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: 0.5866
- Accuracy: 0.702
- F1: 0.7023
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: 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 |
|---|---|---|---|---|---|
| 0.9822 | 1.0 | 104 | 0.7872 | 0.638 | 0.6374 |
| 0.8237 | 2.0 | 208 | 0.7235 | 0.656 | 0.6552 |
| 0.7869 | 3.0 | 312 | 0.7140 | 0.658 | 0.6521 |
| 0.755 | 4.0 | 416 | 0.6894 | 0.678 | 0.6762 |
| 0.7368 | 5.0 | 520 | 0.6562 | 0.7 | 0.7004 |
| 0.7164 | 6.0 | 624 | 0.6501 | 0.696 | 0.6951 |
| 0.7032 | 7.0 | 728 | 0.6437 | 0.708 | 0.7084 |
| 0.6911 | 8.0 | 832 | 0.6097 | 0.694 | 0.6930 |
| 0.6759 | 9.0 | 936 | 0.6034 | 0.702 | 0.7019 |
| 0.6671 | 10.0 | 1040 | 0.6038 | 0.69 | 0.6890 |
| 0.6573 | 11.0 | 1144 | 0.6016 | 0.704 | 0.7033 |
| 0.653 | 12.0 | 1248 | 0.5920 | 0.712 | 0.7126 |
| 0.6364 | 13.0 | 1352 | 0.5950 | 0.708 | 0.7085 |
| 0.6386 | 14.0 | 1456 | 0.5922 | 0.688 | 0.6864 |
| 0.6321 | 15.0 | 1560 | 0.5853 | 0.71 | 0.7105 |
| 0.6193 | 16.0 | 1664 | 0.5936 | 0.69 | 0.6889 |
| 0.6109 | 17.0 | 1768 | 0.5838 | 0.714 | 0.7145 |
| 0.612 | 18.0 | 1872 | 0.5838 | 0.716 | 0.7168 |
| 0.6083 | 19.0 | 1976 | 0.5884 | 0.708 | 0.7077 |
| 0.5948 | 20.0 | 2080 | 0.5866 | 0.702 | 0.7023 |
Framework versions
- Transformers 4.38.1
- Pytorch 2.2.0
- Datasets 2.17.1
- Tokenizers 0.15.2