Commits · ae1d03fc51bb22ed59517ee6f92c560417fdb049 · chenpangpang / transformers

"git@developer.sourcefind.cn:zhaoyu6/sglang.git" did not exist on "87068b5cc7e908385b2ea15c6d42f31d87e0e9f8"

10 Oct, 2019 1 commit
- convert int to str before adding to a str · f382a8de
  Luran He authored Oct 10, 2019
  
  f382a8de
09 Oct, 2019 6 commits
- Improve naming and only do regex when necessary · 69629c4f
  jinoobaek-qz authored Oct 07, 2019
  
  69629c4f
- Golden path · bf34a252
  jinoobaek-qz authored Oct 07, 2019
  
  bf34a252
- Improve readability and improve make less assumptions about checkpoint format · 528d3f32
  jinoobaek-qz authored Oct 07, 2019
  
  528d3f32
- Extract method · 56301bd9
  jinoobaek-qz authored Oct 05, 2019
  
  56301bd9
- Delete older checkpoint after saving new checkpoint · d6c54697
  jinoobaek-qz authored Oct 05, 2019
  
  d6c54697
- Add save_total_limit · 54a31f50
  jinoobaek-qz authored Oct 05, 2019
  
  54a31f50
08 Oct, 2019 1 commit
- Change tensorboard imports to use built-in tensorboard if available · 5ce8d29a
  Bilal Khan authored Oct 08, 2019
  
  5ce8d29a
04 Oct, 2019 1 commit
- update encode_plus - add truncation strategies · 6c1d0bc0
  thomwolf authored Oct 04, 2019
  
  6c1d0bc0
03 Oct, 2019 3 commits
- Update naming + remove f string in run_lm_finetuning example · aebd8323
  LysandreJik authored Oct 02, 2019
  
  aebd8323
- LM finetuning won't mask special tokens anymore · 5ed50a93
  LysandreJik authored Sep 30, 2019
  
  5ed50a93
- Evaluation result.txt path changing #1286 · 2195c0d5
  Brian Ma authored Oct 03, 2019
  
  2195c0d5
01 Oct, 2019 1 commit
- use format instead of f-strings · f7978f70
  thomwolf authored Oct 01, 2019
  
  f7978f70
27 Sep, 2019 1 commit
- Update run_lm_finetuning.py · 94785906
  Denny authored Sep 27, 2019
```
The previous method, just as phrased, did not exist in the class.
```
  94785906
26 Sep, 2019 2 commits
- faster dataset building · f71a4577
  mgrankin authored Sep 26, 2019
  
  f71a4577
- [BIG] pytorch-transformers => transformers · 31c23bd5
  thomwolf authored Sep 26, 2019
  
  31c23bd5
19 Sep, 2019 2 commits
- Sentence -> Sequence. Removed output_mask from the special token addition methods. · bf503158
  LysandreJik authored Sep 19, 2019
  
  bf503158
- Added DistilBERT to `run_lm_finetuning` · 88368c2a
  LysandreJik authored Sep 06, 2019
  
  88368c2a
18 Sep, 2019 1 commit
- Typo · f0340ecc
  Erik Chan authored Sep 18, 2019
```
Typo
```
  f0340ecc
09 Sep, 2019 1 commit
- changes in return statement of evaluate function · e5df3639
  Rohit Kumar Singh authored Sep 09, 2019
```
changed `results` to `result` and removed `results` dict defined previously
```
  e5df3639
06 Sep, 2019 1 commit
- Better examples · 593c0704
  LysandreJik authored Sep 06, 2019
  
  593c0704
23 Aug, 2019 2 commits
- typo · 06510ccb
  thomwolf authored Aug 23, 2019
  
  06510ccb
- fixing tokenization and training · ab7bd5ef
  thomwolf authored Aug 23, 2019
  
  ab7bd5ef
20 Aug, 2019 2 commits
- Sequence special token handling for BERT and RoBERTa · 2d042274
  Lysandre authored Aug 20, 2019
  
  2d042274
- various fix and clean up on run_lm_finetuning · a690edab
  thomwolf authored Aug 20, 2019
  
  a690edab
19 Aug, 2019 1 commit
- Distributed training + tokenizer agnostic mask token · f94f1c60
  Lysandre authored Aug 19, 2019
  
  f94f1c60
16 Aug, 2019 5 commits
- Simplified data generator + better perplexity calculator · 5652f54a
  Lysandre authored Aug 16, 2019
```
GPT-2 now obtains ~20 perplexity on WikiText-2
```
  5652f54a
- BERT + RoBERTa masking tokens handling + GPU device update. · 71553480
  LysandreJik authored Aug 14, 2019
  
  71553480
- CLM for BERT, beginning of CLM fot RoBERTa; still needs a better masking token mechanism. · 339e556f
  LysandreJik authored Aug 09, 2019
  
  339e556f
- Added GPT to the generative fine-tuning. · 3e3e1454
  LysandreJik authored Aug 06, 2019
  
  3e3e1454
- Language Modeling fine-tuning using GPT-2. · 47975ed5
  LysandreJik authored Aug 06, 2019
  
  47975ed5
14 Aug, 2019 1 commit
- loads the tokenizer for each checkpoint, to solve the reproducability issue · 3d47a7f8
  Rabeeh KARIMI authored Aug 14, 2019
  
  3d47a7f8
13 Aug, 2019 2 commits
- Added special tokens <pad> and <mask> to RoBERTa. · 39f426be
  LysandreJik authored Aug 13, 2019
  
  39f426be
- [RoBERTa] run_glue: correct pad_token + reorder labels · baf08ca1
  Julien Chaumond authored Aug 13, 2019
  
  baf08ca1
12 Aug, 2019 1 commit
- [RoBERTa] Update `run_glue` for RoBERTa · 912fdff8
  Julien Chaumond authored Aug 12, 2019
  
  912fdff8
05 Aug, 2019 1 commit
- add option mentioned in #940 · 70c10caa
  thomwolf authored Aug 05, 2019
  
  70c10caa
25 Jul, 2019 1 commit
- multi-gpu training also should be after apex fp16 · adb3ef63
  zijunsun authored Jul 25, 2019
  
  adb3ef63
23 Jul, 2019 2 commits
- fix #868 · 6070b554
  thomwolf authored Jul 23, 2019
  
  6070b554
- fix #858 · 2c9a3115
  thomwolf authored Jul 23, 2019
  
  2c9a3115
21 Jul, 2019 1 commit
- typos · 76be189b
  Peiqin Lin authored Jul 21, 2019
  
  76be189b