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: 0.9490
• Accuracy: {'accuracy': 0.896}

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	0.4908	{'accuracy': 0.865}
0.4238	2.0	500	0.3895	{'accuracy': 0.884}
0.4238	3.0	750	0.7152	{'accuracy': 0.878}
0.1877	4.0	1000	0.6360	{'accuracy': 0.898}
0.1877	5.0	1250	0.7666	{'accuracy': 0.897}
0.0805	6.0	1500	0.8102	{'accuracy': 0.891}
0.0805	7.0	1750	0.8150	{'accuracy': 0.89}
0.0283	8.0	2000	0.9224	{'accuracy': 0.893}
0.0283	9.0	2250	0.9227	{'accuracy': 0.894}
0.0148	10.0	2500	0.9490	{'accuracy': 0.896}

Framework versions

• PEFT 0.10.0
• Transformers 4.39.3
• Pytorch 2.2.2+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2