bert_for_prof_roles
This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0087
- F1: 0.8710
- Roc Auc: 0.9264
- Accuracy: 0.8495
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: 5
Training results
Training Loss | Epoch | Step | Validation Loss | F1 | Roc Auc | Accuracy |
---|---|---|---|---|---|---|
0.0137 | 1.0 | 6885 | 0.0133 | 0.7959 | 0.8698 | 0.7314 |
0.01 | 2.0 | 13770 | 0.0110 | 0.8311 | 0.8941 | 0.7832 |
0.0082 | 3.0 | 20655 | 0.0100 | 0.8487 | 0.9110 | 0.8142 |
0.0066 | 4.0 | 27540 | 0.0094 | 0.8585 | 0.9182 | 0.8337 |
0.0056 | 5.0 | 34425 | 0.0092 | 0.8636 | 0.9222 | 0.8398 |
Framework versions
- Transformers 4.41.0
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1
- Downloads last month
- 3