ntc-scv-distilbert-base-uncased
This model is a fine-tuned version of distilbert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.3672
- Accuracy: 0.8458
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: 256
- eval_batch_size: 256
- 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 |
|---|---|---|---|---|
| No log | 1.0 | 118 | 0.4574 | 0.7902 |
| No log | 2.0 | 236 | 0.4322 | 0.8045 |
| No log | 3.0 | 354 | 0.4200 | 0.8121 |
| No log | 4.0 | 472 | 0.3952 | 0.8271 |
| 0.4318 | 5.0 | 590 | 0.3981 | 0.8312 |
| 0.4318 | 6.0 | 708 | 0.3887 | 0.8343 |
| 0.4318 | 7.0 | 826 | 0.4038 | 0.8316 |
| 0.4318 | 8.0 | 944 | 0.4085 | 0.8333 |
| 0.3168 | 9.0 | 1062 | 0.4098 | 0.835 |
| 0.3168 | 10.0 | 1180 | 0.4104 | 0.8362 |
Framework versions
- Transformers 4.47.0
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0