main

TTobi LütkeMove GRPO training out of default finetune pipeline

189916d6创建于 2月23日历史提交

文件	最后提交记录	最后更新时间
gepa	finetune: strict Pydantic schema, one canonical data format Replace ad-hoc JSON parsing with a strict Pydantic model (TrainingExample with typed OutputPair). All data loading goes through load_examples() which fails loudly on invalid data. - Convert v3_structured.jsonl from "searches" to "output" format - Rewrite all consumer scripts (prepare, validate, score, analyze) to load through the Pydantic schema - Prepared train/val files are ephemeral build artifacts - Restore LFM2 and GEPA experiments under experiments/ - Add pydantic>=2.0 to dependencies	2 个月前
grpo	Move GRPO training out of default finetune pipeline	2 个月前
lfm2	finetune: strict Pydantic schema, one canonical data format Replace ad-hoc JSON parsing with a strict Pydantic model (TrainingExample with typed OutputPair). All data loading goes through load_examples() which fails loudly on invalid data. - Convert v3_structured.jsonl from "searches" to "output" format - Rewrite all consumer scripts (prepare, validate, score, analyze) to load through the Pydantic schema - Prepared train/val files are ephemeral build artifacts - Restore LFM2 and GEPA experiments under experiments/ - Add pydantic>=2.0 to dependencies	2 个月前