joesharratt1229
bd2788ad2a
updated test score board
2025-04-01 16:46:09 +00:00
joesharratt1229
b6b33a1d04
updated with thinking token
2025-04-01 16:29:19 +00:00
joesharratt1229
8d0e7db204
added preappend token
2025-04-01 16:28:04 +00:00
joesharratt1229
4b9c155cef
Merge remote-tracking branch 'origin/main' into feat/curr-adj
2025-04-01 16:17:31 +00:00
joesharratt1229
ba999153bf
updated configs
2025-04-01 16:13:15 +00:00
joesharratt1229
ec388ffc7c
updated read me
2025-04-01 16:12:56 +00:00
joesharratt1229
a957bab805
added algorithmic qwen 3b yaml
2025-04-01 16:12:32 +00:00
joesharratt1229
9aa17f64fa
added fsdp to hf utility
2025-04-01 16:12:00 +00:00
joesharratt1229
37bbd97191
updated datasets
2025-04-01 16:11:31 +00:00
Zafir Stojanovski
50846c3534
fix(env): ARC 1D curriculum ( #402 )
...
* Add arc_1d curriculum
* Add difficulty to metadata
* use range attribute instead of scalar
---------
Co-authored-by: abdulhakeem <abdulhakeemadefioye@gmail.com>
Co-authored-by: Oliver Stanley <olivergestanley@gmail.com>
2025-04-01 13:01:15 +02:00
vncntt
cd85c2d632
add knights knaves curriculum ( #401 )
...
* add knights knaves curriculum
* add metadata + width constraints
2025-04-01 12:20:58 +02:00
Oliver Stanley
ea10a0f932
update task count in readme ( #400 )
...
* update task count in readme
* fix link
2025-04-01 10:51:36 +02:00
Zafir Stojanovski
8c45571a48
visualize heatmap sorted by overall performance ( #397 )
2025-04-01 00:08:39 +02:00
joesharratt1229
9f9f816902
added updates
2025-03-29 08:07:57 +00:00
Zafir Stojanovski
c6663cdb81
fix(training): Prepend <think> token in format reward ( #396 )
...
* prepend think token in format reward
* pre commit + fix some default vals
* add checkpoint config
2025-03-28 09:45:17 +01:00
joesharratt1229
774d23664d
added local evals
2025-03-28 05:00:30 +00:00
joesharratt1229
7368d6d313
updated configs
2025-03-28 00:05:58 +00:00
joesharratt1229
cc0bacd8e1
updated correctness score func
2025-03-26 19:54:37 +00:00
joesharratt1229
f50c7221ac
updated spell back
2025-03-26 19:53:27 +00:00
joesharratt1229
16919223be
Merge branch 'feat/curr-adj' of https://github.com/open-thought/reasoning-gym into feat/curr-adj
2025-03-26 19:52:56 +00:00
joesharratt1229
74eca6c45b
updated curr
2025-03-26 19:52:32 +00:00
joesharratt1229
c952f31a61
updated missing trainer func
2025-03-26 19:51:45 +00:00
joesharratt1229
765d0aa3fe
Add files via upload
2025-03-26 08:06:27 +00:00
joesharratt1229
d4ef7be4e9
Merge branch 'feat/curr-adj' of https://github.com/open-thought/reasoning-gym into feat/curr-adj
2025-03-25 16:49:25 +00:00
joesharratt1229
cd5bd7de5c
added
2025-03-25 08:29:21 +00:00
joesharratt1229
5e41e61058
added qwen2.5
2025-03-25 07:44:00 +00:00
joesharratt1229
d9075a2806
updated read me
2025-03-25 06:39:36 +00:00
joesharratt1229
73f7cc7a66
added spell backward
2025-03-25 06:17:54 +00:00
joesharratt1229
ed31964b06
updated yaml
2025-03-25 06:13:41 +00:00
joesharratt1229
fee4e37ae4
added composite changes
2025-03-25 05:38:07 +00:00
joesharratt1229
a8b1408967
added composite changes
2025-03-25 05:28:44 +00:00
joesharratt1229
4a37dbb5c1
changed config
2025-03-25 05:13:06 +00:00
joesharratt1229
b8a2ac6ba3
removed duplicated fit
2025-03-25 04:07:59 +00:00
joesharratt1229
06dab0e41d
added spell
2025-03-25 04:01:20 +00:00
joesharratt1229
47a2a7eab7
removed redundant argument
2025-03-25 03:54:32 +00:00
joesharratt1229
7f82aae67c
Merge remote-tracking branch 'origin/main' into feat/curr-adj
2025-03-25 03:50:41 +00:00
joesharratt1229
e368058ef1
Delete eval/eval/r1/algorithmic/word_sorting.json
2025-03-25 03:47:19 +00:00
joesharratt1229
9335b56252
corrected small errors
2025-03-25 03:45:18 +00:00
Tiago Serafim
7ae2942c34
Fix small bit of old code ( #386 )
...
Removed the `sat_utils.` that was left there from the original zebra package.
This allows the zebra generator to be used with the full set of available clues.
2025-03-24 09:00:28 +00:00
Zafir Stojanovski
2a970390e8
remove coach and update tests ( #393 )
2025-03-24 00:10:01 +01:00
joesharratt1229
84f3fa731e
readapted readme
2025-03-23 20:30:16 +00:00
joesharratt1229
6fa76f11b5
added curriculum
2025-03-23 20:25:42 +00:00
Oliver Stanley
eb69916c1b
initial verl training codebase ( #389 )
...
* fixes for latest verl
* composite dataset training experiment
* use stateful dataloaders to match verl changes
* training readme
* add formatting reward
* length reward impl
* standalone reasoning_gym config section
* curriculum learning, new length reward, more config
2025-03-20 15:04:57 +00:00
Zafir Stojanovski
ce0a6c4878
fix(envs): Add source dataset and index to metadata ( #388 )
...
* add source dataset and index to metadata
* fix typo
* fix coach class and its test
2025-03-20 11:12:14 +00:00
Oliver Stanley
7475a20700
include ranges rather than sampled values in difficulty metadata dicts ( #387 )
...
* update difficulty metadata for logic datasets
* update difficulty metadata for graph datasets
* update difficulty metadata for geometry datasets
* update difficulty metadata for games datasets
* update difficulty metadata for cognition datasets
* update difficulty metadata for arithmetic datasets
* update difficulty metadata for arc datasets
* update difficulty metadata for algorithmic datasets
* update difficulty metadata for algebra datasets
* use tuples
* update tests
* update tests
2025-03-20 10:27:03 +01:00
Rich Jones
b69c35818a
fix figlet font curr imports ( #383 )
2025-03-18 23:38:17 +01:00
Zafir Stojanovski
814da6e08a
add difficulty metadata
2025-03-18 13:51:43 +01:00
Zafir Stojanovski
29bf78293f
figlet font curriculum
2025-03-18 13:51:43 +01:00
joesharratt1229
9234aa77bf
Feat/open instruct example ( #381 )
...
* added open-instruct
* fixed hooks
* GRPO
---------
Co-authored-by: Andreas Koepf <andreas.koepf@provisio.com>
2025-03-17 23:20:11 +01:00
Andreas Koepf
1511c5e301
don't pass answer value to eval
2025-03-17 23:13:53 +01:00
