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: 5e-05
• train_batch_size: 64
• seed: 42
• distributed_type: multi-GPU (A100 80G)
• num_devices: 4
• gradient_accumulation_steps: 16
• total_train_batch_size: 256
• total_eval_batch_size: 32
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• num_epochs: 10.0

Framework versions

• Transformers 4.28.1
• Pytorch 2.0.0+cu117
• Datasets 2.11.0
• Tokenizers 0.13.3