cf-albert-finetuned1
This model is a fine-tuned version of albert-base-v2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4699
- F1: 0.4523
- Roc Auc: 0.6409
- Accuracy: 0.2215
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: 3e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 | Roc Auc | Accuracy |
|---|---|---|---|---|---|---|
| 0.5419 | 1.0 | 434 | 0.5503 | 0.1048 | 0.5240 | 0.0196 |
| 0.5209 | 2.0 | 868 | 0.5224 | 0.3008 | 0.5775 | 0.1097 |
| 0.4659 | 3.0 | 1302 | 0.4876 | 0.3726 | 0.6082 | 0.1744 |
| 0.4141 | 4.0 | 1736 | 0.4726 | 0.4416 | 0.6358 | 0.2102 |
| 0.4508 | 5.0 | 2170 | 0.4668 | 0.4572 | 0.6432 | 0.2263 |
Framework versions
- Transformers 4.51.3
- Pytorch 2.6.0+cu124
- Datasets 3.5.0
- Tokenizers 0.21.1