【发布时间】:2021-10-22 19:03:57
【问题描述】:
我正在对自定义(使用 HuggingFace)数据集进行微调预训练模型我将从一个 youtube 视频中正确复制所有代码,一切正常,但在此单元格/代码中:
with training_args.strategy.scope():
model=TFDistilBertForSequenceClassification.from_pretrained("distilbert-base-uncased")
trainer = TFTrainer(model=model, # the instantiated ???? Transformers model to be trained
args=training_args, # training arguments, defined above
train_dataset=train_dataset, # training dataset
eval_dataset=test_dataset) # evaluation dataset
trainer.train()
它会给我这个错误:
TypeError: '>' not supported between instances of 'NoneType' and 'int'
【问题讨论】:
-
也许这更适合 Huggingface Github 上的问题。
标签: deep-learning data-science huggingface-transformers huggingface-tokenizers huggingface-datasets