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: 0.8488
• Accuracy: {'accuracy': 0.8924438393464942}

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
0.4284	1.0	1469	0.6122	{'accuracy': 0.8515997277059224}
0.318	2.0	2938	0.4710	{'accuracy': 0.8686181075561606}
0.3091	3.0	4407	0.3991	{'accuracy': 0.8910823689584751}
0.267	4.0	5876	0.3609	{'accuracy': 0.9081007488087134}
0.2111	5.0	7345	0.5392	{'accuracy': 0.8876786929884275}
0.2231	6.0	8814	0.6888	{'accuracy': 0.8978897208985704}
0.1116	7.0	10283	0.6468	{'accuracy': 0.8965282505105514}
0.1111	8.0	11752	0.8718	{'accuracy': 0.8849557522123894}
0.076	9.0	13221	0.8075	{'accuracy': 0.8965282505105514}
0.0672	10.0	14690	0.8488	{'accuracy': 0.8924438393464942}

Framework versions

• Transformers 4.33.2
• Pytorch 2.0.1+cu118
• Datasets 2.14.5
• Tokenizers 0.13.3