AR_10000_41
This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 4.6926
- Accuracy: 0.2521
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: 0.0006
- train_batch_size: 32
- eval_batch_size: 32
- seed: 41
- 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
- lr_scheduler_warmup_steps: 1000
- num_epochs: 10.0
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 922 | 5.9422 | 0.1478 |
| 1.5175 | 2.0 | 1844 | 5.6616 | 0.1549 |
| 1.3377 | 3.0 | 2766 | 5.3969 | 0.1757 |
| 1.2691 | 4.0 | 3688 | 5.1811 | 0.1950 |
| 1.2037 | 5.0 | 4610 | 5.0409 | 0.2101 |
| 1.1554 | 6.0 | 5532 | 4.9227 | 0.2225 |
| 1.1182 | 7.0 | 6454 | 4.8469 | 0.2327 |
| 1.0876 | 8.0 | 7376 | 4.7668 | 0.2422 |
| 1.0606 | 9.0 | 8298 | 4.7165 | 0.2483 |
| 1.0409 | 10.0 | 9220 | 4.6926 | 0.2521 |
Framework versions
- Transformers 4.51.3
- Pytorch 2.5.1+cu121
- Datasets 3.6.0
- Tokenizers 0.21.1