_pickle.UnpicklingError: pickle data was truncated

[Oxtay]

I am trying to get RL4LMs to work, and to achieve this, I've made the docker image using the instructions in the README file. After building the container, I tried running the following command in the container(under Quick start):

python scripts/training/train_text_generation.py --config_path scripts/training/task_configs/summarization/t5_ppo.yml

(docker run -it rl4lms /bin/sh followed by python scripts/training/train_text_generation.py --config_path scripts/training/task_configs/summarization/t5_ppo.yml)

However, I'm getting an UnpicklingError. The complete debugging info right before the error is as follows:

To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
2023-03-02 17:33:13.379149: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer.so.7'; dlerror: libnvinfer.so.7: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /usr/local/nvidia/lib:/usr/local/nvidia/lib64
2023-03-02 17:33:13.379385: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer_plugin.so.7'; dlerror: libnvinfer_plugin.so.7: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /usr/local/nvidia/lib:/usr/local/nvidia/lib64
2023-03-02 17:33:13.379401: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Cannot dlopen some TensorRT libraries. If you would like to use Nvidia GPU with TensorRT, please make sure the missing libraries mentioned above are installed properly.
2023-03-02 17:33:45.988942: I tensorflow/core/platform/cpu_feature_guard.cc:193] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations:  AVX2 FMA
To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
2023-03-02 17:33:48.806522: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer.so.7'; dlerror: libnvinfer.so.7: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /usr/local/nvidia/lib:/usr/local/nvidia/lib64
2023-03-02 17:33:48.806802: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer_plugin.so.7'; dlerror: libnvinfer_plugin.so.7: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /usr/local/nvidia/lib:/usr/local/nvidia/lib64
2023-03-02 17:33:48.806862: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Cannot dlopen some TensorRT libraries. If you would like to use Nvidia GPU with TensorRT, please make sure the missing libraries mentioned above are installed properly.
Killed
# Traceback (most recent call last):
  File "/opt/conda/lib/python3.8/multiprocessing/forkserver.py", line 280, in main
    code = _serve_one(child_r, fds,
  File "/opt/conda/lib/python3.8/multiprocessing/forkserver.py", line 319, in _serve_one
    code = spawn._main(child_r, parent_sentinel)
  File "/opt/conda/lib/python3.8/multiprocessing/spawn.py", line 126, in _main
    self = reduction.pickle.load(from_parent)
_pickle.UnpicklingError: pickle data was truncated

I am using a macbook pro 2019 with intel chip 2.4 GHz Quad-Core Intel Core i5. Should I make any changes to the Dockerfile to be able to run this or is there any other script I can try?

note: I've also tried installing this on my machine (and a different machine with M1 chip) but have run into issues with incompatibility of specific package versions with python 3.10 and 3.11 I have on these two machines.