Hugging Face's logo

richardr1126
/
sql-guanaco-13b-qlora

TensorBoard
LoRA
QLoRa
LoRA Adapter
LLaMA
Model card Files Metrics Community
sql-guanaco-13b-qlora / README.md
richardr1126's picture
richardr1126
Update README.md
cc16d61
preview code
|
raw
history blame
1.22 kB
metadata
tags:
  - LoRA
  - QLoRa
  - LoRA Adapter
model-index:
  - name: sql-guanaco-13b-4
    results: []
datasets:
  - richardr1126/spider-sql_guanaco_style

sql-guanaco-13b-4

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 on richardr1126/sql-create-context_guanaco_style.

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