stanleylsx/entity_extractor_by_ner

start evaluate engines...之后报错

M-YoungBWeN opened this issue · 2 comments

M-YoungBWeN commented

您好，我遇到了一些问题

  1. 运行到start evaluate engines...之后报错
    100%|██████████| 5796/5796 [1:35:50<00:00, 1.01it/s]
    start evaluate engines...
    0%| | 0/1159 [00:00<?, ?it/s]WARNING:tensorflow:The parameters output_attentions, output_hidden_states and use_cache cannot be updated when calling a model.They have to be set to True/False in the config object (i.e.: config=XConfig.from_pretrained('name', output_attentions=True)).
    WARNING:tensorflow:The parameter return_dict cannot be set in graph mode and will always be set to True.
    2024-06-16 20:29:07.033624: W tensorflow/core/grappler/optimizers/loop_optimizer.cc:907] Skipping loop optimization for Merge node with control input: cond/branch_executed/_10
    进程已结束，退出代码为 -1073740791 (0xC0000409)

  2. checkpoint文件夹里没有输出东西
    .# 在此处设置模型保存位置，代码支持在原始模型上继续训练，新数据或从头训练一定要改！
    checkpoints_dir=checkpoints/0616
    .# 模型的名字
    checkpoint_name=model0616

  3. 我把huggingface的东西下载到了本地，不知道这样直接写路径可不可以
    use_pretrained_model=True
    pretrained_model=Bert
    .# Bert/AlBert
    huggingface_tag=E:\1_Code\Transformer\BERT_Data\bert230\bert-base-chinese
    .# huggingface上模型的名字
    finetune=True

  4. 显存最多只能使用70%，不知道如何更改这个限制

M-YoungBWeN commented

问题1、2、3已经解决，问题4不知道咋弄