distilbert-base-uncased-finetuned-lora-stsb

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

• Pearsonr: 0.8935
• Spearmanr: 0.8891
• trainable model parameters: 1181185
• all model parameters: 68135426
• percentage of trainable model parameters: 1.73%

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 5e-04
• train_batch_size: 32
• eval_batch_size: 32
• seed: 42
• weight_decay: 0.01
• rank: 32
• lora_alpha: 32
• lora_dropout: 0.05
• num_epochs: 5