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: 0.8192
• Accuracy: {'accuracy': 0.878}

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: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	125	0.3417	{'accuracy': 0.867}
No log	2.0	250	0.2960	{'accuracy': 0.878}
No log	3.0	375	0.4010	{'accuracy': 0.875}
0.2767	4.0	500	0.5766	{'accuracy': 0.874}
0.2767	5.0	625	0.6314	{'accuracy': 0.878}
0.2767	6.0	750	0.6541	{'accuracy': 0.883}
0.2767	7.0	875	0.7353	{'accuracy': 0.887}
0.0442	8.0	1000	0.7776	{'accuracy': 0.883}
0.0442	9.0	1125	0.8157	{'accuracy': 0.874}
0.0442	10.0	1250	0.8192	{'accuracy': 0.878}

Framework versions

• PEFT 0.11.1
• Transformers 4.43.2
• Pytorch 2.3.1+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1