distilbert-base-uncased-lora-text-classification

This model is a fine-tuned version of distilbert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.6215
• Accuracy: {'accuracy': 0.8248666666666666}

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
0.4666	1.0	7500	0.5550	{'accuracy': 0.8414}
0.537	2.0	15000	0.5152	{'accuracy': 0.8277666666666667}
0.5576	3.0	22500	0.4929	{'accuracy': 0.8178}
0.5947	4.0	30000	0.4912	{'accuracy': 0.8104}
0.5841	5.0	37500	0.5970	{'accuracy': 0.8050666666666667}
0.6447	6.0	45000	0.6422	{'accuracy': 0.8114333333333333}
0.5955	7.0	52500	0.5771	{'accuracy': 0.8209}
0.5419	8.0	60000	0.5765	{'accuracy': 0.821}
0.5966	9.0	67500	0.6055	{'accuracy': 0.8230666666666666}
0.5417	10.0	75000	0.6215	{'accuracy': 0.8248666666666666}

Framework versions

• Transformers 4.32.1
• Pytorch 2.1.0+cu121
• Datasets 2.14.6
• Tokenizers 0.13.2