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: 0.9725
• 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	0.4241	{'accuracy': 0.872}
0.4269	2.0	500	0.5036	{'accuracy': 0.861}
0.4269	3.0	750	0.5352	{'accuracy': 0.892}
0.1965	4.0	1000	0.8070	{'accuracy': 0.878}
0.1965	5.0	1250	0.7119	{'accuracy': 0.89}
0.0751	6.0	1500	0.7886	{'accuracy': 0.89}
0.0751	7.0	1750	0.9721	{'accuracy': 0.885}
0.0192	8.0	2000	0.9711	{'accuracy': 0.883}
0.0192	9.0	2250	0.9572	{'accuracy': 0.894}
0.0184	10.0	2500	0.9725	{'accuracy': 0.891}

Framework versions

• PEFT 0.11.1
• Transformers 4.41.2
• Pytorch 2.1.2+cpu
• Datasets 2.20.0
• Tokenizers 0.19.1