Ethan Perez 28ba345ecc Fixing unused weight_decay argument ...

Currently the L2 regularization is hard-coded to "0.01", even though there is a --weight_decay flag implemented (that is unused). I'm making this flag control the weight decay used for fine-tuning in this script.

2019-08-04 12:31:46 -04:00

..

lm_finetuning

use new API for save and load

2019-07-18 15:45:23 +08:00

single_model_scripts

Fixing unused weight_decay argument

2019-08-04 12:31:46 -04:00

tests_samples

clean up examples - added squad example and test

2019-07-12 14:16:06 +02:00

requirements.txt

update readme and pretrained model weight files

2019-07-16 15:11:29 +02:00

run_bertology.py

updating examples and doc

2019-07-14 23:20:10 +02:00

run_generation.py

update QA models tests + run_generation

2019-07-15 17:45:24 +02:00

run_glue.py

multi-gpu training also should be after apex fp16

2019-07-25 13:09:10 +08:00

run_squad.py

Merge pull request #896 from zijunsun/master

2019-07-26 19:31:02 +02:00

test_examples.py

fix run_generation test

2019-07-15 17:52:35 +02:00

utils_glue.py

Byte order mark management in TSV glue reading.

2019-07-11 20:16:28 -04:00

utils_squad_evaluate.py

updating squad for compatibility with XLNet

2019-07-15 15:28:37 +02:00

utils_squad.py

update tokenizer - update squad example for xlnet

2019-07-15 17:30:42 +02:00