-
assets: headline chart, architecture overview, training pipeline (for README)
-
readme: project description, results, training logs, links
-
Replace SFT reward curve with baseline-anchored learning curve (tool-aware baseline → checkpoint-40 … final)
-
Add HF Job stdout log for grpo_polymorphic_zero_day_1_5b
-
Add HF Job stdout log for grpo_worldsplit_1_5b
-
Add HF Job stdout log for sft_worldsplit_1_5b
-
Upload folder using huggingface_hub
-
Upload folder using huggingface_hub
-
Upload sft_worldsplit_1_5b/adaptshield_sft_worldsplit.summary.json with huggingface_hub
-
Upload folder using huggingface_hub
-
initial commit