xiaomei

Training beyond specified 't_total' steps with schedule warmup_linear. Learning rate set to 0.0. Please set 't_total' of BertAdam correctly.

1

Training beyond specified 't_total' steps with schedule warmup_linear. Learning rate set to 0.0. Please set 't_total' of BertAdam correctly. 请问后台一直提示这个,是什么原因呢?args.py中的test_lines已经设置为train.data文件的行数了

rt

运行代码，报错“cannot feed value of shape(16,400) for tensor ''context:0", which has shape(80,400)”

extension()文本对齐只考虑2个情况是为什么？

run_lm_finetuning.py

4

run_lm_finetuning.py这个文件没有

username：tester 当前账户没有API访问权限 （或试用权限过期）

1

{ "MarkWords": null, "Cases": null, "MustShowMessage": "", "Successed": false, "Message": "当前账户没有API访问权限 （或试用权限过期），请联系管理员开通！", "ClientAction": "", "extension": { "domain_words": null, "result_string": "", "result_string2": "" } }