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: 1.0392
• Accuracy: {'accuracy': 0.878}

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	0.3770	{'accuracy': 0.878}
0.4389	2.0	500	0.5278	{'accuracy': 0.862}
0.4389	3.0	750	0.5955	{'accuracy': 0.877}
0.2051	4.0	1000	0.7697	{'accuracy': 0.868}
0.2051	5.0	1250	0.9253	{'accuracy': 0.874}
0.0755	6.0	1500	0.9588	{'accuracy': 0.878}
0.0755	7.0	1750	1.0716	{'accuracy': 0.869}
0.036	8.0	2000	1.0602	{'accuracy': 0.87}
0.036	9.0	2250	1.0603	{'accuracy': 0.875}
0.0108	10.0	2500	1.0392	{'accuracy': 0.878}

Framework versions

• PEFT 0.12.0
• Transformers 4.42.4
• Pytorch 2.3.1+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1