Giters

izuna385 / Zero-Shot-Entity-Linking

Zero-shot Entity Linking with blitz start in 3 minutes. Hard negative mining and encoder for all entities are also included in this implementation.

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

[Feature Request] Upgrade to the latest AllenNLP version and allow gradient accumulation

ruanchaves opened this issue · comments

commented

Gradient accumulation was implemented on AllenNLP at the GradientDescentTrainer class after v. 0.9.0 ( see this pull request and the current trainer code ).

As this repository uses AllenNLP v. 0.9.0, the code should be upgraded to be compatible with the latest version of AllenNLP, and num_gradient_accumulation_steps should be allowed as a parameter in src/parameters.py .

commented

Thanks for your issue. I'll upgrade and make it compatible soon!