Unable to optimize structures using the DP model

[lcl8888888]

longdeMacBook-Pro openlam % lam-opt relax -i examples/data -m dp0529.pth
To get the best performance, it is recommended to adjust the number of threads by setting the environment variables OMP_NUM_THREADS, DP_INTRA_OP_PARALLELISM_THREADS, and DP_INTER_OP_PARALLELISM_THREADS. See https://deepmd.rtfd.io/parallelism/ for more information.
You can use the environment variable DP_INFER_BATCH_SIZE tocontrol the inference batch size (nframes * natoms). The default value is 1024.

Start to relax structures.

Relaxing: 0it [00:00, ?it/s] Step Time Energy fmax
BFGS: 0 13:44:36 -2.592978 0.0228
BFGS: 1 13:44:48 -2.592985 0.0225
WARNING:root:Failed to relax MP_mp-1093779: RuntimeError('The following operation failed in the TorchScript interpreter.\nTraceback of TorchScript (most recent call last):\nRuntimeError: The following operation failed in the TorchScript interpreter.\nTraceback of TorchScript (most recent call last):\nRuntimeError: The size of tensor a (513) must match the size of tensor b (25) at non-singleton dimension 1\n\n')
Relaxing: 1it [00:15, 15.46s/it]WARNING:root:Failed to relax MP_mp-1006815: RuntimeError('The following operation failed in the TorchScript interpreter.\nTraceback of TorchScript (most recent call last):\nRuntimeError: The following operation failed in the TorchScript interpreter.\nTraceback of TorchScript (most recent call last):\nRuntimeError: The size of tensor a (513) must match the size of tensor b (25) at non-singleton dimension 1\n\n')
Relaxing: 2it [00:15, 7.74s/it]

Saved to df.

[anyangml]

Sorry for the super late reply. I am not able to reproduce the error with a Mac M1chip, CPU relax. Not sure if you have an intel chip or you are trying to use MPS relax.