README.md

metadata

license: apache-2.0
tags:
  - trl
  - dpo
  - generated_from_trainer
base_model: yanolja/EEVE-Korean-Instruct-10.8B-v1.0
model-index:
  - name: nhn_dpo_v3-eeve_EEVE-Korean-Instruct-10.8B-v1.0_DPO
    results: []

nhn_dpo_v3-eeve_EEVE-Korean-Instruct-10.8B-v1.0_DPO

This model is a fine-tuned version of yanolja/EEVE-Korean-Instruct-10.8B-v1.0 on an unknown dataset.

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 1e-06
• train_batch_size: 1
• eval_batch_size: 8
• seed: 42
• distributed_type: multi-GPU
• num_devices: 7
• gradient_accumulation_steps: 8
• total_train_batch_size: 56
• total_eval_batch_size: 56
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 1

Training results

Framework versions

• Transformers 4.38.1
• Pytorch 2.2.1+cu118
• Datasets 2.17.1
• Tokenizers 0.15.2