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: 0.0287
• Accuracy: {'accuracy': 0.992}

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 OptimizerNames.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
0.3979	1.0	1250	0.2949	{'accuracy': 0.903}
0.4384	2.0	2500	0.2595	{'accuracy': 0.9152}
0.3827	3.0	3750	0.2294	{'accuracy': 0.9316}
0.3539	4.0	5000	0.2089	{'accuracy': 0.9394}
0.331	5.0	6250	0.1202	{'accuracy': 0.9594}
0.2554	6.0	7500	0.1205	{'accuracy': 0.9678}
0.2312	7.0	8750	0.0965	{'accuracy': 0.9778}
0.1933	8.0	10000	0.0551	{'accuracy': 0.9864}
0.1389	9.0	11250	0.0404	{'accuracy': 0.989}
0.0822	10.0	12500	0.0287	{'accuracy': 0.992}

Framework versions

• PEFT 0.14.0
• Transformers 4.51.3
• Pytorch 2.6.0+cu124
• Datasets 3.5.0
• Tokenizers 0.21.1