Traceback (most recent call last):
File "/home/user01/pytorch_env/ChatGLM-6B-main/ptuning/main.py", line 430, in
main()
File "/home/user01/pytorch_env/ChatGLM-6B-main/ptuning/main.py", line 248, in main
train_dataset = train_dataset.map(
File "/home/user01/pytorch_env/pytorch_env/lib/python3.10/site-packages/datasets/arrow_dataset.py", line 591, in wrapper
out: Union["Dataset", "DatasetDict"] = func(self, *args, *kwargs)
File "/home/user01/pytorch_env/pytorch_env/lib/python3.10/site-packages/datasets/arrow_dataset.py", line 556, in wrapper
out: Union["Dataset", "DatasetDict"] = func(self, args, kwargs)
File "/home/user01/pytorch_env/pytorch_env/lib/python3.10/site-packages/datasets/arrow_dataset.py", line 3089, in map
for rank, done, content in Dataset._map_single(dataset_kwargs):
File "/home/user01/pytorch_env/pytorch_env/lib/python3.10/site-packages/datasets/arrow_dataset.py", line 3466, in _map_single
batch = apply_function_on_filtered_inputs(
File "/home/user01/pytorch_env/pytorch_env/lib/python3.10/site-packages/datasets/arrow_dataset.py", line 3345, in apply_function_on_filtered_inputs
processed_inputs = function(fn_args, additional_args, **fn_kwargs)
File "/home/user01/pytorch_env/ChatGLM-6B-main/ptuning/main.py", line 203, in preprocess_function_train
for turn_idx, (old_query, response) in enumerate(history):
TypeError: 'NoneType' object is not iterable
Is there an existing issue for this?
Current Behavior
Traceback (most recent call last): File "/home/user01/pytorch_env/ChatGLM-6B-main/ptuning/main.py", line 430, in
main()
File "/home/user01/pytorch_env/ChatGLM-6B-main/ptuning/main.py", line 248, in main
train_dataset = train_dataset.map(
File "/home/user01/pytorch_env/pytorch_env/lib/python3.10/site-packages/datasets/arrow_dataset.py", line 591, in wrapper
out: Union["Dataset", "DatasetDict"] = func(self, *args, *kwargs)
File "/home/user01/pytorch_env/pytorch_env/lib/python3.10/site-packages/datasets/arrow_dataset.py", line 556, in wrapper
out: Union["Dataset", "DatasetDict"] = func(self, args, kwargs)
File "/home/user01/pytorch_env/pytorch_env/lib/python3.10/site-packages/datasets/arrow_dataset.py", line 3089, in map
for rank, done, content in Dataset._map_single(dataset_kwargs):
File "/home/user01/pytorch_env/pytorch_env/lib/python3.10/site-packages/datasets/arrow_dataset.py", line 3466, in _map_single
batch = apply_function_on_filtered_inputs(
File "/home/user01/pytorch_env/pytorch_env/lib/python3.10/site-packages/datasets/arrow_dataset.py", line 3345, in apply_function_on_filtered_inputs
processed_inputs = function(fn_args, additional_args, **fn_kwargs)
File "/home/user01/pytorch_env/ChatGLM-6B-main/ptuning/main.py", line 203, in preprocess_function_train
for turn_idx, (old_query, response) in enumerate(history):
TypeError: 'NoneType' object is not iterable
所使用的数据集示例如下： {"prompt": "四个月感冒咳嗽孝鸣。四个月鼻塞然后当日晚上喂了紫苏陈皮薄荷红糖水第二天喂一天，第三天好转没有鼻涕鼻塞却咳嗽，咳的不算严重还能接受，第四天下午带有孝鸣声支支响，第五天偶尔咳但只要一醒着他呼吸带有孝鸣声，这么小孩不药物干预能好吗，这样病会不会一着凉就发作，现在有什么处理？", "response": "您好，根据您的描述，孩子出现了四个月的感冒咳嗽和鼻塞症状，但在喂了紫苏陈皮薄荷红糖水后，鼻塞好转但出现了咳嗽。咳嗽声音中带有孝鸣声，这种情况可能是毛细支气管炎，属于肺炎的一种。由于孩子年龄较小，我建议您带孩子去医院就诊，以便进行进一步的检查和治疗。", "history": []}
{"prompt": "如果我适合做微创双眼皮手术，您能给我一些建议吗？", "response": "当然可以。如果您适合进行微创双眼皮手术，我建议您在手术前详细了解手术的过程和风险，并与医生充分沟通。此外，术后的护理也非常重要，您需要按照医生的建议进行恢复和护理，避免过度用眼和受伤。请记住，每个人的情况都是独特的，所以请务必在专业医生的指导下进行决策和操作。", "history": [["我现在想做双眼皮，有影响吗？我做斜视手术已经快2年了，能做微创双眼皮吗？", "非常理解您的需求。一般来说，斜视手术对于双眼皮手术并没有直接影响。关于做微创双眼皮的可行性，我们需要根据您的眼睛条件来做进一步的评估。如果您的眼睛条件适合，那么微创双眼皮手术是一种较为安全和有效的选择。"]]}
Expected Behavior
能正常训练自己的数据集
Steps To Reproduce
Run bash train_chat.sh
Environment
Anything else?
No response