38 Commits

Author SHA1 Message Date
Daniel Povey
137ac513bf Some changes to try to reduce mem consumption; decrease batch size 2023-05-28 21:50:34 +08:00
Daniel Povey
815cc1ba4f Add another middle stack; batch size 18->16. 2023-05-28 20:23:30 +08:00
Daniel Povey
d045ef7ce7 Change default lr from 0.025 to 0.035 2023-05-28 15:42:54 +08:00
Daniel Povey
da80241179 Use larger valid set; get --print-diagnostics=True to work 2023-05-28 15:17:09 +08:00
Daniel Povey
105fb56db4 Make base-lr default 0.025 2023-05-24 16:30:23 +08:00
Daniel Povey
8483ca2e8f More partial work 2023-05-24 16:04:05 +08:00
Daniel Povey
8dc070ce37 Increase all ff dims; decrease batch size. 2023-05-20 13:35:23 +08:00
Daniel Povey
7d162bf41e mOve where srand called 2023-05-19 16:43:21 +08:00
Daniel Povey
f37ec0f0da Include start batch in seed 2023-05-19 16:39:13 +08:00
Daniel Povey
26cf13a3e1 Revert batch size to 20 2023-05-18 14:04:14 +08:00
Daniel Povey
5cd2df0cd6 Increase batch size from 20 to 22 2023-05-18 13:57:26 +08:00
Daniel Povey
15aca1fb4a Simplify dataloader code 2023-05-18 13:55:52 +08:00
Daniel Povey
eb64130787 Reverse zlm9..zlm12 2023-05-17 17:31:24 +08:00
Daniel Povey
5d7517e382 Set batch size back to 20 2023-05-17 14:56:38 +08:00
Daniel Povey
8fce9a05fc Revert batch size to 18 2023-05-17 14:53:53 +08:00
Daniel Povey
844844a02d Reduce batch size from 21 to 20 2023-05-17 14:28:56 +08:00
Daniel Povey
e25929c256 Reduce batch size to 21 2023-05-17 13:24:26 +08:00
Daniel Povey
e4246f6ba3 Reduce batch size from 24 to 22 2023-05-17 13:20:23 +08:00
Daniel Povey
6dce7e251d Increase batch size 2023-05-17 13:17:00 +08:00
Daniel Povey
30ace76fbc Add depthwise conv to decoder 2023-05-17 11:26:41 +08:00
Daniel Povey
a405106d2f Add 1-d convolution to text embedding module; reduce batch size 2023-05-16 20:05:52 +08:00
Daniel Povey
399a79ace6 Change chunk-size setup 2023-05-16 19:47:23 +08:00
Daniel Povey
a6eb45840a Reduce batch size 2023-05-16 17:39:59 +08:00
Daniel Povey
0412d19f50 Increase batch size 2023-05-16 16:33:17 +08:00
Daniel Povey
3f72813a96 Various bug fixes, implementing chunking 2023-05-16 16:27:09 +08:00
Daniel Povey
0006a4c4db Implement chunk sizes, to the extent that the program runs. 2023-05-16 16:13:20 +08:00
Daniel Povey
4562b25a6a Remove unused options 2023-05-16 14:25:19 +08:00
Daniel Povey
465d41c429 Increase batch size 2023-05-16 12:13:13 +08:00
Daniel Povey
0a76215fd7 Code cleanup 2023-05-15 22:01:19 +08:00
Daniel Povey
532f95a627 Reduce batch size slightly 2023-05-15 20:13:48 +08:00
Daniel Povey
a397a5973b Increase num parameters 2023-05-15 20:11:20 +08:00
Daniel Povey
047c6ffc58 First version of subformer that runs. 2023-05-15 16:03:01 +08:00
Daniel Povey
1b8be0744f Fix various bugs 2023-05-15 15:20:02 +08:00
Daniel Povey
2f1d377727 Reduce batch size so it fits in memory 2023-05-04 17:01:30 +08:00
Daniel Povey
f0264bed1b Fix DDP issue; Change configurations, reducing subsampling factor; increase sequence length. 2023-05-04 16:18:31 +08:00
Daniel Povey
45f5e9981d Bug fix 2023-05-04 15:41:29 +08:00
Daniel Povey
86c2c60100 Step lr_scheduler on tokens not epoch; add some more debug output 2023-05-04 15:35:22 +08:00
Daniel Povey
3574e7dbb5 Initial version of zipformer1 LM that runs, not sure whether it is working 2023-05-04 14:46:06 +08:00