WIL - SecureAI Labs - Z Jadidi
Collection
This collection contains all source code used for training and testing, datasets used and best performing LoRa Adapters related to this project.
•
7 items
•
Updated
YAML Metadata
Warning:
empty or missing yaml metadata in repo card
(https://huggingface.co/docs/hub/model-cards#model-card-metadata)
This model has been trained for binary classification of the TON-Iot Network dataset.
Refer to adapter_config.json for LoRa Parameters.
Accuracy: 94.6 %
Key Training Params:
- Steps: 100
- Batch Size: 128
- Optimizer: Adam_8bit
- lr_schedular: cosine_with_restarts
- lr_scheduler_kwargs = { "num_cycles": len(trainer.get_train_dataloader()) / 100 }
The datasets are an 80/20 partition of the TON-Iot Network dataset.
Train Dataset:
- train_network.jsonl
Test Dataset:
- test_network.jsonl