metadata
license: cc-by-sa-4.0
base_model: klue/bert-base
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
model-index:
- name: degree-bert-finetuning-2
results: []
degree-bert-finetuning-2
This model is a fine-tuned version of klue/bert-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.6107
- Accuracy: 0.698
- F1: 0.6968
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: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 20
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 1.06 | 1.0 | 104 | 0.8187 | 0.61 | 0.6100 |
| 0.849 | 2.0 | 208 | 0.7525 | 0.642 | 0.6415 |
| 0.8117 | 3.0 | 312 | 0.7479 | 0.616 | 0.6044 |
| 0.7758 | 4.0 | 416 | 0.7269 | 0.652 | 0.6490 |
| 0.7638 | 5.0 | 520 | 0.6960 | 0.674 | 0.6741 |
| 0.7412 | 6.0 | 624 | 0.6842 | 0.676 | 0.6739 |
| 0.7337 | 7.0 | 728 | 0.6653 | 0.692 | 0.6922 |
| 0.723 | 8.0 | 832 | 0.6502 | 0.674 | 0.6711 |
| 0.7045 | 9.0 | 936 | 0.6407 | 0.672 | 0.6681 |
| 0.6975 | 10.0 | 1040 | 0.6330 | 0.686 | 0.6852 |
| 0.6914 | 11.0 | 1144 | 0.6351 | 0.686 | 0.6846 |
| 0.6876 | 12.0 | 1248 | 0.6230 | 0.702 | 0.7023 |
| 0.672 | 13.0 | 1352 | 0.6230 | 0.698 | 0.6978 |
| 0.6733 | 14.0 | 1456 | 0.6251 | 0.678 | 0.6736 |
| 0.6701 | 15.0 | 1560 | 0.6124 | 0.706 | 0.7064 |
| 0.6592 | 16.0 | 1664 | 0.6195 | 0.688 | 0.6853 |
| 0.6534 | 17.0 | 1768 | 0.6070 | 0.708 | 0.7082 |
| 0.6528 | 18.0 | 1872 | 0.6093 | 0.704 | 0.7040 |
| 0.6514 | 19.0 | 1976 | 0.6124 | 0.698 | 0.6963 |
| 0.6406 | 20.0 | 2080 | 0.6107 | 0.698 | 0.6968 |
Framework versions
- Transformers 4.38.1
- Pytorch 2.2.0
- Datasets 2.17.1
- Tokenizers 0.15.2