Stas Bekman
cd8c93f701
[DeepSpeed] improve checkpoint loading code plus tests ( #10760 )
...
* deepspeed checkpoint loading code plus tests
* style
* style
2021-03-17 10:22:58 -07:00
Cheng Li
c83fbc5f2d
[Deepspeed] Allow HF optimizer and scheduler to be passed to deepspeed ( #10464 )
...
* pass hf optimizer and scheduler to deepspeed if not specified in ds config
* pass hf optimizer and scheduler to deepspeed if not specified in ds config
* update
* make init_deepspeed support config dict
* fix docstring formatting
* clean up trainer's comments
* add new tests
* fix type
* composit argparse doesn't work
* style
* add a new test, rename others
* document new functionality
* complete tests, add docs
* style
* correct level
* Apply suggestions from code review
Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com>
* add new methods to the doc
* must tell DS we are using a non-native optimizer
* add protection against cpu_offload + HF optimizer combo
* fix the cli overrides
* sync docs + tests
* restore AdamW
* better docs
* need new version
* no longer needed
* remove outdate information
* refactor duplicated code
Co-authored-by: Stas Bekman <stas@stason.org>
Co-authored-by: Stas Bekman <stas00@users.noreply.github.com>
Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com>
2021-03-16 15:51:09 -07:00
Théo Matussière
6f840990a7
split seq2seq script into summarization & translation ( #10611 )
...
* split seq2seq script, update docs
* needless diff
* fix readme
* remove test diff
* s/summarization/translation
Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com>
* cr
* fix arguments & better mbart/t5 refs
* copyright
Co-authored-by: Suraj Patil <surajp815@gmail.com>
* reword readme
Co-authored-by: Suraj Patil <surajp815@gmail.com>
* s/summarization/translation
* short script names
* fix tests
* fix isort, include mbart doc
* delete old script, update tests
* automate source prefix
* automate source prefix for translation
* s/translation/trans
Co-authored-by: Stas Bekman <stas00@users.noreply.github.com>
* fix script name (short version)
* typos
Co-authored-by: Stas Bekman <stas00@users.noreply.github.com>
* exact parameter
Co-authored-by: Stas Bekman <stas00@users.noreply.github.com>
* remove superfluous source_prefix calls in docs
* rename scripts & warn for source prefix
* black
* flake8
Co-authored-by: theo <theo@matussie.re>
Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com>
Co-authored-by: Suraj Patil <surajp815@gmail.com>
Co-authored-by: Stas Bekman <stas00@users.noreply.github.com>
2021-03-15 09:11:42 -04:00
Stas Bekman
4c32f9f26e
AdamW is now supported by default ( #9624 )
2021-03-12 13:40:07 -08:00
Sylvain Gugger
0d909f6bd8
Fairscale FSDP fix model save ( #10596 )
...
* Hotfix fairscale FSDP
* Evaluation works
* Save on process zero
2021-03-09 14:42:07 -05:00
Stas Bekman
917f104502
[examples tests] various fixes ( #10584 )
...
* fix sharded ddp enum
* test fixes
* stronger validation + apex breaks other tests
2021-03-08 10:28:44 -08:00
Sylvain Gugger
9d14be5c20
Add support for ZeRO-2/3 and ZeRO-offload in fairscale ( #10354 )
...
* Ass support for ZeRO-2/3 and ZeRO-offload in fairscale
* Quality
* Rework from review comments
* Add doc
* Apply suggestions from code review
Co-authored-by: Stas Bekman <stas00@users.noreply.github.com>
* Address review comments
Co-authored-by: Stas Bekman <stas00@users.noreply.github.com>
2021-02-25 11:07:53 -05:00
Stas Bekman
3437d12134
[Trainer/Deepspeed] handle get_last_lr() before first step() ( #10362 )
...
* handle get_last_lr() before first step()
* abstract away the lr getting logic
* cleanup
* add test
* move to utils
2021-02-23 17:42:25 -08:00
Stas Bekman
eab0afc19c
[Trainer] implement gradient_accumulation_steps support in DeepSpeed integration ( #10310 )
...
* implement gradient_accumulation_steps support in DeepSpeed integration
* typo
* cleanup
* cleanup
2021-02-22 11:15:59 -08:00
Stas Bekman
97e688bc22
[Trainer] memory tracker metrics ( #10225 )
...
* memory tracker metrics
* go back to eval for somewhat consistency
* handle no-gpu case
* deal with stackable eval calls
* restore callback order
* style
* simplify the API
* add test
* docs
* consistently use eval_ prefix
* improve docs
* Update src/transformers/trainer_utils.py
Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com>
* rename method
* style
Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com>
2021-02-18 09:27:32 -08:00
Stas Bekman
d1eb88f42d
[CI] 2 fixes ( #10248 )
...
* fix invalid port
* missing requirements
2021-02-17 14:12:39 -08:00
Stas Bekman
0b1f552a24
fix run_seq2seq.py; porting trainer tests to it ( #10162 )
...
* fix run_seq2seq.py; porting DeepSpeed tests to it
* unrefactor
* defensive programming
* defensive programming 2
* port the rest of the trainer tests
* style
* a cleaner scripts dir finder
* cleanup
2021-02-15 09:12:17 -08:00
Stas Bekman
b54cb0bd82
[DeepSpeed in notebooks] Jupyter + Colab ( #10130 )
...
* init devices/setup explicitly
* docs + test
* simplify
* cleanup
* cleanup
* cleanup
* correct the required dist setup
* derive local_rank from env LOCAL_RANK
2021-02-11 14:02:05 -08:00
Stas Bekman
77b862847b
[DeepSpeed] restore memory for evaluation ( #10114 )
...
* free up memory at the end of train
* rework tests
* consistent formatting
* correction
2021-02-10 09:09:48 -08:00
Stas Bekman
781220acab
transition to new tests dir ( #10080 )
2021-02-08 12:41:52 -08:00
