Delete experiments/weak_to_strong/reasoning/knights_knaves/distill_baseline/260814-delta-sampledrkl-knights_knaves-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-b64-mb32-dp4/global_step_15/actor/optim_world_size_4_rank_3.pt with huggingface_hub
Delete experiments/weak_to_strong/reasoning/knights_knaves/distill_baseline/260814-delta-sampledrkl-knights_knaves-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-b64-mb32-dp4/global_step_15/actor/optim_world_size_4_rank_2.pt with huggingface_hub
Delete experiments/weak_to_strong/reasoning/knights_knaves/distill_baseline/260814-delta-sampledrkl-knights_knaves-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-b64-mb32-dp4/global_step_15/actor/optim_world_size_4_rank_1.pt with huggingface_hub
Delete experiments/weak_to_strong/reasoning/knights_knaves/distill_baseline/260814-delta-sampledrkl-knights_knaves-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-b64-mb32-dp4/global_step_15/actor/optim_world_size_4_rank_0.pt with huggingface_hub
Upload experiments/weak_to_strong/reasoning/knights_knaves/distill_baseline/260814-delta-sampledrkl-knights_knaves-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-b64-mb32-dp4/global_step_30/data.pt with huggingface_hub
Upload experiments/weak_to_strong/reasoning/knights_knaves/distill_baseline/260814-delta-sampledrkl-knights_knaves-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-b64-mb32-dp4/global_step_30/actor/optim_world_size_4_rank_3.pt with huggingface_hub
Upload experiments/weak_to_strong/reasoning/knights_knaves/distill_baseline/260814-delta-sampledrkl-knights_knaves-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-b64-mb32-dp4/global_step_30/actor/optim_world_size_4_rank_2.pt with huggingface_hub
Upload experiments/weak_to_strong/reasoning/knights_knaves/distill_baseline/260814-delta-sampledrkl-knights_knaves-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-b64-mb32-dp4/global_step_30/actor/optim_world_size_4_rank_1.pt with huggingface_hub
Upload experiments/weak_to_strong/reasoning/knights_knaves/distill_baseline/260814-delta-sampledrkl-knights_knaves-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-b64-mb32-dp4/global_step_30/actor/optim_world_size_4_rank_0.pt with huggingface_hub
Upload experiments/weak_to_strong/reasoning/knights_knaves/distill_baseline/260814-delta-sampledrkl-knights_knaves-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-b64-mb32-dp4/global_step_30/actor/model_world_size_4_rank_3.pt with huggingface_hub
Upload experiments/weak_to_strong/reasoning/knights_knaves/distill_baseline/260814-delta-sampledrkl-knights_knaves-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-b64-mb32-dp4/global_step_30/actor/model_world_size_4_rank_2.pt with huggingface_hub
Upload experiments/weak_to_strong/reasoning/knights_knaves/distill_baseline/260814-delta-sampledrkl-knights_knaves-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-b64-mb32-dp4/global_step_30/actor/model_world_size_4_rank_1.pt with huggingface_hub
Upload experiments/weak_to_strong/reasoning/knights_knaves/distill_baseline/260814-delta-sampledrkl-knights_knaves-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-b64-mb32-dp4/global_step_30/actor/model_world_size_4_rank_0.pt with huggingface_hub
Upload experiments/weak_to_strong/reasoning/knights_knaves/distill_baseline/260814-delta-sampledrkl-knights_knaves-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-b64-mb32-dp4/global_step_30/actor/huggingface/tokenizer_config.json with huggingface_hub
Upload experiments/weak_to_strong/reasoning/knights_knaves/distill_baseline/260814-delta-sampledrkl-knights_knaves-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-b64-mb32-dp4/global_step_30/actor/huggingface/tokenizer.json with huggingface_hub
Upload experiments/weak_to_strong/reasoning/knights_knaves/distill_baseline/260814-delta-sampledrkl-knights_knaves-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-b64-mb32-dp4/global_step_30/actor/huggingface/generation_config.json with huggingface_hub
Upload experiments/weak_to_strong/reasoning/knights_knaves/distill_baseline/260814-delta-sampledrkl-knights_knaves-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-b64-mb32-dp4/global_step_30/actor/huggingface/config.json with huggingface_hub
Upload experiments/weak_to_strong/reasoning/knights_knaves/distill_baseline/260814-delta-sampledrkl-knights_knaves-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-b64-mb32-dp4/global_step_30/actor/huggingface/chat_template.jinja with huggingface_hub
Upload experiments/weak_to_strong/reasoning/knights_knaves/distill_baseline/260814-delta-sampledrkl-knights_knaves-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-b64-mb32-dp4/global_step_30/actor/fsdp_config.json with huggingface_hub
Upload experiments/weak_to_strong/reasoning/knights_knaves/distill_baseline/260814-delta-sampledrkl-knights_knaves-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-b64-mb32-dp4/global_step_30/actor/extra_state_world_size_4_rank_3.pt with huggingface_hub
Upload experiments/weak_to_strong/reasoning/knights_knaves/distill_baseline/260814-delta-sampledrkl-knights_knaves-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-b64-mb32-dp4/global_step_30/actor/extra_state_world_size_4_rank_2.pt with huggingface_hub
Upload experiments/weak_to_strong/reasoning/knights_knaves/distill_baseline/260814-delta-sampledrkl-knights_knaves-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-b64-mb32-dp4/global_step_30/actor/extra_state_world_size_4_rank_1.pt with huggingface_hub
Upload experiments/weak_to_strong/reasoning/knights_knaves/distill_baseline/260814-delta-sampledrkl-knights_knaves-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-b64-mb32-dp4/global_step_30/actor/extra_state_world_size_4_rank_0.pt with huggingface_hub
Upload experiments/weak_to_strong/reasoning/knights_knaves/distill_baseline/260814-delta-sampledrkl-knights_knaves-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-b64-mb32-dp4/global_step_30/actor/distill_teacher_world_size_4_rank_3.pt with huggingface_hub
Upload experiments/weak_to_strong/reasoning/knights_knaves/distill_baseline/260814-delta-sampledrkl-knights_knaves-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-b64-mb32-dp4/global_step_30/actor/distill_teacher_world_size_4_rank_2.pt with huggingface_hub
Upload experiments/weak_to_strong/reasoning/knights_knaves/distill_baseline/260814-delta-sampledrkl-knights_knaves-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-b64-mb32-dp4/global_step_30/actor/distill_teacher_world_size_4_rank_1.pt with huggingface_hub
Upload experiments/weak_to_strong/reasoning/knights_knaves/distill_baseline/260814-delta-sampledrkl-knights_knaves-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-b64-mb32-dp4/global_step_30/actor/distill_teacher_world_size_4_rank_0.pt with huggingface_hub
Upload experiments/weak_to_strong/reasoning/knights_knaves/distill_baseline/260814-delta-sampledrkl-knights_knaves-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-b64-mb32-dp4/global_step_30/actor/distill_resume_state_world_size_4_rank_3.pt with huggingface_hub
Upload experiments/weak_to_strong/reasoning/knights_knaves/distill_baseline/260814-delta-sampledrkl-knights_knaves-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-b64-mb32-dp4/global_step_30/actor/distill_resume_state_world_size_4_rank_2.pt with huggingface_hub
Upload experiments/weak_to_strong/reasoning/knights_knaves/distill_baseline/260814-delta-sampledrkl-knights_knaves-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-b64-mb32-dp4/global_step_30/actor/distill_resume_state_world_size_4_rank_1.pt with huggingface_hub
Upload experiments/weak_to_strong/reasoning/knights_knaves/distill_baseline/260814-delta-sampledrkl-knights_knaves-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-b64-mb32-dp4/global_step_30/actor/distill_resume_state_world_size_4_rank_0.pt with huggingface_hub
Upload experiments/weak_to_strong/reasoning/knights_knaves/distill_baseline/260814-delta-sampledrkl-knights_knaves-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-b64-mb32-dp4/global_step_30/actor/.worker_sidecars_ready_world_size_4_rank_3.json with huggingface_hub
Upload experiments/weak_to_strong/reasoning/knights_knaves/distill_baseline/260814-delta-sampledrkl-knights_knaves-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-b64-mb32-dp4/global_step_30/actor/.worker_sidecars_ready_world_size_4_rank_2.json with huggingface_hub
Upload experiments/weak_to_strong/reasoning/knights_knaves/distill_baseline/260814-delta-sampledrkl-knights_knaves-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-b64-mb32-dp4/global_step_30/actor/.worker_sidecars_ready_world_size_4_rank_1.json with huggingface_hub
Upload experiments/weak_to_strong/reasoning/knights_knaves/distill_baseline/260814-delta-sampledrkl-knights_knaves-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-b64-mb32-dp4/global_step_30/actor/.worker_sidecars_ready_world_size_4_rank_0.json with huggingface_hub
Upload experiments/weak_to_strong/reasoning/knights_knaves/distill_baseline/260814-delta-sampledrkl-knights_knaves-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-b64-mb32-dp4/global_step_30/actor/.checkpoint_complete.json with huggingface_hub
Upload experiments/weak_to_strong/reasoning/knights_knaves/distill_baseline/260814-delta-sampledrkl-knights_knaves-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-b64-mb32-dp4/global_step_30/actor/.async_checkpoint_started_world_size_4_rank_3.json with huggingface_hub
Upload experiments/weak_to_strong/reasoning/knights_knaves/distill_baseline/260814-delta-sampledrkl-knights_knaves-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-b64-mb32-dp4/global_step_30/actor/.async_checkpoint_started_world_size_4_rank_2.json with huggingface_hub
Upload experiments/weak_to_strong/reasoning/knights_knaves/distill_baseline/260814-delta-sampledrkl-knights_knaves-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-b64-mb32-dp4/global_step_30/actor/.async_checkpoint_started_world_size_4_rank_1.json with huggingface_hub
Upload experiments/weak_to_strong/reasoning/knights_knaves/distill_baseline/260814-delta-sampledrkl-knights_knaves-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-b64-mb32-dp4/global_step_30/actor/.async_checkpoint_started_world_size_4_rank_0.json with huggingface_hub
Upload experiments/weak_to_strong/reasoning/knights_knaves/distill_baseline/260814-delta-sampledrkl-knights_knaves-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-b64-mb32-dp4/global_step_30/actor/.async_checkpoint_ready_world_size_4_rank_3.json with huggingface_hub
Upload experiments/weak_to_strong/reasoning/knights_knaves/distill_baseline/260814-delta-sampledrkl-knights_knaves-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-b64-mb32-dp4/global_step_30/actor/.async_checkpoint_ready_world_size_4_rank_2.json with huggingface_hub
Upload experiments/weak_to_strong/reasoning/knights_knaves/distill_baseline/260814-delta-sampledrkl-knights_knaves-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-b64-mb32-dp4/global_step_30/actor/.async_checkpoint_ready_world_size_4_rank_1.json with huggingface_hub
Upload experiments/weak_to_strong/reasoning/knights_knaves/distill_baseline/260814-delta-sampledrkl-knights_knaves-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-b64-mb32-dp4/global_step_30/actor/.async_checkpoint_ready_world_size_4_rank_0.json with huggingface_hub
Upload experiments/weak_to_strong/reasoning/knights_knaves/distill_baseline/260814-delta-sampledrkl-knights_knaves-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-b64-mb32-dp4/global_step_15/data.pt with huggingface_hub
Upload experiments/weak_to_strong/reasoning/knights_knaves/distill_baseline/260814-delta-sampledrkl-knights_knaves-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-b64-mb32-dp4/global_step_15/actor/optim_world_size_4_rank_3.pt with huggingface_hub
Upload experiments/weak_to_strong/reasoning/knights_knaves/distill_baseline/260814-delta-sampledrkl-knights_knaves-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-b64-mb32-dp4/global_step_15/actor/optim_world_size_4_rank_2.pt with huggingface_hub
Upload experiments/weak_to_strong/reasoning/knights_knaves/distill_baseline/260814-delta-sampledrkl-knights_knaves-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-b64-mb32-dp4/global_step_15/actor/optim_world_size_4_rank_1.pt with huggingface_hub
Upload experiments/weak_to_strong/reasoning/knights_knaves/distill_baseline/260814-delta-sampledrkl-knights_knaves-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-b64-mb32-dp4/global_step_15/actor/optim_world_size_4_rank_0.pt with huggingface_hub
Upload experiments/weak_to_strong/math/distill_baseline/260813-math-delta-kdrl-b5e3-s30-qwen3-8b-teacher4b-step75-dp4/best_validation_checkpoint.json with huggingface_hub