<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
hc3-wiki-domain-classification-roberta
This model is a fine-tuned version of roberta-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1821
- Accuracy: 0.9810
- F1 Score: 0.9810
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: 5e-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: 1
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Score |
---|---|---|---|---|---|
0.5388 | 0.04 | 400 | 0.3470 | 0.9626 | 0.9626 |
0.4795 | 0.08 | 800 | 0.4603 | 0.9659 | 0.9659 |
0.4419 | 0.12 | 1200 | 0.3184 | 0.9622 | 0.9622 |
0.3985 | 0.15 | 1600 | 0.3919 | 0.9697 | 0.9697 |
0.3954 | 0.19 | 2000 | 0.3571 | 0.9718 | 0.9718 |
0.4891 | 0.23 | 2400 | 0.4775 | 0.9668 | 0.9668 |
0.4283 | 0.27 | 2800 | 0.3616 | 0.9677 | 0.9677 |
0.4157 | 0.31 | 3200 | 0.4152 | 0.9519 | 0.9519 |
0.4477 | 0.35 | 3600 | 0.3460 | 0.9673 | 0.9673 |
0.426 | 0.39 | 4000 | 0.4334 | 0.9669 | 0.9669 |
0.3704 | 0.43 | 4400 | 0.3405 | 0.9634 | 0.9634 |
0.4027 | 0.46 | 4800 | 0.3232 | 0.9738 | 0.9738 |
0.3704 | 0.5 | 5200 | 0.3475 | 0.9672 | 0.9672 |
0.3459 | 0.54 | 5600 | 0.4094 | 0.9738 | 0.9738 |
0.3707 | 0.58 | 6000 | 0.3176 | 0.9703 | 0.9703 |
0.3145 | 0.62 | 6400 | 0.3329 | 0.9760 | 0.9760 |
0.3153 | 0.66 | 6800 | 0.3762 | 0.9733 | 0.9733 |
0.293 | 0.7 | 7200 | 0.2815 | 0.9761 | 0.9761 |
0.2981 | 0.74 | 7600 | 0.2577 | 0.9771 | 0.9771 |
0.2481 | 0.77 | 8000 | 0.2134 | 0.9780 | 0.9780 |
0.2418 | 0.81 | 8400 | 0.1978 | 0.9779 | 0.9779 |
0.2235 | 0.85 | 8800 | 0.1896 | 0.9794 | 0.9794 |
0.1934 | 0.89 | 9200 | 0.1895 | 0.9796 | 0.9796 |
0.2167 | 0.93 | 9600 | 0.1804 | 0.9792 | 0.9792 |
0.1992 | 0.97 | 10000 | 0.1821 | 0.9810 | 0.9810 |
Framework versions
- Transformers 4.33.0
- Pytorch 2.0.0
- Datasets 2.13.0
- Tokenizers 0.13.3