distilbert-base-uncased-lora-text-classification

This model is a fine-tuned version of distilbert-base-uncased on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.8405
• Accuracy: {'accuracy': 0.898}

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	0.7051	{'accuracy': 0.761}
0.4561	2.0	500	0.9751	{'accuracy': 0.793}
0.4561	3.0	750	0.4668	{'accuracy': 0.882}
0.2196	4.0	1000	0.5190	{'accuracy': 0.895}
0.2196	5.0	1250	0.6079	{'accuracy': 0.905}
0.0804	6.0	1500	0.7639	{'accuracy': 0.895}
0.0804	7.0	1750	0.8768	{'accuracy': 0.892}
0.0119	8.0	2000	0.8436	{'accuracy': 0.893}
0.0119	9.0	2250	0.8417	{'accuracy': 0.897}
0.001	10.0	2500	0.8405	{'accuracy': 0.898}

Framework versions

• PEFT 0.13.2
• Transformers 4.46.3
• Pytorch 2.5.1+cu121
• Datasets 3.2.0
• Tokenizers 0.20.3