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: 0.9161
• Accuracy: {'accuracy': 0.891}

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: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	250	0.5546	{'accuracy': 0.843}
0.431	2.0	500	0.5321	{'accuracy': 0.843}
0.431	3.0	750	0.6471	{'accuracy': 0.871}
0.2156	4.0	1000	0.6370	{'accuracy': 0.894}
0.2156	5.0	1250	0.7770	{'accuracy': 0.879}
0.0585	6.0	1500	0.8067	{'accuracy': 0.887}
0.0585	7.0	1750	0.9062	{'accuracy': 0.892}
0.0296	8.0	2000	0.8693	{'accuracy': 0.895}
0.0296	9.0	2250	0.8794	{'accuracy': 0.893}
0.0129	10.0	2500	0.9161	{'accuracy': 0.891}

Framework versions

• PEFT 0.14.0
• Transformers 4.47.0
• Pytorch 2.2.2
• Datasets 3.1.0
• Tokenizers 0.21.0