alonkonchitsky12345
alonkonchitsky12345
>> g = self.model.split_params() In addition, the model has no attribute/method 'split_params'
@Laughing-q , thank you for taking part in the discussion! In the case you suggested, the training actually starts, but if you look at the arguments with which it started,...
Colleagues, thank you so much for your advices! You claim that the arguments specified in the "args.yaml" file reflect only the default settings. As far as I understand (correct me...
@pderrenger I am grateful to you for the detailed answer! One thing remains unclear... When training the model using optimizers: SGD, Adam, AdamW, NAdam, RAdam - training occurs normally, losses...
@pderrenger Thank you so much for the clarification, I wasn't even hoping for such a detailed answer.