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: 1.3091
• Accuracy: {'accuracy': 0.873}

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	0.5954	{'accuracy': 0.859}
0.4135	2.0	500	0.6391	{'accuracy': 0.868}
0.4135	3.0	750	0.9071	{'accuracy': 0.865}
0.2914	4.0	1000	1.0446	{'accuracy': 0.846}
0.2914	5.0	1250	1.1057	{'accuracy': 0.86}
0.1852	6.0	1500	1.0235	{'accuracy': 0.872}
0.1852	7.0	1750	1.1211	{'accuracy': 0.874}
0.0728	8.0	2000	1.2524	{'accuracy': 0.873}
0.0728	9.0	2250	1.2872	{'accuracy': 0.874}
0.0241	10.0	2500	1.3091	{'accuracy': 0.873}

Framework versions

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