README.md

metadata

license: mit
base_model: beomi/open-llama-2-ko-7b
tags:
  - generated_from_trainer
model-index:
  - name: open-llama-2-ko-7b-ko-alpaca-finetuned-50steps
    results: []

open-llama-2-ko-7b-ko-alpaca-finetuned-50steps

This model is a fine-tuned version of beomi/open-llama-2-ko-7b 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: 0.0001
• train_batch_size: 2
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• training_steps: 50

Training results

Framework versions

• Transformers 4.31.0
• Pytorch 2.2.2+cu121
• Datasets 2.18.0
• Tokenizers 0.13.3