<!-- 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. -->
final_five_class_classification
This model is a fine-tuned version of bert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1000
- F1: 0.9566
- Roc Auc: 0.9664
- Accuracy: 0.875
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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 | Roc Auc | Accuracy |
|---|---|---|---|---|---|---|
| No log | 1.0 | 250 | 0.2560 | 0.8761 | 0.9004 | 0.665 |
| 0.3126 | 2.0 | 500 | 0.2082 | 0.8966 | 0.9177 | 0.7025 |
| 0.3126 | 3.0 | 750 | 0.1879 | 0.9024 | 0.9254 | 0.705 |
| 0.2165 | 4.0 | 1000 | 0.1654 | 0.9166 | 0.9348 | 0.755 |
| 0.2165 | 5.0 | 1250 | 0.1403 | 0.9346 | 0.9500 | 0.7975 |
| 0.1619 | 6.0 | 1500 | 0.1288 | 0.9394 | 0.9523 | 0.815 |
| 0.1619 | 7.0 | 1750 | 0.1112 | 0.9515 | 0.9614 | 0.855 |
| 0.1161 | 8.0 | 2000 | 0.1112 | 0.9492 | 0.9585 | 0.8575 |
| 0.1161 | 9.0 | 2250 | 0.1029 | 0.9536 | 0.9631 | 0.8725 |
| 0.086 | 10.0 | 2500 | 0.1000 | 0.9566 | 0.9664 | 0.875 |
Framework versions
- Transformers 4.20.1
- Pytorch 1.12.1+cpu
- Datasets 2.8.0
- Tokenizers 0.12.1
