Edit model card

KULLM-Polyglot-12.8B-v2

This model is a fine-tuned version of EleutherAI/polyglot-ko-12.8b on a KULLM v2

Detail Codes are available at KULLM Github Repository

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 3e-4
  • train_batch_size: 6
  • seed: 42
  • distributed_type: multi-GPU (A100 80G)
  • num_devices: 4
  • gradient_accumulation_steps: 21.3
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 8.0

Framework versions

  • Transformers 4.28.1
  • Pytorch 2.0.0+cu117
  • Datasets 2.11.0
  • Tokenizers 0.13.3
Downloads last month
4,567
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for nlpai-lab/kullm-polyglot-12.8b-v2

Adapters
1 model