Koala-12.8b-v1 / README.md
mssongit's picture
Update README.md
6e6754a
metadata
license: apache-2.0
datasets:
  - beomi/KoAlpaca-v1.1a
language:
  - ko
tags:
  - polyglot-ko
  - gpt-neox

This model is a fine-tuned version of EleutherAI/polyglot-ko-12.8b

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 5e-05
  • train_batch_size: 2
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 2.0
  • mixed_precision_training: Native AMP

Framework versions

  • Transformers 4.29.0.dev0
  • Pytorch 2.0.0+cu116
  • Datasets 2.10.1
  • Tokenizers 0.13.2