a2c_model_error

/data/home/srinjoym/miniconda3/envs/vizdoom/lib/python3.9/site-packages/torch/autograd/__init__.py:251: UserWarning: Error detected in AddmmBackward0. Traceback of forward call that caused the error:
  File "/data/home/srinjoym/Grounding_RL/a2c_main.py", line 86, in <module>
    train(args)
  File "/data/home/srinjoym/Grounding_RL/a2c_train.py", line 91, in train
    result, final_eval_score, training_time, wallclock_time = agent.train(make_envs_fn,
  File "/data/home/srinjoym/Grounding_RL/a2c_model.py", line 240, in train
    next_values, (new_hx, new_cx) = self.ac_model.evaluate_state((img_stack, instruction_mat, (tx, hx, cx)))
  File "/data/home/srinjoym/Grounding_RL/models.py", line 169, in evaluate_state
    _, value, (hx, cx) = self.forward(inputs)
  File "/data/home/srinjoym/Grounding_RL/models.py", line 119, in forward
    new_hx, new_cx = self.lstm(x, (hx, cx))
  File "/data/home/srinjoym/miniconda3/envs/vizdoom/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
  File "/data/home/srinjoym/miniconda3/envs/vizdoom/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1527, in _call_impl
    return forward_call(*args, **kwargs)
  File "/data/home/srinjoym/miniconda3/envs/vizdoom/lib/python3.9/site-packages/torch/nn/modules/rnn.py", line 1347, in forward
    ret = _VF.lstm_cell(
 (Triggered internally at ../torch/csrc/autograd/python_anomaly_mode.cpp:114.)
  Variable._execution_engine.run_backward(  # Calls into the C++ engine to run the backward pass
Traceback (most recent call last):
  File "/data/home/srinjoym/Grounding_RL/a2c_main.py", line 86, in <module>
    train(args)
  File "/data/home/srinjoym/Grounding_RL/a2c_train.py", line 91, in train
    result, final_eval_score, training_time, wallclock_time = agent.train(make_envs_fn,
  File "/data/home/srinjoym/Grounding_RL/a2c_model.py", line 247, in train
    self.optimize_model()
  File "/data/home/srinjoym/Grounding_RL/a2c_model.py", line 124, in optimize_model
    loss.backward()
  File "/data/home/srinjoym/miniconda3/envs/vizdoom/lib/python3.9/site-packages/torch/_tensor.py", line 492, in backward
    torch.autograd.backward(
  File "/data/home/srinjoym/miniconda3/envs/vizdoom/lib/python3.9/site-packages/torch/autograd/__init__.py", line 251, in backward
    Variable._execution_engine.run_backward(  # Calls into the C++ engine to run the backward pass
RuntimeError: one of the variables needed for gradient computation has been modified by an inplace operation: [torch.FloatTensor [256, 1024]], which is output 0 of AsStridedBackward0, is at version 2; expected version 1 instead. Hint: the backtrace further above shows the operation that failed to compute its gradient. The variable in question was changed in there or anywhere later. Good luck!