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: 0.9625
• Accuracy: {'accuracy': 0.894}

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
No log	1.0	250	0.4171	{'accuracy': 0.873}
0.4212	2.0	500	0.4391	{'accuracy': 0.877}
0.4212	3.0	750	0.6435	{'accuracy': 0.882}
0.2071	4.0	1000	0.7271	{'accuracy': 0.876}
0.2071	5.0	1250	0.7477	{'accuracy': 0.887}
0.0601	6.0	1500	0.8896	{'accuracy': 0.883}
0.0601	7.0	1750	0.8930	{'accuracy': 0.898}
0.0185	8.0	2000	0.9622	{'accuracy': 0.892}
0.0185	9.0	2250	0.9708	{'accuracy': 0.891}
0.0157	10.0	2500	0.9625	{'accuracy': 0.894}

Framework versions

• PEFT 0.14.0
• Transformers 4.48.3
• Pytorch 2.6.0+cu124
• Datasets 3.4.1
• Tokenizers 0.21.1