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: 1.0287
• Accuracy: {'accuracy': 0.874}

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	0.4453	{'accuracy': 0.867}
0.4345	2.0	500	0.5586	{'accuracy': 0.853}
0.4345	3.0	750	0.6398	{'accuracy': 0.867}
0.3044	4.0	1000	0.6654	{'accuracy': 0.872}
0.3044	5.0	1250	0.8133	{'accuracy': 0.883}
0.1693	6.0	1500	0.9307	{'accuracy': 0.864}
0.1693	7.0	1750	1.0022	{'accuracy': 0.872}
0.0851	8.0	2000	1.0017	{'accuracy': 0.869}
0.0851	9.0	2250	0.9970	{'accuracy': 0.878}
0.0407	10.0	2500	1.0287	{'accuracy': 0.874}

Framework versions

• PEFT 0.12.0
• Transformers 4.42.4
• Pytorch 2.4.0+cu121
• Datasets 2.21.0
• Tokenizers 0.19.1