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: 0.2711
• Accuracy: {'accuracy': 0.903}

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: 64
• eval_batch_size: 64
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	16	0.3245	{'accuracy': 0.886}
No log	2.0	32	0.2693	{'accuracy': 0.892}
No log	3.0	48	0.2717	{'accuracy': 0.887}
No log	4.0	64	0.2650	{'accuracy': 0.898}
No log	5.0	80	0.2711	{'accuracy': 0.903}

Framework versions

• PEFT 0.13.2
• Transformers 4.44.2
• Pytorch 2.5.0+cu121
• Datasets 3.1.0
• Tokenizers 0.19.1