以上代码有以下问题，分析修改：(style_tune) C:\Users\28996\Desktop\AI\persona_contrastive_finetuning>python Contrastive_Training_LM.py
Map: 0%| | 0/1 [00:00<?, ? examples/s]ERROR:__main__:无法解析anchor_input_ids: 你如何看待气候变化？
ERROR:__main__:无法解析positive_input_ids: 气候变化是严峻的全球危机，我们需要立即采取行动减少碳排放！
ERROR:__main__:无法解析negative_input_ids: 哈哈天气什么的随便啦，不如聊聊游戏？
Map: 100%|████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 13.02 examples/s]
Map: 0%| | 0/1 [00:00<?, ? examples/s]ERROR:__main__:无法解析anchor_input_ids: 你如何看待气候变化？
ERROR:__main__:无法解析positive_input_ids: 气候变化是严峻的全球危机，我们需要立即采取行动减少碳排放！
ERROR:__main__:无法解析negative_input_ids: 哈哈天气什么的随便啦，不如聊聊游戏？
Map: 100%|████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 67.37 examples/s]
训练集样本示例: {'anchor_input_ids': '你如何看待气候变化？', 'positive_input_ids': '气候变化是严峻的全球危机，我们需要立即采取行动减少碳排放！', 'negative_input_ids': '哈哈天气什么的随便啦，不如聊聊游戏？'}
验证集样本示例: {'anchor_input_ids': '你如何看待气候变化？', 'positive_input_ids': '气候变化是严峻的全球危机，我们需要立即采取行动减少碳排放！', 'negative_input_ids': '哈哈天气什么的随便啦，不如聊聊游戏？'}
0%| | 0/3 [00:00<?, ?it/s]ERROR:__main__:无法解析token IDs: 你如何看待气候变化？
ERROR:__main__:无法解析token IDs: 气候变化是严峻的全球危机，我们需要立即采取行动减少碳排放！
ERROR:__main__:无法解析token IDs: 哈哈天气什么的随便啦，不如聊聊游戏？
You're using a Qwen2TokenizerFast tokenizer. Please note that with a fast tokenizer, using the `__call__` method is faster than using a method to encode the text followed by a call to the `pad` method to get a padded encoding.
Traceback (most recent call last):
File "C:\Users\28996\Desktop\AI\persona_contrastive_finetuning\Contrastive_Training_LM.py", line 281, in <module>
trainer.train()
File "C:\Users\28996\miniconda3\envs\style_tune\lib\site-packages\transformers\trainer.py", line 2171, in train
return inner_training_loop(
File "C:\Users\28996\miniconda3\envs\style_tune\lib\site-packages\transformers\trainer.py", line 2480, in _inner_training_loop
batch_samples, num_items_in_batch = self.get_batch_samples(epoch_iterator, num_batches)
File "C:\Users\28996\miniconda3\envs\style_tune\lib\site-packages\transformers\trainer.py", line 5156, in get_batch_samples
batch_samples += [next(epoch_iterator)]
File "C:\Users\28996\miniconda3\envs\style_tune\lib\site-packages\accelerate\data_loader.py", line 567, in __iter__
current_batch = next(dataloader_iter)
File "C:\Users\28996\miniconda3\envs\style_tune\lib\site-packages\torch\utils\data\dataloader.py", line 701, in __next__
data = self._next_data()
File "C:\Users\28996\miniconda3\envs\style_tune\lib\site-packages\torch\utils\data\dataloader.py", line 757, in _next_data
data = self._dataset_fetcher.fetch(index) # may raise StopIteration
File "C:\Users\28996\miniconda3\envs\style_tune\lib\site-packages\torch\utils\data\_utils\fetch.py", line 55, in fetch
return self.collate_fn(data)
File "C:\Users\28996\Desktop\AI\persona_contrastive_finetuning\Contrastive_Training_LM.py", line 96, in __call__
"positive_attention_mask": create_to_attention_mask(batch_positive["input_ids"]),
NameError: name 'create_to_attention_mask' is not defined. Did you mean: 'create_attention_mask'?
0%| | 0/3 [00:00<?, ?it/s]
扫一扫
1520
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
