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
..
__init__.py	first commit	2025-04-29 12:10:10 -07:00
test_heterogeneous_batching.py	first commit	2025-04-29 12:10:10 -07:00
test_heterogeneous_packing.py	feat: add minimum batch allocation support for environments	2025-07-07 08:50:28 -05:00
test_min_batch_allocation.py	feat: add minimum batch allocation support for environments	2025-07-07 08:50:28 -05:00
test_tokenize_for_trainer.py	Fix API to accept messages without reward field + comprehensive tests	2025-06-09 14:03:08 -05:00