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: 1.1000
• Accuracy: {'accuracy': 0.871}

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	0.3592	{'accuracy': 0.877}
0.4557	2.0	500	0.7061	{'accuracy': 0.812}
0.4557	3.0	750	0.6457	{'accuracy': 0.875}
0.2774	4.0	1000	0.8260	{'accuracy': 0.858}
0.2774	5.0	1250	1.0227	{'accuracy': 0.867}
0.18	6.0	1500	0.8672	{'accuracy': 0.878}
0.18	7.0	1750	1.0398	{'accuracy': 0.873}
0.0522	8.0	2000	1.0858	{'accuracy': 0.869}
0.0522	9.0	2250	1.0951	{'accuracy': 0.867}
0.0166	10.0	2500	1.1000	{'accuracy': 0.871}

Framework versions

• PEFT 0.12.0
• Transformers 4.44.2
• Pytorch 2.4.1+cu121
• Datasets 3.0.0
• Tokenizers 0.19.1