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: 0.5876
- Accuracy: 0.7
- F1: 0.7002
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 |
0.8238 | 2.0 | 208 | 0.7232 | 0.654 | 0.6532 |
0.787 | 3.0 | 312 | 0.7135 | 0.66 | 0.6543 |
0.7555 | 4.0 | 416 | 0.6902 | 0.682 | 0.6801 |
0.7369 | 5.0 | 520 | 0.6555 | 0.7 | 0.7005 |
0.7163 | 6.0 | 624 | 0.6495 | 0.7 | 0.6994 |
0.7028 | 7.0 | 728 | 0.6438 | 0.708 | 0.7080 |
0.6914 | 8.0 | 832 | 0.6087 | 0.698 | 0.6972 |
0.6761 | 9.0 | 936 | 0.6039 | 0.7 | 0.6995 |
0.6676 | 10.0 | 1040 | 0.6042 | 0.692 | 0.6911 |
0.6572 | 11.0 | 1144 | 0.6019 | 0.704 | 0.7033 |
0.6527 | 12.0 | 1248 | 0.5927 | 0.712 | 0.7126 |
0.6364 | 13.0 | 1352 | 0.5951 | 0.708 | 0.7086 |
0.6387 | 14.0 | 1456 | 0.5917 | 0.688 | 0.6864 |
0.6326 | 15.0 | 1560 | 0.5870 | 0.71 | 0.7105 |
0.6199 | 16.0 | 1664 | 0.5944 | 0.696 | 0.6942 |
0.6107 | 17.0 | 1768 | 0.5850 | 0.714 | 0.7145 |
0.6118 | 18.0 | 1872 | 0.5853 | 0.716 | 0.7168 |
0.6083 | 19.0 | 1976 | 0.5895 | 0.704 | 0.7037 |
0.5946 | 20.0 | 2080 | 0.5876 | 0.7 | 0.7002 |
Framework versions
- Transformers 4.38.1
- Pytorch 2.2.0
- Datasets 2.17.1
- Tokenizers 0.15.2