Commit Graph
80 Commits
Author SHA1 Message Date
Joost VandeVondeleandnodchip b49fd3ab30 Add -lstdc++fs to the link line of gcc
older versions of gcc (<8.1) need this, even if they accept -std=c++17

with this patch, the code can be run on fishtest again,
at least by the majority of workers (fishtest doesn't require c++17 to be available)

See e.g.
https://tests.stockfishchess.org/tests/view/5fcfbf801ac1691201888235

Bench: 3820648
2020-12-09 08:40:34 +09:00
Tomasz Sobczykandnodchip 28d6d7cb03 Avoid computing gradient for validation loss. 2020-12-02 08:56:20 +09:00
Tomasz Sobczykandnodchip fafb9557a8 Get train loss from update_parameters. 2020-12-02 08:56:20 +09:00
Tomasz Sobczykandnodchip 4eb0e77a2a Store references instead of copying the results of intermediate autograd computations. 2020-12-02 08:56:20 +09:00
Tomasz Sobczykandnodchip 6cd0b03098 Add some comments regarding the current state of autograd loss computation. 2020-12-02 08:56:20 +09:00
Tomasz Sobczykandnodchip 99cb869db3 Reintroduce use_wdl. 2020-12-02 08:56:20 +09:00
Tomasz Sobczykandnodchip cf6bc7ecaf Cleanup around get_loss 2020-12-02 08:56:20 +09:00
Tomasz Sobczykandnodchip 256c4b55ec Properly apply gradient norm clipping after it's scaled in the update_parameters. 2020-12-02 08:56:20 +09:00
Tomasz Sobczykandnodchip de675e3503 Reintroduce optional scaling of the teacher signal. 2020-12-02 08:56:20 +09:00
Tomasz Sobczykandnodchip 01ae7b1e2c Simplify passing constants that may vary between calls. 2020-12-02 08:56:20 +09:00
Tomasz Sobczykandnodchip e975889132 Move cross_entropy calculation to a separate function. 2020-12-02 08:56:20 +09:00
Tomasz Sobczykandnodchip 891abf5511 Make the autograd loss expression chain thread_local. 2020-12-02 08:56:20 +09:00
Tomasz Sobczykandnodchip a5c20bee5b Apply gradient clipping. 2020-12-02 08:56:20 +09:00
Tomasz Sobczykandnodchip aa55692b97 Cross entropy loss. 2020-12-02 08:56:20 +09:00
Tomasz Sobczykandnodchip 539bd2d1c8 Replace the old loss/grad calculation completely. 2020-12-02 08:56:20 +09:00
Tomasz Sobczykandnodchip 5a58eb803a Loss func with autograd 2020-12-02 08:56:20 +09:00
Tomasz Sobczykandnodchip 9030020a85 Add smart_fen_skipping option to learn. 2020-11-23 19:22:11 +09:00
Tomasz Sobczykandnodchip 3cee6881ee Move the terminal position check to after qsearch, otherwise qsearch may end up in a terminal position. 2020-11-23 08:29:38 +09:00
Tomasz Sobczykandnodchip 3dbc45bdfc Add gradient clipping. 2020-11-16 10:08:56 +09:00
Tomasz Sobczykandnodchip 00bc80c3c4 Add assume_quiet option to the learner. 2020-11-15 22:18:13 +09:00
Tomasz Sobczykandnodchip 69bc3ef9be Output loss more often. 2020-11-14 12:33:25 +09:00
Tomasz Sobczykandnodchip ee0917a345 Pass ThreadPool to update_parameters, propagate, and backpropagate. 2020-10-29 09:21:19 +09:00
Tomasz Sobczykandnodchip 317fda2516 Cleanup eval saving and lr scheduling. 2020-10-28 23:08:05 +09:00
Tomasz Sobczykandnodchip 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 Sobczykandnodchip cde6ec2bf2 Make all grad related functions in learn static. Pass calc_grad as a parameter. 2020-10-27 14:47:50 +09:00
Tomasz Sobczykandnodchip e4868cb59e Move setting learn search limits to learner. 2020-10-27 14:47:07 +09:00
Tomasz Sobczykandnodchip c229929d26 Remove the position parameter from learn. 2020-10-27 00:35:43 +09:00
Tomasz Sobczykandnodchip a8066cd4a9 Rename elmo lambdas 2020-10-27 00:33:58 +09:00
Tomasz Sobczykandnodchip f7de49eb66 Create a collective parameter struct for learner. 2020-10-27 00:33:58 +09:00
Tomasz Sobczykandnodchip 2c477d76ec Cleaner and more outputs during training initialization. 2020-10-25 22:18:28 +09:00
Tomasz Sobczykandnodchip 4b72658409 Synchronize printed info regions in the learner and sfen reader. 2020-10-25 22:18:28 +09:00
Tomasz Sobczykandnodchip cf3edfed82 Improve info messages. 2020-10-25 22:18:28 +09:00
Tomasz Sobczykandnodchip c49ae541c4 Add layer info for check_health. Print subsequent infos from the same scope with "-->" instead of "INFO:" for clarity. 2020-10-25 22:18:28 +09:00
Tomasz Sobczykandnodchip 8ddef320e6 Print an additional new line before calc_loss progress instead of after check_health in the feature transformer layer. 2020-10-25 22:18:28 +09:00
Tomasz Sobczykandnodchip a351c1d65e Add verbose flag to learn. Only print update parameters info when vebose=true 2020-10-25 22:18:28 +09:00
Tomasz Sobczykandnodchip ec436d3dfd Print some weight update stats 2020-10-25 22:18:28 +09:00
Tomasz Sobczykandnodchip 371acaa0b5 Allow changing sfen reader buffer sizes for the learn command. 2020-10-25 19:22:56 +09:00
Tomasz Sobczykandnodchip 8fb208598b pass shuffle flag in the constructor 2020-10-25 19:22:56 +09:00
Tomasz Sobczykandnodchip 31f94a18b3 Update readme and docs after change from loop to epochs. 2020-10-25 19:22:56 +09:00
Tomasz Sobczykandnodchip fc3788f630 Use cyclic sfen reader for learning, change loop option to epochs. 2020-10-25 19:22:56 +09:00
Tomasz Sobczykandnodchip ad3d1b42e4 Make sfen reader only stop when it's destroyed. Now it is fully RAII. 2020-10-25 19:22:56 +09:00
Tomasz Sobczykandnodchip c58aa9696a Start sfen reader worker thread in the constructor. 2020-10-25 19:22:56 +09:00
Tomasz Sobczykandnodchip 0636e1256d Add cyclic mode to the sfen reader. Make sfen reader take all files at construction 2020-10-25 19:22:56 +09:00
Tomasz Sobczykandnodchip c7ac3688a7 Move the old convert stuff from learn to their own commands. 2020-10-24 08:52:42 +09:00
Tomasz Sobczykandnodchip 9564a52523 Remove whole file shuffling as it does not change learning behaviour, only works for bin, and is considered harmful for binpack. 2020-10-23 09:33:20 +09:00
Tomasz Sobczykandnodchip 7b4a769cca Fix base_dir not being applied to singular filenames. 2020-10-22 20:01:55 +09:00
Tomasz Sobczykandnodchip 11b28ad3b5 Don't treat unknown options in learn as file names. Add targetfile to specify individual files. 2020-10-22 20:01:55 +09:00
Tomasz Sobczykandnodchip 8f3e64a6d5 move sfen reader to separate file 2020-10-22 10:42:28 +09:00
Tomasz Sobczykandnodchip ff06d1e0ad Rewrite learner to be based on stockfish's thread pool. Reduce coupling along the way 2020-10-21 18:17:34 +09:00
Tomasz Sobczykandnodchip 146a6b056e PascalCase -> snake_case for consistency with the rest of the codebase. 2020-10-19 18:37:23 +09:00