fix(collector): persist task cursor across PPO updates - was resetting to 0 each update so only first IC_ROLLOUTS tasks were ever trained on; now round-robins full shard (3 rollouts x 60 updates = 180 visits over 127-task shard = full coverage); also log first/last 5 task ids at startup so coverage is visible

feat(train): make HF_TOKEN optional + continuous live ETA heartbeat during rollouts

feat(kaggle): 3 sharded training notebooks + local-critic mode + LoRA merge

feat(train): warm-start adapter loading + IC_TASK_MODE (curated/all/hard) + phase2/phase3 launchers

feat(train): live tqdm+ETA, per-update HF Hub checkpoint upload, HF Jobs entrypoint + launcher