-
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
da2d8ca2
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