lion_130m_8 / README.md
KaiyueWen's picture
Upload folder using huggingface_hub
84b88de verified

Model Card

Best configuration

Hyperparameter Value
beta1 0.9
beta2 0.98
learning_rate 0.001
max_grad_norm 1
min_lr_ratio 0
train_batch_size 128
warmup 2000
weight_decay 0.7