metadata
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: medlid-identify
results: []
medlid-identify
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: 0.1617
- Precision: 0.4085
- Recall: 0.4551
- F1: 0.4305
- Accuracy: 0.9452
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: 81
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 381 | 0.1447 | 0.3867 | 0.2215 | 0.2817 | 0.9440 |
| 0.1714 | 2.0 | 762 | 0.1410 | 0.3937 | 0.4513 | 0.4206 | 0.9457 |
| 0.107 | 3.0 | 1143 | 0.1487 | 0.4061 | 0.4347 | 0.4199 | 0.9456 |
| 0.0702 | 4.0 | 1524 | 0.1617 | 0.4085 | 0.4551 | 0.4305 | 0.9452 |
Framework versions
- Transformers 4.30.2
- Pytorch 1.11.0
- Datasets 2.13.1
- Tokenizers 0.13.3