Novel_Genre_Classification_bert-finetuned
This model is a fine-tuned version of bert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4720
- F1: 0.5474
- Roc Auc: 0.6950
- Accuracy: 0.4906
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: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 25
Training results
Training Loss | Epoch | Step | Validation Loss | F1 | Roc Auc | Accuracy |
---|---|---|---|---|---|---|
0.5711 | 1.0 | 40 | 0.5745 | 0.0 | 0.5 | 0.0 |
0.5629 | 2.0 | 80 | 0.5789 | 0.0 | 0.5 | 0.0 |
0.5364 | 3.0 | 120 | 0.5439 | 0.0 | 0.5 | 0.0 |
0.4734 | 4.0 | 160 | 0.5813 | 0.1644 | 0.5126 | 0.0377 |
0.3793 | 5.0 | 200 | 0.4709 | 0.5116 | 0.6730 | 0.4151 |
0.2771 | 6.0 | 240 | 0.4720 | 0.5474 | 0.6950 | 0.4906 |
0.2473 | 7.0 | 280 | 0.5489 | 0.4694 | 0.6478 | 0.4340 |
0.1499 | 8.0 | 320 | 0.5645 | 0.5143 | 0.6761 | 0.4717 |
0.1041 | 9.0 | 360 | 0.6179 | 0.4600 | 0.6415 | 0.4340 |
0.0644 | 10.0 | 400 | 0.6355 | 0.5098 | 0.6730 | 0.4906 |
0.0462 | 11.0 | 440 | 0.7175 | 0.4808 | 0.6541 | 0.4717 |
0.0366 | 12.0 | 480 | 0.7688 | 0.4717 | 0.6478 | 0.4528 |
0.0321 | 13.0 | 520 | 0.7665 | 0.4854 | 0.6572 | 0.4717 |
0.0278 | 14.0 | 560 | 0.7572 | 0.4762 | 0.6509 | 0.4528 |
0.0253 | 15.0 | 600 | 0.7946 | 0.4615 | 0.6415 | 0.4528 |
0.0232 | 16.0 | 640 | 0.8142 | 0.4615 | 0.6415 | 0.4528 |
0.0218 | 17.0 | 680 | 0.8370 | 0.4706 | 0.6478 | 0.4528 |
0.02 | 18.0 | 720 | 0.8390 | 0.4615 | 0.6415 | 0.4528 |
0.019 | 19.0 | 760 | 0.8148 | 0.4808 | 0.6541 | 0.4717 |
0.0185 | 20.0 | 800 | 0.8482 | 0.4571 | 0.6384 | 0.4340 |
0.0177 | 21.0 | 840 | 0.8714 | 0.4660 | 0.6447 | 0.4528 |
0.0175 | 22.0 | 880 | 0.8810 | 0.4660 | 0.6447 | 0.4528 |
0.0166 | 23.0 | 920 | 0.8748 | 0.4660 | 0.6447 | 0.4528 |
0.0165 | 24.0 | 960 | 0.8865 | 0.4660 | 0.6447 | 0.4528 |
0.0163 | 25.0 | 1000 | 0.8880 | 0.4660 | 0.6447 | 0.4528 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0
- Downloads last month
- 5