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: 1.2300
• Accuracy: {'accuracy': 0.861}

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	0.5358	{'accuracy': 0.853}
0.398	2.0	500	0.5237	{'accuracy': 0.866}
0.398	3.0	750	0.6152	{'accuracy': 0.849}
0.1864	4.0	1000	0.7506	{'accuracy': 0.855}
0.1864	5.0	1250	0.9820	{'accuracy': 0.867}
0.0382	6.0	1500	1.0581	{'accuracy': 0.856}
0.0382	7.0	1750	1.1583	{'accuracy': 0.862}
0.0149	8.0	2000	1.2200	{'accuracy': 0.858}
0.0149	9.0	2250	1.2581	{'accuracy': 0.862}
0.006	10.0	2500	1.2300	{'accuracy': 0.861}

Framework versions

• PEFT 0.8.1
• Transformers 4.37.2
• Pytorch 2.2.0
• Datasets 2.16.1
• Tokenizers 0.15.1