piopio

Results 6 issues of piopio

I run python train.py --actor-model facebook/opt-1.3b --reward-model facebook/opt-350m --deployment-type single_gpu in colab,but got errors. training.log file: 2023-05-11 07:32:43.560027: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT [2023-05-11 07:32:44,353] [WARNING] [runner.py:191:fetch_hostfile]...

bug
training

How long does it take for the review? I have been applying for 4 days and it has not been approved yet

### Reminder - [X] I have read the README and searched the existing issues. ### Reproduction 如果我想基于大模型微调一个特定的分类任务,我该选择哪种微调方式呢 ### Expected behavior 给出相应的微调方法 ### System Info _No response_ ### Others _No response_

solved

When I use the initial_prompt parameter, the model will recognize some professional vocabulary correctly, but it affects the recognition of other non professional vocabulary