Skip to content

GitLab

"...resnet50_tensorflow.git" did not exist on "ada2ed77bdef7d7d9ada617e094e62fc05f0d7db"
Switch branch/tag
  1. 07 Nov, 2019 2 commits
  3. 06 Nov, 2019 1 commit
  5. 05 Nov, 2019 1 commit
    • ngoyal2707's avatar
      XLM-R code and model release (#900) · e23e5eaa
      ngoyal2707 authored 
      Summary:
TODO:
1) Need to update bibtex entry
2) Need to upload models, spm_vocab and dict.txt to public s3 location.

For Future:

1) I will probably add instructions to finetune on XNLI and NER, POS etc. but currently no timeline for that.
Pull Request resolved: https://github.com/fairinternal/fairseq-py/pull/900

Reviewed By: myleott

Differential Revision: D18333076

Pulled By: myleott

fbshipit-source-id: 3f3d3716fcc41c78d2dd4525f60b519abbd0459c
      e23e5eaa
  7. 02 Nov, 2019 1 commit
  9. 27 Oct, 2019 1 commit
    • Angela Fan's avatar
      adding layerdrop code for training, pruning, and readme (#890) · dabbef46
      Angela Fan authored 
      Summary:
TEST 1: EVALUATION TIME WORKS
checked
achieves correct model perplexity: 18.68

TEST 2: TRAINING NEW MODEL WORKS
checked

without layerdrop:
--decoder-layerdrop 0 OR no flag at all
| epoch 001:     10 / 11201 loss=27.469, nll_loss=27.469, ppl=185799477.36, wps=1764, ups=0, wpb=9216.000, bsz=3.000, num_updates=7, lr=0.0004376, gnorm=25.471, clip=1.000, oom=0.000, loss_scale=8.000, wall=37, train_wall=30
| epoch 001:     20 / 11201 loss=27.443, nll_loss=27.443, ppl=182500427.22, wps=2449, ups=0, wpb=9216.000, bsz=3.000, num_updates=17, lr=0.0010626, gnorm=25.273, clip=1.000, oom=0.000, loss_scale=8.000, wall=64, train_wall=57
| epoch 001:     30 / 11201 loss=27.404, nll_loss=27.404, ppl=177612215.78, wps=2720, ups=0, wpb=9216.000, bsz=3.000, num_updates=27, lr=0.0016876, gnorm=25.136, clip=1.000, oom=0.000, loss_scale=8.000, wall=91, train_wall=84
| epoch 001:     40 / 11201 loss=27.009, nll_loss=27.009, ppl=135079983.00, wps=2865, ups=...
      dabbef46
  11. 20 Oct, 2019 1 commit
  13. 18 Oct, 2019 1 commit
  15. 10 Oct, 2019 2 commits
    • Dmytro Okhonko's avatar
      Add ctc loss to ASR task (#1233) · c4893ca6
      Dmytro Okhonko authored 
      Summary:
Adds CTC loss and corresponding transformer ctc based models.

Tested with
`CUDA_VISIBLE_DEVICES=0 python train.py $DATA_PATH --save-dir $SAVE_DIR --max-epoch 30 --task speech_recognition --arch vggtransformer_enc_1 --optimizer adadelta --lr 1.0 --adadelta-eps 1e-8 --adadelta-rho 0.95 --clip-norm 10.0  --max-tokens 10000 --log-format json --log-interval 1 --criterion ctc_loss --user-dir examples/speech_recognition/ --validate-interval=10`
Pull Request resolved: https://github.com/pytorch/fairseq/pull/1233

Reviewed By: jcai1

Differential Revision: D17856824

Pulled By: okhonko

fbshipit-source-id: f3eac64d3fdd0c37cf8c539dd360cfb610d8a6ef
      c4893ca6
    • Jeff Cai's avatar
      wav2letter integration · 33646ac9
      Jeff Cai authored 
      Summary: Pull Request resolved: https://github.com/fairinternal/fairseq-py/pull/846

Reviewed By: jcai1

Differential Revision: D17845996

Pulled By: okhonko

fbshipit-source-id: 3826fd9a4418496916bf1835c319dd85c89945cc
      33646ac9
  17. 05 Oct, 2019 1 commit
  19. 30 Sep, 2019 1 commit
  21. 29 Sep, 2019 1 commit
  23. 28 Sep, 2019 1 commit
  25. 27 Sep, 2019 3 commits
  27. 24 Sep, 2019 1 commit
  29. 20 Sep, 2019 1 commit
  31. 17 Sep, 2019 2 commits
  33. 05 Sep, 2019 1 commit
    • Roman Rädle's avatar
      Return predicted token for RoBERTa filling mask · 3e3fe722
      Roman Rädle authored 
      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
      3e3fe722
  35. 03 Sep, 2019 1 commit
    • altale's avatar
      Fix an error in the command about Hierarchical Neural Story Generation (#1099) · 6c00b338
      altale authored 
      Summary:
When I try to reproduce the experiment in  _Hierarchical Neural Story Generation_, I found the command about generation cannot be executed.

It said that **fairseq-generate: error: unrecognized arguments: --sampling-temperature 0.8**
In the document, I find:
```
--temperature   temperature for generation
Default: 1.0
```
And I don't find a parameter named `--sampling-temperature`, so I think the parameter `--sampling-temperature` should be changed to `--temperature`
Pull Request resolved: https://github.com/pytorch/fairseq/pull/1099

Differential Revision: D17163065

Pulled By: myleott

fbshipit-source-id: 25c430eeee4703f8ec30353825ffec4bb973da0d
      6c00b338
  37. 27 Aug, 2019 1 commit
  39. 22 Aug, 2019 3 commits
  41. 20 Aug, 2019 1 commit
  43. 19 Aug, 2019 2 commits
  45. 15 Aug, 2019 4 commits
  47. 14 Aug, 2019 2 commits
  49. 13 Aug, 2019 2 commits
  51. 12 Aug, 2019 1 commit
  53. 10 Aug, 2019 1 commit