hjc-puro
72210cf4ad
rename fn
2025-07-11 04:04:55 +00:00
hjc-puro
d133ba3867
comment
2025-07-11 03:54:03 +00:00
hjc-puro
ccb8eaf230
move table to util
2025-07-11 03:52:24 +00:00
hjc-puro
5e61331360
simplify schema
2025-07-11 03:49:49 +00:00
hjc-puro
290e087fc5
remove some imports
2025-07-11 03:25:10 +00:00
hjc-puro
68da3809e2
move table to display util
2025-07-11 02:06:56 +00:00
hjc-puro
3e08c6d788
simplify schema
2025-07-11 00:52:09 +00:00
hjc-puro
6c64df0226
remove jsonlines dependency
2025-07-11 00:42:55 +00:00
hjc-puro
da0d64ae89
linting errors
2025-07-11 00:29:57 +00:00
hjc-puro
e601251893
gsm8k eval example
2025-07-11 00:22:36 +00:00
hjc-puro
eb926dc58b
working evals
2025-07-10 01:45:21 +00:00
hjc-puro
f4de3ad6f5
add printing
2025-07-09 23:35:26 +00:00
hjc-puro
a11af27298
add eval saving cli args
2025-07-09 03:12:13 +00:00
hjc-puro
5519f190d2
add evaluate subcommand to cli
2025-07-07 17:39:33 -04:00
dmahan93
58446dbcb1
Merge pull request #204 from NousResearch/multienv-enforce-mins
...
Multienv with enforced minimum samples in a batch
2025-07-07 08:53:43 -05:00
Dakota
08e14cc745
feat: add minimum batch allocation support for environments
...
- Add min_batch_allocation parameter to ensure environments contribute minimum proportion to each batch
- Implement grab_batch_with_minimum_allocations function with proper scaling when allocations exceed 100%
- Add mixed-size group buffering to handle variable-sized data submissions
- Update server to use minimum allocation logic when any env has min_batch_allocation set
- Add comprehensive tests for minimum allocation scenarios
- Update documentation in API README and CONFIG.md
- Update example environments to demonstrate the feature
This feature allows critical environments to guarantee they contribute at least a specified proportion (0.0-1.0) to each training batch, ensuring important data sources are always represented during training.
🤖 Generated with [Claude Code](https://claude.ai/code )
Co-Authored-By: Claude <noreply@anthropic.com>
2025-07-07 08:50:28 -05:00
dmahan93
3b8d8a6f09
Merge pull request #202 from Myashka/main
...
Include run name in wandb initialization in BaseEnv
2025-07-07 08:05:47 -05:00
Alexey Gorbatovski
35c542328a
Fix infinite loop in wait_for_sem by updating semaphore values inside loop
2025-07-06 00:27:45 +03:00
pre-commit-ci[bot]
ee5257522a
[pre-commit.ci] auto fixes from pre-commit.com hooks
...
for more information, see https://pre-commit.ci
2025-07-04 14:34:37 +00:00
Alexey Gorbatovski
14c70c0e68
Include run name in wandb initialization in BaseEnv
2025-07-04 17:13:34 +03:00
Dakota
683559afd2
allow inf (<= 0 max_token_len) generations if trainer requests it, but raise a warning so that users can check their logs and get info if their trainers are doing something weird
2025-07-01 09:52:10 -05:00
crStiv
e9a547ce32
Update base.py
2025-06-19 22:52:26 +02:00
Cypher Pepe
24e963d393
fixed typo envs/README.md
2025-06-08 16:50:35 +03:00
Dakota
f3bbc6a42d
Fix import ordering with isort
...
- Move typing_extensions import to proper location
- Satisfy pre-commit isort requirements
2025-06-04 10:40:41 -05:00
Dakota
0ff55bf2cf
Fix TypedDict import for Python 3.10 compatibility
...
- Use typing_extensions.TypedDict instead of typing.TypedDict
- Fixes Pydantic error on Python < 3.12
2025-06-04 10:37:51 -05:00
hjc-puro
b5e7746c99
remove process defaults, respect config init
2025-06-02 21:19:45 -04:00
dmahan93
4a21ed0891
Enhance ScoredData model and API documentation
...
- Added optional fields: advantages, messages, and images to the ScoredData model.
- Updated API responses to include these new fields when no data is available.
- Revised README.md to reflect changes in the API structure and response format.
2025-06-02 17:28:25 -05:00
dmahan93
44b96c7b6c
Add max_n_completions parameter to ServerManager for handling multiple completions
...
- Introduced max_n_completions configuration to limit the number of completions requested per server call.
- Updated chat_completion and completion methods to split requests exceeding max_n_completions into multiple calls, merging results accordingly.
- Enhanced documentation for max_n_completions in ServerManagerConfig.
2025-06-02 11:11:55 -05:00
shannonsands
d232b0fd17
Merge pull request #58 from leehanchung/patch-1
...
docs: update README.md in atroposlib/env/README.md
2025-05-26 22:48:39 -07:00
Shannon Sands
c6a0439ec6
Integrate Sanskrit Poetry Environment from KhoomeiK - Add ChandasMeterReward to reward function registry - Move sanskrit_poetry_env.py to environments/community/sanskrit_poetry/ - Add comprehensive documentation as entry #25 in community README - Environment supports traditional Sanskrit meter validation using chandas classifier - Includes IAST to SLP1 transliteration for accurate meter analysis - Fixed code formatting with pre-commit hooks
2025-05-27 13:29:45 +10:00
leopardracer
2796b7db5f
Update README.md
2025-05-23 19:42:00 +03:00
Shannon Sands
2eddcb3cd9
fu linting
2025-05-23 11:18:16 +10:00
Shannon Sands
d98f65f444
linting
2025-05-23 11:09:06 +10:00
Shannon Sands
606a2615f0
loop check
2025-05-23 11:05:08 +10:00
Rohan Pandey
9c02ebc054
Fix chandas reward to use classifier
2025-05-18 17:26:13 -07:00
Shannon Sands
6f6084e513
linting
2025-05-18 16:55:25 -07:00
Shannon Sands
99a64f5bce
removing debugs
2025-05-18 16:48:42 -07:00
Shannon Sands
24d41720ef
debugging
2025-05-18 16:43:59 -07:00
Shannon Sands
955832a349
debugging
2025-05-18 16:32:45 -07:00
Shannon Sands
cb08629bcf
fixing error
2025-05-18 16:06:59 -07:00
Shannon Sands
5f36d0c658
debugging
2025-05-18 16:01:38 -07:00
Han
76abb16dac
docs: update README.md in atroposlib/env/README.md
...
Fixing wrong link to the base environment class documentation
2025-05-18 13:34:13 -07:00
Shannon Sands
76736ec4c2
removed unused
2025-05-17 13:37:55 -07:00
Shannon Sands
c05d9f7f53
added health check flag to skip entirely
2025-05-17 13:36:26 -07:00
Shannon Sands
f84934363c
linting
2025-05-17 13:06:16 -07:00
Shannon Sands
90138376f9
thanks cursor
2025-05-17 13:00:35 -07:00
Shannon Sands
59b08a1aa9
Added flag for chat completion, switch in OpenAI client
2025-05-17 12:59:20 -07:00
Shannon Sands
81534f7c8a
message
2025-05-17 12:50:35 -07:00
Shannon Sands
7dc3938038
changed health check to chat completions since all oai models are compatible with that, and it should work with compatible servers
2025-05-17 12:46:50 -07:00
Shannon Sands
00dd120067
Merge branch 'main' into blackjack2-env
2025-05-14 17:27:44 -07:00
