FR_20000_41
This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 3.7302
- Accuracy: 0.3312
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 | 998 | 4.7661 | 0.2262 |
| 1.2399 | 2.0 | 1996 | 4.3380 | 0.2675 |
| 1.0378 | 3.0 | 2994 | 4.1929 | 0.2781 |
| 0.9739 | 4.0 | 3992 | 4.1035 | 0.2866 |
| 0.9423 | 5.0 | 4990 | 4.0010 | 0.2978 |
| 0.9155 | 6.0 | 5988 | 3.9371 | 0.3040 |
| 0.8943 | 7.0 | 6986 | 3.8595 | 0.3146 |
| 0.8736 | 8.0 | 7984 | 3.8007 | 0.3212 |
| 0.8539 | 9.0 | 8982 | 3.7534 | 0.3274 |
| 0.8352 | 10.0 | 9980 | 3.7302 | 0.3312 |
Framework versions
- Transformers 4.51.3
- Pytorch 2.5.1+cu121
- Datasets 3.6.0
- Tokenizers 0.21.1
- Downloads last month
- 2