Commit graph

593 commits

Author SHA1 Message Date
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
emmmm
10f1b466b6
Update curriculum.py 2025-07-02 10:22:33 +02:00
pre-commit-ci[bot]
ab06a1ed52 [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
2025-07-01 03:33:35 +00:00
interstellarninja
256e0498da Merge branch 'feat/interleaved_tool_use' of github.com:interstellarninja/atropos into feat/interleaved_tool_use 2025-06-30 23:31:43 -04:00
interstellarninja
2827f55a04 overriding max_token_len from base 2025-06-30 23:29:58 -04:00
pre-commit-ci[bot]
ac5c341eee [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
2025-06-30 12:37:40 +00:00
interstellarninja
eb7a54de96 tool_use_interleaved_thinking.py 2025-06-30 08:35:10 -04:00
interstellarninja
72e91e5a1d fixing merge errors 2025-06-30 08:32:13 -04:00
pre-commit-ci[bot]
9e02d020fc [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
2025-06-30 12:19:46 +00:00
interstellarninja
a0d53e9bdc Merge branch 'feat/interleaved_tool_use' of github.com:interstellarninja/atropos into feat/interleaved_tool_use 2025-06-30 08:18:12 -04:00
interstellarninja
71ef50ffc7 implementing execution feedback mode 2025-06-30 08:15:30 -04:00
interstellarninja
9ea8ce26c6 Merge branch 'feat/multiturn_tool_use_env' of github.com:interstellarninja/atropos into feat/multiturn_tool_use_env 2025-06-27 01:41:55 -04:00
interstellarninja
b162813048 allowing only one think block 2025-06-26 23:20:30 -04:00
pre-commit-ci[bot]
34d45d2445 [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
2025-06-26 17:12:42 +00:00
interstellarninja
ee8755c388 using scenario for single, multistep and multiturn tool calls 2025-06-26 13:11:43 -04:00
Alex Pikme
ba992757e1
fix dead link README.md 2025-06-25 10:51:21 +02:00
pre-commit-ci[bot]
85f7a0b226 [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
2025-06-24 19:27:16 +00:00
interstellarninja
1570a8a106 resoling conflicts 2025-06-24 15:25:55 -04:00
interstellarninja
53138404b7 adding dynamic few-shot and controlling max gen per turn 2025-06-24 15:21:42 -04:00
pre-commit-ci[bot]
5ee01a7911 [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
2025-06-24 12:26:59 +00:00
interstellarninja
569a8303f3 creating environment for interleaved tool use 2025-06-24 08:21:37 -04:00
interstellarninja
45bc484931 option to generate all gpt turns 2025-06-24 08:14:14 -04:00
dmahan93
5b2b5e9947
Merge pull request #192 from rnkrtt/main
Fix typo in author name Gurning -> Gurung in community README
2025-06-23 10:15:58 -05:00
Merkel Tranjes
af1c98d7a8
Update README.md 2025-06-23 16:23:02 +02:00
Tomass
14917440db
fix duplicate plot.py 2025-06-23 15:32:54 +02:00
Teknium
8bf0312b8a
Merge pull request #190 from crStiv/a
fix: multiple typos of different importance
2025-06-22 13:15:39 -07:00
Jeremy Melvin
3bed7c64b9
Ethereum Virtual Machine Text to Transaction Environment (#187)
* EVM-text_to_transaction

* update structure

* Update README

---------

Co-authored-by: Jeremy Melvin <jeremy@openblocklabs.com>
2025-06-20 09:16:00 +10:00
crStiv
b65b614132
Update hpo.py 2025-06-19 22:59:42 +02:00
crStiv
e934094173
Update helpers.py 2025-06-19 22:52:43 +02:00
leopardracer
0d6297ad35
Update default.yaml 2025-06-18 22:23:15 +03:00
leopardracer
117783f5d5
Update README.md 2025-06-18 22:22:38 +03:00
Teknium
202ecff996
Merge pull request #170 from NousResearch/add-format-following-environment
Add format following environment
2025-06-16 06:50:17 -07:00
Teknium
9b93e56dbe
Merge pull request #181 from NousResearch/updates-to-instructfollowing-env
Add cycling curriculum, difficulty threshold, update datadumps
2025-06-16 06:49:59 -07:00
teknium1
81631b9c59 Merge branch 'updates-to-instructfollowing-env' of https://github.com/NousResearch/atropos into updates-to-instructfollowing-env 2025-06-14 12:32:31 -07:00
teknium1
bf78ad44e3 Add optional solve flagging strategy 2025-06-14 12:32:27 -07:00
pre-commit-ci[bot]
baed9b331e [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
2025-06-14 18:25:45 +00:00
FT
ad7f89d5c2
Update accessibility_env.py 2025-06-14 20:24:01 +02:00
FT
db15736775
Update README.md 2025-06-14 20:22:59 +02:00
pre-commit-ci[bot]
7fa9980b5c [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
2025-06-14 14:47:51 +00:00
teknium1
ad1bdf7f80 Add cycling curriculum, difficulty threshold, update datadumps 2025-06-14 07:44:47 -07:00
fuder.eth
6ec3054591
Update README.md 2025-06-13 14:52:30 +02:00
fuder.eth
9c2a495e75
Update plot.py 2025-06-13 14:51:25 +02:00
Teknium
e75ce6ccce
Merge pull request #176 from emmanuel-ferdman/main
Display cat behaviors file path on error
2025-06-13 04:42:48 -07:00
Teknium
eeeb0f1cd2
Merge pull request #172 from NousResearch/improve-data-dumping-in-sweRL
add additional data dumping features
2025-06-13 04:40:11 -07:00
pre-commit-ci[bot]
dcb926b73f [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
2025-06-13 11:39:36 +00:00
Teknium
32b739a757
Merge branch 'main' into add-format-following-environment 2025-06-13 04:39:06 -07:00
teknium1
ec6b9bb626 Merge branch 'letter-counting-environment' of https://github.com/NousResearch/atropos into letter-counting-environment 2025-06-13 04:27:32 -07:00
pre-commit-ci[bot]
2f9132ae63 [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
2025-06-12 15:20:13 +00:00
Dakota
d3e6ddddbc fixed pre-commit :) 2025-06-12 10:12:49 -05:00