 0.8337 | 0.8147 | 0.9768 |
0.013 | 7.0 | 5474 | 0.1274 | 0.7932 | 0.8266 | 0.8095 | 0.9773 |
0.0236 | 8.0 | 6256 | 0.1419 | 0.7976 | 0.8213 | 0.8093 | 0.9771 |
0.0004 | 9.0 | 7038 | 0.1519 | 0.8004 | 0.8261 | 0.8130 | 0.9772 |
0.0 | 10.0 | 7820 | 0.1528 | 0.7988 | 0.8243 | 0.8114 | 0.9772 |
Framework versions
- Transformers 4.23.1
- Pytorch 1.12.1+cu113
- Datasets 2.6.1
- Tokenizers 0.13.1