unirome_collab

Slimshadys's group workspace

Group: d0.1

17840

5489

1-2

of 2

Timestamps visible

2023-12-14 12:37:02

Checkpoint 46919522 saved!

2023-12-14 12:37:24

LEARNING LOOP ENCOUNTERED AN ERROR

2023-12-14 12:37:24

Saving checkpoint 46969554...

2023-12-14 12:37:24

Checkpoint 46969554 saved!

2023-12-14 12:37:26

Traceback (most recent call last):

2023-12-14 12:37:26

File "C:\Users\gianc\anaconda3\envs\rlgym\lib\site-packages\rlgym_ppo\learner.py", line 207, in learn

2023-12-14 12:37:26

self._learn()

2023-12-14 12:37:26

File "C:\Users\gianc\anaconda3\envs\rlgym\lib\site-packages\rlgym_ppo\learner.py", line 252, in _learn

2023-12-14 12:37:26

ppo_report = self.ppo_learner.learn(self.experience_buffer)

2023-12-14 12:37:26

File "C:\Users\gianc\anaconda3\envs\rlgym\lib\site-packages\rlgym_ppo\ppo\ppo_learner.py", line 118, in learn

2023-12-14 12:37:26

ppo_loss.backward()

2023-12-14 12:37:26

File "C:\Users\gianc\anaconda3\envs\rlgym\lib\site-packages\torch\_tensor.py", line 492, in backward

2023-12-14 12:37:26

torch.autograd.backward(

2023-12-14 12:37:26

File "C:\Users\gianc\anaconda3\envs\rlgym\lib\site-packages\torch\autograd\__init__.py", line 251, in backward

2023-12-14 12:37:26

Variable._execution_engine.run_backward( # Calls into the C++ engine to run the backward pass

2023-12-14 12:37:26

torch.cuda.OutOfMemoryError: CUDA out of memory. Tried to allocate 98.00 MiB. GPU 0 has a total capacty of 6.00 GiB of which 3.70 GiB is free. Of the allocated memory 1.12 GiB is allocated by PyTorch, and 162.05 MiB is reserved by PyTorch but unallocated. If reserved but unallocated memory is large try setting max_split_size_mb to avoid fragmentation. See documentation for Memory Management and PYTORCH_CUDA_ALLOC_CONF