metadata
tags:
- generated_from_trainer
datasets:
- ncbi_disease
metrics:
- precision
- recall
- f1
- accuracy
base_model: dmis-lab/biobert-base-cased-v1.2
model-index:
- name: biobert-base-cased-v1.2-finetuned-ner
results:
- task:
type: token-classification
name: Token Classification
dataset:
name: ncbi_disease
type: ncbi_disease
args: ncbi_disease
metrics:
- type: precision
value: 0.8396334478808706
name: Precision
- type: recall
value: 0.8731387730792138
name: Recall
- type: f1
value: 0.856058394160584
name: F1
- type: accuracy
value: 0.9824805769647444
name: Accuracy
biobert-base-cased-v1.2-finetuned-ner
This model is a fine-tuned version of dmis-lab/biobert-base-cased-v1.2 on the ncbi_disease dataset. It achieves the following results on the evaluation set:
- Loss: 0.0706
- Precision: 0.8396
- Recall: 0.8731
- F1: 0.8561
- Accuracy: 0.9825
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: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 340 | 0.0691 | 0.8190 | 0.7868 | 0.8026 | 0.9777 |
| 0.101 | 2.0 | 680 | 0.0700 | 0.8334 | 0.8553 | 0.8442 | 0.9807 |
| 0.0244 | 3.0 | 1020 | 0.0706 | 0.8396 | 0.8731 | 0.8561 | 0.9825 |
Framework versions
- Transformers 4.19.4
- Pytorch 1.11.0+cu113
- Datasets 2.3.0
- Tokenizers 0.12.1