"git@developer.sourcefind.cn:zhaoyu6/sglang.git" did not exist on "770d63123c70f4eeb2d69c7268154cb0204e3e93"
-
lukovnikov authored
fix for negative learning rate with warmup_linear in BertAdam (happens when t_total is specified incorrectly) + copied BERT optimization warmup functions to OpenAI optimization file + added comments
e04bab59
