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: 0.7922
• Accuracy: {'accuracy': 0.88}

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	0.3212	{'accuracy': 0.862}
0.4694	2.0	500	0.3175	{'accuracy': 0.89}
0.4694	3.0	750	0.4655	{'accuracy': 0.872}
0.3081	4.0	1000	0.5394	{'accuracy': 0.885}
0.3081	5.0	1250	0.6248	{'accuracy': 0.871}
0.1875	6.0	1500	0.7691	{'accuracy': 0.877}
0.1875	7.0	1750	0.6730	{'accuracy': 0.884}
0.1041	8.0	2000	0.6989	{'accuracy': 0.882}
0.1041	9.0	2250	0.7978	{'accuracy': 0.879}
0.0363	10.0	2500	0.7922	{'accuracy': 0.88}

Framework versions

• PEFT 0.11.1
• Transformers 4.37.0
• Pytorch 2.4.1+cu121
• Datasets 2.21.0
• Tokenizers 0.15.2