Hello, when I run step3 (sh run_data_pipeline.sh), the output json file content is as follows:
The process supervision tags are not extracted at all.
After inspecting the code, I found that the output of model_outputs = self.model.generate(inputs, sampling_params=sampling_params) did not follow the self.pattern2 pattern, resulting in matches = re.findall(self.pattern2, response, re.DOTALL) being empty.
However, I checked the code and did not find any instructions indicating that the output of the model needs to follow self.pattern2. I'm not sure if I've missed a crucial step that's preventing me from generating the correct data. I'd appreciate your help.
Hello, when I run step3 (sh run_data_pipeline.sh), the output json file content is as follows:
After inspecting the code, I found that the output of
model_outputs = self.model.generate(inputs, sampling_params=sampling_params)did not follow theself.pattern2pattern, resulting inmatches = re.findall(self.pattern2, response, re.DOTALL)being empty.However, I checked the code and did not find any instructions indicating that the output of the model needs to follow self.pattern2. I'm not sure if I've missed a crucial step that's preventing me from generating the correct data. I'd appreciate your help.