|
--- |
|
language: |
|
- ko |
|
license: apache-2.0 |
|
tags: |
|
- generated_from_trainer |
|
- polyglot-ko |
|
- gpt-neox |
|
- KoQuality |
|
datasets: |
|
- DILAB-HYU/KoQuality |
|
pipeline_tag: text-generation |
|
base_model: EleutherAI/polyglot-ko-5.8b |
|
model-index: |
|
- name: KoAlpaca-Polyglot-5.8B |
|
results: [] |
|
--- |
|
This model is a test version that was learned by integrating several Instruction datasets. The final version can be found at [DILAB-HYU/KoQuality-Polyglot-5.8b](https://huggingface.co/DILAB-HYU/KoQuality-Polyglot-5.8b). |
|
|
|
|
|
## Training hyperparameters |
|
- learning_rate: 5e-5 |
|
- train_batch_size: 2 |
|
- seed: 42 |
|
- distributed_type: multi-GPU (A30 24G) + Cpu Offloading |
|
- num_devices: 2 |
|
- gradient_accumulation_steps: 32 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 2.0 |
|
|
|
## Framework versions |
|
- Transformers 4.30.2 |
|
- Pytorch 2.0.1+cu117 |
|
- Datasets 2.11.0 |
|
- deepspeed 0.9.5 |
