This model is a test version that was learned by integrating several Instruction datasets. The final version can be found at DILAB-HYU/KoQuality-Polyglot-5.8b.
Training hyperparameters
learning_rate: 5e-5
train_batch_size: 2
seed: 42
distributed_type: multi-GPU (A30 24G) + Cpu Offloading
num_devices: 2
gradient_accumulation_steps: 32
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
