GitLab

Summary:
For batched predictions in Roberta, the README was giving an example that was pretty unclear. After a thorough discussion with ngoyal2707 in issue https://github.com/pytorch/fairseq/issues/1167 he gave a clear example of how batched predictions were supposed to be done. Since I spent a lot of time on this inconsistency, I thought that it might benefit the community if his solution was in the official README 😄 !

For for details, see issue https://github.com/pytorch/fairseq/issues/1167
Pull Request resolved: https://github.com/pytorch/fairseq/pull/1195

Differential Revision: D17639354

Pulled By: myleott

fbshipit-source-id: 3eb60c5804a6481f533b19073da7880dfd0d522d

Summary:
Added the `predicted_token` to each `topk` filled output item

Updated RoBERTa filling mask example in README.md

Reviewed By: myleott

Differential Revision: D17188810

fbshipit-source-id: 5fdc57ff2c13239dabf13a8dad43ae9a55e8931c

Summary: Pull Request resolved: https://github.com/fairinternal/fairseq-py/pull/840

Differential Revision: D16947645

Pulled By: myleott

fbshipit-source-id: e869789bc22bbf5cb08d9adfa44f9fc09b3805af

Summary: Pull Request resolved: https://github.com/fairinternal/fairseq-py/pull/827

Differential Revision: D16833252

Pulled By: myleott

fbshipit-source-id: 8eded8cc651002dfd60869fc2383d305ed335d3a

Summary: Pull Request resolved: https://github.com/fairinternal/fairseq-py/pull/826

Differential Revision: D16830402

Pulled By: myleott

fbshipit-source-id: 25afaa6d9de7b51cc884e3f417c8e6b349f5a7bc

Summary:
1) So far getting `78%`  on winogrande validation dataset comapred to `63.5%` in the paper.
2) Will upgrade readme once everything is finalized.

Questions:

1) Should I just call `binary_wsc_task` instead of `winogrande` to be less specific to dataset and be generic?
Pull Request resolved: https://github.com/fairinternal/fairseq-py/pull/825

Differential Revision: D16810159

fbshipit-source-id: cfde73561fa4caaaa63a4773c0aecd12ce1fa518

Summary: Pull Request resolved: https://github.com/fairinternal/fairseq-py/pull/823

Differential Revision: D16804995

Pulled By: myleott

fbshipit-source-id: abac5dc0ed6b7bfe2309ba273456e54b37340b2c

Summary: Pull Request resolved: https://github.com/pytorch/fairseq/pull/1014

Differential Revision: D16784120

Pulled By: myleott

fbshipit-source-id: 946c0e33b594f8378e4ab6482ce49efcb36e1743

Summary: Pull Request resolved: https://github.com/pytorch/fairseq/pull/1004

Differential Revision: D16751443

Pulled By: myleott

fbshipit-source-id: f70acd6c7be6d69da45b5b32fe4c4eff021539ab

Summary: Pull Request resolved: https://github.com/fairinternal/fairseq-py/pull/815

Differential Revision: D16733633

fbshipit-source-id: 0a5029e41b6dbb9fb28e9703ad057d939d489d90

Summary:
1) This currently works only for single `<mask>` token as multi mask, we might have to look more into order of factorization.
2) This is currently only for single BPE token
Pull Request resolved: https://github.com/fairinternal/fairseq-py/pull/807

Differential Revision: D16674509

fbshipit-source-id: 0a020030ee5df6a5115e5f85d5a9ef52b1ad9e1c

Summary: Pull Request resolved: https://github.com/fairinternal/fairseq-py/pull/805

Differential Revision: D16670825

Pulled By: myleott

fbshipit-source-id: 872a1a0274681a34d54bda00bfcfcda2e94144c6

Summary: Pull Request resolved: https://github.com/fairinternal/fairseq-py/pull/795

Differential Revision: D16620488

Pulled By: myleott

fbshipit-source-id: 1998a9ccd8816fc7f590861fb4898f910a36bc1e

Summary:
Added readme for IMDB classification as tutorial for custm finetuning of roberta
Pull Request resolved: https://github.com/fairinternal/fairseq-py/pull/790

Reviewed By: myleott

Differential Revision: D16587877

Pulled By: myleott

fbshipit-source-id: ed265b7254e6fa2fc8a899ba04c0d2bb45a7f5c4

Summary:
Fixes https://github.com/pytorch/fairseq/issues/930.
Pull Request resolved: https://github.com/pytorch/fairseq/pull/931

Differential Revision: D16562511

Pulled By: myleott

fbshipit-source-id: c4c07e2f067326b79daa547dcb3db84aeddbd555

Summary:
1) Added glue data pre-processing script.
2) updated README with usage.

TODO:
1) releasing fairseq dictionary and remove hardcoded path.
2) remove hard-coded path for bpe-encoding,

myleott what do you recommend for above TODOs?
Pull Request resolved: https://github.com/fairinternal/fairseq-py/pull/771

Reviewed By: myleott

Differential Revision: D16547679

Pulled By: myleott

fbshipit-source-id: 6a6562d9b6215523d048fdf3daee63ffac21e231

Summary: Pull Request resolved: https://github.com/pytorch/fairseq/pull/921

Differential Revision: D16541025

Pulled By: myleott

fbshipit-source-id: bb78d30fe285da2adfc7c4e5897ee01fa413b2e4

Summary: Pull Request resolved: https://github.com/pytorch/fairseq/pull/916

Differential Revision: D16537774

Pulled By: myleott

fbshipit-source-id: 86bb7b1913a428ee4a21674cc3fc7b39264067ec

Summary: Pull Request resolved: https://github.com/pytorch/fairseq/pull/909

Differential Revision: D16532919

Pulled By: myleott

fbshipit-source-id: 16ce884cf3d84579026e4406a75ba3c01a128dbd

Summary: Pull Request resolved: https://github.com/fairinternal/fairseq-py/pull/778

Differential Revision: D16525447

Pulled By: myleott

fbshipit-source-id: e721e3a10e243a2408a04f89f06b5adbbe2fdff2