请作者帮忙看一下，一直跑不通，各种报错

[253701]

ERROR:models:emb_g. weight is not in the checkpoint INFO:models:Loaded checkpointData 456456 models G 0. pth (iteration 0) INFO:models:Loaded checkpoint Data 456456 models D 0. pth (iteration 0)**检测到模型存在, epoch为1, gloab1 step为0INFO:models:Loaded checkpoint Data 456456 models WD 0. pth (iteration 0)Some weights of the model checkpoint at./sln/wavlm-base-plus were not used when initializing WavLllodel: ['encoder.posconv_embed. conv.weight_v, encoder. pos_conv_embed. conv.weight_g- This IS expected if you are initializing WavLMModel fron the checkpoint of a model trained on another task or with anther architecture (e.g. initializing a BertForSeguenceClassification model from a BertForPreTraining model).- This IS NOT expected if you are initializing WavLMModel from the checkpoint of a model that you expect to be exactlydentical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).Some weights of WavLMModel were not initialized from the model checkpoint at./sln/wavlm-base-plus and are newly initialized: ['encoder, pos_conv_embed. conv. parametrizations. weight. originalo', encoder. pos_conv_embed. conv. parametrizations.weight. original1']You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference. 0it 100:00, ?it/sl

之后就是进度飞快的跑，最后也没有模型生成，我的操作全是按照up的视频教程来的，有报错是在阿里打标那一块，中途有报错但是进度依然跑玩，但是最后训练这里实在搞不明白了，前几步有识别到数据集按理说不应该是位置出错啊，看还有一个人也是类似的操作

[YYuX-1145]

打标产生的文件有内容吗？

[253701]

打标产生的文件有内容吗？ 有的

[YYuX-1145]

你可能空跑了，导致这个问题的原因可能是数据集数量太少或质量不过关，我没遇到过这中数据集所以不好下结论，你可以先尝试训练一下原神/星铁的数据集看看能不能跑通

[253701]

你可能空跑了，导致这个问题的原因可能是数据集数量太少或质量不过关，我没遇到过这中数据集所以不好下结论，你可以先尝试训练一下原神/星铁的数据集看看能不能跑通

好的，我先下载成品数据集试试，一点点排查问题，在提问区还看到有个跑空的，