UK_Energy_Industry_Complaints_Identifier_ver1

This model is a fine-tuned version of distilbert-base-uncased on a balanced dataset consisting of 17,620 publicy available customer reviews of various domestic energy suppliers in the United Kingdom. It achieves the following results on the evaluation set:

• Loss: 0.3369
• Accuracy: 0.9561
• F1: [0.95594347 0.95621041]

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: 2e-05
• 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

Framework versions

• Transformers 4.28.1
• Pytorch 2.0.1
• Datasets 2.13.1
• Tokenizers 0.11.0