metadata
tags:
- generated_from_trainer
datasets:
- jnlpba
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: biobert-base-cased-v1.2-finetuned-ner
results:
- task:
name: Token Classification
type: token-classification
dataset:
name: jnlpba
type: jnlpba
args: jnlpba
metrics:
- name: Precision
type: precision
value: 0.894958702110781
- name: Recall
type: recall
value: 0.9286290713063688
- name: F1
type: f1
value: 0.9114830451416668
- name: Accuracy
type: accuracy
value: 0.9602011115815866
biobert-base-cased-v1.2-finetuned-ner
This model is a fine-tuned version of dmis-lab/biobert-base-cased-v1.2 on the jnlpba dataset. It achieves the following results on the evaluation set:
- Loss: 0.1253
- Precision: 0.8950
- Recall: 0.9286
- F1: 0.9115
- Accuracy: 0.9602
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 |
|---|---|---|---|---|---|---|---|
| 0.2267 | 1.0 | 1858 | 0.1822 | 0.8389 | 0.8841 | 0.8609 | 0.9383 |
| 0.1495 | 2.0 | 3716 | 0.1439 | 0.8750 | 0.9166 | 0.8953 | 0.9536 |
| 0.1141 | 3.0 | 5574 | 0.1253 | 0.8950 | 0.9286 | 0.9115 | 0.9602 |
Framework versions
- Transformers 4.11.3
- Pytorch 1.9.1+cu102
- Datasets 1.13.2
- Tokenizers 0.10.3