Zafir Stojanovski
c2ac6fae32
Update README.md ( #475 )
2025-06-24 14:19:11 +01:00
Zafir Stojanovski
56ce2e79a7
tutorial(training): Add a minimal example with trl ( #473 )
...
* v0
* 2 gpu setup
* improve parsing from yaml
* update yaml dataset example
* remove restriction on flash attn
* more comments
* first version of the readme
* pin torch
* simplify requirements
* just flash attn
* use set env instead
* simpler set env
* readme
* add wandb project to setup
* update template
* update model id
* post init to capture the config and weight
* extract metadata
* update config
* update dataset config
* move env for wandb project
* pre-commit
* remove qwen-math from training
* more instructions
* unused import
* remove trl old
* warmup ratio
* warmup ratio
* change model id
* change model_id
* add info about CUDA_VISIBLE_DEVICES
2025-06-21 00:01:31 +02:00
Oliver Stanley
49f3821098
add minimal verifiers example ( #472 )
2025-06-20 16:31:02 +01:00
Adefioye
9e79fc84b6
fix: Rounding issues in score_answer and add unit tests ( #462 )
2025-06-09 19:18:11 +01:00
joesharratt1229
51c2afc1fc
Fix/verl example ( #465 )
...
* updated verl ex
* updated script
* removed curriculum verl and updated
* updatied linting errors
* renamed
* updated config
2025-06-09 09:53:43 +01:00
Oliver Stanley
5726034a26
fix color_cubes answer strings, update gallery with latest envs ( #464 )
...
* update gallery with latest envs
* fix regression where answer str is wrong in color_cubes
* re-update gallery
2025-06-08 13:16:54 +02:00
Oliver Stanley
602e4be0a2
add survo env ( #461 )
...
* add survo env
* add survo curriculum
* add survo tests
2025-06-08 11:56:33 +01:00
Zafir Stojanovski
0159b1b571
Update README.md - Star History ( #463 )
2025-06-08 11:51:43 +01:00
Oliver Stanley
c2fdb11980
add kakurasu env ( #460 )
...
* add kakurasu env
* add kakurasu curriculum
* add kakurasu tests
2025-06-08 09:20:53 +01:00
Andreas Köpf
be2babea9c
Use raw URLs for images in README.md ( #459 )
...
On pypi images were not correctly rendered because the old img src urls in README.md
pointed to files on github with UI.
2025-06-06 21:23:59 +01:00
Oliver Stanley
1232a7d1e5
simplify training setup instructions ( #454 )
...
* simplify training setup instructions
* tweaks
* update cfgs
* readme update
* readme update
2025-06-06 09:51:29 +01:00
Zafir Stojanovski
0ebabf709b
Update README.md with Atropos ( #458 )
2025-06-06 09:24:25 +01:00
Zafir Stojanovski
0699e2f507
Update README.md ( #451 )
2025-06-04 12:45:23 +02:00
Oliver Stanley
1a727ecf4e
support python 3.10 ( #450 )
...
* support python 3.10
* add 3.10 to tests
* new StrEnum
2025-06-04 10:34:01 +01:00
Zafir Stojanovski
84958baa69
abs path for images ( #449 )
...
* abs path for images
* width and height outside of style
2025-06-04 10:33:13 +02:00
Oliver Stanley
2a57a95ca2
add minimal example for building training datasets ( #448 )
2025-06-03 19:28:45 +01:00
Zafir Stojanovski
b3f81a6609
fix(README): Arxiv link ( #447 )
2025-06-02 12:20:38 +02:00
Zafir Stojanovski
17a8431013
rename to easy and hard ( #445 )
2025-06-02 10:34:05 +02:00
Zafir Stojanovski
af2548f8f2
Add README assets ( #446 )
...
* add assets
* pre-commit
* remove bg
2025-06-02 10:33:54 +02:00
Adefioye
9053009dbe
Fix bug in normalize_answer method ( #444 )
2025-06-02 08:58:54 +02:00
Oliver Stanley
c0e98f93b4
make task entries json serializable ( #443 )
...
* make sympy-based task entries json serializable
* remove datetime objs from time_intervals metadata
* make adv geometry json serializable
* make futoshiki metadata json serializable
* fixes
* futoshiki tweaks
* fix adv geometry
* deal with fractions in str representations
* fix
* restore start_time, end_time as str
2025-06-02 08:57:15 +02:00
Zafir Stojanovski
6614338ecc
add numbers to performance heatmap ( #442 )
2025-05-30 18:39:13 +02:00
Zafir Stojanovski
b843f33b1d
fix(eval): comparison plot ( #441 )
...
* heatmap
* filter comparison plots
* latex style
* curriculum heatmap
* pre-commit
* update figsize
* large y-ticks
* larger font
* thinner
* include 50
2025-05-29 12:31:07 +02:00
Oliver Stanley
f51769927e
add .gitattributes for correct repo classification ( #439 )
2025-05-19 21:41:07 +03:00
Zafir Stojanovski
93e731c29c
heatmap ( #438 )
2025-05-19 09:07:45 +01:00
Oliver Stanley
add527ada1
update training dir with external eval details ( #437 )
...
* added games
* added llama 3b training conf
* update readme with details of external evals
* readme update
---------
Co-authored-by: joesharratt1229 <joesharratt1229@gmail.com>
2025-05-19 00:35:41 +02:00
Zafir Stojanovski
5961a10145
comparison plot ( #436 )
2025-05-18 22:57:49 +01:00
Zafir Stojanovski
0cda6b1205
qwen math training code ( #435 )
...
* qwen math training code
* pre-commit
2025-05-16 13:19:19 +02:00
Oliver Stanley
47303211b3
update gallery ( #434 )
2025-05-15 22:41:43 +02:00
Zafir Stojanovski
6d9e14729a
fix rubiks cube prompt ( #433 )
2025-05-15 21:31:21 +01:00
Oliver Stanley
85f3c6dd02
updated inter-domain generalisation eval configs ( #432 )
...
* tweak eval configs
* add eval configs
* add eval config
2025-05-15 09:08:16 +02:00
Zafir Stojanovski
4cab1c3e6d
comparison plots ( #431 )
2025-05-12 15:41:58 +02:00
Oliver Stanley
3df26e0fb2
fix decimal arithmetic curriculum to respect constraints ( #430 )
...
* fix decimal arithmetic curriculum to respect constraints
* update test accordingly
2025-05-06 19:23:19 +01:00
rasdani
dca8117e7e
Feat: Add script to save datasets on HuggingFace ( #416 )
...
* feat: add script to save datasets on HuggingFace
* fix
* refactor
* fix formatting
---------
Co-authored-by: Oliver Stanley <olivergestanley@gmail.com>
2025-04-28 18:04:53 +01:00
joesharratt1229
73e3cb33a4
Added games training and evaluation configuration ( #426 )
...
* added games
* Update eval_games_composite.yaml
* Delete training/evaluations/eval_qwen_3b.yaml
* Add files via upload
* Delete training/evaluations/eval_algebraic_composite.yaml
* Delete training/evaluations/eval_algorithmic_composite.yaml
* Delete training/evaluations/eval_arithmetic_composite.yaml
* Delete training/evaluations/eval_cognition_composite.yaml
* Delete training/evaluations/eval_games_composite.yaml
2025-04-26 19:45:32 +01:00
Oliver Stanley
10863ea12b
inter-domain generalisation evaluation configs ( #424 )
...
* add inter-domain generalisation eval config for algebra
* add algorithmic eval cfg
* vllm infer
* add arithmetic eval cfg
* add geometry eval cfg
* add arc cfg
* add games eval cfg
* add cognition eval cfg
* add graphs eval cfg
2025-04-22 17:32:35 +01:00
Zafir Stojanovski
98e976642d
gemini flash and o3 mini configs ( #425 )
2025-04-20 21:24:52 +02:00
rasdani
72e45e9401
Feat: expose score_answer function without needing to instantiate a dataset ( #422 )
...
* feat: get `score_answer` for a given dataset
* fix: `self` error
* add test
2025-04-18 10:36:44 +02:00
Adefioye
169d8c3aec
Evals: Sonnet-3.7-eval partial results ( #423 )
...
* Add results for sonnet and config
* Make some cleanup
2025-04-18 10:31:40 +02:00
joesharratt1229
d0ef136d5b
Feat/intragen experiments ( #414 )
...
* added curriculum
* readapted readme
* corrected small errors
* Delete eval/eval/r1/algorithmic/word_sorting.json
* removed redundant argument
* added spell
* removed duplicated fit
* changed config
* added composite changes
* added composite changes
* updated yaml
* added spell backward
* updated read me
* added qwen2.5
* added
* Add files via upload
* updated missing trainer func
* updated curr
* updated spell back
* updated correctness score func
* updated configs
* added local evals
* added updates
* updated datasets
* added fsdp to hf utility
* added algorithmic qwen 3b yaml
* updated read me
* updated configs
* added preappend token
* updated with thinking token
* updated test score board
* resolved comments
* added evaluation scripts
* removed results from pr
* added config
* added partial reward scoring
* added evaluation composites
* added training configs
* added games eval
* added rubriks cube
* resolved merge cinflicts
* added games config
* added latest eval configs
* updated strucutre
* Delete training/evaluations/eval_graphs_composite.yaml
---------
Co-authored-by: joesharratt1229 <joesharrat1229@gmail.com>
2025-04-16 08:04:52 +02:00
Oliver Stanley
224532f12a
first inter-domain generalisation experiments ( #412 )
...
* tweak len reward
* first inter-generalisation experiment config
* update inter algorithmic config
* default to empty config
* fix typo
* change config to match experiment script
* long prompt fixes
* algorithmic training config tweaks
* imports
* update algorithmic training cfgs
* first logic composite config
* fix dset name
* tweaks
* fix syllogisms dataset
* rm temp print
* initial algebra config
* algebra cfg tweaks
* add gc
* add initial games cfg
* rename games cfg
* fix dset name
* fix sokoban metadata
* remove boxnet
* games cfg tweak
2025-04-14 21:06:40 +01:00
Oliver Stanley
ff5407f766
fix boxnet scoring function ( #420 )
...
* avoid error print on invalid move format in tower of hanoi
* avoid boxnet error on hallucinated starting posittions
2025-04-14 20:44:24 +01:00
Zafir Stojanovski
71787c6a0e
fix(env): Remove custom score function in bf ( #418 )
...
* remove custom score function in bf
* pre commit
2025-04-14 11:26:18 +02:00
Zafir Stojanovski
290bfc4fdd
(evals): Medium configs ( #415 )
...
* updated medium configs
* fix problematic curriculum values / small issues causing exceptions to be raised
* optimus alpha config
* all configs so far
* fix tests
2025-04-14 08:25:31 +02:00
Andreas Köpf
cd1a9ea58b
add llama-4-maverick eval yaml config ( #413 )
2025-04-06 21:10:00 +01:00
Zafir Stojanovski
dced3bfc45
fix(curriculum): Make boundaries in curriculum more sensible ( #407 )
...
* init
* fix tests
* unify codeio
* filtered for libraries not present in reasoning-gym
* fix more bounds
* puzzle24
* knight swap curriculum
* fix number sorting
* fix attributes
* add validation of config in creation of dataset
* dry run for instantiating and validating the datasets
* remove unused imports
* fix curriculum tests to reference newly updated attribute names
2025-04-04 20:24:14 +02:00
Andreas Köpf
7853263650
bump dev version to 0.1.19
2025-04-03 22:19:07 +01:00
Zafir Stojanovski
dafdee621e
fix(env): Unify CodeIO datasets ( #405 )
...
* unify codeio
* filtered for libraries not present in reasoning-gym
2025-04-02 22:40:03 +02:00
Adefioye
5b653b346c
Data collisions notebooks and data ( #406 )
...
* Add collisions data
* Fix logic issues in basic_arithmetic and gsm_symbolic data
2025-04-02 09:36:09 +02:00
joesharratt1229
43c739cb3e
Feat/curr adj ( #394 )
2025-04-02 06:39:14 +01:00
