open-thought/reasoning-gym
1
0
Fork 0
mirror of https://github.com/open-thought/reasoning-gym.git synced 2026-04-19 12:58:07 +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

8
reasoning_gym/arithmetic/basic_arithmetic.py
View file

@ -2,7 +2,7 @@ from dataclasses import dataclass
from random import Random
from typing import Any, Literal, Optional
from ..coaching import BaseCurriculum, RangeAttributeDefinition
from ..coaching import BaseCurriculum, RangeAttributeDefinition, ScalarAttributeDefinition
from ..factory import ProceduralDataset, register_dataset
DATASET_NAME = "basic_arithmetic"
@ -250,17 +250,19 @@ class BasicArithmeticCurriculum(BaseCurriculum):
self._define_attributes(
RangeAttributeDefinition(
name="num_terms",
levels=[2, 5, 10, 15],
levels=[2, 3, 4, 5, 6],
description="Number of terms in the expression",
lower_field_name="min_terms",
upper_field_name="max_terms",
ensure_interval=False,
),
RangeAttributeDefinition(
name="num_digits",
levels=[1, 2, 5, 10],
levels=[1, 2, 3, 4],
description="Number of digits in the numbers",
lower_field_name="min_digits",
upper_field_name="max_digits",
ensure_interval=False,
),
)