theblackcat102
2d19f13e0f
[ fix #484 ] resolve basic_arithmetic fails when size is large ( #485 )
...
* [fix] resolve basic_arithmetic fails when size is large by replacing zero divisor with 1
2025-07-07 09:46:23 +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
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
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
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
Andreas Köpf
d2c895f1d3
Refactor Curriculum Attributes ( #335 )
...
* remove min_value from AttributeDefinition
* remove type from AttributeDefinition
* Add CurriculumContext
* add ensure_interval option for RangeAttributes
* docs: Add legend explaining curriculum indicators in dataset gallery
* update GALLERY.md
2025-03-16 15:40:28 +01:00
joesharratt1229
1888fe2bb4
added basic arith curricula ( #276 )
...
* added basic arith curricula
* register BasicArithmeticCurriculum
---------
Co-authored-by: Andreas Koepf <andreas.koepf@provisio.com>
2025-03-07 22:54:49 +01:00
Andreas Koepf
acde58a200
use Decimal class for numeric comparison e.g. +0123.100 == 123.1
2025-02-21 15:36:06 +01:00
Andreas Koepf
3e7ff3b084
use native types List->list, Dict->dict, Set->set, Tuple->tuple
2025-02-21 15:15:38 +01:00
AhmedSaif2
5d02064b5a
add a helper function to handle redundant code
2025-02-21 15:54:00 +02:00
AhmedSaif2
73dfaa7f58
remove added instructions
2025-02-20 21:29:01 +02:00
AhmedSaif2
dcdef3f9ec
Add score answer to support comma format
2025-02-20 20:52:31 +02:00
Andreas Koepf
203394314e
minor formatting changes
2025-02-17 18:20:18 +01:00
abdulhakeem
15140d06e7
Tweaked some question templates
2025-02-17 02:58:42 -06:00
Andreas Koepf
44f8d7b6af
formatting
2025-02-16 16:18:39 +01:00
joesharratt1229
ba58ecf8ea
corrected failing airthmetic test
2025-02-16 12:01:54 +00:00
joesharratt1229
52869e3f89
reformatted prompt
2025-02-16 09:27:21 +00:00
joesharratt1229
68be1f6177
reformatted basic airth question template
2025-02-16 09:07:56 +00:00
Andreas Koepf
5410bb78a0
add ProductsDataset (multiplication tasks)
2025-02-13 17:59:02 +01:00
Andreas Koepf
0dcff77b37
add reasoning_gym.create_dataset({name}, ...) global factory function
2025-01-25 00:58:34 +01:00
Andreas Koepf
e9549f2a63
pass config to ProceduralDataset base
2025-01-25 00:23:05 +01:00
Andreas Koepf
ddc22868e9
Add support for integer division in basic arithmetic dataset
2025-01-24 15:07:31 +01:00
Andreas Koepf (aider)
7a64273f2e
feat: Add support for integer division in BasicArithmeticDataset
2025-01-24 11:30:38 +01:00
Andreas Koepf
20069b2a7d
formatting
2025-01-24 10:34:07 +01:00
Andreas Koepf
98988c8481
Rename ArithmeticDataset to BasicArithmeticDataset
2025-01-24 10:31:26 +01:00
Andreas Koepf (aider)
95d9974911
refactor: Rename ArithmeticDataset to BasicArithmeticDataset
2025-01-24 10:02:02 +01:00
Andreas Koepf (aider)
1b556b70f7
refactor: Inherit ArithmeticDataset from ProceduralDataset base class
2025-01-24 10:00:19 +01:00
Andreas Koepf (aider)
03a3bcf059
feat: Add configurable whitespace option to ArithmeticDataset
2025-01-23 14:25:54 +01:00
Andreas Koepf (aider)
6dbb5b39ee
refactor: Reorder parameters of _format_question to match other methods
2025-01-23 14:22:46 +01:00
Andreas Koepf (aider)
f12e3788d1
refactor: Pass item_rng to _format_question() method in ArithmeticDataset
2025-01-23 14:20:22 +01:00
Andreas Koepf (aider)
48492c4fd8
feat: Add arithmetic_dataset() factory function to basic_arithmetic.py
2025-01-23 12:47:01 +01:00
Andreas Koepf
72ada57dc5
style: Format code with consistent whitespace and remove unnecessary lines
2025-01-23 12:45:15 +01:00
Andreas Koepf (aider)
38801a7e6f
refactor: Remove duplicate chain_sum function from basic_arithmetic.py
2025-01-23 12:41:18 +01:00
Andreas Koepf (aider)
c253b1adbb
feat: Add chain_sum() factory function to create ChainSum dataset instances
2025-01-23 12:40:50 +01:00
Andreas Koepf (aider)
272ebc5a42
fix: Ensure deterministic iteration for ArithmeticDataset
2025-01-23 12:37:40 +01:00
Andreas Koepf (aider)
a8b3a86831
feat: Add iteration support to ArithmeticDataset with size-based termination
2025-01-23 12:34:54 +01:00
Andreas Koepf (aider)
fbba398c91
fix: Prevent infinite loop in arithmetic dataset space generation
2025-01-23 11:34:18 +01:00
Andreas Koepf (aider)
40596262e1
feat: Unify arithmetic task generation with configurable dataset class
...
This commit introduces a new `ArithmeticDataset` class that:
- Combines complex and simple arithmetic task generation approaches
- Provides configurable task generation via `ArithmeticDatasetConfig`
- Supports deterministic task generation
- Implements dataset interface for easy use with HuggingFace datasets
- Adds comprehensive test coverage for the new implementation
Changes include:
- Refactored `basic_arithmetic.py` to use a unified dataset approach
- Added configuration validation and flexible generation options
- Created test suite to validate dataset behavior
- Removed file generation methods in favor of in-memory generation
2025-01-23 11:30:09 +01:00
Andreas Koepf
8a6364a791
feat: Add basic arithmetic module to reasoning_gym
2025-01-23 11:30:03 +01:00
