metadata

base_model: dmis-lab/biobert-base-cased-v1.2
tags:
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: biobert-base-cased-v1.2-finetuned-NER
    results: []

biobert-base-cased-v1.2-finetuned-NER

This model is a fine-tuned version of dmis-lab/biobert-base-cased-v1.2 on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.0905
Accuracy: 0.9765
Precision (macro): 0.8596
Recall (macro): 0.8601
F1 (macro): 0.8563
Precision (micro): 0.9765
Recall (micro): 0.9765
F1 (micro): 0.9765

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	Accuracy	Precision (macro)	Recall (macro)	F1 (macro)	Precision (micro)	Recall (micro)	F1 (micro)
No log	1.0	152	0.1382	0.9621	0.8016	0.6594	0.6754	0.9621	0.9621	0.9621
No log	2.0	304	0.0907	0.9740	0.8363	0.7827	0.7993	0.9740	0.9740	0.9740
No log	3.0	456	0.0811	0.9750	0.8661	0.8285	0.8261	0.9750	0.9750	0.9750
0.1768	4.0	608	0.0829	0.9738	0.8322	0.8581	0.8410	0.9738	0.9738	0.9738
0.1768	5.0	760	0.0786	0.9755	0.8350	0.8737	0.8526	0.9755	0.9755	0.9755
0.1768	6.0	912	0.0866	0.9766	0.8539	0.8491	0.8490	0.9766	0.9766	0.9766
0.0496	7.0	1064	0.0828	0.9757	0.8454	0.8563	0.8494	0.9757	0.9757	0.9757
0.0496	8.0	1216	0.0932	0.9754	0.8416	0.8622	0.8511	0.9754	0.9754	0.9754
0.0496	9.0	1368	0.0939	0.9752	0.8368	0.8617	0.8483	0.9752	0.9752	0.9752
0.0297	10.0	1520	0.0955	0.9759	0.8426	0.8597	0.8500	0.9759	0.9759	0.9759

Framework versions

Transformers 4.41.2
Pytorch 2.3.0+cu121
Datasets 2.20.0
Tokenizers 0.19.1