distilbert-base-uncased-lora

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

distilbert-base-uncased-lora

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: 1.2409
• Accuracy: {'accuracy': 0.895}

Model description

DistilBERT has been fine-tuned on a toxicity dataset to effectively detect and label toxic content. The fine-tuning process incorporates the Low-Rank Adaptation (LoRA) method, enhancing the model's performance and efficiency in identifying toxic language by improving the computation time.

Intended uses & limitations

The following model is used for research purposes. The future improvement can include other multilingual languages.

Training and evaluation data

The model is evaluated on a test data which has been split in the begining of the train/test distribution. In addition, it was validated on a sample data.

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

Framework versions

• PEFT 0.12.0
• Transformers 4.42.4
• Pytorch 2.3.1+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1