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: 0.9997
• Accuracy: {'accuracy': 0.882}

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	0.3444	{'accuracy': 0.888}
0.4135	2.0	500	0.4854	{'accuracy': 0.887}
0.4135	3.0	750	0.6411	{'accuracy': 0.882}
0.2383	4.0	1000	0.6366	{'accuracy': 0.891}
0.2383	5.0	1250	0.7062	{'accuracy': 0.891}
0.1144	6.0	1500	0.7646	{'accuracy': 0.882}
0.1144	7.0	1750	0.9373	{'accuracy': 0.884}
0.0176	8.0	2000	1.0347	{'accuracy': 0.884}
0.0176	9.0	2250	0.9923	{'accuracy': 0.883}
0.0188	10.0	2500	0.9997	{'accuracy': 0.882}

Framework versions

• Transformers 4.34.1
• Pytorch 2.1.0+cu118
• Datasets 2.14.6
• Tokenizers 0.14.1