TensorFlow error( CUBLAS_STATUS_EXECUTION_FAILED)

I'm training sentences by BERT. I used cpu but it was slow so i decided to use gpu.

I'm using RTX 3080Ti. but as i changed to gpu-setup. this error happened..

how can i fix it?

I1227 21:38:02.311986 10468 basic_session_run_hooks.py:606] Saving checkpoints for 1 into D:\google-research\CV\model.ckpt.
2020-12-27 21:38:34.124242: E tensorflow/stream_executor/cuda/cuda_blas.cc:428] failed to run cuBLAS routine: CUBLAS_STATUS_EXECUTION_FAILED
Traceback (most recent call last):
  File "C:\Users\User\anaconda3\envs\lab37\lib\site-packages\tensorflow\python\client\session.py", line 1356, in _do_call
    return fn(*args)
  File "C:\Users\User\anaconda3\envs\lab37\lib\site-packages\tensorflow\python\client\session.py", line 1341, in _run_fn
    options, feed_dict, fetch_list, target_list, run_metadata)
  File "C:\Users\User\anaconda3\envs\lab37\lib\site-packages\tensorflow\python\client\session.py", line 1429, in _call_tf_sessionrun
    run_metadata)
tensorflow.python.framework.errors_impl.InternalError: 2 root error(s) found.
  (0) Internal: Blas GEMM launch failed : a.shape=(200, 2), b.shape=(2, 768), m=200, n=768, k=2
         [[{{node bert/embeddings/MatMul}}]]
         [[loss/Mul_3/_4855]]
  (1) Internal: Blas GEMM launch failed : a.shape=(200, 2), b.shape=(2, 768), m=200, n=768, k=2
         [[{{node bert/embeddings/MatMul}}]]
0 successful operations.
0 derived errors ignored.

During handling of the above exception, another exception occurred: