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: 1.3644
• Accuracy: {'accuracy': 0.858}

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	0.3793	{'accuracy': 0.856}
0.435	2.0	500	0.5190	{'accuracy': 0.858}
0.435	3.0	750	0.8326	{'accuracy': 0.857}
0.2005	4.0	1000	0.9137	{'accuracy': 0.856}
0.2005	5.0	1250	1.0362	{'accuracy': 0.862}
0.0827	6.0	1500	1.2331	{'accuracy': 0.852}
0.0827	7.0	1750	1.2110	{'accuracy': 0.856}
0.033	8.0	2000	1.2963	{'accuracy': 0.864}
0.033	9.0	2250	1.3438	{'accuracy': 0.863}
0.0128	10.0	2500	1.3644	{'accuracy': 0.858}

Framework versions

• PEFT 0.7.1
• Transformers 4.36.0
• Pytorch 2.1.1+cpu
• Datasets 2.15.0
• Tokenizers 0.15.0