Bitsandbytes 文件

RMSprop

Hugging Face's logo
加入 Hugging Face 社群

並獲得增強的文件體驗

開始使用

RMSprop

RMSprop 是一種自適應學習率最佳化器,與 Adagrad 非常相似。RMSprop 為每個引數儲存過去梯度的平方的*加權平均值*,並用它來調整學習率。這使得學習率可以根據梯度的大小自動降低或提高,並防止學習率衰減。

RMSprop

class bitsandbytes.optim.RMSprop

< >

( params lr = 0.01 alpha = 0.99 eps = 1e-08 weight_decay = 0 momentum = 0 centered = False optim_bits = 32 args = None min_8bit_size = 4096 percentile_clipping = 100 block_wise = True )

RMSprop8bit

class bitsandbytes.optim.RMSprop8bit

< >

( params lr = 0.01 alpha = 0.99 eps = 1e-08 weight_decay = 0 momentum = 0 centered = False args = None min_8bit_size = 4096 percentile_clipping = 100 block_wise = True )

RMSprop32bit

class bitsandbytes.optim.RMSprop32bit

< >

( params lr = 0.01 alpha = 0.99 eps = 1e-08 weight_decay = 0 momentum = 0 centered = False args = None min_8bit_size = 4096 percentile_clipping = 100 block_wise = True )

< > 在 GitHub 上更新

© . This site is unofficial and not affiliated with Hugging Face, Inc.