 Piotr Czapla
|
260faa703c
|
Correct the label smoothing implementation
|
2019-02-22 16:55:35 +01:00 |
|
|
Piotr Czapla
|
015f04ec08
|
Training with noise & label smoothing
|
2019-02-22 12:02:18 +01:00 |
|
|
Tomasz Pietruszka
|
c6cf44a7b9
|
Fixed test_bilm_classifier_loads_encoder - inconsistent settings, problematic input (too short)
|
2019-01-23 00:05:45 +01:00 |
|
|
Tomasz Pietruszka
|
386fc49431
|
Adapted test_text_data to batch dimension being the first, and only xxbos token at the start
|
2019-01-22 20:31:30 +01:00 |
|
|
Tomasz Pietruszka
|
0e864fb291
|
test_end_to_end now working, added instructions to README, sentencepiece dependency
|
2019-01-22 20:10:38 +01:00 |
|
|
Piotr Czapla
|
514a9e6b86
|
Fix BiLM training after update to newest fastai
|
2018-12-31 12:13:53 +01:00 |
|
|
Piotr Czapla
|
f9394b9af1
|
Add callbacks to save history and best weights remove bs & drop_mult
|
2018-12-12 00:31:16 +01:00 |
|
|
Piotr Czapla
|
4454af167f
|
Use more text during pretraining of imdb
|
2018-12-05 16:26:16 +01:00 |
|
|
Piotr Czapla
|
039624870a
|
Fix loading tokenized data set in train cls
|
2018-12-04 01:28:03 +01:00 |
|
|
Piotr Czapla
|
a499bf9a20
|
Make cls train work with relative paths
|
2018-12-04 01:24:44 +01:00 |
|
|
Piotr Czapla
|
35a5dcb75a
|
Fix issue when running cls training from command line
|
2018-12-04 00:59:36 +01:00 |
|
|
Piotr Czapla
|
82c955ce6a
|
Add different tokenization algorithms to train_clas
|
2018-12-04 00:51:21 +01:00 |
|
|
Piotr Czapla
|
83427aadc6
|
Add moses with fastai preprocessing
|
2018-12-02 21:43:57 +01:00 |
|
|
Piotr Czapla
|
b9eb7388f6
|
Fix bidir for fastai tokenizer
|
2018-12-01 23:58:14 +01:00 |
|
|
Piotr Czapla
|
0c4aed6d05
|
Really fix conversion from str to Tokenzier
|
2018-12-01 16:51:21 +01:00 |
|
|
Piotr Czapla
|
887211137a
|
Add fastai tokenizer to pretrain_lm
|
2018-12-01 16:42:11 +01:00 |
|
|
Piotr Czapla
|
ab9faa2ad9
|
Clean up Fire interface.
|
2018-12-01 13:42:10 +01:00 |
|
|
Piotr Czapla
|
4b29376b44
|
Rewrite classifier to use changed pretrain_lm
|
2018-12-01 10:58:46 +01:00 |
|
|
Piotr Czapla
|
80d4d4da29
|
Extract params to an experiment data class
You can run this as follows:
`python -m ulmfit.pretrain_lm --dir-path 'data/wiki/wikitext-2' --qrnn=True train_lm --num_epochs=1`
|
2018-11-25 12:37:45 +01:00 |
|
|
Piotr Czapla
|
be117abac4
|
Make the end to end test run correctly
|
2018-11-24 23:51:23 +01:00 |
|
|
Piotr Czapla
|
8da47324c2
|
Clean ups and fixes
|
2018-11-22 15:32:40 +01:00 |
|
|
Piotr Czapla
|
cbed02d5e0
|
Merge branch 'master' into bilm
|
2018-11-21 18:23:54 +01:00 |
|
|
Aayush
|
69ed7b4169
|
Added preliminary test scripts for sentencepiece
Other minor changes:
- Function renaming: `test_pretrain_lm` -> `test_ulmfit_default_end_to_end`
- Delete test models after completing each test.
|
2018-11-19 19:11:20 +05:30 |
|
|
Piotr Czapla
|
c821d2e783
|
first version of bi classifier
|
2018-11-19 09:59:08 +01:00 |
|
|
Piotr Czapla
|
895a58c88d
|
Merge branch 'master' into bilm
|
2018-11-16 23:39:15 +01:00 |
|
|
Piotr Czapla
|
36b056a465
|
Fix issues discovered during execution of end-to-end test.
|
2018-11-16 23:31:16 +01:00 |
|
|
Piotr Czapla
|
ebbf09775f
|
Merge branch 'master' into bilm
|
2018-11-16 20:09:41 +01:00 |
|
|
Piotr Czapla
|
23b17da61e
|
Add end to end test and improve the train_clas params
|
2018-11-16 19:51:29 +01:00 |
|
|
Piotr Czapla
|
5ba83b1d4e
|
Working version of BILM - probably won't train well yet
|
2018-11-14 14:55:56 +01:00 |
|
|
Piotr Czapla
|
a85800610b
|
WIP Working Backward LM using our new LangaugeModelLoader
|
2018-11-14 13:22:03 +01:00 |
|
|
Piotr Czapla
|
6ee1a2b27d
|
Add BiLM LanguageModelLoader with tests
|
2018-11-14 12:48:29 +01:00 |
|
|
Piotr Czapla
|
40ca6c200e
|
Refactor and temporary fix the pretrain_lm by adding learn.lr_find
For some reason this fixes the training issue. I though I've nailed it down but i haven't. :/ .
|
2018-11-10 00:32:29 +01:00 |
|