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
- lr_scheduler_type: linear
- num_epochs: 2.0
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu117
- Datasets 2.11.0
- deepspeed 0.9.5