distilbert-base-uncased-lora-text-classification

This model is a fine-tuned version of distilbert-base-uncased on a truncated IMDB dataset. It achieves the following results on the evaluation set:

• Loss: 1.7208
• Accuracy: {'accuracy': 0.876}

Model description

The purpose of this model is to turn distilbert into a sentiment classification model.

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: 4

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	250	2.0890	{'accuracy': 0.862}
0.2005	2.0	500	1.8919	{'accuracy': 0.874}
0.2005	3.0	750	1.7205	{'accuracy': 0.871}
0.0963	4.0	1000	1.7208	{'accuracy': 0.876}

Framework versions

• Transformers 4.37.1
• Pytorch 2.1.2+cu118
• Datasets 2.16.1
• Tokenizers 0.15.1