Deng Cai comments

Results 17 comments of


                                            Deng Cai

A BUG? when performing gradient accumulation

@muellerzr I think the problem is that when we finish the `for batch in eval_dataloader` loop. the state of `end_of_dataloader` is set to True. but note that we are still...

A BUG? when performing gradient accumulation

Just wanted to propose my original solution again: Just keep a copy of the current gradient_state before entering a new dataset, and recover it when exit. So the users does...

Does it support Apple Silicon (M1/M2/M3)?

@zoopigzoo Thank you for bringing this to our attention. We confirm that the CPU version of Inferflow can run on Apple’s M-series chips; however, please note that it may not...

The program runs too long

Thank you for pointing out that!

training data

SANCL2012 2018-05-25 14:55 GMT+08:00 Bin Zhou : > hello, where is your training data from, conll-2012? > > — > You are receiving this because you are subscribed to this...

I run your code both on PTB and CTB dataset, but in CTB data LAS could not achieve the performence in paper

Sorry, but I don't have the results. Could you report your results here? Just the LAS of CTB is not good?

I run your code both on PTB and CTB dataset, but in CTB data LAS could not achieve the performence in paper

@baoy-nlp wow, thank you!