distilbert-base-uncased-lora-text-classification

This model is a fine-tuned version of distilbert/distilbert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.0476
• Accuracy: {'accuracy': 0.878}

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	0.3883	{'accuracy': 0.874}
0.436	2.0	500	0.4803	{'accuracy': 0.863}
0.436	3.0	750	0.7892	{'accuracy': 0.843}
0.1824	4.0	1000	0.7530	{'accuracy': 0.874}
0.1824	5.0	1250	0.9025	{'accuracy': 0.876}
0.0705	6.0	1500	0.9245	{'accuracy': 0.872}
0.0705	7.0	1750	0.9648	{'accuracy': 0.878}
0.0244	8.0	2000	1.0001	{'accuracy': 0.877}
0.0244	9.0	2250	1.0236	{'accuracy': 0.88}
0.0045	10.0	2500	1.0476	{'accuracy': 0.878}

Framework versions

• PEFT 0.14.0
• Transformers 4.48.0
• Pytorch 2.5.1+cu118
• Datasets 3.2.0
• Tokenizers 0.21.0