base_model: dmis-lab/biobert-v1.1
tags:
- generated_from_trainer
model-index:
- name: JNLPBA_bioBERT_NER
results: []
JNLPBA_bioBERT_NER
This model is a fine-tuned version of dmis-lab/biobert-v1.1 on the None dataset. It achieves the following results on the evaluation set:
Loss: 0.1433
Seqeval classification report: precision recall f1-score support
DNA 0.81 0.83 0.82 1593 RNA 0.79 0.83 0.81 1400
cell_line 0.77 0.82 0.79 1016 cell_type 0.98 0.96 0.97 37439 protein 0.85 0.86 0.85 2992
micro avg 0.95 0.94 0.95 44440 macro avg 0.84 0.86 0.85 44440
weighted avg 0.95 0.94 0.95 44440
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
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- 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 | Seqeval classification report |
---|---|---|---|---|
0.2673 | 1.0 | 582 | 0.1492 | precision recall f1-score support |
DNA 0.79 0.81 0.80 1593
RNA 0.78 0.79 0.79 1400
cell_line 0.74 0.84 0.79 1016 cell_type 0.98 0.96 0.97 37439 protein 0.84 0.86 0.85 2992
micro avg 0.95 0.94 0.94 44440 macro avg 0.83 0.85 0.84 44440 weighted avg 0.95 0.94 0.94 44440 | | 0.1408 | 2.0 | 1164 | 0.1469 | precision recall f1-score support
DNA 0.83 0.80 0.81 1593
RNA 0.78 0.83 0.80 1400
cell_line 0.75 0.83 0.79 1016 cell_type 0.98 0.96 0.97 37439 protein 0.84 0.87 0.85 2992
micro avg 0.95 0.94 0.95 44440 macro avg 0.84 0.86 0.85 44440 weighted avg 0.95 0.94 0.95 44440 | | 0.1237 | 3.0 | 1746 | 0.1433 | precision recall f1-score support
DNA 0.81 0.83 0.82 1593
RNA 0.79 0.83 0.81 1400
cell_line 0.77 0.82 0.79 1016 cell_type 0.98 0.96 0.97 37439 protein 0.85 0.86 0.85 2992
micro avg 0.95 0.94 0.95 44440 macro avg 0.84 0.86 0.85 44440 weighted avg 0.95 0.94 0.95 44440 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0