albert-base-v2_fold_0
This model is a fine-tuned version of albert-base-v2 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1392
- Accuracy: 0.9586
- F1: 0.9547
- Precision: 0.9584
- Recall: 0.9509
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: 40
- eval_batch_size: 40
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|---|---|---|---|---|---|---|---|
| 0.1096 | 1.0 | 15481 | 0.1335 | 0.9505 | 0.9455 | 0.9541 | 0.9371 |
| 0.0895 | 2.0 | 30962 | 0.1170 | 0.9570 | 0.9531 | 0.9535 | 0.9526 |
| 0.0654 | 3.0 | 46443 | 0.1392 | 0.9586 | 0.9547 | 0.9584 | 0.9509 |
Framework versions
- Transformers 5.3.0
- Pytorch 2.10.0+cu128
- Datasets 4.6.1
- Tokenizers 0.22.2