albert-base-v2_fold_4
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: 0.1260
- Accuracy: 0.9577
- F1: 0.9534
- Precision: 0.9594
- Recall: 0.9475
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 |
|---|---|---|---|---|---|---|---|
| 0.1148 | 1.0 | 15481 | 0.1369 | 0.9449 | 0.9399 | 0.9378 | 0.9421 |
| 0.1071 | 2.0 | 30962 | 0.1315 | 0.9500 | 0.9437 | 0.9726 | 0.9165 |
| 0.0772 | 3.0 | 46443 | 0.1260 | 0.9577 | 0.9534 | 0.9594 | 0.9475 |
Framework versions
- Transformers 5.3.0
- Pytorch 2.10.0+cu128
- Datasets 4.6.1
- Tokenizers 0.22.2