metadata

license: other
library_name: peft
tags:
  - llama-factory
  - lora
  - generated_from_trainer
base_model: abacusai/Smaug-34B-v0.1
model-index:
  - name: model-update
    results: []

model-update

This model is a fine-tuned version of abacusai/Smaug-34B-v0.1 on the oncc_medqa_instruct dataset.

Training procedure

git clone https://github.com/chenhaodev/LLaMA-Factory; cd LLaMA-Factory; pip install -r requirements.txt;
python create_pods.py 'Qwen/Qwen-72B' 'NVIDIA A100 80GB PCIe' 1 xxx xxx xxx 6rhltjf914

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 0.0005
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: cosine
lr_scheduler_warmup_steps: 20
num_epochs: 1.0

Training results

Framework versions

PEFT 0.8.2
Transformers 4.37.2
Pytorch 2.0.1+cu118
Datasets 2.17.0
Tokenizers 0.15.2