nayohan's picture
Update README.md
1be158f
metadata
license: apache-2.0
datasets:
  - DILAB-HYU/KoQuality
language:
  - ko
pipeline_tag: text-generation
tags:
  - llama-2-ko
  - KoQuality
base_model: hyunseoki/ko-ref-llama2-7b

This model is a instruct-tuned ko-ref-llama2-7b model, using only 10% of [Kullm, OIG, KoAlpaca] Instruction dataset. len10_k100_mppl_n0.1.json -> 152step

Training hyperparameters

  • learning_rate: 5e-5
  • train_batch_size: 1
  • seed: 42
  • distributed_type: multi-GPU (A30 24G) + CPU Offloading(160GB)
  • 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

Framework versions

  • Transformers 4.30.2
  • Pytorch 2.0.1+cu117
  • Datasets 2.11.0
  • deepspeed 0.9.5