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: 0.9507
• Accuracy: {'accuracy': 0.891}

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	0.3891	{'accuracy': 0.869}
0.4379	2.0	500	0.3792	{'accuracy': 0.889}
0.4379	3.0	750	0.4238	{'accuracy': 0.885}
0.2161	4.0	1000	0.7566	{'accuracy': 0.88}
0.2161	5.0	1250	0.7623	{'accuracy': 0.891}
0.0603	6.0	1500	0.8379	{'accuracy': 0.893}
0.0603	7.0	1750	0.9690	{'accuracy': 0.887}
0.0124	8.0	2000	0.9971	{'accuracy': 0.888}
0.0124	9.0	2250	0.9412	{'accuracy': 0.891}
0.0069	10.0	2500	0.9507	{'accuracy': 0.891}

Framework versions

• Transformers 4.34.0
• Pytorch 2.0.1+cpu
• Datasets 2.15.0
• Tokenizers 0.14.0