Skip to content
GitLab
Menu
Projects
Groups
Snippets
Loading...
Help
Help
Support
Community forum
Keyboard shortcuts
?
Submit feedback
Contribute to GitLab
Sign in / Register
Toggle navigation
Menu
Open sidebar
OpenDAS
Megatron-LM
Commits
064a68815c32e473a2071706637bf9dca5f9cab9
Switch branch/tag
megatron-lm
megatron
14 Apr, 2020
5 commits
Re-adjust dataloader properties
· 064a6881
Neel Kant
authored
Apr 13, 2020
064a6881
Modify InverseClozeDataset and its usage to use blocks
· 46b2addd
Neel Kant
authored
Apr 13, 2020
46b2addd
Debug helpers compilation
· 64aef3a5
Neel Kant
authored
Apr 13, 2020
64aef3a5
Modify preprocess_data.py to accommodate titles dataset
· 27ecc17a
Neel Kant
authored
Apr 13, 2020
27ecc17a
Add build_blocks_mapping code to helpers.cpp
· 7bd2a3c5
Neel Kant
authored
Apr 13, 2020
7bd2a3c5
07 Apr, 2020
2 commits
Fix issue with validation dataloader
· 064bdc46
Neel Kant
authored
Apr 07, 2020
064bdc46
Complete implementation of InverseClozeDataset with IndexedDataset
· 72fb0d5c
Neel Kant
authored
Apr 06, 2020
72fb0d5c
06 Apr, 2020
1 commit
Fix ICTBertModel args
· 2f6d2a3a
Neel Kant
authored
Apr 05, 2020
2f6d2a3a
05 Apr, 2020
1 commit
Hacks to build IndexedDataset and run pretrain
· b03af49e
Neel Kant
authored
Apr 05, 2020
b03af49e
03 Apr, 2020
6 commits
Implement InverseClozeDataset with IndexedDataset
· 4558e42f
Neel Kant
authored
Apr 03, 2020
4558e42f
Remove commented out test code
· 9238c57a
Neel Kant
authored
Apr 03, 2020
9238c57a
Fix InverseClozeDataset behavior (with commented out test code)
· ca6b6687
Neel Kant
authored
Apr 03, 2020
ca6b6687
sample generation runs
· fffa0497
Mohammad
authored
Apr 02, 2020
fffa0497
code runs
· 752eeae3
Mohammad
authored
Apr 02, 2020
752eeae3
working on refactoring text generation
· ce29d4d5
Mohammad
authored
Apr 02, 2020
ce29d4d5
02 Apr, 2020
2 commits
some changes to args
· 2bd6196c
Mohammad
authored
Apr 02, 2020
2bd6196c
refactored evaluate_gpt2
· 8fae1cdd
Mohammad
authored
Apr 01, 2020
8fae1cdd
01 Apr, 2020
2 commits
addressed comments from raul, neel, and jared
· bf3ce751
Mohammad
authored
Apr 01, 2020
bf3ce751
Bugfix and remove unneeded script
· 423c51b0
Neel Kant
authored
Mar 31, 2020
423c51b0
31 Mar, 2020
5 commits
Make InverseClozeDataset more efficient
· e949a5c5
Neel Kant
authored
Mar 31, 2020
e949a5c5
Add while condition to InverseClozeDataset to protect against corner cases
· 6e856fac
Neel Kant
authored
Mar 31, 2020
6e856fac
Remove debug statements and correct dataloader
· 6f56b909
Neel Kant
authored
Mar 31, 2020
6f56b909
deprecated data_utils
· 8600642e
Mohammad
authored
Mar 31, 2020
8600642e
arguments in the model refactored
· deffcb6a
Mohammad
authored
Mar 31, 2020
deffcb6a
30 Mar, 2020
8 commits
removed unused values in samplers
· 259062c2
Mohammad
authored
Mar 30, 2020
259062c2
added samplers from data_utils
· 32e1ddb0
Mohammad
authored
Mar 30, 2020
32e1ddb0
Add debug statements
· f1b2524b
Neel Kant
authored
Mar 30, 2020
f1b2524b
removed building tokenizer from bert dataset
· dedb2ef7
Mohammad
authored
Mar 30, 2020
dedb2ef7
both bert and gpt2 tested and working
· 1788c910
Mohammad
authored
Mar 29, 2020
1788c910
both bert and gpt are working
· 5f8623db
Mohammad
authored
Mar 29, 2020
5f8623db
added gpt2 tokenizer
· 46379244
Mohammad
authored
Mar 29, 2020
46379244
added gpt2 tokenizer
· 0e5dfd7f
Mohammad
authored
Mar 29, 2020
0e5dfd7f
29 Mar, 2020
4 commits
refactored learning-rate
· b6e0377b
Mohammad
authored
Mar 29, 2020
b6e0377b
refactored training
· 27e14f82
Mohammad
authored
Mar 28, 2020
27e14f82
utils partially refactored and tested
· 3f58649b
Mohammad
authored
Mar 28, 2020
3f58649b
refactored checkpooints but not tested yet
· 86e7d624
Mohammad
authored
Mar 28, 2020
86e7d624
28 Mar, 2020
4 commits
tokenizer moved to its own directory
· 11220df8
Mohammad
authored
Mar 28, 2020
11220df8
working on utils
· 5050203f
Mohammad
authored
Mar 28, 2020
5050203f
arguments.py refactored
· 94e2ca57
Mohammad
authored
Mar 27, 2020
94e2ca57
added initialize megatron
· a9e19f8e
Mohammad
authored
Mar 27, 2020
a9e19f8e
