Results 18 issues of Timothee Mickus

- [ ] break down accuracy and validation loss per task when reporting stats - [ ] introduce validation-based LR scheduling ([reduce LR on plateau](https://pytorch.org/docs/stable/generated/torch.optim.lr_scheduler.ReduceLROnPlateau.html)) that's properly adjusted depending on...

enhancement

- [ ] Redesign parameter initialization so as to ensure a consistent and systematic design - [ ] Allow non-random initialization: - [ ] from huggingface - [ ] from...

enhancement

In the long run, rather than having our custom transforms for data cleaning (as suggested b y #13), it would be better to leave it to a relevant third party,...

enhancement

Setting a shard_size different from 0 currently causes the model to duplicate the test set. The simplest way to circumvent this at the moment is to set the flag -shard_size...

bug
enhancement

General PR for the HF/mammoth integration project, will also put some doc/pointers here

Description of the problem --------------------------------------- Attested on a live competition on the production LISP UP Saclay server. One of our participants is not able to submit through the platform: every...

Bug

Currently logs are overwhelming and not human-readable. Would be great to sift through the current messages and set appropriate logging levels (also remove sneaky prints that are surely still around).

bug
enhancement

Given the scope of experiments, it should be enough to have a global flag in the config, and then after the encoder is created here: https://github.com/Helsinki-NLP/mammoth/blob/1e6b03a6ce3853131d093d73bf91fdad1ed2a48d/mammoth/model_builder.py#L361 iterate over its parameters...