FR_10000_41
This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 3.4917
- Accuracy: 0.3542
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 |
|---|---|---|---|---|
| 1.2234 | 1.0 | 1051 | 4.6312 | 0.2227 |
| 1.015 | 2.0 | 2102 | 4.2010 | 0.2651 |
| 0.9468 | 3.0 | 3153 | 4.0149 | 0.2858 |
| 0.9083 | 4.0 | 4204 | 3.8844 | 0.3032 |
| 0.8769 | 5.0 | 5255 | 3.7722 | 0.3163 |
| 0.8502 | 6.0 | 6306 | 3.6949 | 0.3261 |
| 0.8276 | 7.0 | 7357 | 3.6137 | 0.3367 |
| 0.8078 | 8.0 | 8408 | 3.5608 | 0.3435 |
| 0.7895 | 9.0 | 9459 | 3.5129 | 0.3507 |
| 0.7746 | 10.0 | 10510 | 3.4917 | 0.3542 |
Framework versions
- Transformers 4.51.3
- Pytorch 2.5.1+cu121
- Datasets 3.6.0
- Tokenizers 0.21.1
- Downloads last month
- 2