albert-base-v2
This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.9137
- Accuracy: 0.7434
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: 16
- eval_batch_size: 16
- 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 | Accuracy |
---|---|---|---|---|
No log | 1.0 | 293 | 0.4585 | 0.7766 |
0.5555 | 2.0 | 586 | 0.5768 | 0.7200 |
0.5555 | 3.0 | 879 | 0.6414 | 0.7065 |
0.3357 | 4.0 | 1172 | 0.7783 | 0.7328 |
0.3357 | 5.0 | 1465 | 0.9137 | 0.7434 |
Framework versions
- Transformers 4.40.0
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1
- Downloads last month
- 4