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: 1.0362
• Accuracy: {'accuracy': 0.866}

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: 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	250	0.5633	{'accuracy': 0.822}
0.4445	2.0	500	0.5395	{'accuracy': 0.85}
0.4445	3.0	750	0.7314	{'accuracy': 0.844}
0.3104	4.0	1000	0.6346	{'accuracy': 0.867}
0.3104	5.0	1250	0.7909	{'accuracy': 0.854}
0.1899	6.0	1500	0.8945	{'accuracy': 0.872}
0.1899	7.0	1750	0.9758	{'accuracy': 0.866}
0.0805	8.0	2000	1.0404	{'accuracy': 0.865}
0.0805	9.0	2250	1.0483	{'accuracy': 0.861}
0.0581	10.0	2500	1.0362	{'accuracy': 0.866}

Framework versions

• PEFT 0.12.0
• Transformers 4.44.2
• Pytorch 2.4.1+cu121
• Datasets 3.0.0
• Tokenizers 0.19.1