- 26 Sep, 2019 1 commit
-
-
thomwolf authored
-
- 15 Jul, 2019 2 commits
- 12 Jul, 2019 1 commit
-
-
thomwolf authored
-
- 05 Jul, 2019 1 commit
-
-
thomwolf authored
-
- 03 Jul, 2019 1 commit
-
-
thomwolf authored
-
- 24 Jun, 2019 1 commit
-
-
thomwolf authored
-
- 18 Jun, 2019 8 commits
- 22 May, 2019 1 commit
-
-
tguens authored
Indentation change so that the output "nbest_predictions.json" is not empty.
-
- 13 May, 2019 1 commit
-
-
samuelbroscheit authored
-
- 11 May, 2019 2 commits
-
-
samuel.broscheit authored
-
https://github.com/huggingface/pytorch-pretrained-BERT/issues/556samuel.broscheit authored
Reason for issue was that optimzation steps where computed from example size, which is different from actual size of dataloader when an example is chunked into multiple instances. Solution in this pull request is to compute num_optimization_steps directly from len(data_loader).
-
- 09 May, 2019 2 commits
-
-
burcturkoglu authored
-
burcturkoglu authored
-
- 02 May, 2019 1 commit
-
-
MottoX authored
-
- 23 Apr, 2019 1 commit
-
-
thomwolf authored
-
- 15 Apr, 2019 6 commits
- 03 Apr, 2019 1 commit
-
-
thomwolf authored
-
- 14 Mar, 2019 3 commits
-
-
Yongbo Wang authored
modify `heruistic` to `heuristic` in line 660, `charcter` to `character` in line 661.
-
Yongbo Wang authored
modify `mull` to `null` in line 474 annotation.
-
thomwolf authored
-
- 06 Mar, 2019 2 commits
- 15 Feb, 2019 1 commit
-
-
wlhgtc authored
-
- 11 Feb, 2019 3 commits
- 06 Feb, 2019 1 commit
-
-
Baoyang Song authored
-