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: 1.4335
• Accuracy: {'accuracy': 0.8008898776418243}

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
0.5327	1.0	525	0.5946	{'accuracy': 0.796440489432703}
0.4557	2.0	1050	0.6396	{'accuracy': 0.8020022246941045}
0.4072	3.0	1575	0.6353	{'accuracy': 0.7986651835372637}
0.37	4.0	2100	0.8301	{'accuracy': 0.7842046718576196}
0.3246	5.0	2625	1.0083	{'accuracy': 0.7986651835372637}
0.2574	6.0	3150	1.1111	{'accuracy': 0.8120133481646273}
0.1955	7.0	3675	1.1856	{'accuracy': 0.7997775305895439}
0.1479	8.0	4200	1.2189	{'accuracy': 0.8008898776418243}
0.1088	9.0	4725	1.3530	{'accuracy': 0.8042269187986651}
0.1091	10.0	5250	1.4335	{'accuracy': 0.8008898776418243}

Framework versions

• PEFT 0.13.2
• Transformers 4.46.2
• Pytorch 2.5.1+cu121
• Datasets 3.1.0
• Tokenizers 0.20.3