tiedemann
tiedemann
### Bug description Training breaks with ``` [2021-05-12 10:19:19] [training] skipping 250846-th update due to loss being nan [2021-05-12 10:19:19] Error: CUDA error 700 'an illegal memory access was encountered'...
Create apps for mobiles. First, use on-line services - later integrate translation engine in the app? collaborate with bergamot project? (https://browser.mt/) (include also fine-tuning options and data donation)
Add knowledge distillation and teacher-student models - smaller student models + quantization - 3 layers encoder + 1-2 layers decoder?
fine-tune for a specific domain - sample from selected sub-corpus
- multilingual models - backtranslation - pivoting - data augmentation and new data sources?
improve models for translating from and to Sámi languages - multilingual models and transfer learning - integration of monolingual data / backtranslation - pivoting - data augmentation using rule-based MT...
integrate data filtering using OPUS-filter * parallel corpus filtering * monolingual corpus filtering (good for back-translation) * language (pair) specific configuration files
details about training, testing and evaluating models and doing all kinds of special tasks.
marian throws an error message when training with workspaces > 26000 (tested on a V100 with 32GB memory): ``` [2019-10-22 17:37:55] Compiled without MPI support. Falling back to FakeMPIWrapper [2019-10-22...