metadata

license: cc-by-sa-4.0
base_model: nlp-waseda/gpt2-small-japanese-wikipedia
tags:
  - generated_from_trainer
datasets:
  - livedoor-news-corpus
model-index:
  - name: ja-news-gen
    results: []

ja-news-gen

This model is a fine-tuned version of nlp-waseda/gpt2-small-japanese-wikipedia on the livedoor-news-corpus 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: 0.0005
train_batch_size: 16
eval_batch_size: 16
seed: 42
gradient_accumulation_steps: 8
total_train_batch_size: 128
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 1000
num_epochs: 6

Training results

Framework versions

Transformers 4.31.0
Pytorch 2.0.1+cu118
Datasets 2.14.4
Tokenizers 0.13.3