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: 0.8762
• Accuracy: {'accuracy': 0.9003333333333333}

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
0.4732	1.0	750	0.3050	{'accuracy': 0.8973333333333333}
0.3815	2.0	1500	0.4199	{'accuracy': 0.881}
0.3115	3.0	2250	0.5065	{'accuracy': 0.8843333333333333}
0.2536	4.0	3000	0.4385	{'accuracy': 0.898}
0.1905	5.0	3750	0.6383	{'accuracy': 0.9033333333333333}
0.1749	6.0	4500	0.5822	{'accuracy': 0.8926666666666667}
0.1161	7.0	5250	0.6724	{'accuracy': 0.9033333333333333}
0.0696	8.0	6000	0.8629	{'accuracy': 0.8993333333333333}
0.0607	9.0	6750	0.8520	{'accuracy': 0.905}
0.0347	10.0	7500	0.8762	{'accuracy': 0.9003333333333333}

Framework versions

• PEFT 0.13.2
• Transformers 4.44.2
• Pytorch 2.5.0+cu121
• Datasets 3.1.0
• Tokenizers 0.19.1