2026-04-28 06:31:23,298 INFO cleanslate.fsid.training.trainer: [RANK 0] FSID train: model=Qwen/Qwen3-8B objective=simnpo run_dir=runs/qwen3-8b/baseline-simnpo_gentle-debug-qwen-8b/simnpo_Qwen3-8B_20260428_063109 2026-04-28 06:31:23,298 INFO cleanslate.fsid.training.trainer: [RANK 0] Starting training: objective=simnpo epochs=1 2026-04-28 06:38:03,277 INFO cleanslate.fsid.training.trainer: [RANK 0] Saved checkpoint to runs/qwen3-8b/baseline-simnpo_gentle-debug-qwen-8b/simnpo_Qwen3-8B_20260428_063109 2026-04-28 06:38:03,280 INFO cleanslate.fsid.training.trainer: [RANK 0] Training complete (363.1s) 2026-04-28 06:38:03,666 INFO cleanslate.fsid.training.trainer: [RANK 0] Pushing checkpoint dir runs/qwen3-8b/baseline-simnpo_gentle-debug-qwen-8b/simnpo_Qwen3-8B_20260428_063109 to unlearning-cleanslate/qwen3-8b-simnpo_gentle-baseline-debug-qwen-8b