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: 1.0281
• Accuracy: {'accuracy': 0.888}

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	0.3331	{'accuracy': 0.881}
0.4182	2.0	500	0.4217	{'accuracy': 0.89}
0.4182	3.0	750	0.5842	{'accuracy': 0.882}
0.2061	4.0	1000	0.6004	{'accuracy': 0.891}
0.2061	5.0	1250	0.7716	{'accuracy': 0.89}
0.0663	6.0	1500	0.9055	{'accuracy': 0.887}
0.0663	7.0	1750	1.0172	{'accuracy': 0.88}
0.0307	8.0	2000	1.0077	{'accuracy': 0.891}
0.0307	9.0	2250	0.9932	{'accuracy': 0.887}
0.0114	10.0	2500	1.0281	{'accuracy': 0.888}

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.0+cu118
• Datasets 2.15.0
• Tokenizers 0.15.0