richardr1126/sql-guanaco-13b-qlora

lora-sql-guanaco-13b-adapter

This is a LoRA adapter for richardr1126/guanaco-13b-merged, or any other merged guanaco-13b model, fine tuned from LLaMA.
This LoRA was fine-tuned using QLoRA techniques on the richardr1126/sql-create-context_guanaco_style dataset.

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 0.0002
• train_batch_size: 4
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 16
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.03
• training_steps: 1875
• mixed_precision_training: Native AMP

Framework versions

• Transformers 4.30.0.dev0
• Pytorch 2.0.1+cu118
• Datasets 2.13.0
• Tokenizers 0.13.3

Citation

@article{dettmers2023qlora,
  title={QLoRA: Efficient Finetuning of Quantized LLMs},
  author={Dettmers, Tim and Pagnoni, Artidoro and Holtzman, Ari and Zettlemoyer, Luke},
  journal={arXiv preprint arXiv:2305.14314},
  year={2023}
}