Upload experiments/weak_to_strong/reasoning/string_manipulation/ours/260806-rcd-string_manipulation-q3-8b-base-t4b-s75-h1b-s0-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp4/global_step_105/data.pt with huggingface_hub
Upload experiments/weak_to_strong/reasoning/string_manipulation/ours/260806-rcd-string_manipulation-q3-8b-base-t4b-s75-h1b-s0-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp4/global_step_105/actor/huggingface/tokenizer_config.json with huggingface_hub
Upload experiments/weak_to_strong/reasoning/string_manipulation/ours/260806-rcd-string_manipulation-q3-8b-base-t4b-s75-h1b-s0-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp4/global_step_105/actor/huggingface/tokenizer.json with huggingface_hub
Upload experiments/weak_to_strong/reasoning/string_manipulation/ours/260806-rcd-string_manipulation-q3-8b-base-t4b-s75-h1b-s0-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp4/global_step_105/actor/huggingface/generation_config.json with huggingface_hub
Upload experiments/weak_to_strong/reasoning/string_manipulation/ours/260806-rcd-string_manipulation-q3-8b-base-t4b-s75-h1b-s0-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp4/global_step_105/actor/huggingface/config.json with huggingface_hub
Upload experiments/weak_to_strong/reasoning/string_manipulation/ours/260806-rcd-string_manipulation-q3-8b-base-t4b-s75-h1b-s0-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp4/global_step_105/actor/huggingface/chat_template.jinja with huggingface_hub
Upload experiments/weak_to_strong/reasoning/string_manipulation/ours/260806-rcd-string_manipulation-q3-8b-base-t4b-s75-h1b-s0-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp4/global_step_105/actor/fsdp_config.json with huggingface_hub
Upload experiments/weak_to_strong/reasoning/string_manipulation/ours/260806-rcd-string_manipulation-q3-8b-base-t4b-s75-h1b-s0-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp4/global_step_105/actor/extra_state_world_size_4_rank_3.pt with huggingface_hub
Upload experiments/weak_to_strong/reasoning/string_manipulation/ours/260806-rcd-string_manipulation-q3-8b-base-t4b-s75-h1b-s0-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp4/global_step_105/actor/extra_state_world_size_4_rank_2.pt with huggingface_hub
Upload experiments/weak_to_strong/reasoning/string_manipulation/ours/260806-rcd-string_manipulation-q3-8b-base-t4b-s75-h1b-s0-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp4/global_step_105/actor/extra_state_world_size_4_rank_1.pt with huggingface_hub
Upload experiments/weak_to_strong/reasoning/string_manipulation/ours/260806-rcd-string_manipulation-q3-8b-base-t4b-s75-h1b-s0-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp4/global_step_105/actor/extra_state_world_size_4_rank_0.pt with huggingface_hub
Upload experiments/weak_to_strong/reasoning/string_manipulation/ours/260806-rcd-string_manipulation-q3-8b-base-t4b-s75-h1b-s0-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp4/global_step_105/actor/.worker_sidecars_ready_world_size_4_rank_3.json with huggingface_hub
Upload experiments/weak_to_strong/reasoning/string_manipulation/ours/260806-rcd-string_manipulation-q3-8b-base-t4b-s75-h1b-s0-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp4/global_step_105/actor/.worker_sidecars_ready_world_size_4_rank_2.json with huggingface_hub
Upload experiments/weak_to_strong/reasoning/string_manipulation/ours/260806-rcd-string_manipulation-q3-8b-base-t4b-s75-h1b-s0-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp4/global_step_105/actor/.worker_sidecars_ready_world_size_4_rank_1.json with huggingface_hub
Upload experiments/weak_to_strong/reasoning/string_manipulation/ours/260806-rcd-string_manipulation-q3-8b-base-t4b-s75-h1b-s0-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp4/global_step_105/actor/.worker_sidecars_ready_world_size_4_rank_0.json with huggingface_hub
Upload experiments/weak_to_strong/reasoning/string_manipulation/ours/260806-rcd-string_manipulation-q3-8b-base-t4b-s75-h1b-s0-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp4/global_step_105/actor/.checkpoint_complete.json with huggingface_hub
Upload experiments/weak_to_strong/reasoning/string_manipulation/ours/260806-rcd-string_manipulation-q3-8b-base-t4b-s75-h1b-s0-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp4/global_step_105/actor/.async_checkpoint_started_world_size_4_rank_3.json with huggingface_hub
Upload experiments/weak_to_strong/reasoning/string_manipulation/ours/260806-rcd-string_manipulation-q3-8b-base-t4b-s75-h1b-s0-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp4/global_step_105/actor/.async_checkpoint_started_world_size_4_rank_2.json with huggingface_hub
Upload experiments/weak_to_strong/reasoning/string_manipulation/ours/260806-rcd-string_manipulation-q3-8b-base-t4b-s75-h1b-s0-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp4/global_step_105/actor/.async_checkpoint_started_world_size_4_rank_1.json with huggingface_hub
Upload experiments/weak_to_strong/reasoning/string_manipulation/ours/260806-rcd-string_manipulation-q3-8b-base-t4b-s75-h1b-s0-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp4/global_step_105/actor/.async_checkpoint_started_world_size_4_rank_0.json with huggingface_hub
Upload experiments/weak_to_strong/reasoning/string_manipulation/ours/260806-rcd-string_manipulation-q3-8b-base-t4b-s75-h1b-s0-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp4/global_step_105/actor/.async_checkpoint_ready_world_size_4_rank_3.json with huggingface_hub
Upload experiments/weak_to_strong/reasoning/string_manipulation/ours/260806-rcd-string_manipulation-q3-8b-base-t4b-s75-h1b-s0-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp4/global_step_105/actor/.async_checkpoint_ready_world_size_4_rank_2.json with huggingface_hub
Upload experiments/weak_to_strong/reasoning/string_manipulation/ours/260806-rcd-string_manipulation-q3-8b-base-t4b-s75-h1b-s0-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp4/global_step_105/actor/.async_checkpoint_ready_world_size_4_rank_1.json with huggingface_hub
Upload experiments/weak_to_strong/reasoning/string_manipulation/ours/260806-rcd-string_manipulation-q3-8b-base-t4b-s75-h1b-s0-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp4/global_step_105/actor/.async_checkpoint_ready_world_size_4_rank_0.json with huggingface_hub
Upload experiments/weak_to_strong/reasoning/string_manipulation/distill_baseline/260806-kdrl-b5e3-d6p6667e5-min0-sched75-string_manipulation-q3-8b-base-t4b-s75-tr8k-va8k-save30-best-finalopt-static10k-tistoken-clip0p2-0p28-b64-mb32-dp4/global_step_30/data.pt with huggingface_hub
Upload experiments/weak_to_strong/reasoning/string_manipulation/distill_baseline/260806-kdrl-b5e3-d6p6667e5-min0-sched75-string_manipulation-q3-8b-base-t4b-s75-tr8k-va8k-save30-best-finalopt-static10k-tistoken-clip0p2-0p28-b64-mb32-dp4/global_step_30/actor/huggingface/tokenizer_config.json with huggingface_hub
Upload experiments/weak_to_strong/reasoning/string_manipulation/distill_baseline/260806-kdrl-b5e3-d6p6667e5-min0-sched75-string_manipulation-q3-8b-base-t4b-s75-tr8k-va8k-save30-best-finalopt-static10k-tistoken-clip0p2-0p28-b64-mb32-dp4/global_step_30/actor/huggingface/tokenizer.json with huggingface_hub
Upload experiments/weak_to_strong/reasoning/string_manipulation/distill_baseline/260806-kdrl-b5e3-d6p6667e5-min0-sched75-string_manipulation-q3-8b-base-t4b-s75-tr8k-va8k-save30-best-finalopt-static10k-tistoken-clip0p2-0p28-b64-mb32-dp4/global_step_30/actor/huggingface/generation_config.json with huggingface_hub
Upload experiments/weak_to_strong/reasoning/string_manipulation/distill_baseline/260806-kdrl-b5e3-d6p6667e5-min0-sched75-string_manipulation-q3-8b-base-t4b-s75-tr8k-va8k-save30-best-finalopt-static10k-tistoken-clip0p2-0p28-b64-mb32-dp4/global_step_30/actor/huggingface/config.json with huggingface_hub
Upload experiments/weak_to_strong/reasoning/string_manipulation/distill_baseline/260806-kdrl-b5e3-d6p6667e5-min0-sched75-string_manipulation-q3-8b-base-t4b-s75-tr8k-va8k-save30-best-finalopt-static10k-tistoken-clip0p2-0p28-b64-mb32-dp4/global_step_30/actor/huggingface/chat_template.jinja with huggingface_hub
Upload experiments/weak_to_strong/reasoning/string_manipulation/distill_baseline/260806-kdrl-b5e3-d6p6667e5-min0-sched75-string_manipulation-q3-8b-base-t4b-s75-tr8k-va8k-save30-best-finalopt-static10k-tistoken-clip0p2-0p28-b64-mb32-dp4/global_step_30/actor/fsdp_config.json with huggingface_hub
Upload experiments/weak_to_strong/reasoning/string_manipulation/distill_baseline/260806-kdrl-b5e3-d6p6667e5-min0-sched75-string_manipulation-q3-8b-base-t4b-s75-tr8k-va8k-save30-best-finalopt-static10k-tistoken-clip0p2-0p28-b64-mb32-dp4/global_step_30/actor/extra_state_world_size_4_rank_3.pt with huggingface_hub
Upload experiments/weak_to_strong/reasoning/string_manipulation/distill_baseline/260806-kdrl-b5e3-d6p6667e5-min0-sched75-string_manipulation-q3-8b-base-t4b-s75-tr8k-va8k-save30-best-finalopt-static10k-tistoken-clip0p2-0p28-b64-mb32-dp4/global_step_30/actor/extra_state_world_size_4_rank_2.pt with huggingface_hub
Upload experiments/weak_to_strong/reasoning/string_manipulation/distill_baseline/260806-kdrl-b5e3-d6p6667e5-min0-sched75-string_manipulation-q3-8b-base-t4b-s75-tr8k-va8k-save30-best-finalopt-static10k-tistoken-clip0p2-0p28-b64-mb32-dp4/global_step_30/actor/extra_state_world_size_4_rank_1.pt with huggingface_hub
Upload experiments/weak_to_strong/reasoning/string_manipulation/distill_baseline/260806-kdrl-b5e3-d6p6667e5-min0-sched75-string_manipulation-q3-8b-base-t4b-s75-tr8k-va8k-save30-best-finalopt-static10k-tistoken-clip0p2-0p28-b64-mb32-dp4/global_step_30/actor/extra_state_world_size_4_rank_0.pt with huggingface_hub
Upload experiments/weak_to_strong/reasoning/string_manipulation/distill_baseline/260806-kdrl-b5e3-d6p6667e5-min0-sched75-string_manipulation-q3-8b-base-t4b-s75-tr8k-va8k-save30-best-finalopt-static10k-tistoken-clip0p2-0p28-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/string_manipulation/distill_baseline/260806-kdrl-b5e3-d6p6667e5-min0-sched75-string_manipulation-q3-8b-base-t4b-s75-tr8k-va8k-save30-best-finalopt-static10k-tistoken-clip0p2-0p28-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/string_manipulation/distill_baseline/260806-kdrl-b5e3-d6p6667e5-min0-sched75-string_manipulation-q3-8b-base-t4b-s75-tr8k-va8k-save30-best-finalopt-static10k-tistoken-clip0p2-0p28-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/string_manipulation/distill_baseline/260806-kdrl-b5e3-d6p6667e5-min0-sched75-string_manipulation-q3-8b-base-t4b-s75-tr8k-va8k-save30-best-finalopt-static10k-tistoken-clip0p2-0p28-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/string_manipulation/distill_baseline/260806-kdrl-b5e3-d6p6667e5-min0-sched75-string_manipulation-q3-8b-base-t4b-s75-tr8k-va8k-save30-best-finalopt-static10k-tistoken-clip0p2-0p28-b64-mb32-dp4/global_step_30/actor/.checkpoint_complete.json with huggingface_hub
Upload experiments/weak_to_strong/reasoning/string_manipulation/distill_baseline/260806-kdrl-b5e3-d6p6667e5-min0-sched75-string_manipulation-q3-8b-base-t4b-s75-tr8k-va8k-save30-best-finalopt-static10k-tistoken-clip0p2-0p28-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/string_manipulation/distill_baseline/260806-kdrl-b5e3-d6p6667e5-min0-sched75-string_manipulation-q3-8b-base-t4b-s75-tr8k-va8k-save30-best-finalopt-static10k-tistoken-clip0p2-0p28-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/string_manipulation/distill_baseline/260806-kdrl-b5e3-d6p6667e5-min0-sched75-string_manipulation-q3-8b-base-t4b-s75-tr8k-va8k-save30-best-finalopt-static10k-tistoken-clip0p2-0p28-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/string_manipulation/distill_baseline/260806-kdrl-b5e3-d6p6667e5-min0-sched75-string_manipulation-q3-8b-base-t4b-s75-tr8k-va8k-save30-best-finalopt-static10k-tistoken-clip0p2-0p28-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/string_manipulation/distill_baseline/260806-kdrl-b5e3-d6p6667e5-min0-sched75-string_manipulation-q3-8b-base-t4b-s75-tr8k-va8k-save30-best-finalopt-static10k-tistoken-clip0p2-0p28-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/string_manipulation/distill_baseline/260806-kdrl-b5e3-d6p6667e5-min0-sched75-string_manipulation-q3-8b-base-t4b-s75-tr8k-va8k-save30-best-finalopt-static10k-tistoken-clip0p2-0p28-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/string_manipulation/distill_baseline/260806-kdrl-b5e3-d6p6667e5-min0-sched75-string_manipulation-q3-8b-base-t4b-s75-tr8k-va8k-save30-best-finalopt-static10k-tistoken-clip0p2-0p28-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/string_manipulation/distill_baseline/260806-kdrl-b5e3-d6p6667e5-min0-sched75-string_manipulation-q3-8b-base-t4b-s75-tr8k-va8k-save30-best-finalopt-static10k-tistoken-clip0p2-0p28-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/string_manipulation/ours/260806-rcd-string_manipulation-q3-8b-base-t4b-s75-h1b-s0-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp4/global_step_90/data.pt with huggingface_hub
Upload experiments/weak_to_strong/reasoning/string_manipulation/ours/260806-rcd-string_manipulation-q3-8b-base-t4b-s75-h1b-s0-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp4/global_step_90/actor/huggingface/tokenizer_config.json with huggingface_hub