53 lines
1.1 KiB
Markdown
53 lines
1.1 KiB
Markdown
---
|
|
language:
|
|
- ko
|
|
license: apache-2.0
|
|
tags:
|
|
- generated_from_trainer
|
|
- polyglot-ko
|
|
- gpt-neox
|
|
- KoAlpaca
|
|
datasets:
|
|
- KoAlpaca-v1.1b
|
|
pipeline_tag: text-generation
|
|
base_model: EleutherAI/polyglot-ko-12.8b
|
|
model-index:
|
|
- name: KoAlpaca-Polyglot-12.8B
|
|
results: []
|
|
---
|
|
|
|
Update @ 2023.06.01
|
|
|
|
- Add Safetensor sharded model weight (max shard = 1GB)
|
|
|
|
|
|
# KoAlpaca-Polyglot-12.8B (v1.1b)
|
|
|
|
This model is a fine-tuned version of [EleutherAI/polyglot-ko-12.8b](https://huggingface.co/EleutherAI/polyglot-ko-12.8b) on a KoAlpaca Dataset v1.1b
|
|
|
|
Detail Codes are available at [KoAlpaca Github Repository](https://github.com/Beomi/KoAlpaca)
|
|
|
|
|
|
## Training procedure
|
|
|
|
### Training hyperparameters
|
|
|
|
The following hyperparameters were used during training:
|
|
- learning_rate: 5e-05
|
|
- train_batch_size: 1
|
|
- seed: 42
|
|
- distributed_type: multi-GPU (A100 80G)
|
|
- num_devices: 4
|
|
- gradient_accumulation_steps: 64
|
|
- 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: linear
|
|
- num_epochs: 2.0
|
|
|
|
### Framework versions
|
|
|
|
- Transformers 4.28.1
|
|
- Pytorch 2.0.0+cu117
|
|
- Datasets 2.11.0
|
|
- Tokenizers 0.13.3 |