Mirrors
/
EveryDream2trainer
mirror of https://github.com/victorchall/EveryDream2trainer.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
518 Commits 6 Branches 0 Tags 5.4 MiB
Commit Graph

11 Commits

Author SHA1 Message Date
Victor Hall f59b882376 Merge branch 'main' of https://github.com/victorchall/EveryDream2trainer 2023-05-26 21:54:12 -04:00
Victor Hall e6a176ea28 new bnb and beta zero terminal snr 2023-05-26 21:54:02 -04:00
Damian Stewart 1939cd52b7 apply clip_grad_scale to the unscaled gradients just before stepping the scaler 2023-05-22 23:58:22 -04:00
Damian Stewart a6610625eb Squashed commit of the following: 
commit 0f890f2d6bbccee225f738934f4c4450323f19a2
Merge: c008c40 003b089
Author: Damian Stewart <d@damianstewart.com>
Date:   Sun May 14 11:47:40 2023 +0200

    Merge remote-tracking branch 'upstream/main' into feat_te_last_n_layers_unsquashed

commit c008c404f19ebc6b78085f42a4e39aeb2ba00d04
Author: Damian Stewart <d@damianstewart.com>
Date:   Sun May 14 11:23:20 2023 +0200

    finalize TE layer freezing

commit 7377b10d59e32a6fea5d321a598ae4504e1a9f36
Author: Damian Stewart <d@damianstewart.com>
Date:   Thu May 11 20:45:28 2023 +0200

    remove zero_lr method

commit 4af13ba816c2811d7b5bd6fbb81a32bca6747e99
Author: Damian Stewart <d@damianstewart.com>
Date:   Thu May 11 20:05:01 2023 +0200

    Revert "rename parameters"

    This reverts commit aa33c61337599ab2d90b34aaf8c3d36fd4edf147.

commit aa33c61337599ab2d90b34aaf8c3d36fd4edf147
Author: Damian Stewart <d@damianstewart.com>
Date:   Tue May 9 00:28:00 2023 +0200

    rename parameters

commit 1da867e6fadb873da2571371a73b522406d76a18
Author: Damian Stewart <d@damianstewart.com>
Date:   Sun May 7 22:28:29 2023 +0200

    remove silly check

commit 483cb2a635c3fe5a044edf4ea8de095bedc3f0ac
Author: Damian Stewart <d@damianstewart.com>
Date:   Sun May 7 20:53:43 2023 +0200

    use 1e-10 not 0 as 'zero' lr

commit e5d230e6c765a7e25dc6381d09bd0a66a9a54ec2
Author: Damian Stewart <d@damianstewart.com>
Date:   Sun May 7 20:51:51 2023 +0200

    add experimental 'zero_lr' freeze method

commit bcf24ee59a443c0ee71d622e65e1043b547f845e
Author: Damian Stewart <d@damianstewart.com>
Date:   Sun May 7 17:32:11 2023 +0200

    fix layer selection bug

commit 7ee33eff8740e095f85042dcbb792e025b179c6c
Author: Damian Stewart <d@damianstewart.com>
Date:   Sun May 7 17:25:25 2023 +0200

    put back the 'drop' method and make accessible

commit 76dfbf6dd6f43f3aa9a7f4629baa8e86573d9520
Author: Damian Stewart <d@damianstewart.com>
Date:   Sun May 7 16:39:05 2023 +0200

    wip getting final_layer_norm to work

commit a19d43651a87525251106ed57238cd2cd1c3f3ff
Author: Damian Stewart <d@damianstewart.com>
Date:   Sun May 7 16:15:53 2023 +0200

    work around a crash when freeze_final_layer_norm is True

commit c2a44eb25132941b92e2ecd0be3682ae3c6838c2
Author: Damian Stewart <d@damianstewart.com>
Date:   Sun May 7 15:47:10 2023 +0200

    improve logging, add extra freezing controls

commit a31e64c4c0d12dfb6583dd6f22c8c09ba7840410
Author: Damian Stewart <d@damianstewart.com>
Date:   Sun May 7 13:46:38 2023 +0200

    alternative method to freeze early TE layers

commit 095692fd4ea53707c012217898321860d8b9329f
Merge: 876072c 4c5ce81
Author: Damian Stewart <d@damianstewart.com>
Date:   Sun May 7 11:52:51 2023 +0200

    Merge branch 'victorchall:main' into feat_te_last_n_layers

commit 876072c46394fde721a6026f7a6ef72ccb150ddb
Author: Damian Stewart <d@damianstewart.com>
Date:   Sun May 7 01:41:50 2023 +0200

    implement last N layers training only for TE
 2023-05-16 13:57:05 -04:00
Damian Stewart e14973a9da fix restoring optimizer state typo 2023-05-14 12:27:24 -04:00
Victor Hall 003b08992b remove old print 2023-05-11 19:17:19 -04:00
Victor Hall cb511025ed finalizing optimizer split 2023-05-04 20:15:36 -04:00
Victor Hall 4e81a0eb55 optimizer split works 2023-05-04 20:15:36 -04:00
Victor Hall 970065c206 more wip optimizer splitting 2023-05-04 20:15:36 -04:00
Victor Hall 72a47741f0 optimizer spltting 2023-05-04 20:15:36 -04:00
Victor Hall 3639e36135 refactor optimizer to split te and unet 2023-05-04 20:15:36 -04:00