distilbert-base-uncased-lora-text-classification
This model was trained from scratch on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 1.0224
- Accuracy: {'accuracy': 0.889}
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: 0.001
- train_batch_size: 4
- eval_batch_size: 4
- 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 | 250 | 0.4405 | {'accuracy': 0.879} |
| 0.4414 | 2.0 | 500 | 0.4236 | {'accuracy': 0.873} |
| 0.4414 | 3.0 | 750 | 0.6297 | {'accuracy': 0.857} |
| 0.2009 | 4.0 | 1000 | 0.6088 | {'accuracy': 0.892} |
| 0.2009 | 5.0 | 1250 | 0.7049 | {'accuracy': 0.894} |
| 0.0606 | 6.0 | 1500 | 0.8470 | {'accuracy': 0.891} |
| 0.0606 | 7.0 | 1750 | 0.9384 | {'accuracy': 0.894} |
| 0.015 | 8.0 | 2000 | 1.0103 | {'accuracy': 0.891} |
| 0.015 | 9.0 | 2250 | 1.0147 | {'accuracy': 0.89} |
| 0.0074 | 10.0 | 2500 | 1.0224 | {'accuracy': 0.889} |
Framework versions
- PEFT 0.14.0
- Transformers 4.47.0
- Pytorch 2.1.1+cu121
- Datasets 2.14.0
- Tokenizers 0.21.0
