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: 0.9787
• Accuracy: {'accuracy': 0.897}

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: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	250	0.3674	{'accuracy': 0.891}
0.4133	2.0	500	0.4185	{'accuracy': 0.861}
0.4133	3.0	750	0.5729	{'accuracy': 0.88}
0.1943	4.0	1000	0.7140	{'accuracy': 0.89}
0.1943	5.0	1250	0.8534	{'accuracy': 0.884}
0.0825	6.0	1500	0.9309	{'accuracy': 0.882}
0.0825	7.0	1750	0.9520	{'accuracy': 0.886}
0.0304	8.0	2000	0.9556	{'accuracy': 0.889}
0.0304	9.0	2250	0.9718	{'accuracy': 0.896}
0.0055	10.0	2500	0.9787	{'accuracy': 0.897}

Framework versions

• PEFT 0.11.2.dev0
• Transformers 4.41.0
• Pytorch 2.3.0+cu121
• Datasets 2.19.1
• Tokenizers 0.19.1