finetune with fparam

[chtchelkatchev]

I pretrained the deepmd potential with fparam using the descriptor se_atten_v2 and deepmd=2.2.7. Then an attempt was made to finetune this potential on a new database with fparam, which led to an error message: "... in _prepare_feed_dict assert fparam is not None ... AssertionError". Without fparam fintuning works well. The ussue appears only with fparam. Does finetuning work with fparam?

[njzjz]

This is a bug. I'll convert the discussion to an issue to track it.

deepmd-kit/deepmd/fit/ener.py

Line 853 in b875ea8

ret = dp.eval(coord, box, atype, mixed_type=mixed_type)

[chtchelkatchev]

Thank You for quick reply!