Hugging Face's logo

raymin0223
/
reverse_distill_assets

Safetensors
Model card Files
xet
 Community
2

Remove obsolete SFT100 experiment checkpoints: 260728-rcd-knights_knaves-q3-1p7b-base-t8b-s105-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2-sftstep100-260731

#2
by yr-park - opened
base: refs/heads/main
←
from: refs/pr/2
Discussion Files changed
+9884
-618434
Squash history to reclaim storage after deleting KDRL annealing runs1501f5a7
882 hidden commits · view all commits
 Upload experiments/weak_to_strong/reasoning/binary_matrix/ours/260801-rcd-binary_matrix-q3-8b-base-t4b-s105-4bbase-step0-lp1-lm0to1-s75-seed1234-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_60/actor/.worker_sidecars_ready_world_size_2_rank_1.json with huggingface_hubd9e5e086
 Upload experiments/weak_to_strong/math/ours/260801-rcd-fixedlambda-plus1p0-minus1p0-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_150/actor/extra_state_world_size_4_rank_3.pt with huggingface_hub8ea90ef8
 Upload experiments/weak_to_strong/math/ours/260801-rcd-fixedlambda-plus1p0-minus1p0-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_150/actor/fsdp_config.json with huggingface_hub586f2913
 Upload experiments/weak_to_strong/math/ours/260801-rcd-fixedlambda-plus1p0-minus1p0-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_150/actor/huggingface/chat_template.jinja with huggingface_hubaeb13571
 Upload experiments/weak_to_strong/math/ours/260801-rcd-fixedlambda-plus1p0-minus1p0-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_150/actor/huggingface/config.json with huggingface_hub255af970
 Upload experiments/weak_to_strong/reasoning/binary_matrix/ours/260801-rcd-binary_matrix-q3-8b-base-t4b-s105-4bbase-step0-lp1-lm0to1-s75-seed1234-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_60/actor/extra_state_world_size_2_rank_0.pt with huggingface_hubee87cfde
 Upload experiments/weak_to_strong/math/ours/260801-rcd-fixedlambda-plus1p0-minus1p0-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_150/actor/huggingface/generation_config.json with huggingface_hub40ce9cc0
 Upload experiments/weak_to_strong/reasoning/binary_matrix/ours/260801-rcd-binary_matrix-q3-8b-base-t4b-s105-4bbase-step0-lp1-lm0to1-s75-seed1234-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_60/actor/extra_state_world_size_2_rank_1.pt with huggingface_hubed360e47
 Upload experiments/weak_to_strong/math/ours/260801-rcd-fixedlambda-plus1p0-minus1p0-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_150/actor/huggingface/tokenizer.json with huggingface_huba9d41cfb
 Upload experiments/weak_to_strong/reasoning/binary_matrix/ours/260801-rcd-binary_matrix-q3-8b-base-t4b-s105-4bbase-step0-lp1-lm0to1-s75-seed1234-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_60/actor/fsdp_config.json with huggingface_hub9e6601d1
 Upload experiments/weak_to_strong/math/ours/260801-rcd-fixedlambda-plus1p0-minus1p0-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_150/actor/huggingface/tokenizer_config.json with huggingface_hub74b11cf3
 Upload experiments/weak_to_strong/reasoning/binary_matrix/ours/260801-rcd-binary_matrix-q3-8b-base-t4b-s105-4bbase-step0-lp1-lm0to1-s75-seed1234-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_60/actor/huggingface/chat_template.jinja with huggingface_hub3dfbe418
 Upload experiments/weak_to_strong/reasoning/binary_matrix/ours/260801-rcd-binary_matrix-q3-8b-base-t4b-s105-4bbase-step0-lp1-lm0to1-s75-seed1234-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_60/actor/huggingface/config.json with huggingface_hub8ad8ca87
 Upload experiments/weak_to_strong/reasoning/binary_matrix/ours/260801-rcd-binary_matrix-q3-8b-base-t4b-s105-4bbase-step0-lp1-lm0to1-s75-seed1234-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_60/actor/huggingface/generation_config.json with huggingface_hube64f6d38
 Upload experiments/weak_to_strong/reasoning/binary_matrix/ours/260801-rcd-binary_matrix-q3-8b-base-t4b-s105-4bbase-step0-lp1-lm0to1-s75-seed1234-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_60/actor/huggingface/tokenizer.json with huggingface_hub5e39ad56
 Upload experiments/weak_to_strong/reasoning/binary_matrix/ours/260801-rcd-binary_matrix-q3-8b-base-t4b-s105-4bbase-step0-lp1-lm0to1-s75-seed1234-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_60/actor/huggingface/tokenizer_config.json with huggingface_hub5fdcbdcc
 Upload experiments/weak_to_strong/reasoning/binary_matrix/ours/260801-rcd-binary_matrix-q3-8b-base-t4b-s105-4bbase-step0-lp1-lm0to1-s75-seed1234-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_60/data.pt with huggingface_hub687483e8
 Upload experiments/weak_to_strong/reasoning/binary_matrix/ours/260801-rcd-binary_matrix-q3-8b-base-t4b-s105-4bbase-step0-lp1-lm0to1-s75-seed1234-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_90/actor/.async_checkpoint_ready_world_size_2_rank_0.json with huggingface_hubc5025df7
 Upload experiments/weak_to_strong/reasoning/binary_matrix/ours/260801-rcd-binary_matrix-q3-8b-base-t4b-s105-4bbase-step0-lp1-lm0to1-s75-seed1234-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_90/actor/.async_checkpoint_ready_world_size_2_rank_1.json with huggingface_hubed2304ba
 Upload experiments/weak_to_strong/reasoning/binary_matrix/ours/260801-rcd-binary_matrix-q3-8b-base-t4b-s105-4bbase-step0-lp1-lm0to1-s75-seed1234-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_90/actor/.async_checkpoint_started_world_size_2_rank_0.json with huggingface_hub59361a57
 Upload experiments/weak_to_strong/reasoning/binary_matrix/ours/260801-rcd-binary_matrix-q3-8b-base-t4b-s105-4bbase-step0-lp1-lm0to1-s75-seed1234-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_90/actor/.async_checkpoint_started_world_size_2_rank_1.json with huggingface_hub7181d205
 Upload experiments/weak_to_strong/reasoning/binary_matrix/ours/260801-rcd-binary_matrix-q3-8b-base-t4b-s105-4bbase-step0-lp1-lm0to1-s75-seed1234-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_90/actor/.checkpoint_complete.json with huggingface_hub7c6b14ff
 Upload experiments/weak_to_strong/reasoning/binary_matrix/ours/260801-rcd-binary_matrix-q3-8b-base-t4b-s105-4bbase-step0-lp1-lm0to1-s75-seed1234-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_90/actor/.worker_sidecars_ready_world_size_2_rank_0.json with huggingface_hube6545a63
 Upload experiments/weak_to_strong/reasoning/binary_matrix/ours/260801-rcd-binary_matrix-q3-8b-base-t4b-s105-4bbase-step0-lp1-lm0to1-s75-seed1234-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_90/actor/.worker_sidecars_ready_world_size_2_rank_1.json with huggingface_hubd6f892ad
 Upload experiments/weak_to_strong/reasoning/binary_matrix/ours/260801-rcd-binary_matrix-q3-8b-base-t4b-s105-h1b-s45-lp1-lm0to1-s75-seed1234-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_150/actor/.async_checkpoint_ready_world_size_2_rank_0.json with huggingface_hub289e2c01
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_150/actor/.async_checkpoint_ready_world_size_2_rank_0.json with huggingface_hub9705e702
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_150/actor/.async_checkpoint_ready_world_size_2_rank_1.json with huggingface_hubac08ca88
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_150/actor/.async_checkpoint_started_world_size_2_rank_0.json with huggingface_hub9e2168b9
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_150/actor/.async_checkpoint_started_world_size_2_rank_1.json with huggingface_hube614d208
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_150/actor/.checkpoint_complete.json with huggingface_hub22a55707
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_150/actor/.worker_sidecars_ready_world_size_2_rank_0.json with huggingface_hubb3f24501
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_150/actor/.worker_sidecars_ready_world_size_2_rank_1.json with huggingface_hub36bb0c8c
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_150/actor/extra_state_world_size_2_rank_0.pt with huggingface_hubdd1c85a0
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_150/actor/extra_state_world_size_2_rank_1.pt with huggingface_hub7c8802f6
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_150/actor/fsdp_config.json with huggingface_hub8795d672
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_150/actor/huggingface/chat_template.jinja with huggingface_hube8fb740c
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_150/actor/huggingface/config.json with huggingface_hub2d878da8
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_150/actor/huggingface/generation_config.json with huggingface_hub2f237f10
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_150/actor/huggingface/tokenizer.json with huggingface_hub34fe9911
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_150/actor/huggingface/tokenizer_config.json with huggingface_hubda996e35
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_150/data.pt with huggingface_huba119c6a2
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_15/actor/.async_checkpoint_ready_world_size_2_rank_0.json with huggingface_hubf9016bd9
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_15/actor/.async_checkpoint_ready_world_size_2_rank_1.json with huggingface_hub384ef041
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_15/actor/.async_checkpoint_started_world_size_2_rank_0.json with huggingface_hubbeb437b0
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_15/actor/.async_checkpoint_started_world_size_2_rank_1.json with huggingface_hubbd5068fe
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_15/actor/.checkpoint_complete.json with huggingface_hub617d35af
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_15/actor/.worker_sidecars_ready_world_size_2_rank_0.json with huggingface_hub7f67cb5b
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_15/actor/.worker_sidecars_ready_world_size_2_rank_1.json with huggingface_hub561ced96
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_15/actor/extra_state_world_size_2_rank_0.pt with huggingface_hub10a5d0bc
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_15/actor/extra_state_world_size_2_rank_1.pt with huggingface_hubb726f921
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_15/actor/huggingface/chat_template.jinja with huggingface_hub12766696
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_15/actor/fsdp_config.json with huggingface_hub1a8bf85e
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_15/actor/huggingface/generation_config.json with huggingface_hubeac3873d
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_15/actor/huggingface/config.json with huggingface_hub4e43d05f
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_15/actor/huggingface/tokenizer.json with huggingface_hub9e2532a9
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_15/actor/huggingface/tokenizer_config.json with huggingface_hub1169b6fd
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_15/data.pt with huggingface_hubbaa778bd
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_30/actor/.async_checkpoint_ready_world_size_2_rank_0.json with huggingface_hubc737545b
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_30/actor/.async_checkpoint_started_world_size_2_rank_0.json with huggingface_hubc348b4f6
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_30/actor/.async_checkpoint_ready_world_size_2_rank_1.json with huggingface_hubad6ced08
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_30/actor/.async_checkpoint_started_world_size_2_rank_1.json with huggingface_hub1205b5f3
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_30/actor/.checkpoint_complete.json with huggingface_hub3a95264d
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_30/actor/.worker_sidecars_ready_world_size_2_rank_0.json with huggingface_hub9da23416
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_30/actor/.worker_sidecars_ready_world_size_2_rank_1.json with huggingface_hubf63a65a2
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_30/actor/extra_state_world_size_2_rank_0.pt with huggingface_hub859f7832
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_30/actor/extra_state_world_size_2_rank_1.pt with huggingface_hub1a28e7a3
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_30/actor/fsdp_config.json with huggingface_huba97942ae
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_30/actor/huggingface/chat_template.jinja with huggingface_hubca1a8cea
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_30/actor/huggingface/config.json with huggingface_hub2feadf33
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_30/actor/huggingface/generation_config.json with huggingface_hubcbe06c3e
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_30/actor/huggingface/tokenizer.json with huggingface_hub9d8bd025
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_30/actor/huggingface/tokenizer_config.json with huggingface_hubeb38599a
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_30/data.pt with huggingface_hubc6c42b50
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_45/actor/.async_checkpoint_ready_world_size_2_rank_0.json with huggingface_hub1bc29bdc
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_45/actor/.async_checkpoint_ready_world_size_2_rank_1.json with huggingface_hube843f6d6
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_45/actor/.async_checkpoint_started_world_size_2_rank_0.json with huggingface_hub0b1f5df1
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_45/actor/.async_checkpoint_started_world_size_2_rank_1.json with huggingface_hub3866552e
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_45/actor/.checkpoint_complete.json with huggingface_hubbdb367f2
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_45/actor/.worker_sidecars_ready_world_size_2_rank_0.json with huggingface_huba63e57c3
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_45/actor/.worker_sidecars_ready_world_size_2_rank_1.json with huggingface_hub40a5c0d9
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_45/actor/extra_state_world_size_2_rank_0.pt with huggingface_hub1ff25334
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_45/actor/extra_state_world_size_2_rank_1.pt with huggingface_hub09b158a0
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_45/actor/fsdp_config.json with huggingface_hubc9d94648
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_45/actor/huggingface/chat_template.jinja with huggingface_hub047ef1ac
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_45/actor/huggingface/config.json with huggingface_hube6cedd5f
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_45/actor/huggingface/generation_config.json with huggingface_hub18e19c5c
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_45/actor/huggingface/tokenizer.json with huggingface_hub71f266ba
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_45/actor/huggingface/tokenizer_config.json with huggingface_hub5c23a280
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_45/data.pt with huggingface_hub4b38fbb2
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_60/actor/.async_checkpoint_ready_world_size_2_rank_1.json with huggingface_hub18faa6ba
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_60/actor/.async_checkpoint_ready_world_size_2_rank_0.json with huggingface_hub185e9fb9
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_60/actor/.async_checkpoint_started_world_size_2_rank_0.json with huggingface_hub7782a09d
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_60/actor/.async_checkpoint_started_world_size_2_rank_1.json with huggingface_hub4704a75b
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_60/actor/.checkpoint_complete.json with huggingface_hub095fbd18
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_60/actor/.worker_sidecars_ready_world_size_2_rank_0.json with huggingface_huba6a0ac4c
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_60/actor/.worker_sidecars_ready_world_size_2_rank_1.json with huggingface_hube3827900
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_60/actor/extra_state_world_size_2_rank_0.pt with huggingface_hub091f4d43
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_60/actor/extra_state_world_size_2_rank_1.pt with huggingface_hube8691ef3
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_60/actor/fsdp_config.json with huggingface_hub95050d17
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_60/actor/huggingface/chat_template.jinja with huggingface_hub22388493
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_60/actor/huggingface/config.json with huggingface_hub8562ef5a
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_60/actor/huggingface/generation_config.json with huggingface_hub4963d8fa
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_60/actor/huggingface/tokenizer.json with huggingface_hubea353162
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_60/actor/huggingface/tokenizer_config.json with huggingface_hub9e159253
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_60/data.pt with huggingface_hubf20cccd7
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_75/actor/.async_checkpoint_ready_world_size_2_rank_0.json with huggingface_hube96c6369
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_75/actor/.async_checkpoint_ready_world_size_2_rank_1.json with huggingface_hub94eb5e01
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_75/actor/.async_checkpoint_started_world_size_2_rank_0.json with huggingface_hub8be6e4ec
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_75/actor/.async_checkpoint_started_world_size_2_rank_1.json with huggingface_hubd2ec06ca
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_75/actor/.checkpoint_complete.json with huggingface_hub41204d83
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_75/actor/.worker_sidecars_ready_world_size_2_rank_0.json with huggingface_hubbf7a60c5
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_75/actor/.worker_sidecars_ready_world_size_2_rank_1.json with huggingface_hub3273a837
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_75/actor/extra_state_world_size_2_rank_0.pt with huggingface_hub5d4bb30b
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_75/actor/extra_state_world_size_2_rank_1.pt with huggingface_hub079f50cf
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_75/actor/fsdp_config.json with huggingface_hub4ae48ee8
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_75/actor/huggingface/chat_template.jinja with huggingface_hub5ca73693
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_75/actor/huggingface/config.json with huggingface_hubff834802
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_75/actor/huggingface/generation_config.json with huggingface_hub2263571b
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_75/actor/huggingface/tokenizer_config.json with huggingface_hubebd427ab
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_75/actor/huggingface/tokenizer.json with huggingface_hub15af5009
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_75/data.pt with huggingface_hub69773eab
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_90/actor/.async_checkpoint_ready_world_size_2_rank_0.json with huggingface_hubff363fbe
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_90/actor/.async_checkpoint_ready_world_size_2_rank_1.json with huggingface_hubce661cfb
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_90/actor/.async_checkpoint_started_world_size_2_rank_0.json with huggingface_hub39733af3
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_90/actor/.async_checkpoint_started_world_size_2_rank_1.json with huggingface_hub87e00f48
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_90/actor/.checkpoint_complete.json with huggingface_hubfe3fc46a
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_90/actor/.worker_sidecars_ready_world_size_2_rank_0.json with huggingface_hubccbfefb9
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_90/actor/.worker_sidecars_ready_world_size_2_rank_1.json with huggingface_hub772ee53d
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_90/actor/extra_state_world_size_2_rank_0.pt with huggingface_hubf894608e
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_90/actor/extra_state_world_size_2_rank_1.pt with huggingface_hubb9e66589
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_90/actor/fsdp_config.json with huggingface_hubf0b76c4f
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_90/actor/huggingface/chat_template.jinja with huggingface_hub86df98cd
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_90/actor/huggingface/config.json with huggingface_hub3bc568f0
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_90/actor/huggingface/generation_config.json with huggingface_hubd6f6e902
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_90/actor/huggingface/tokenizer.json with huggingface_hubc207d505
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_90/actor/huggingface/tokenizer_config.json with huggingface_hub553c2371
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_90/data.pt with huggingface_hub879e18cb
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_105/actor/.async_checkpoint_ready_world_size_2_rank_1.json with huggingface_hub4f2ad2cb
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_105/actor/.async_checkpoint_ready_world_size_2_rank_0.json with huggingface_hub4e4f7fe5
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_105/actor/.async_checkpoint_started_world_size_2_rank_0.json with huggingface_hubccbcf5eb
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_105/actor/.async_checkpoint_started_world_size_2_rank_1.json with huggingface_hubc1a4ceb2
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_105/actor/.checkpoint_complete.json with huggingface_hub2d4881a3
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_105/actor/.worker_sidecars_ready_world_size_2_rank_0.json with huggingface_hubb6880253
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_105/actor/.worker_sidecars_ready_world_size_2_rank_1.json with huggingface_hub6cfbece6
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_105/actor/extra_state_world_size_2_rank_0.pt with huggingface_hub066aee74
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_105/actor/extra_state_world_size_2_rank_1.pt with huggingface_hubdf7dd80c
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_105/actor/fsdp_config.json with huggingface_hub176d3b24
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_105/actor/huggingface/chat_template.jinja with huggingface_hubf696e249
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_105/actor/huggingface/config.json with huggingface_hub6d0e5f73
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_105/actor/huggingface/generation_config.json with huggingface_hub55b4bc26
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_105/actor/huggingface/tokenizer.json with huggingface_hubd2af3fc9
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_105/actor/huggingface/tokenizer_config.json with huggingface_hub4b2d8994
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_105/data.pt with huggingface_hub7ec1f8cb
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_120/actor/.async_checkpoint_ready_world_size_2_rank_0.json with huggingface_hubc5ef5a20
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_120/actor/.async_checkpoint_ready_world_size_2_rank_1.json with huggingface_hub5dd3cbc5
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_120/actor/.async_checkpoint_started_world_size_2_rank_0.json with huggingface_hub312dfa60
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_120/actor/.async_checkpoint_started_world_size_2_rank_1.json with huggingface_hubdb10a605
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_120/actor/.checkpoint_complete.json with huggingface_hub5b511665
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_120/actor/.worker_sidecars_ready_world_size_2_rank_0.json with huggingface_hubb1c05db3
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_120/actor/.worker_sidecars_ready_world_size_2_rank_1.json with huggingface_hub64e5d302
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_120/actor/extra_state_world_size_2_rank_0.pt with huggingface_hub721f2019
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_120/actor/extra_state_world_size_2_rank_1.pt with huggingface_hub6e58ed50
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_120/actor/fsdp_config.json with huggingface_hub0c90df7b
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_120/actor/huggingface/chat_template.jinja with huggingface_hub5cb239b0
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_120/actor/huggingface/config.json with huggingface_hub7753cd1f
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_120/actor/huggingface/generation_config.json with huggingface_hub5fe37f5e
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_120/actor/huggingface/tokenizer.json with huggingface_hub71cc56dc
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_120/actor/huggingface/tokenizer_config.json with huggingface_hub68c281ca
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_120/data.pt with huggingface_hub572f9c7d
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_135/actor/.async_checkpoint_ready_world_size_2_rank_0.json with huggingface_hub2baf5857
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_135/actor/.async_checkpoint_ready_world_size_2_rank_1.json with huggingface_hub61ade86e
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_135/actor/.async_checkpoint_started_world_size_2_rank_0.json with huggingface_huba348b6aa
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_135/actor/.async_checkpoint_started_world_size_2_rank_1.json with huggingface_hub99437b88
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_135/actor/.checkpoint_complete.json with huggingface_hubea816826
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_135/actor/.worker_sidecars_ready_world_size_2_rank_0.json with huggingface_hubef8892b1
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_135/actor/.worker_sidecars_ready_world_size_2_rank_1.json with huggingface_hubcb9a6911
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_135/actor/extra_state_world_size_2_rank_0.pt with huggingface_hub1b9f7b17
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_135/actor/extra_state_world_size_2_rank_1.pt with huggingface_hubc900c194
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_135/actor/fsdp_config.json with huggingface_hub0c792300
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_135/actor/huggingface/chat_template.jinja with huggingface_hub0de43c6f
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_135/actor/huggingface/config.json with huggingface_hub57f5dfbc
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_135/actor/huggingface/generation_config.json with huggingface_hubf5d38ba2
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_135/actor/huggingface/tokenizer.json with huggingface_hub20c6e06e
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_135/actor/huggingface/tokenizer_config.json with huggingface_hubd201ed60
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_135/data.pt with huggingface_hubedd17e96
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/latest_checkpoint.json with huggingface_hubd3d71928
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/baseline/260801-grpo-zebra_puzzles-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/best_validation_checkpoint.json with huggingface_hub50b1955e
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/ours/260801-rcd-zebra_puzzles-q3-8b-base-t4b-s105-h1b-s0-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_45/actor/.async_checkpoint_ready_world_size_2_rank_0.json with huggingface_huba3a5b5d6
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/ours/260801-rcd-zebra_puzzles-q3-8b-base-t4b-s105-h1b-s0-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_45/actor/.async_checkpoint_ready_world_size_2_rank_1.json with huggingface_hub98cd8933
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/ours/260801-rcd-zebra_puzzles-q3-8b-base-t4b-s105-h1b-s0-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_45/actor/.async_checkpoint_started_world_size_2_rank_0.json with huggingface_hubb34acc20
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/ours/260801-rcd-zebra_puzzles-q3-8b-base-t4b-s105-h1b-s0-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_45/actor/.async_checkpoint_started_world_size_2_rank_1.json with huggingface_hubb58fc19b
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/ours/260801-rcd-zebra_puzzles-q3-8b-base-t4b-s105-h1b-s0-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_45/actor/.checkpoint_complete.json with huggingface_hub986ae418
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/ours/260801-rcd-zebra_puzzles-q3-8b-base-t4b-s105-h1b-s0-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_45/actor/.worker_sidecars_ready_world_size_2_rank_0.json with huggingface_hubd96d723a
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/ours/260801-rcd-zebra_puzzles-q3-8b-base-t4b-s105-h1b-s0-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_45/actor/.worker_sidecars_ready_world_size_2_rank_1.json with huggingface_hub5096dc1e
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/ours/260801-rcd-zebra_puzzles-q3-8b-base-t4b-s105-h1b-s0-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_45/actor/fsdp_config.json with huggingface_hub77f68856
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/ours/260801-rcd-zebra_puzzles-q3-8b-base-t4b-s105-h1b-s0-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_45/actor/huggingface/chat_template.jinja with huggingface_hub0c8c7f58
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/ours/260801-rcd-zebra_puzzles-q3-8b-base-t4b-s105-h1b-s0-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_45/actor/huggingface/config.json with huggingface_hubbefa6067
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/ours/260801-rcd-zebra_puzzles-q3-8b-base-t4b-s105-h1b-s0-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_45/actor/huggingface/generation_config.json with huggingface_hubb03b1d18
 Upload experiments/weak_to_strong/reasoning/zebra_puzzles/ours/260801-rcd-zebra_puzzles-q3-8b-base-t4b-s105-h1b-s0-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_45/actor/huggingface/tokenizer_config.json with huggingface_huba7d8ecf8
yr-park
No description provided.
Remove obsolete SFT100 experiment checkpoints: 260728-rcd-knights_knaves-q3-1p7b-base-t8b-s105-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2-sftstep100-2607319936958b
yr-park

Deleted directly from main with the repository owner token; superseded.
yr-park changed pull request status to closed

Sign up or log in to comment