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: 1.0024
• Accuracy: {'accuracy': 0.884}

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_FUSED 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	0.3059	{'accuracy': 0.873}
0.4329	2.0	500	0.4790	{'accuracy': 0.887}
0.4329	3.0	750	0.5350	{'accuracy': 0.876}
0.2328	4.0	1000	0.5796	{'accuracy': 0.878}
0.2328	5.0	1250	0.8671	{'accuracy': 0.861}
0.056	6.0	1500	0.8909	{'accuracy': 0.878}
0.056	7.0	1750	0.9056	{'accuracy': 0.876}
0.0296	8.0	2000	0.9462	{'accuracy': 0.878}
0.0296	9.0	2250	0.9914	{'accuracy': 0.881}
0.0142	10.0	2500	1.0024	{'accuracy': 0.884}

Framework versions

• PEFT 0.17.1
• Transformers 4.57.1
• Pytorch 2.9.0
• Datasets 4.3.0
• Tokenizers 0.22.1