Daisy Deng
|
2f17d54014
|
modify notebook for faster quick run
|
2020-03-21 05:04:49 +00:00 |
|
Daisy Deng
|
d646485eaa
|
modify notebook for faster quick run
|
2020-03-21 05:04:10 +00:00 |
|
Daisy Deng
|
2e6a9379a7
|
remove raise error
|
2020-03-20 21:26:36 +00:00 |
|
Daisy Deng
|
557fd0eb33
|
clean up notebook
|
2020-03-20 21:16:33 +00:00 |
|
Daisy Deng
|
808e1a4f06
|
fix test and add example cells in the notebook
|
2020-03-20 21:12:22 +00:00 |
|
Daisy Deng
|
3dad522c5c
|
new
|
2020-03-20 20:00:07 +00:00 |
|
Daisy Deng
|
dafc09cc63
|
minor changes
|
2020-03-20 19:58:53 +00:00 |
|
Daisy Deng
|
18c9e661b2
|
change default value of batch size
|
2020-03-20 19:55:11 +00:00 |
|
Daisy Deng
|
013350581e
|
use raw dataset
|
2020-03-20 19:53:49 +00:00 |
|
Daisy Deng
|
a7795c17bb
|
update to make sure if works for raw dataset and preprocessed dataset
|
2020-03-20 19:51:02 +00:00 |
|
Daisy Deng
|
b27ae985d6
|
minor changes
|
2020-03-20 19:50:14 +00:00 |
|
Daisy Deng
|
219ab4b752
|
minor changes
|
2020-03-20 19:26:18 +00:00 |
|
Daisy Deng
|
b30a77c143
|
move iterabledistributedsampler and chunkdataloader out from extsum file
|
2020-03-20 19:21:01 +00:00 |
|
Daisy Deng
|
055645f590
|
fix move and parallelized model for DistributedDataParallel models
|
2020-03-20 19:18:29 +00:00 |
|
Daisy Deng
|
c44920b988
|
add distributed test for bertsum
|
2020-03-20 19:15:55 +00:00 |
|
Daisy Deng
|
946ae06fb6
|
fixed dataset for abstractive sum
|
2020-03-20 19:14:27 +00:00 |
Said Bleik
|
fedb34f2f0
|
Merge pull request #573 from microsoft/daden/bertsumext
Daden/bertsumext improvement of bertsum extractive summarization
|
2020-03-19 17:43:55 -04:00 |
|
Daisy Deng
|
03948df1b0
|
model stays the same if there is no valid new gpu_ids
|
2020-03-19 20:13:32 +00:00 |
|
Daisy Deng
|
784c5ccac0
|
fixed test; slightly modiflied parallelize_model to capture errors and mismatched inputs
|
2020-03-19 18:36:17 +00:00 |
|
Daisy Deng
|
746788095f
|
remove the backup notebook
|
2020-03-19 05:04:54 +00:00 |
|
Daisy Deng
|
bad0cdf3cf
|
merge froms staging
|
2020-03-19 05:03:33 +00:00 |
|
Daisy Deng
|
1592ced9cc
|
verified test
|
2020-03-19 05:00:31 +00:00 |
|
Daisy Deng
|
df8fd67219
|
delete old notebook
|
2020-03-19 03:31:24 +00:00 |
|
Daisy Deng
|
fda15d37ba
|
notebook works for preprocessed data
|
2020-03-18 14:57:24 +00:00 |
|
Daisy Deng
|
868266117b
|
add example cells in the notebook to predict on the input text; sort the selected sentences as they appear in the input text and use the sorted version as summary
|
2020-03-18 06:30:03 +00:00 |
|
Daisy Deng
|
4372ba7813
|
Merge pull request #571 from microsoft/daden/bertsumabs_test
Daden/bertsumabs test remove two debug cells from the notebooks
|
2020-03-18 00:23:17 -04:00 |
|
Daisy Deng
|
c4e2b7a712
|
change the commented sample code for loading checkpoint
|
2020-03-18 03:57:33 +00:00 |
|
Daisy Deng
|
5b57bf4928
|
add DistributedSampler import
|
2020-03-17 21:55:31 +00:00 |
|
Daisy Deng
|
24c69d50ae
|
move clear cuda cache into the finetune and predict function
|
2020-03-17 20:56:51 +00:00 |
|
Daisy Deng
|
87dbd64dbe
|
fix test
|
2020-03-17 19:42:00 +00:00 |
|
Daisy Deng
|
5ae6a5fae9
|
move max_pos_length into collate function
|
2020-03-16 03:50:39 +00:00 |
|
Said Bleik
|
af74216505
|
Merge pull request #568 from microsoft/cache-dir-patch
add cache dir
|
2020-03-13 12:55:27 -04:00 |
|
Daisy Deng
|
4b0a17bafb
|
remove cells that are not needed
|
2020-03-13 15:06:25 +00:00 |
|
Daisy Deng
|
80883d520f
|
draft collocate
|
2020-03-13 14:45:08 +00:00 |
|
Daisy Deng
|
043e1f7eef
|
Merge pull request #567 from microsoft/daden/bertsumabs
Daden/bertsumabs Add BertSumAbs Algorithm for Abstractive Summarization
|
2020-03-13 10:31:09 -04:00 |
|
Daisy Deng
|
98536e099f
|
formatting
|
2020-03-13 04:11:05 +00:00 |
|
Daisy Deng
|
63f0d56539
|
formatting
|
2020-03-13 04:04:50 +00:00 |
|
Daisy Deng
|
eafb73e1c4
|
adjust the preprocessing for max_pos_length
|
2020-03-13 03:25:40 +00:00 |
|
Daisy Deng
|
7e36572b01
|
add copyright and license info for bertsum; polish the notebook; resolve review comments
|
2020-03-13 02:36:03 +00:00 |
|
Daisy Deng
|
8de8c9f501
|
remove bertsum git dependency; enable max_pos_length customization for extractive summarization
|
2020-03-12 04:22:24 +00:00 |
|
Daisy Deng
|
d05f359c55
|
add more in docstring for test argument
|
2020-03-11 20:48:45 +00:00 |
|
Daisy Deng
|
feeab6e23d
|
resolve review comments
|
2020-03-11 20:36:08 +00:00 |
|
Said Bleik
|
b02daff5d6
|
Merge pull request #570 from microsoft/daden-ms-patch-1
Daden ms patch 1: pin papermill version to 1.2.1
|
2020-03-11 13:43:42 -04:00 |
|
Daisy Deng
|
cab0e3cf87
|
pin papermill version to make gpu integration test pass
|
2020-03-11 11:01:23 -04:00 |
Hong Lu
|
0501420ab9
|
Merge pull request #569 from microsoft/hlu/replace_s2sft_commit_hash_with_release_tag
Replace s2sft commit hash with release tag.
|
2020-03-11 00:12:22 -04:00 |
|
Daisy Deng
|
706d7d9f5a
|
add distributed training
|
2020-03-11 03:56:06 +00:00 |
|
hlums
|
99727ea65a
|
Replace s2sft commit hash with release tag.
|
2020-03-10 22:35:25 +00:00 |
|
Daisy Deng
|
391579e2aa
|
fix saving path in the notebook
|
2020-03-10 21:51:44 +00:00 |
|
Daisy Deng
|
0018067c9d
|
fix import error; add parameters tag to the cell
|
2020-03-10 21:39:43 +00:00 |
|
Said Bleik
|
0439f99066
|
add cache dir
|
2020-03-10 17:30:52 -04:00 |