albert_albert-base-v2
This model is a fine-tuned version of albert/albert-base-v2 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.3806
- Accuracy: 0.4479
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: 5e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Use 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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.392 | 1.0 | 283 | 1.3819 | 0.4479 |
| 1.4077 | 2.0 | 566 | 1.3793 | 0.4479 |
| 1.3917 | 3.0 | 849 | 1.3679 | 0.4479 |
Framework versions
- Transformers 4.49.0
- Pytorch 2.6.0+cu118
- Datasets 3.4.0
- Tokenizers 0.21.1