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: 0.9693
• Accuracy: {'accuracy': 0.869}

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	0.3269	{'accuracy': 0.874}
0.4812	2.0	500	0.5846	{'accuracy': 0.85}
0.4812	3.0	750	0.5519	{'accuracy': 0.839}
0.3542	4.0	1000	0.5615	{'accuracy': 0.862}
0.3542	5.0	1250	0.5924	{'accuracy': 0.874}
0.2267	6.0	1500	0.7992	{'accuracy': 0.868}
0.2267	7.0	1750	0.8458	{'accuracy': 0.868}
0.1275	8.0	2000	0.9919	{'accuracy': 0.86}
0.1275	9.0	2250	0.9489	{'accuracy': 0.871}
0.0565	10.0	2500	0.9693	{'accuracy': 0.869}

Framework versions

• PEFT 0.13.2
• Transformers 4.44.2
• Pytorch 2.4.1+cu121
• Datasets 3.0.1
• Tokenizers 0.19.1