Zafir Stojanovski
0e4582f83b
fix(evaluation): Add instructions for running on MMLU Pro ( #497 )
...
* add instructions for mmlu pro, format instructions for math benchmarks
* lint
* remove `--fewshot_as_multiturn`
2025-08-01 16:27:56 +02:00
Zafir Stojanovski
a969d8ef05
feat(curriculum): Knights and Knaves configs ( #488 )
...
* configs
* reduce complexity of curriculum
* update lower bound
* add failure threshold
* update last_k
* update thresholds for success and failure
* update curriculum file as well
* update run name for noncurriculum
* lint
* dtype model eval
* return binary scoring
* set eval repeats to 3
* fix tests
2025-07-31 10:18:05 +02:00
Zafir Stojanovski
0f5352e5cd
fix: Training README.md ( #491 )
...
* Update README.md in `training`
* add pip install for verl
2025-07-27 11:56:00 +02:00
joesharratt1229
4b60c32978
Curr exp ( #487 )
...
* began curr exp
* added holdout words
* updated config
* added context
* updated base curriculum
* updaed
* updated curriculum
* updated
* updated
* updated automatic flag
* updated ray trainer
* update
2025-07-25 20:38:47 +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
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
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
0cda6b1205
qwen math training code ( #435 )
...
* qwen math training code
* pre-commit
2025-05-16 13:19:19 +02:00
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
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
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
joesharratt1229
43c739cb3e
Feat/curr adj ( #394 )
2025-04-02 06:39:14 +01:00
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
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
