nayohan's picture
Update README.md
08a90ad
metadata
license: apache-2.0
datasets:
  - DILAB-HYU/KoQuality
language:
  - ko
pipeline_tag: text-generation
tags:
  - polyglot-ko
  - gpt-neox
  - KoQuality
base_model: EleutherAI/polyglot-ko-5.8b

This model is a instruct-tuned poylglot-ko-5.8b model, using full [Kullm, OIG, KoAlpaca] Instruction dataset. koquality_raw.json -> 410step

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: 1.0

Framework versions

  • Transformers 4.30.2

  • Pytorch 2.0.1+cu117

  • Datasets 2.11.0

  • deepspeed 0.9.5