JWmer
|
36c801699f
|
Update k.cpp
|
2020-11-22 07:45:39 +09:00 |
|
JWmer
|
5b3e9b0eb3
|
Update p.cpp
|
2020-11-22 07:45:39 +09:00 |
|
JWmer
|
c04c5b6658
|
Update nnue_common.h
|
2020-11-22 07:45:39 +09:00 |
|
JWmer
|
b27c51b5cf
|
Delete k-p-cr-ep_256x2-32-32.h
|
2020-11-22 07:45:39 +09:00 |
|
JWmer
|
72fee2f7a4
|
Delete k-p-cr_256x2-32-32.h
|
2020-11-22 07:45:39 +09:00 |
|
JWmer
|
d9dcdc2b73
|
Delete k-p_256x2-32-32.h
|
2020-11-22 07:45:39 +09:00 |
|
Tomasz Sobczyk
|
5f18c88b3d
|
Docs for book in gensfen.
|
2020-11-17 09:43:23 +09:00 |
|
Tomasz Sobczyk
|
e1dbad47ce
|
Add support for opening book to gensfen.
|
2020-11-17 09:43:23 +09:00 |
|
Tomasz Sobczyk
|
d4350a16f3
|
Add representation of an opening book.
|
2020-11-17 09:43:23 +09:00 |
|
Tomasz Sobczyk
|
d793663188
|
Add docs for max_grad option for learn
|
2020-11-16 10:08:56 +09:00 |
|
Tomasz Sobczyk
|
3dbc45bdfc
|
Add gradient clipping.
|
2020-11-16 10:08:56 +09:00 |
|
Tomasz Sobczyk
|
50358e26c7
|
Fix searching terminal nodes in gensfen.
|
2020-11-15 22:18:13 +09:00 |
|
Tomasz Sobczyk
|
00bc80c3c4
|
Add assume_quiet option to the learner.
|
2020-11-15 22:18:13 +09:00 |
|
Tomasz Sobczyk
|
00797a3d86
|
add option ensure_quiet for gensfen that makes the generated position quiet
|
2020-11-15 22:18:13 +09:00 |
|
Tomasz Sobczyk
|
9b930023fb
|
Fix default value for batchsize in learn docs.
|
2020-11-15 00:51:04 +09:00 |
|
Tomasz Sobczyk
|
691da3bdad
|
Add more information for factorizers at the start of training.
|
2020-11-14 18:47:22 +09:00 |
|
Tomasz Sobczyk
|
4e1653d53a
|
Fix reliance on transitive includes for factorizers in trainer feature transformer. Add a file that includes all factorizers.
|
2020-11-14 12:35:12 +09:00 |
|
Tomasz Sobczyk
|
69bc3ef9be
|
Output loss more often.
|
2020-11-14 12:33:25 +09:00 |
|
Tomasz Sobczyk
|
a71623f74c
|
Add explicit read head seek to the start of the binpack file. Otherwise on MACOS the read head is placed at the end when app is specified.
|
2020-11-13 19:56:36 +09:00 |
|
Tomasz Sobczyk
|
2a8576b804
|
Fix compilation issues.
|
2020-11-10 10:21:09 +09:00 |
|
Tomasz Sobczyk
|
8069963c56
|
Update convert docs.
|
2020-11-10 10:21:09 +09:00 |
|
Tomasz Sobczyk
|
5d88e7bce8
|
Add optional move validation to training data conversion. No longer rely on static initialization order for magics initialization.
|
2020-11-10 10:21:09 +09:00 |
|
Tomasz Sobczyk
|
987b6c98d4
|
Move the observed feature collection to the threaded part now that it can be done safely.
|
2020-11-01 11:02:44 +09:00 |
|
Tomasz Sobczyk
|
c53be1b23f
|
Add specialized bitset for use in the trainer for observed features tracking.
|
2020-11-01 11:02:44 +09:00 |
|
Tomasz Sobczyk
|
e8907bcfc4
|
Replace omp in trainer_feature_transformer
|
2020-10-31 11:54:03 +09:00 |
|
Tomasz Sobczyk
|
db1b33d4ac
|
Optimize trainer clipped relu propagate
|
2020-10-31 11:52:51 +09:00 |
|
Tomasz Sobczyk
|
b5714c4084
|
Parallelize input slice trainer backprop.
|
2020-10-31 11:52:26 +09:00 |
|
Tomasz Sobczyk
|
941897ff2c
|
Optimize trainer clipped relu backpropagate.
|
2020-10-31 11:50:12 +09:00 |
|
Tomasz Sobczyk
|
c96743c5bd
|
Optimize feature transformer backpropagation stats.
|
2020-10-31 11:49:29 +09:00 |
|
Tomasz Sobczyk
|
2c10b1babc
|
Optimize feature transformer clipped relu.
|
2020-10-31 11:48:02 +09:00 |
|
Tomasz Sobczyk
|
7bedf6c5ab
|
Specify the whole evalsave message because otherwise the first evalsave/0 triggers it.
|
2020-10-31 08:36:58 +09:00 |
|
Tomasz Sobczyk
|
8c81bbd3db
|
Fix the counter in for_each_index_with_workers going out of scope before workers finish.
|
2020-10-31 08:36:58 +09:00 |
|
Tomasz Sobczyk
|
a56d8124d8
|
Replace non-blas parts of trainers with our own blas-like routines.
|
2020-10-31 08:36:58 +09:00 |
|
Tomasz Sobczyk
|
c56a4a36eb
|
Add our own blas-like routines that use stockfish's thread pool for parallelization.
|
2020-10-29 23:57:51 +09:00 |
|
Tomasz Sobczyk
|
ee0917a345
|
Pass ThreadPool to update_parameters, propagate, and backpropagate.
|
2020-10-29 09:21:19 +09:00 |
|
Tomasz Sobczyk
|
f1e96cab55
|
Align trainer arrays to cache line.
|
2020-10-29 09:12:50 +09:00 |
|
Tomasz Sobczyk
|
8fac468259
|
Add a cache line aligned allocator.
|
2020-10-29 09:12:50 +09:00 |
|
Tomasz Sobczyk
|
ec9e49e875
|
Add a HalfKA architecture (a product of K - king, and A - any piece) along with all required infrastructure. HalfKA doesn't discriminate kings compared to HalfKP. Keep old architecture as the default one.
|
2020-10-29 09:10:01 +09:00 |
|
Tomasz Sobczyk
|
317fda2516
|
Cleanup eval saving and lr scheduling.
|
2020-10-28 23:08:05 +09:00 |
|
Tomasz Sobczyk
|
680654b254
|
Add dots to output every epoch for progress visualization.
|
2020-10-28 09:36:43 +09:00 |
|
Tomasz Sobczyk
|
f81fa3d712
|
Replace global_learning_rate with learning_rate local to the learner and passed to update_parameters as a parameter.
|
2020-10-28 09:36:07 +09:00 |
|
Tomasz Sobczyk
|
cde6ec2bf2
|
Make all grad related functions in learn static. Pass calc_grad as a parameter.
|
2020-10-27 14:47:50 +09:00 |
|
Tomasz Sobczyk
|
e4868cb59e
|
Move setting learn search limits to learner.
|
2020-10-27 14:47:07 +09:00 |
|
Tomasz Sobczyk
|
c229929d26
|
Remove the position parameter from learn.
|
2020-10-27 00:35:43 +09:00 |
|
Tomasz Sobczyk
|
a8066cd4a9
|
Rename elmo lambdas
|
2020-10-27 00:33:58 +09:00 |
|
Tomasz Sobczyk
|
f7de49eb66
|
Create a collective parameter struct for learner.
|
2020-10-27 00:33:58 +09:00 |
|
Tomasz Sobczyk
|
ba390a7f9a
|
Print the used factorizer when intializing training.
|
2020-10-27 00:32:39 +09:00 |
|
Tomasz Sobczyk
|
e01397c674
|
Remove multi_think
|
2020-10-26 19:40:40 +09:00 |
|
Tomasz Sobczyk
|
e515f1f61f
|
Move SfenWriter to a separate file
|
2020-10-26 19:39:58 +09:00 |
|
Tomasz Sobczyk
|
65e443954a
|
Update expected gensfen finished responses.
|
2020-10-26 09:37:59 +09:00 |
|