open-thought/reasoning-gym
1
0
Fork 0
mirror of https://github.com/open-thought/reasoning-gym.git synced 2026-04-28 17:29:39 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Feat/intragen experiments (#414)

Browse source 
* 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>
This commit is contained in:
joesharratt1229 2025-04-16 07:04:52 +01:00 • committed by GitHub
parent 224532f12a
commit d0ef136d5b
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
21 changed files with 1331 additions and 48 deletions
Download patch file Download diff file Expand all files Collapse all files

7
tests/test_number_sorting.py
View file

@ -56,6 +56,7 @@ def test_number_sorting_dataset_items():
# Verify number count constraints
numbers = item["metadata"]["original_numbers"]
print(numbers)
assert len(numbers) >= config.min_numbers
assert len(numbers) <= config.max_numbers
@ -99,7 +100,7 @@ def test_number_sorting_curriculum():
base_cfg: NumberSortingConfig = curriculum.generate_configuration(base_value)
assert base_cfg.seed == 1
assert base_cfg.size == 150
assert base_cfg.min_numbers == 10 and base_cfg.max_numbers == 50
assert base_cfg.min_numbers == 10 and base_cfg.max_numbers == 100
assert base_cfg.min_decimals == 0 and base_cfg.max_decimals == 1
assert base_cfg.min_value == -100 and base_cfg.max_value == 100
@ -107,14 +108,14 @@ def test_number_sorting_curriculum():
curriculum.increment_attr_level("numbers")
curriculum.increment_attr_level("decimals")
increased_cfg = curriculum.generate_configuration(base_value)
assert increased_cfg.min_numbers == 10 and increased_cfg.max_numbers == 100
assert increased_cfg.min_numbers == 10 and increased_cfg.max_numbers == 500
assert increased_cfg.min_decimals == 0 and increased_cfg.max_decimals == 2
assert increased_cfg.min_value == -100 and increased_cfg.max_value == 100
# test decrementing attribute level for numbers again
curriculum.decrement_attr_level("numbers")
partially_decreased_cfg = curriculum.generate_configuration(base_value)
assert partially_decreased_cfg.min_numbers == 10 and partially_decreased_cfg.max_numbers == 50
assert partially_decreased_cfg.min_numbers == 10 and partially_decreased_cfg.max_numbers == 100
assert partially_decreased_cfg.min_decimals == 0 and partially_decreased_cfg.max_decimals == 2
assert partially_decreased_cfg.min_value == -100 and partially_decreased_cfg.max_value == 100