distilbert-base-uncased-lora-text-classification

This model is a fine-tuned version of distilbert/distilbert-base-uncased on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.3129
• Accuracy: {'accuracy': 0.86}

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	0.4795	{'accuracy': 0.85}
0.4131	2.0	500	0.6526	{'accuracy': 0.851}
0.4131	3.0	750	0.6766	{'accuracy': 0.854}
0.2017	4.0	1000	0.9597	{'accuracy': 0.855}
0.2017	5.0	1250	0.9623	{'accuracy': 0.857}
0.1102	6.0	1500	0.9842	{'accuracy': 0.866}
0.1102	7.0	1750	1.1943	{'accuracy': 0.859}
0.023	8.0	2000	1.2874	{'accuracy': 0.859}
0.023	9.0	2250	1.3154	{'accuracy': 0.859}
0.0047	10.0	2500	1.3129	{'accuracy': 0.86}

Framework versions

• PEFT 0.10.0
• Transformers 4.40.1
• Pytorch 2.2.1+cu121
• Datasets 2.19.0
• Tokenizers 0.19.1