metadata
base_model: dmis-lab/biobert-base-cased-v1.2
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: devicebert-base-cased-v1.0
results: []
devicebert-base-cased-v1.0
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: nan
- Precision: 0.9429
- Recall: 0.9449
- F1: 0.9439
- Accuracy: 0.9737
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: 1e-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 | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 81 | nan | 0.9429 | 0.9449 | 0.9439 | 0.9737 |
| No log | 2.0 | 162 | nan | 0.9198 | 0.9470 | 0.9332 | 0.9615 |
| No log | 3.0 | 243 | nan | 0.9196 | 0.9449 | 0.9321 | 0.9653 |
| No log | 4.0 | 324 | nan | 0.9379 | 0.9280 | 0.9329 | 0.9719 |
| No log | 5.0 | 405 | nan | 0.9245 | 0.9343 | 0.9294 | 0.9690 |
| No log | 6.0 | 486 | nan | 0.9450 | 0.9470 | 0.9460 | 0.9747 |
| 0.0945 | 7.0 | 567 | nan | 0.9446 | 0.9386 | 0.9416 | 0.9747 |
| 0.0945 | 8.0 | 648 | nan | 0.9189 | 0.9364 | 0.9276 | 0.9672 |
| 0.0945 | 9.0 | 729 | nan | 0.9245 | 0.9343 | 0.9294 | 0.9662 |
| 0.0945 | 10.0 | 810 | nan | 0.9407 | 0.9407 | 0.9407 | 0.9728 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.2
- Tokenizers 0.19.1