Skip to page content
SAVRN
Search Plan a project

Open-weight model

reverse_distill_assets

by Youngrok Park yr-park/reverse_distill_assets

reverse_distill_assets is an open-weight model from Youngrok Park. Its published files total 4.3 TB.

Parameters—
Context—
Weights4.3 TB
License—
AccessOpen weights
Monthly Downloads—

Model Card

The publisher has not written a card for this model.

Identity and Version

Repository
yr-park/reverse_distill_assets
Publisher
Youngrok Park
Task
Not stated by the source
Modality
Other
Library
Not stated by the source
Parameters
Not stated by the source
Languages
Not stated by the source
Revision
f2c98c82b6fe57828bb4ffcf0be7ebb163f662c6
First published
2026-04-16
Last updated
2026-09-22

Files and Weights

3,706 files, 4.3 TB in total. The weights are 964 files totalling 4.3 TB in pt, safetensors.

Weights964 files · 4.3 TB
Configuration2036 files · 2.2 MB
Every file (first 3,000)
FileTypeSizeSHA-256
experiments/distillation/reasoning/binary_matrix/baseline/260716-grpo-binary_matrix-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_150/actor/extra_state_world_size_2_rank_0.ptWeights15.3 KB 2a359580bc97
experiments/distillation/reasoning/binary_matrix/baseline/260716-grpo-binary_matrix-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_150/actor/extra_state_world_size_2_rank_1.ptWeights15.3 KB b861910565bb
experiments/distillation/reasoning/binary_matrix/baseline/260716-grpo-binary_matrix-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_150/actor/model_world_size_2_rank_0.ptWeights8.8 GB 0dc90796b042
experiments/distillation/reasoning/binary_matrix/baseline/260716-grpo-binary_matrix-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_150/actor/model_world_size_2_rank_1.ptWeights8.8 GB 8cc9e00b30ba
experiments/distillation/reasoning/binary_matrix/baseline/260716-grpo-binary_matrix-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_150/actor/optim_world_size_2_rank_0.ptWeights16.1 GB 30cd9c2e0e25
experiments/distillation/reasoning/binary_matrix/baseline/260716-grpo-binary_matrix-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_150/actor/optim_world_size_2_rank_1.ptWeights16.1 GB 17d320c514e7
experiments/distillation/reasoning/binary_matrix/baseline/260716-grpo-binary_matrix-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_150/data.ptWeights7.0 KB 6d96285c52da
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_105/actor/extra_state_world_size_2_rank_0.ptWeights15.3 KB 51a8607465a7
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_105/actor/extra_state_world_size_2_rank_1.ptWeights15.3 KB 42e4b2f9de40
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_105/actor/model_world_size_2_rank_0.ptWeights8.8 GB f665d1825fe1
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_105/actor/model_world_size_2_rank_1.ptWeights8.8 GB 3da8ebc1b514
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_105/data.ptWeights7.0 KB 09a40d508dab
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_120/actor/extra_state_world_size_2_rank_0.ptWeights15.3 KB 6e6521c6351d
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_120/actor/extra_state_world_size_2_rank_1.ptWeights15.3 KB 97f2228d29d0
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_120/actor/model_world_size_2_rank_0.ptWeights8.8 GB 670451b18d54
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_120/actor/model_world_size_2_rank_1.ptWeights8.8 GB 960dd547800a
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_120/data.ptWeights7.0 KB a66fc981d533
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_135/actor/extra_state_world_size_2_rank_0.ptWeights15.3 KB 7442a3b91fb0
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_135/actor/extra_state_world_size_2_rank_1.ptWeights15.3 KB a68a5cc3bda8
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_135/actor/model_world_size_2_rank_0.ptWeights8.8 GB 5e58a96a9d8f
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_135/actor/model_world_size_2_rank_1.ptWeights8.8 GB 0b5d7f7d5585
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_135/data.ptWeights7.0 KB 30fa55d9f0ad
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_15/actor/extra_state_world_size_2_rank_0.ptWeights15.3 KB 7de782b86c3f
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_15/actor/extra_state_world_size_2_rank_1.ptWeights15.3 KB e6e6d98880a3
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_15/actor/model_world_size_2_rank_0.ptWeights8.8 GB 05f0902ae40a
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_15/actor/model_world_size_2_rank_1.ptWeights8.8 GB 87e50168a2f8
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_15/data.ptWeights7.0 KB dd157db893bc
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_150/actor/extra_state_world_size_2_rank_0.ptWeights15.3 KB 8c115c8f423b
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_150/actor/extra_state_world_size_2_rank_1.ptWeights15.3 KB aff0c5a9c88b
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_150/actor/model_world_size_2_rank_0.ptWeights8.8 GB 89e5c9c9147d
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_150/actor/model_world_size_2_rank_1.ptWeights8.8 GB f16637020365
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_150/data.ptWeights7.0 KB 6d96285c52da
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_30/actor/extra_state_world_size_2_rank_0.ptWeights15.3 KB ccf323e8144d
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_30/actor/extra_state_world_size_2_rank_1.ptWeights15.3 KB 9ed8c5583820
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_30/actor/model_world_size_2_rank_0.ptWeights8.8 GB 00fe0a20e77e
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_30/actor/model_world_size_2_rank_1.ptWeights8.8 GB e7e01e735cc2
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_30/data.ptWeights7.0 KB 3d3cf8f5fa73
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_45/actor/extra_state_world_size_2_rank_0.ptWeights15.3 KB d80f7a564a39
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_45/actor/extra_state_world_size_2_rank_1.ptWeights15.3 KB 0583c3216dcc
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_45/actor/model_world_size_2_rank_0.ptWeights8.8 GB a4540d75732e
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_45/actor/model_world_size_2_rank_1.ptWeights8.8 GB ab263eeb6ea8
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_45/data.ptWeights7.0 KB fc55ca80ba58
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_60/actor/extra_state_world_size_2_rank_0.ptWeights15.3 KB d1e11e5ad690
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_60/actor/extra_state_world_size_2_rank_1.ptWeights15.3 KB c3dde20d4fc7
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_60/actor/model_world_size_2_rank_0.ptWeights8.8 GB 0dac8a8642ce
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_60/actor/model_world_size_2_rank_1.ptWeights8.8 GB 700d25d62cba
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_60/data.ptWeights7.0 KB fbed549ebe24
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_75/actor/extra_state_world_size_2_rank_0.ptWeights15.3 KB ce9d82ee6982
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_75/actor/extra_state_world_size_2_rank_1.ptWeights15.3 KB 2ba2db410b03
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_75/actor/model_world_size_2_rank_0.ptWeights8.8 GB 2ef462c1ceb5
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_75/actor/model_world_size_2_rank_1.ptWeights8.8 GB 00534ac7091f
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_75/data.ptWeights7.0 KB 24aeb2207229
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_90/actor/extra_state_world_size_2_rank_0.ptWeights15.3 KB 777d8e7c1490
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_90/actor/extra_state_world_size_2_rank_1.ptWeights15.3 KB 828b435576a0
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_90/actor/model_world_size_2_rank_0.ptWeights8.8 GB 63bb21320c8f
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_90/actor/model_world_size_2_rank_1.ptWeights8.8 GB c294bce4bcfa
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_90/data.ptWeights7.0 KB cbda6dcb9d24
experiments/weak_to_strong/agent/baseline/260917-pixel-qwen25vl-3b-grpo-b64-n8-step150-2gpu/global_step_30/actor/extra_state_world_size_2_rank_0.ptWeights15.1 KB 876bb6b8ba68
experiments/weak_to_strong/agent/baseline/260917-pixel-qwen25vl-3b-grpo-b64-n8-step150-2gpu/global_step_30/actor/extra_state_world_size_2_rank_1.ptWeights15.1 KB 764d700cce8c
experiments/weak_to_strong/agent/baseline/260917-pixel-qwen25vl-3b-grpo-b64-n8-step150-2gpu/global_step_30/actor/huggingface/model-00001-of-00002.safetensorsWeights5.0 GB a17e71774d69
experiments/weak_to_strong/agent/baseline/260917-pixel-qwen25vl-3b-grpo-b64-n8-step150-2gpu/global_step_30/actor/huggingface/model-00002-of-00002.safetensorsWeights3.1 GB 7b5f4795c7cf
experiments/weak_to_strong/agent/baseline/260917-pixel-qwen25vl-3b-grpo-b64-n8-step150-2gpu/global_step_30/actor/model_world_size_2_rank_0.ptWeights4.1 GB 5efd5126b7da
experiments/weak_to_strong/agent/baseline/260917-pixel-qwen25vl-3b-grpo-b64-n8-step150-2gpu/global_step_30/actor/model_world_size_2_rank_1.ptWeights4.1 GB 4cf172245dd0
experiments/weak_to_strong/agent/baseline/260917-pixel-qwen25vl-3b-grpo-b64-n8-step150-2gpu/global_step_30/data.ptWeights1.8 KB 4d8e1e307fb1
experiments/weak_to_strong/agent/baseline/260917-pixel-qwen25vl-3b-grpo-b64-n8-step150-2gpu/global_step_60/actor/extra_state_world_size_2_rank_0.ptWeights15.1 KB 97bc80ed38d9
experiments/weak_to_strong/agent/baseline/260917-pixel-qwen25vl-3b-grpo-b64-n8-step150-2gpu/global_step_60/actor/extra_state_world_size_2_rank_1.ptWeights15.1 KB 85e6a53ade4d
experiments/weak_to_strong/agent/baseline/260917-pixel-qwen25vl-3b-grpo-b64-n8-step150-2gpu/global_step_60/actor/huggingface/model-00001-of-00002.safetensorsWeights5.0 GB 63610cdc9bca
experiments/weak_to_strong/agent/baseline/260917-pixel-qwen25vl-3b-grpo-b64-n8-step150-2gpu/global_step_60/actor/huggingface/model-00002-of-00002.safetensorsWeights3.1 GB fd6241229bd7
experiments/weak_to_strong/agent/baseline/260917-pixel-qwen25vl-3b-grpo-b64-n8-step150-2gpu/global_step_60/actor/model_world_size_2_rank_0.ptWeights4.1 GB 8d343d060ad7
experiments/weak_to_strong/agent/baseline/260917-pixel-qwen25vl-3b-grpo-b64-n8-step150-2gpu/global_step_60/actor/model_world_size_2_rank_1.ptWeights4.1 GB bd405b2cb6d2
experiments/weak_to_strong/agent/baseline/260917-pixel-qwen25vl-3b-grpo-b64-n8-step150-2gpu/global_step_60/actor/optim_world_size_2_rank_0.ptWeights7.5 GB cd15a9f74833
experiments/weak_to_strong/agent/baseline/260917-pixel-qwen25vl-3b-grpo-b64-n8-step150-2gpu/global_step_60/actor/optim_world_size_2_rank_1.ptWeights7.5 GB ff613f595978
experiments/weak_to_strong/agent/baseline/260917-pixel-qwen25vl-3b-grpo-b64-n8-step150-2gpu/global_step_60/data.ptWeights1.8 KB 317d12622db3
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen25vl-3b-grpo-b64-mb32-n8-sysv1-step150-2gpu-fp32/global_step_30/actor/extra_state_world_size_2_rank_0.ptWeights15.1 KB 876bb6b8ba68
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen25vl-3b-grpo-b64-mb32-n8-sysv1-step150-2gpu-fp32/global_step_30/actor/extra_state_world_size_2_rank_1.ptWeights15.1 KB 764d700cce8c
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen25vl-3b-grpo-b64-mb32-n8-sysv1-step150-2gpu-fp32/global_step_30/actor/huggingface/model-00001-of-00004.safetensorsWeights5.0 GB 8c7866dc2629
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen25vl-3b-grpo-b64-mb32-n8-sysv1-step150-2gpu-fp32/global_step_30/actor/huggingface/model-00002-of-00004.safetensorsWeights4.9 GB 1b8daee5ca0c
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen25vl-3b-grpo-b64-mb32-n8-sysv1-step150-2gpu-fp32/global_step_30/actor/huggingface/model-00003-of-00004.safetensorsWeights4.9 GB d2288304c26b
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen25vl-3b-grpo-b64-mb32-n8-sysv1-step150-2gpu-fp32/global_step_30/actor/huggingface/model-00004-of-00004.safetensorsWeights1.4 GB 67550ca70f96
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen25vl-3b-grpo-b64-mb32-n8-sysv1-step150-2gpu-fp32/global_step_30/actor/model_world_size_2_rank_0.ptWeights8.1 GB e5e3ac5b2ce1
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen25vl-3b-grpo-b64-mb32-n8-sysv1-step150-2gpu-fp32/global_step_30/actor/model_world_size_2_rank_1.ptWeights8.1 GB bf9a5e5b5dc8
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen25vl-3b-grpo-b64-mb32-n8-sysv1-step150-2gpu-fp32/global_step_30/actor/optim_world_size_2_rank_0.ptWeights15.0 GB a9f38a8fcbea
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen25vl-3b-grpo-b64-mb32-n8-sysv1-step150-2gpu-fp32/global_step_30/actor/optim_world_size_2_rank_1.ptWeights15.0 GB 2a8cbf670ded
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen25vl-3b-grpo-b64-mb32-n8-sysv1-step150-2gpu-fp32/global_step_30/data.ptWeights1.8 KB 19e2f3c3666b
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen25vl-3b-grpo-b64-mb64-n8-sysv1-step150-2gpu-fp32/global_step_120/actor/extra_state_world_size_2_rank_0.ptWeights15.1 KB b5d7c22927bf
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen25vl-3b-grpo-b64-mb64-n8-sysv1-step150-2gpu-fp32/global_step_120/actor/extra_state_world_size_2_rank_1.ptWeights15.1 KB ef09e798f256
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen25vl-3b-grpo-b64-mb64-n8-sysv1-step150-2gpu-fp32/global_step_120/actor/huggingface/model-00001-of-00004.safetensorsWeights5.0 GB 316f1fb43685
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen25vl-3b-grpo-b64-mb64-n8-sysv1-step150-2gpu-fp32/global_step_120/actor/huggingface/model-00002-of-00004.safetensorsWeights4.9 GB 3368c9068c75
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen25vl-3b-grpo-b64-mb64-n8-sysv1-step150-2gpu-fp32/global_step_120/actor/huggingface/model-00003-of-00004.safetensorsWeights4.9 GB 4e2e8c04c07c
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen25vl-3b-grpo-b64-mb64-n8-sysv1-step150-2gpu-fp32/global_step_120/actor/huggingface/model-00004-of-00004.safetensorsWeights1.4 GB 3f1e3a9321c7
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen25vl-3b-grpo-b64-mb64-n8-sysv1-step150-2gpu-fp32/global_step_120/actor/model_world_size_2_rank_0.ptWeights8.1 GB f040485a9c71
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen25vl-3b-grpo-b64-mb64-n8-sysv1-step150-2gpu-fp32/global_step_120/actor/model_world_size_2_rank_1.ptWeights8.1 GB d5f88e56a659
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen25vl-3b-grpo-b64-mb64-n8-sysv1-step150-2gpu-fp32/global_step_120/data.ptWeights1.8 KB fe2722335fea
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen25vl-3b-grpo-b64-mb64-n8-sysv1-step150-2gpu-fp32/global_step_150/actor/extra_state_world_size_2_rank_0.ptWeights15.1 KB 989f285bc0bd
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen25vl-3b-grpo-b64-mb64-n8-sysv1-step150-2gpu-fp32/global_step_150/actor/extra_state_world_size_2_rank_1.ptWeights15.1 KB c7835b7557a4
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen25vl-3b-grpo-b64-mb64-n8-sysv1-step150-2gpu-fp32/global_step_150/actor/huggingface/model-00001-of-00004.safetensorsWeights5.0 GB 63d54adc2011
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen25vl-3b-grpo-b64-mb64-n8-sysv1-step150-2gpu-fp32/global_step_150/actor/huggingface/model-00002-of-00004.safetensorsWeights4.9 GB bed57f8f0d8d
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen25vl-3b-grpo-b64-mb64-n8-sysv1-step150-2gpu-fp32/global_step_150/actor/huggingface/model-00003-of-00004.safetensorsWeights4.9 GB 093450a54f83
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen25vl-3b-grpo-b64-mb64-n8-sysv1-step150-2gpu-fp32/global_step_150/actor/huggingface/model-00004-of-00004.safetensorsWeights1.4 GB 85f18ac4934f
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen25vl-3b-grpo-b64-mb64-n8-sysv1-step150-2gpu-fp32/global_step_150/actor/model_world_size_2_rank_0.ptWeights8.1 GB 503c86349805
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen25vl-3b-grpo-b64-mb64-n8-sysv1-step150-2gpu-fp32/global_step_150/actor/model_world_size_2_rank_1.ptWeights8.1 GB 50ab62c4fa4f
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen25vl-3b-grpo-b64-mb64-n8-sysv1-step150-2gpu-fp32/global_step_150/actor/optim_world_size_2_rank_0.ptWeights15.0 GB d31b66dbdf62
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen25vl-3b-grpo-b64-mb64-n8-sysv1-step150-2gpu-fp32/global_step_150/actor/optim_world_size_2_rank_1.ptWeights15.0 GB 3dc455d879a1
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen25vl-3b-grpo-b64-mb64-n8-sysv1-step150-2gpu-fp32/global_step_150/data.ptWeights1.8 KB 7b2f0e1e8295
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen25vl-3b-grpo-b64-mb64-n8-sysv1-step150-2gpu-fp32/global_step_30/actor/extra_state_world_size_2_rank_0.ptWeights15.1 KB 876bb6b8ba68
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen25vl-3b-grpo-b64-mb64-n8-sysv1-step150-2gpu-fp32/global_step_30/actor/extra_state_world_size_2_rank_1.ptWeights15.1 KB 764d700cce8c
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen25vl-3b-grpo-b64-mb64-n8-sysv1-step150-2gpu-fp32/global_step_30/actor/huggingface/model-00001-of-00004.safetensorsWeights5.0 GB 1f78fe9bf3d3
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen25vl-3b-grpo-b64-mb64-n8-sysv1-step150-2gpu-fp32/global_step_30/actor/huggingface/model-00002-of-00004.safetensorsWeights4.9 GB 84c0e2c3749d
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen25vl-3b-grpo-b64-mb64-n8-sysv1-step150-2gpu-fp32/global_step_30/actor/huggingface/model-00003-of-00004.safetensorsWeights4.9 GB fb050c7400d9
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen25vl-3b-grpo-b64-mb64-n8-sysv1-step150-2gpu-fp32/global_step_30/actor/huggingface/model-00004-of-00004.safetensorsWeights1.4 GB 3e0221ed204c
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen25vl-3b-grpo-b64-mb64-n8-sysv1-step150-2gpu-fp32/global_step_30/actor/model_world_size_2_rank_0.ptWeights8.1 GB f86714756f44
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen25vl-3b-grpo-b64-mb64-n8-sysv1-step150-2gpu-fp32/global_step_30/actor/model_world_size_2_rank_1.ptWeights8.1 GB c03e1310c933
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen25vl-3b-grpo-b64-mb64-n8-sysv1-step150-2gpu-fp32/global_step_30/data.ptWeights1.8 KB 017c730775a1
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen25vl-3b-grpo-b64-mb64-n8-sysv1-step150-2gpu-fp32/global_step_60/actor/extra_state_world_size_2_rank_0.ptWeights15.1 KB 97bc80ed38d9
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen25vl-3b-grpo-b64-mb64-n8-sysv1-step150-2gpu-fp32/global_step_60/actor/extra_state_world_size_2_rank_1.ptWeights15.1 KB 85e6a53ade4d
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen25vl-3b-grpo-b64-mb64-n8-sysv1-step150-2gpu-fp32/global_step_60/actor/huggingface/model-00001-of-00004.safetensorsWeights5.0 GB 106a2bcb6ed2
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen25vl-3b-grpo-b64-mb64-n8-sysv1-step150-2gpu-fp32/global_step_60/actor/huggingface/model-00002-of-00004.safetensorsWeights4.9 GB bc8458352321
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen25vl-3b-grpo-b64-mb64-n8-sysv1-step150-2gpu-fp32/global_step_60/actor/huggingface/model-00003-of-00004.safetensorsWeights4.9 GB fd42b0500c34
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen25vl-3b-grpo-b64-mb64-n8-sysv1-step150-2gpu-fp32/global_step_60/actor/huggingface/model-00004-of-00004.safetensorsWeights1.4 GB 58cc0eec4bb4
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen25vl-3b-grpo-b64-mb64-n8-sysv1-step150-2gpu-fp32/global_step_60/actor/model_world_size_2_rank_0.ptWeights8.1 GB b99557e3d30a
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen25vl-3b-grpo-b64-mb64-n8-sysv1-step150-2gpu-fp32/global_step_60/actor/model_world_size_2_rank_1.ptWeights8.1 GB 90d73a3cab29
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen25vl-3b-grpo-b64-mb64-n8-sysv1-step150-2gpu-fp32/global_step_60/data.ptWeights1.8 KB a36af6087b1a
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen25vl-3b-grpo-b64-mb64-n8-sysv1-step150-2gpu-fp32/global_step_90/actor/extra_state_world_size_2_rank_0.ptWeights15.1 KB 4c70b47f8897
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen25vl-3b-grpo-b64-mb64-n8-sysv1-step150-2gpu-fp32/global_step_90/actor/extra_state_world_size_2_rank_1.ptWeights15.1 KB 580e55cd1470
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen25vl-3b-grpo-b64-mb64-n8-sysv1-step150-2gpu-fp32/global_step_90/actor/huggingface/model-00001-of-00004.safetensorsWeights5.0 GB f87e79e8bf21
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen25vl-3b-grpo-b64-mb64-n8-sysv1-step150-2gpu-fp32/global_step_90/actor/huggingface/model-00002-of-00004.safetensorsWeights4.9 GB b647a27a90a4
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen25vl-3b-grpo-b64-mb64-n8-sysv1-step150-2gpu-fp32/global_step_90/actor/huggingface/model-00003-of-00004.safetensorsWeights4.9 GB 8d05a7b0e85f
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen25vl-3b-grpo-b64-mb64-n8-sysv1-step150-2gpu-fp32/global_step_90/actor/huggingface/model-00004-of-00004.safetensorsWeights1.4 GB b9dc1f480efd
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen25vl-3b-grpo-b64-mb64-n8-sysv1-step150-2gpu-fp32/global_step_90/actor/model_world_size_2_rank_0.ptWeights8.1 GB e8e4c4dfcd6c
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen25vl-3b-grpo-b64-mb64-n8-sysv1-step150-2gpu-fp32/global_step_90/actor/model_world_size_2_rank_1.ptWeights8.1 GB 2bb91ef4ba8c
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen25vl-3b-grpo-b64-mb64-n8-sysv1-step150-2gpu-fp32/global_step_90/data.ptWeights1.8 KB 091696525c7c
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen3vl-4b-instruct-grpo-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_30/actor/extra_state_world_size_4_rank_0.ptWeights15.1 KB d73ac65b297e
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen3vl-4b-instruct-grpo-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_30/actor/extra_state_world_size_4_rank_1.ptWeights15.1 KB 64ad6bce704d
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen3vl-4b-instruct-grpo-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_30/actor/extra_state_world_size_4_rank_2.ptWeights15.1 KB 3cdbe10b6ced
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen3vl-4b-instruct-grpo-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_30/actor/extra_state_world_size_4_rank_3.ptWeights15.1 KB 37c15092db97
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen3vl-4b-instruct-grpo-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_30/actor/huggingface/model-00001-of-00004.safetensorsWeights4.9 GB 72e21c72c9a6
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen3vl-4b-instruct-grpo-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_30/actor/huggingface/model-00002-of-00004.safetensorsWeights4.9 GB c4331de53ea0
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen3vl-4b-instruct-grpo-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_30/actor/huggingface/model-00003-of-00004.safetensorsWeights4.9 GB d83bf3403720
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen3vl-4b-instruct-grpo-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_30/actor/huggingface/model-00004-of-00004.safetensorsWeights4.5 GB 8d90ba7968ec
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen3vl-4b-instruct-grpo-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_30/actor/model_world_size_4_rank_0.ptWeights4.8 GB f5c07b925dec
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen3vl-4b-instruct-grpo-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_30/actor/model_world_size_4_rank_1.ptWeights4.8 GB 1a994d8be5ff
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen3vl-4b-instruct-grpo-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_30/actor/model_world_size_4_rank_2.ptWeights4.8 GB 7b3a6ec35ac2
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen3vl-4b-instruct-grpo-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_30/actor/model_world_size_4_rank_3.ptWeights4.8 GB 0744127ee8f0
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen3vl-4b-instruct-grpo-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_30/actor/optim_world_size_4_rank_0.ptWeights8.9 GB 32e0214444f1
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen3vl-4b-instruct-grpo-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_30/actor/optim_world_size_4_rank_1.ptWeights8.9 GB fe1ee8cdcd81
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen3vl-4b-instruct-grpo-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_30/actor/optim_world_size_4_rank_2.ptWeights8.9 GB f2461401a39c
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen3vl-4b-instruct-grpo-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_30/actor/optim_world_size_4_rank_3.ptWeights8.9 GB bdf3a34dd371
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen3vl-4b-instruct-grpo-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_30/data.ptWeights1.8 KB 0f420cddf3c4
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen25vl-3b-sft-grpo-b64-mb64-n8-alpha1-sysv1-step150-4gpu-fp32/global_step_30/actor/extra_state_world_size_4_rank_0.ptWeights15.1 KB d73ac65b297e
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen25vl-3b-sft-grpo-b64-mb64-n8-alpha1-sysv1-step150-4gpu-fp32/global_step_30/actor/extra_state_world_size_4_rank_1.ptWeights15.1 KB 64ad6bce704d
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen25vl-3b-sft-grpo-b64-mb64-n8-alpha1-sysv1-step150-4gpu-fp32/global_step_30/actor/extra_state_world_size_4_rank_2.ptWeights15.1 KB 3cdbe10b6ced
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen25vl-3b-sft-grpo-b64-mb64-n8-alpha1-sysv1-step150-4gpu-fp32/global_step_30/actor/extra_state_world_size_4_rank_3.ptWeights15.1 KB 37c15092db97
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen25vl-3b-sft-grpo-b64-mb64-n8-alpha1-sysv1-step150-4gpu-fp32/global_step_30/actor/huggingface/model-00001-of-00004.safetensorsWeights5.0 GB 35b68e8594c0
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen25vl-3b-sft-grpo-b64-mb64-n8-alpha1-sysv1-step150-4gpu-fp32/global_step_30/actor/huggingface/model-00002-of-00004.safetensorsWeights4.9 GB 84c3e906ad68
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen25vl-3b-sft-grpo-b64-mb64-n8-alpha1-sysv1-step150-4gpu-fp32/global_step_30/actor/huggingface/model-00003-of-00004.safetensorsWeights4.9 GB 545e9768c26a
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen25vl-3b-sft-grpo-b64-mb64-n8-alpha1-sysv1-step150-4gpu-fp32/global_step_30/actor/huggingface/model-00004-of-00004.safetensorsWeights1.4 GB e0f8d860cf9d
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen25vl-3b-sft-grpo-b64-mb64-n8-alpha1-sysv1-step150-4gpu-fp32/global_step_30/actor/model_world_size_4_rank_0.ptWeights4.1 GB 5f2e4ec0750c
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen25vl-3b-sft-grpo-b64-mb64-n8-alpha1-sysv1-step150-4gpu-fp32/global_step_30/actor/model_world_size_4_rank_1.ptWeights4.1 GB 28111cb41a76
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen25vl-3b-sft-grpo-b64-mb64-n8-alpha1-sysv1-step150-4gpu-fp32/global_step_30/actor/model_world_size_4_rank_2.ptWeights4.1 GB 0aebbde434ae
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen25vl-3b-sft-grpo-b64-mb64-n8-alpha1-sysv1-step150-4gpu-fp32/global_step_30/actor/model_world_size_4_rank_3.ptWeights4.1 GB 4a82de7aaff2
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen25vl-3b-sft-grpo-b64-mb64-n8-alpha1-sysv1-step150-4gpu-fp32/global_step_30/data.ptWeights1.8 KB adf46450dbb6
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_120/actor/extra_state_world_size_4_rank_0.ptWeights15.1 KB d9281336b934
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_120/actor/extra_state_world_size_4_rank_1.ptWeights15.1 KB 5f39e32b4373
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_120/actor/extra_state_world_size_4_rank_2.ptWeights15.1 KB a09f1d19d832
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_120/actor/extra_state_world_size_4_rank_3.ptWeights15.1 KB ec23e2ab9d02
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_120/actor/huggingface/model-00001-of-00007.safetensorsWeights5.0 GB 4233d47efa13
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_120/actor/huggingface/model-00002-of-00007.safetensorsWeights5.0 GB d3d93f53f777
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_120/actor/huggingface/model-00003-of-00007.safetensorsWeights4.9 GB 47b41fd32491
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_120/actor/huggingface/model-00004-of-00007.safetensorsWeights5.0 GB 4891610cb31a
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_120/actor/huggingface/model-00005-of-00007.safetensorsWeights5.0 GB 3c846c28d23a
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_120/actor/huggingface/model-00006-of-00007.safetensorsWeights4.9 GB 74ac6bef0672
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_120/actor/huggingface/model-00007-of-00007.safetensorsWeights3.4 GB 78f3833b5734
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_120/actor/model_world_size_4_rank_0.ptWeights8.3 GB e895151cecee
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_120/actor/model_world_size_4_rank_1.ptWeights8.3 GB 1656a2f2eaa2
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_120/actor/model_world_size_4_rank_2.ptWeights8.3 GB 5401fc76877c
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_120/actor/model_world_size_4_rank_3.ptWeights8.3 GB 0edce672fcd8
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_120/actor/optim_world_size_4_rank_0.ptWeights16.6 GB 86be9e59da24
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_120/actor/optim_world_size_4_rank_1.ptWeights16.6 GB 18b906310143
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_120/actor/optim_world_size_4_rank_2.ptWeights16.6 GB c5ad9e7f8170
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_120/actor/optim_world_size_4_rank_3.ptWeights16.6 GB 03909eb34095
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_120/data.ptWeights1.8 KB 359bb7867a4f
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_30/actor/extra_state_world_size_4_rank_0.ptWeights15.1 KB d73ac65b297e
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_30/actor/extra_state_world_size_4_rank_1.ptWeights15.1 KB 64ad6bce704d
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_30/actor/extra_state_world_size_4_rank_2.ptWeights15.1 KB 3cdbe10b6ced
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_30/actor/extra_state_world_size_4_rank_3.ptWeights15.1 KB 37c15092db97
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_30/actor/huggingface/model-00001-of-00007.safetensorsWeights5.0 GB 5d5801a4c32c
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_30/actor/huggingface/model-00002-of-00007.safetensorsWeights5.0 GB 68588caa0359
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_30/actor/huggingface/model-00003-of-00007.safetensorsWeights4.9 GB a1286009774a
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_30/actor/huggingface/model-00004-of-00007.safetensorsWeights5.0 GB 681a9b8f9fac
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_30/actor/huggingface/model-00005-of-00007.safetensorsWeights5.0 GB d03deb1d5e3c
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_30/actor/huggingface/model-00006-of-00007.safetensorsWeights4.9 GB 252ba1ececc2
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_30/actor/huggingface/model-00007-of-00007.safetensorsWeights3.4 GB cee1e143e343
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_30/actor/model_world_size_4_rank_0.ptWeights8.3 GB 70cf63222e4a
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_30/actor/model_world_size_4_rank_1.ptWeights8.3 GB 11614b52d412
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_30/actor/model_world_size_4_rank_2.ptWeights8.3 GB 403c202c5634
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_30/actor/model_world_size_4_rank_3.ptWeights8.3 GB a39ff8ab1a74
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_30/data.ptWeights1.8 KB bbbb20769661
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_60/actor/extra_state_world_size_4_rank_0.ptWeights15.1 KB 7c88cdf37d85
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_60/actor/extra_state_world_size_4_rank_1.ptWeights15.1 KB bf62a3c1413d
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_60/actor/extra_state_world_size_4_rank_2.ptWeights15.1 KB 4e4e92c05ba5
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_60/actor/extra_state_world_size_4_rank_3.ptWeights15.1 KB dcf40427ed27
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_60/actor/huggingface/model-00001-of-00007.safetensorsWeights5.0 GB 669020dbfde2
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_60/actor/huggingface/model-00002-of-00007.safetensorsWeights5.0 GB a16d3fd9791c
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_60/actor/huggingface/model-00003-of-00007.safetensorsWeights4.9 GB ff48ab3bc821
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_60/actor/huggingface/model-00004-of-00007.safetensorsWeights5.0 GB 33a702db4c6c
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_60/actor/huggingface/model-00005-of-00007.safetensorsWeights5.0 GB b17ffaa7de38
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_60/actor/huggingface/model-00006-of-00007.safetensorsWeights4.9 GB 83201d3c9273
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_60/actor/huggingface/model-00007-of-00007.safetensorsWeights3.4 GB cf1b1a0be632
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_60/actor/model_world_size_4_rank_0.ptWeights8.3 GB d4f3c90510af
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_60/actor/model_world_size_4_rank_1.ptWeights8.3 GB fe8305fcd74f
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_60/actor/model_world_size_4_rank_2.ptWeights8.3 GB 9c648aabd08f
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_60/actor/model_world_size_4_rank_3.ptWeights8.3 GB 357c2ad62285
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_60/data.ptWeights1.8 KB 98bda8f5bc73
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_90/actor/extra_state_world_size_4_rank_0.ptWeights15.1 KB c4c3fe835e27
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_90/actor/extra_state_world_size_4_rank_1.ptWeights15.1 KB efc46fd4361d
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_90/actor/extra_state_world_size_4_rank_2.ptWeights15.1 KB 194b63349b82
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_90/actor/extra_state_world_size_4_rank_3.ptWeights15.1 KB 2d81adc57119
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_90/actor/huggingface/model-00001-of-00007.safetensorsWeights5.0 GB 69399acf43a3
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_90/actor/huggingface/model-00002-of-00007.safetensorsWeights5.0 GB 92cced5ae537
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_90/actor/huggingface/model-00003-of-00007.safetensorsWeights4.9 GB 572768663211
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_90/actor/huggingface/model-00004-of-00007.safetensorsWeights5.0 GB 23a3b1b9cdf3
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_90/actor/huggingface/model-00005-of-00007.safetensorsWeights5.0 GB dab23f4c8af9
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_90/actor/huggingface/model-00006-of-00007.safetensorsWeights4.9 GB 7f2e346bc2c4
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_90/actor/huggingface/model-00007-of-00007.safetensorsWeights3.4 GB 61b1d4826907
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_90/actor/model_world_size_4_rank_0.ptWeights8.3 GB f822abf35c2a
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_90/actor/model_world_size_4_rank_1.ptWeights8.3 GB 3f5344c569af
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_90/actor/model_world_size_4_rank_2.ptWeights8.3 GB 61714ce34f75
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_90/actor/model_world_size_4_rank_3.ptWeights8.3 GB 2b299da51b99
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_90/data.ptWeights1.8 KB caba559959f3
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen3vl-4b-instruct-grpo-b64-mb64-n8-alpha2-sysv1-step150-4gpu-fp32/global_step_30/actor/extra_state_world_size_4_rank_0.ptWeights15.1 KB d73ac65b297e
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen3vl-4b-instruct-grpo-b64-mb64-n8-alpha2-sysv1-step150-4gpu-fp32/global_step_30/actor/extra_state_world_size_4_rank_1.ptWeights15.1 KB 64ad6bce704d
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen3vl-4b-instruct-grpo-b64-mb64-n8-alpha2-sysv1-step150-4gpu-fp32/global_step_30/actor/extra_state_world_size_4_rank_2.ptWeights15.1 KB 3cdbe10b6ced
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen3vl-4b-instruct-grpo-b64-mb64-n8-alpha2-sysv1-step150-4gpu-fp32/global_step_30/actor/extra_state_world_size_4_rank_3.ptWeights15.1 KB 37c15092db97
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen3vl-4b-instruct-grpo-b64-mb64-n8-alpha2-sysv1-step150-4gpu-fp32/global_step_30/actor/huggingface/model-00001-of-00004.safetensorsWeights4.9 GB 6b103b864359
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen3vl-4b-instruct-grpo-b64-mb64-n8-alpha2-sysv1-step150-4gpu-fp32/global_step_30/actor/huggingface/model-00002-of-00004.safetensorsWeights4.9 GB 331f6c9cd2c8
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen3vl-4b-instruct-grpo-b64-mb64-n8-alpha2-sysv1-step150-4gpu-fp32/global_step_30/actor/huggingface/model-00003-of-00004.safetensorsWeights4.9 GB 363b216aff87
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen3vl-4b-instruct-grpo-b64-mb64-n8-alpha2-sysv1-step150-4gpu-fp32/global_step_30/actor/huggingface/model-00004-of-00004.safetensorsWeights4.5 GB 1470cdf2e273
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen3vl-4b-instruct-grpo-b64-mb64-n8-alpha2-sysv1-step150-4gpu-fp32/global_step_30/actor/model_world_size_4_rank_0.ptWeights4.8 GB d96f18c1c54d
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen3vl-4b-instruct-grpo-b64-mb64-n8-alpha2-sysv1-step150-4gpu-fp32/global_step_30/actor/model_world_size_4_rank_1.ptWeights4.8 GB 618538453d56
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen3vl-4b-instruct-grpo-b64-mb64-n8-alpha2-sysv1-step150-4gpu-fp32/global_step_30/actor/model_world_size_4_rank_2.ptWeights4.8 GB efab27e40018
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen3vl-4b-instruct-grpo-b64-mb64-n8-alpha2-sysv1-step150-4gpu-fp32/global_step_30/actor/model_world_size_4_rank_3.ptWeights4.8 GB 100da7a4cb32
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen3vl-4b-instruct-grpo-b64-mb64-n8-alpha2-sysv1-step150-4gpu-fp32/global_step_30/data.ptWeights1.8 KB 6643a78c6350
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen3vl-4b-instruct-grpo-b64-mb64-n8-alpha2-sysv1-step150-4gpu-fp32/global_step_60/actor/extra_state_world_size_4_rank_0.ptWeights15.1 KB 7c88cdf37d85
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen3vl-4b-instruct-grpo-b64-mb64-n8-alpha2-sysv1-step150-4gpu-fp32/global_step_60/actor/extra_state_world_size_4_rank_1.ptWeights15.1 KB bf62a3c1413d
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen3vl-4b-instruct-grpo-b64-mb64-n8-alpha2-sysv1-step150-4gpu-fp32/global_step_60/actor/extra_state_world_size_4_rank_2.ptWeights15.1 KB 4e4e92c05ba5
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen3vl-4b-instruct-grpo-b64-mb64-n8-alpha2-sysv1-step150-4gpu-fp32/global_step_60/actor/extra_state_world_size_4_rank_3.ptWeights15.1 KB dcf40427ed27
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen3vl-4b-instruct-grpo-b64-mb64-n8-alpha2-sysv1-step150-4gpu-fp32/global_step_60/actor/huggingface/model-00001-of-00004.safetensorsWeights4.9 GB c577d22c5bad
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen3vl-4b-instruct-grpo-b64-mb64-n8-alpha2-sysv1-step150-4gpu-fp32/global_step_60/actor/huggingface/model-00002-of-00004.safetensorsWeights4.9 GB a83bc5ec7c8d
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen3vl-4b-instruct-grpo-b64-mb64-n8-alpha2-sysv1-step150-4gpu-fp32/global_step_60/actor/huggingface/model-00003-of-00004.safetensorsWeights4.9 GB 50d6f7ca7b18
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen3vl-4b-instruct-grpo-b64-mb64-n8-alpha2-sysv1-step150-4gpu-fp32/global_step_60/actor/huggingface/model-00004-of-00004.safetensorsWeights4.5 GB 66f0762c5ed0
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen3vl-4b-instruct-grpo-b64-mb64-n8-alpha2-sysv1-step150-4gpu-fp32/global_step_60/actor/model_world_size_4_rank_0.ptWeights4.8 GB 0f8a75b90c94
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen3vl-4b-instruct-grpo-b64-mb64-n8-alpha2-sysv1-step150-4gpu-fp32/global_step_60/actor/model_world_size_4_rank_1.ptWeights4.8 GB b37e5918bf43
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen3vl-4b-instruct-grpo-b64-mb64-n8-alpha2-sysv1-step150-4gpu-fp32/global_step_60/actor/model_world_size_4_rank_2.ptWeights4.8 GB 7d2cf4b2c02c
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen3vl-4b-instruct-grpo-b64-mb64-n8-alpha2-sysv1-step150-4gpu-fp32/global_step_60/actor/model_world_size_4_rank_3.ptWeights4.8 GB ae947bec39c2
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen3vl-4b-instruct-grpo-b64-mb64-n8-alpha2-sysv1-step150-4gpu-fp32/global_step_60/data.ptWeights1.8 KB dd7b40a12db2
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen3vl-4b-instruct-grpo-b64-mb64-n8-alpha2-sysv1-step150-4gpu-fp32/global_step_75/actor/extra_state_world_size_4_rank_0.ptWeights15.1 KB 7e606b725c40
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen3vl-4b-instruct-grpo-b64-mb64-n8-alpha2-sysv1-step150-4gpu-fp32/global_step_75/actor/extra_state_world_size_4_rank_1.ptWeights15.1 KB e37dbf6ed9c9
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen3vl-4b-instruct-grpo-b64-mb64-n8-alpha2-sysv1-step150-4gpu-fp32/global_step_75/actor/extra_state_world_size_4_rank_2.ptWeights15.1 KB de075d476c34
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen3vl-4b-instruct-grpo-b64-mb64-n8-alpha2-sysv1-step150-4gpu-fp32/global_step_75/actor/extra_state_world_size_4_rank_3.ptWeights15.1 KB be4f7f585ddb
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen3vl-4b-instruct-grpo-b64-mb64-n8-alpha2-sysv1-step150-4gpu-fp32/global_step_75/actor/huggingface/model-00001-of-00004.safetensorsWeights4.9 GB 30f4ea1022dd
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen3vl-4b-instruct-grpo-b64-mb64-n8-alpha2-sysv1-step150-4gpu-fp32/global_step_75/actor/huggingface/model-00002-of-00004.safetensorsWeights4.9 GB e6bc234a99c2
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen3vl-4b-instruct-grpo-b64-mb64-n8-alpha2-sysv1-step150-4gpu-fp32/global_step_75/actor/huggingface/model-00003-of-00004.safetensorsWeights4.9 GB 6d67fb601dd5
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen3vl-4b-instruct-grpo-b64-mb64-n8-alpha2-sysv1-step150-4gpu-fp32/global_step_75/actor/huggingface/model-00004-of-00004.safetensorsWeights4.5 GB 6875296a8f78
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen3vl-4b-instruct-grpo-b64-mb64-n8-alpha2-sysv1-step150-4gpu-fp32/global_step_75/actor/model_world_size_4_rank_0.ptWeights4.8 GB e2077f89baaf
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen3vl-4b-instruct-grpo-b64-mb64-n8-alpha2-sysv1-step150-4gpu-fp32/global_step_75/actor/model_world_size_4_rank_1.ptWeights4.8 GB 488071fbf9ea
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen3vl-4b-instruct-grpo-b64-mb64-n8-alpha2-sysv1-step150-4gpu-fp32/global_step_75/actor/model_world_size_4_rank_2.ptWeights4.8 GB fdc6e9219e73
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen3vl-4b-instruct-grpo-b64-mb64-n8-alpha2-sysv1-step150-4gpu-fp32/global_step_75/actor/model_world_size_4_rank_3.ptWeights4.8 GB 73ec15b10153
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen3vl-4b-instruct-grpo-b64-mb64-n8-alpha2-sysv1-step150-4gpu-fp32/global_step_75/actor/optim_world_size_4_rank_0.ptWeights8.9 GB 3618aeae122c
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen3vl-4b-instruct-grpo-b64-mb64-n8-alpha2-sysv1-step150-4gpu-fp32/global_step_75/actor/optim_world_size_4_rank_1.ptWeights8.9 GB 21a2cd397070
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen3vl-4b-instruct-grpo-b64-mb64-n8-alpha2-sysv1-step150-4gpu-fp32/global_step_75/actor/optim_world_size_4_rank_2.ptWeights8.9 GB f0c9d5bbd5be
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen3vl-4b-instruct-grpo-b64-mb64-n8-alpha2-sysv1-step150-4gpu-fp32/global_step_75/actor/optim_world_size_4_rank_3.ptWeights8.9 GB 4c8c7d897e49
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen3vl-4b-instruct-grpo-b64-mb64-n8-alpha2-sysv1-step150-4gpu-fp32/global_step_75/data.ptWeights1.8 KB d03f847be3cf
experiments/weak_to_strong/agent/ours/260920-pixel-qwen25vl-7b-warmstart-oprd-t3b-step90-lp0p5-lm0to0p5-s45-b64-mb64-n8-sysv1-step150-4gpu-fp32-toolmatch-v2/global_step_30/actor/extra_state_world_size_4_rank_0.ptWeights15.1 KB d73ac65b297e
experiments/weak_to_strong/agent/ours/260920-pixel-qwen25vl-7b-warmstart-oprd-t3b-step90-lp0p5-lm0to0p5-s45-b64-mb64-n8-sysv1-step150-4gpu-fp32-toolmatch-v2/global_step_30/actor/extra_state_world_size_4_rank_1.ptWeights15.1 KB 64ad6bce704d
experiments/weak_to_strong/agent/ours/260920-pixel-qwen25vl-7b-warmstart-oprd-t3b-step90-lp0p5-lm0to0p5-s45-b64-mb64-n8-sysv1-step150-4gpu-fp32-toolmatch-v2/global_step_30/actor/extra_state_world_size_4_rank_2.ptWeights15.1 KB 3cdbe10b6ced
experiments/weak_to_strong/agent/ours/260920-pixel-qwen25vl-7b-warmstart-oprd-t3b-step90-lp0p5-lm0to0p5-s45-b64-mb64-n8-sysv1-step150-4gpu-fp32-toolmatch-v2/global_step_30/actor/extra_state_world_size_4_rank_3.ptWeights15.1 KB 37c15092db97
experiments/weak_to_strong/agent/ours/260920-pixel-qwen25vl-7b-warmstart-oprd-t3b-step90-lp0p5-lm0to0p5-s45-b64-mb64-n8-sysv1-step150-4gpu-fp32-toolmatch-v2/global_step_30/actor/huggingface/model-00001-of-00007.safetensorsWeights5.0 GB 245ef4a79f02
experiments/weak_to_strong/agent/ours/260920-pixel-qwen25vl-7b-warmstart-oprd-t3b-step90-lp0p5-lm0to0p5-s45-b64-mb64-n8-sysv1-step150-4gpu-fp32-toolmatch-v2/global_step_30/actor/huggingface/model-00002-of-00007.safetensorsWeights5.0 GB baa564075032
experiments/weak_to_strong/agent/ours/260920-pixel-qwen25vl-7b-warmstart-oprd-t3b-step90-lp0p5-lm0to0p5-s45-b64-mb64-n8-sysv1-step150-4gpu-fp32-toolmatch-v2/global_step_30/actor/huggingface/model-00003-of-00007.safetensorsWeights4.9 GB 077e9ee11fcd
experiments/weak_to_strong/agent/ours/260920-pixel-qwen25vl-7b-warmstart-oprd-t3b-step90-lp0p5-lm0to0p5-s45-b64-mb64-n8-sysv1-step150-4gpu-fp32-toolmatch-v2/global_step_30/actor/huggingface/model-00004-of-00007.safetensorsWeights5.0 GB 8752f042e77d
experiments/weak_to_strong/agent/ours/260920-pixel-qwen25vl-7b-warmstart-oprd-t3b-step90-lp0p5-lm0to0p5-s45-b64-mb64-n8-sysv1-step150-4gpu-fp32-toolmatch-v2/global_step_30/actor/huggingface/model-00005-of-00007.safetensorsWeights5.0 GB 47b76bf78882
experiments/weak_to_strong/agent/ours/260920-pixel-qwen25vl-7b-warmstart-oprd-t3b-step90-lp0p5-lm0to0p5-s45-b64-mb64-n8-sysv1-step150-4gpu-fp32-toolmatch-v2/global_step_30/actor/huggingface/model-00006-of-00007.safetensorsWeights4.9 GB 533bf3432c0c
experiments/weak_to_strong/agent/ours/260920-pixel-qwen25vl-7b-warmstart-oprd-t3b-step90-lp0p5-lm0to0p5-s45-b64-mb64-n8-sysv1-step150-4gpu-fp32-toolmatch-v2/global_step_30/actor/huggingface/model-00007-of-00007.safetensorsWeights3.4 GB 5f06c7fefe87
experiments/weak_to_strong/agent/ours/260920-pixel-qwen25vl-7b-warmstart-oprd-t3b-step90-lp0p5-lm0to0p5-s45-b64-mb64-n8-sysv1-step150-4gpu-fp32-toolmatch-v2/global_step_30/actor/model_world_size_4_rank_0.ptWeights8.3 GB 08b02d2ae989
experiments/weak_to_strong/agent/ours/260920-pixel-qwen25vl-7b-warmstart-oprd-t3b-step90-lp0p5-lm0to0p5-s45-b64-mb64-n8-sysv1-step150-4gpu-fp32-toolmatch-v2/global_step_30/actor/model_world_size_4_rank_1.ptWeights8.3 GB 911ca7659881
experiments/weak_to_strong/agent/ours/260920-pixel-qwen25vl-7b-warmstart-oprd-t3b-step90-lp0p5-lm0to0p5-s45-b64-mb64-n8-sysv1-step150-4gpu-fp32-toolmatch-v2/global_step_30/actor/model_world_size_4_rank_2.ptWeights8.3 GB 577c614b4813
experiments/weak_to_strong/agent/ours/260920-pixel-qwen25vl-7b-warmstart-oprd-t3b-step90-lp0p5-lm0to0p5-s45-b64-mb64-n8-sysv1-step150-4gpu-fp32-toolmatch-v2/global_step_30/actor/model_world_size_4_rank_3.ptWeights8.3 GB f9dec8101f61
experiments/weak_to_strong/agent/ours/260920-pixel-qwen25vl-7b-warmstart-oprd-t3b-step90-lp0p5-lm0to0p5-s45-b64-mb64-n8-sysv1-step150-4gpu-fp32-toolmatch-v2/global_step_30/actor/optim_world_size_4_rank_0.ptWeights16.6 GB ce6df744057b
experiments/weak_to_strong/agent/ours/260920-pixel-qwen25vl-7b-warmstart-oprd-t3b-step90-lp0p5-lm0to0p5-s45-b64-mb64-n8-sysv1-step150-4gpu-fp32-toolmatch-v2/global_step_30/actor/optim_world_size_4_rank_1.ptWeights16.6 GB e7493093a431
experiments/weak_to_strong/agent/ours/260920-pixel-qwen25vl-7b-warmstart-oprd-t3b-step90-lp0p5-lm0to0p5-s45-b64-mb64-n8-sysv1-step150-4gpu-fp32-toolmatch-v2/global_step_30/actor/optim_world_size_4_rank_2.ptWeights16.6 GB 71b7d03f1c5f
experiments/weak_to_strong/agent/ours/260920-pixel-qwen25vl-7b-warmstart-oprd-t3b-step90-lp0p5-lm0to0p5-s45-b64-mb64-n8-sysv1-step150-4gpu-fp32-toolmatch-v2/global_step_30/actor/optim_world_size_4_rank_3.ptWeights16.6 GB 46f9e3206df9
experiments/weak_to_strong/agent/ours/260920-pixel-qwen25vl-7b-warmstart-oprd-t3b-step90-lp0p5-lm0to0p5-s45-b64-mb64-n8-sysv1-step150-4gpu-fp32-toolmatch-v2/global_step_30/data.ptWeights1.8 KB d129cbf2896f
experiments/weak_to_strong/agent/ours/260920-pixel-qwen25vl-7b-warmstart-oprd-t3b-step90-lp0p5-lm0to0p5-s45-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_15/actor/extra_state_world_size_4_rank_0.ptWeights15.1 KB b29d85216824
experiments/weak_to_strong/agent/ours/260920-pixel-qwen25vl-7b-warmstart-oprd-t3b-step90-lp0p5-lm0to0p5-s45-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_15/actor/extra_state_world_size_4_rank_1.ptWeights15.1 KB 2e3d7680fbe0
experiments/weak_to_strong/agent/ours/260920-pixel-qwen25vl-7b-warmstart-oprd-t3b-step90-lp0p5-lm0to0p5-s45-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_15/actor/extra_state_world_size_4_rank_2.ptWeights15.1 KB d0c25fbc60bd
experiments/weak_to_strong/agent/ours/260920-pixel-qwen25vl-7b-warmstart-oprd-t3b-step90-lp0p5-lm0to0p5-s45-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_15/actor/extra_state_world_size_4_rank_3.ptWeights15.1 KB a0836382c9e7
experiments/weak_to_strong/agent/ours/260920-pixel-qwen25vl-7b-warmstart-oprd-t3b-step90-lp0p5-lm0to0p5-s45-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_15/actor/huggingface/model-00001-of-00007.safetensorsWeights5.0 GB 089c7e087289
experiments/weak_to_strong/agent/ours/260920-pixel-qwen25vl-7b-warmstart-oprd-t3b-step90-lp0p5-lm0to0p5-s45-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_15/actor/huggingface/model-00002-of-00007.safetensorsWeights5.0 GB 3d2e5930241f
experiments/weak_to_strong/agent/ours/260920-pixel-qwen25vl-7b-warmstart-oprd-t3b-step90-lp0p5-lm0to0p5-s45-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_15/actor/huggingface/model-00003-of-00007.safetensorsWeights4.9 GB ecd9e91ad251
experiments/weak_to_strong/agent/ours/260920-pixel-qwen25vl-7b-warmstart-oprd-t3b-step90-lp0p5-lm0to0p5-s45-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_15/actor/huggingface/model-00004-of-00007.safetensorsWeights5.0 GB 89ee633f97be
experiments/weak_to_strong/agent/ours/260920-pixel-qwen25vl-7b-warmstart-oprd-t3b-step90-lp0p5-lm0to0p5-s45-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_15/actor/huggingface/model-00005-of-00007.safetensorsWeights5.0 GB 367949acd074
experiments/weak_to_strong/agent/ours/260920-pixel-qwen25vl-7b-warmstart-oprd-t3b-step90-lp0p5-lm0to0p5-s45-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_15/actor/huggingface/model-00006-of-00007.safetensorsWeights4.9 GB 883bf48a147c
experiments/weak_to_strong/agent/ours/260920-pixel-qwen25vl-7b-warmstart-oprd-t3b-step90-lp0p5-lm0to0p5-s45-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_15/actor/huggingface/model-00007-of-00007.safetensorsWeights3.4 GB 6aa1e9004d6b
experiments/weak_to_strong/agent/ours/260920-pixel-qwen25vl-7b-warmstart-oprd-t3b-step90-lp0p5-lm0to0p5-s45-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_15/actor/model_world_size_4_rank_0.ptWeights8.3 GB 84ee60489de9
experiments/weak_to_strong/agent/ours/260920-pixel-qwen25vl-7b-warmstart-oprd-t3b-step90-lp0p5-lm0to0p5-s45-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_15/actor/model_world_size_4_rank_1.ptWeights8.3 GB 8a814ae90b1c
experiments/weak_to_strong/agent/ours/260920-pixel-qwen25vl-7b-warmstart-oprd-t3b-step90-lp0p5-lm0to0p5-s45-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_15/actor/model_world_size_4_rank_2.ptWeights8.3 GB 96bf8bbaba92
experiments/weak_to_strong/agent/ours/260920-pixel-qwen25vl-7b-warmstart-oprd-t3b-step90-lp0p5-lm0to0p5-s45-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_15/actor/model_world_size_4_rank_3.ptWeights8.3 GB 8dcb10a1cef3
experiments/weak_to_strong/agent/ours/260920-pixel-qwen25vl-7b-warmstart-oprd-t3b-step90-lp0p5-lm0to0p5-s45-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_15/actor/optim_world_size_4_rank_0.ptWeights16.6 GB 92e0c06f0902
experiments/weak_to_strong/agent/ours/260920-pixel-qwen25vl-7b-warmstart-oprd-t3b-step90-lp0p5-lm0to0p5-s45-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_15/actor/optim_world_size_4_rank_1.ptWeights16.6 GB 081770555998
experiments/weak_to_strong/agent/ours/260920-pixel-qwen25vl-7b-warmstart-oprd-t3b-step90-lp0p5-lm0to0p5-s45-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_15/actor/optim_world_size_4_rank_2.ptWeights16.6 GB bad93361a61f
experiments/weak_to_strong/agent/ours/260920-pixel-qwen25vl-7b-warmstart-oprd-t3b-step90-lp0p5-lm0to0p5-s45-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_15/actor/optim_world_size_4_rank_3.ptWeights16.6 GB fb64280bf345
experiments/weak_to_strong/agent/ours/260920-pixel-qwen25vl-7b-warmstart-oprd-t3b-step90-lp0p5-lm0to0p5-s45-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_15/data.ptWeights1.8 KB 79211a3035a4
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_105/actor/extra_state_world_size_2_rank_0.ptWeights15.2 KB 83abee072574
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_105/actor/extra_state_world_size_2_rank_1.ptWeights15.2 KB 52d5faba1a5b
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_105/actor/model_world_size_2_rank_0.ptWeights4.1 GB 4d6ea6d29e8f
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_105/actor/model_world_size_2_rank_1.ptWeights4.1 GB fb18cc6ba07d
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_105/data.ptWeights7.0 KB 09a40d508dab
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_120/actor/extra_state_world_size_2_rank_0.ptWeights15.2 KB 37149f7df567
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_120/actor/extra_state_world_size_2_rank_1.ptWeights15.2 KB 59467fe8599f
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_120/actor/model_world_size_2_rank_0.ptWeights4.1 GB cce7fa53e167
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_120/actor/model_world_size_2_rank_1.ptWeights4.1 GB 13718c58061a
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_120/data.ptWeights7.0 KB a66fc981d533
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_135/actor/extra_state_world_size_2_rank_0.ptWeights15.2 KB b21f7c904f41
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_135/actor/extra_state_world_size_2_rank_1.ptWeights15.2 KB fbb2c777b934
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_135/actor/model_world_size_2_rank_0.ptWeights4.1 GB 268bff8944a9
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_135/actor/model_world_size_2_rank_1.ptWeights4.1 GB 9d7d6dadc14a
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_135/data.ptWeights7.0 KB 30fa55d9f0ad
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_15/actor/extra_state_world_size_2_rank_0.ptWeights15.2 KB 657a503452b2
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_15/actor/extra_state_world_size_2_rank_1.ptWeights15.2 KB 4469097f9639
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_15/actor/model_world_size_2_rank_0.ptWeights4.1 GB 4296cdb1904d
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_15/actor/model_world_size_2_rank_1.ptWeights4.1 GB 234f5eb2f974
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_15/data.ptWeights7.0 KB dd157db893bc
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_150/actor/extra_state_world_size_2_rank_0.ptWeights15.2 KB 9de96a68e3a7
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_150/actor/extra_state_world_size_2_rank_1.ptWeights15.2 KB 4d10db14bf69
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_150/actor/model_world_size_2_rank_0.ptWeights4.1 GB 4d5c0ad022cb
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_150/actor/model_world_size_2_rank_1.ptWeights4.1 GB 957a493ccfd5
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_150/data.ptWeights7.0 KB 6d96285c52da
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_180/actor/extra_state_world_size_2_rank_0.ptWeights15.2 KB cc0bb131581e
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_180/actor/extra_state_world_size_2_rank_1.ptWeights15.2 KB ff37156ed44c
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_180/actor/model_world_size_2_rank_0.ptWeights4.1 GB c66836f108be
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_180/actor/model_world_size_2_rank_1.ptWeights4.1 GB 67f251e63ff1
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_180/data.ptWeights7.0 KB 18b8448c14d3
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_210/actor/extra_state_world_size_2_rank_0.ptWeights15.2 KB d428758ac69f
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_210/actor/extra_state_world_size_2_rank_1.ptWeights15.2 KB 00568a341a2a
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_210/actor/model_world_size_2_rank_0.ptWeights4.1 GB 93699c8f5c1e
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_210/actor/model_world_size_2_rank_1.ptWeights4.1 GB dc7910280ca9
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_210/data.ptWeights7.0 KB fcf0c575a7cc
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_240/actor/extra_state_world_size_2_rank_0.ptWeights15.2 KB caad68f1a853
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_240/actor/extra_state_world_size_2_rank_1.ptWeights15.2 KB c659c38603e6
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_240/actor/model_world_size_2_rank_0.ptWeights4.1 GB 22a71de06d35
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_240/actor/model_world_size_2_rank_1.ptWeights4.1 GB 8b0a1f55d875
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_240/actor/optim_world_size_2_rank_0.ptWeights6.9 GB 57fe14e6007a
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_240/actor/optim_world_size_2_rank_1.ptWeights6.9 GB e5f804869b02
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_240/data.ptWeights7.0 KB b04e6f2b9a5f
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_30/actor/extra_state_world_size_2_rank_0.ptWeights15.2 KB a7e15981962c
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_30/actor/extra_state_world_size_2_rank_1.ptWeights15.2 KB eb5307e44bb3
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_30/actor/model_world_size_2_rank_0.ptWeights4.1 GB 5b35bb1b8866
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_30/actor/model_world_size_2_rank_1.ptWeights4.1 GB 968dbd136f86
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_30/data.ptWeights7.0 KB 3d3cf8f5fa73
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_45/actor/extra_state_world_size_2_rank_0.ptWeights15.2 KB 902dc9919a2c
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_45/actor/extra_state_world_size_2_rank_1.ptWeights15.2 KB 2b7920e1abcd
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_45/actor/model_world_size_2_rank_0.ptWeights4.1 GB 2f003d15b3b1
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_45/actor/model_world_size_2_rank_1.ptWeights4.1 GB b599c4414fdb
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_45/data.ptWeights7.0 KB fc55ca80ba58
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_60/actor/extra_state_world_size_2_rank_0.ptWeights15.2 KB 12849cb3d054
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_60/actor/extra_state_world_size_2_rank_1.ptWeights15.2 KB 8ee646b2c6be
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_60/actor/model_world_size_2_rank_0.ptWeights4.1 GB ed26a29af318
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_60/actor/model_world_size_2_rank_1.ptWeights4.1 GB a6c2215e7d88
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_60/data.ptWeights7.0 KB fbed549ebe24
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_75/actor/extra_state_world_size_2_rank_0.ptWeights15.2 KB 6a777de1b6a4
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_75/actor/extra_state_world_size_2_rank_1.ptWeights15.2 KB 7fdc69a02034
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_75/actor/model_world_size_2_rank_0.ptWeights4.1 GB cc0ea840fa47
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_75/actor/model_world_size_2_rank_1.ptWeights4.1 GB b6480f6e53aa
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_75/data.ptWeights7.0 KB 24aeb2207229
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_90/actor/extra_state_world_size_2_rank_0.ptWeights15.2 KB 00c20c91ed6a
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_90/actor/extra_state_world_size_2_rank_1.ptWeights15.2 KB 4a8977c6f45d
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_90/actor/model_world_size_2_rank_0.ptWeights4.1 GB a14ca3878f8f
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_90/actor/model_world_size_2_rank_1.ptWeights4.1 GB 13bc59c05fc0
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_90/data.ptWeights7.0 KB cbda6dcb9d24
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-4b-base-len20480-overlong4k-pf1p0-dp2-step150-b64-mb32-nosystem-save15-eval15-bestval-finalopt-aime24/global_step_150/actor/extra_state_world_size_2_rank_0.ptWeights15.3 KB 5ede5ed69fa6
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-4b-base-len20480-overlong4k-pf1p0-dp2-step150-b64-mb32-nosystem-save15-eval15-bestval-finalopt-aime24/global_step_150/actor/extra_state_world_size_2_rank_1.ptWeights15.3 KB 692548cb1ba8
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-4b-base-len20480-overlong4k-pf1p0-dp2-step150-b64-mb32-nosystem-save15-eval15-bestval-finalopt-aime24/global_step_150/actor/model_world_size_2_rank_0.ptWeights8.8 GB 3bd097c4a80b
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-4b-base-len20480-overlong4k-pf1p0-dp2-step150-b64-mb32-nosystem-save15-eval15-bestval-finalopt-aime24/global_step_150/actor/model_world_size_2_rank_1.ptWeights8.8 GB 86941016ec42
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-4b-base-len20480-overlong4k-pf1p0-dp2-step150-b64-mb32-nosystem-save15-eval15-bestval-finalopt-aime24/global_step_150/actor/optim_world_size_2_rank_0.ptWeights16.1 GB 5b73b07b4101
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-4b-base-len20480-overlong4k-pf1p0-dp2-step150-b64-mb32-nosystem-save15-eval15-bestval-finalopt-aime24/global_step_150/actor/optim_world_size_2_rank_1.ptWeights16.1 GB 08cd1bd6fd61
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-4b-base-len20480-overlong4k-pf1p0-dp2-step150-b64-mb32-nosystem-save15-eval15-bestval-finalopt-aime24/global_step_150/data.ptWeights7.0 KB 6d96285c52da
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-4b-len20480-overlong4k-pf1p0-dp2-step150-b64-mb64-save15-eval15-bestval-finalopt-aime24/global_step_150/actor/extra_state_world_size_2_rank_0.ptWeights15.3 KB 840ab5cbb3a9
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-4b-len20480-overlong4k-pf1p0-dp2-step150-b64-mb64-save15-eval15-bestval-finalopt-aime24/global_step_150/actor/extra_state_world_size_2_rank_1.ptWeights15.3 KB aa44567b0ab8
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-4b-len20480-overlong4k-pf1p0-dp2-step150-b64-mb64-save15-eval15-bestval-finalopt-aime24/global_step_150/actor/model_world_size_2_rank_0.ptWeights8.8 GB 3ca27a70c064
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-4b-len20480-overlong4k-pf1p0-dp2-step150-b64-mb64-save15-eval15-bestval-finalopt-aime24/global_step_150/actor/model_world_size_2_rank_1.ptWeights8.8 GB 82c5b4b92060
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-4b-len20480-overlong4k-pf1p0-dp2-step150-b64-mb64-save15-eval15-bestval-finalopt-aime24/global_step_150/actor/optim_world_size_2_rank_0.ptWeights16.1 GB 819b456a0570
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-4b-len20480-overlong4k-pf1p0-dp2-step150-b64-mb64-save15-eval15-bestval-finalopt-aime24/global_step_150/actor/optim_world_size_2_rank_1.ptWeights16.1 GB bf7f7b5dc147
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-4b-len20480-overlong4k-pf1p0-dp2-step150-b64-mb64-save15-eval15-bestval-finalopt-aime24/global_step_150/data.ptWeights7.0 KB 6d96285c52da
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-8b-base-len20480-overlong4k-pf1p0-dp2-step150-b64-mb32-nosystem-save30-eval15-bestval-finalopt-aime24/global_step_150/actor/extra_state_world_size_2_rank_0.ptWeights15.3 KB b263a46bc387
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-8b-base-len20480-overlong4k-pf1p0-dp2-step150-b64-mb32-nosystem-save30-eval15-bestval-finalopt-aime24/global_step_150/actor/extra_state_world_size_2_rank_1.ptWeights15.3 KB cebc4e456e7f
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-8b-base-len20480-overlong4k-pf1p0-dp2-step150-b64-mb32-nosystem-save30-eval15-bestval-finalopt-aime24/global_step_150/actor/model_world_size_2_rank_0.ptWeights16.4 GB ddd7a432a8e4
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-8b-base-len20480-overlong4k-pf1p0-dp2-step150-b64-mb32-nosystem-save30-eval15-bestval-finalopt-aime24/global_step_150/actor/model_world_size_2_rank_1.ptWeights16.4 GB 89244103d4b5
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-8b-base-len20480-overlong4k-pf1p0-dp2-step150-b64-mb32-nosystem-save30-eval15-bestval-finalopt-aime24/global_step_150/actor/optim_world_size_2_rank_0.ptWeights32.8 GB 47f20d04a797
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-8b-base-len20480-overlong4k-pf1p0-dp2-step150-b64-mb32-nosystem-save30-eval15-bestval-finalopt-aime24/global_step_150/actor/optim_world_size_2_rank_1.ptWeights32.8 GB ae70b4d49466
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-8b-base-len20480-overlong4k-pf1p0-dp2-step150-b64-mb32-nosystem-save30-eval15-bestval-finalopt-aime24/global_step_150/data.ptWeights7.0 KB 6d96285c52da
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-8b-base-len20480-overlong4k-pf1p0-dp2-step150-b64-mb32-nosystem-save30-eval15-bestval-finalopt-aime24/global_step_30/actor/extra_state_world_size_2_rank_0.ptWeights15.3 KB 9a7e126c841e
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-8b-base-len20480-overlong4k-pf1p0-dp2-step150-b64-mb32-nosystem-save30-eval15-bestval-finalopt-aime24/global_step_30/actor/extra_state_world_size_2_rank_1.ptWeights15.3 KB ceee520c9bb9
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-8b-base-len20480-overlong4k-pf1p0-dp2-step150-b64-mb32-nosystem-save30-eval15-bestval-finalopt-aime24/global_step_30/actor/model_world_size_2_rank_0.ptWeights16.4 GB 93225fab93be
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-8b-base-len20480-overlong4k-pf1p0-dp2-step150-b64-mb32-nosystem-save30-eval15-bestval-finalopt-aime24/global_step_30/actor/model_world_size_2_rank_1.ptWeights16.4 GB 86b491e51d33
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-8b-base-len20480-overlong4k-pf1p0-dp2-step150-b64-mb32-nosystem-save30-eval15-bestval-finalopt-aime24/global_step_30/data.ptWeights7.0 KB 3d3cf8f5fa73
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-8b-len20480-overlong4k-pf1p0-dp2-step150-b64-mb64-save30-eval15-bestval-finalopt-aime24/global_step_135/actor/extra_state_world_size_2_rank_0.ptWeights15.3 KB f3a27fa05212
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-8b-len20480-overlong4k-pf1p0-dp2-step150-b64-mb64-save30-eval15-bestval-finalopt-aime24/global_step_135/actor/extra_state_world_size_2_rank_1.ptWeights15.3 KB d04833223504
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-8b-len20480-overlong4k-pf1p0-dp2-step150-b64-mb64-save30-eval15-bestval-finalopt-aime24/global_step_135/actor/model_world_size_2_rank_0.ptWeights16.4 GB c24e6633dbc3
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-8b-len20480-overlong4k-pf1p0-dp2-step150-b64-mb64-save30-eval15-bestval-finalopt-aime24/global_step_135/actor/model_world_size_2_rank_1.ptWeights16.4 GB 4382049846f1
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-8b-len20480-overlong4k-pf1p0-dp2-step150-b64-mb64-save30-eval15-bestval-finalopt-aime24/global_step_135/data.ptWeights7.0 KB 30fa55d9f0ad
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-8b-len20480-overlong4k-pf1p0-dp2-step150-b64-mb64-save30-eval15-bestval-finalopt-aime24/global_step_150/actor/extra_state_world_size_2_rank_0.ptWeights15.3 KB adefd4b3d0d4
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-8b-len20480-overlong4k-pf1p0-dp2-step150-b64-mb64-save30-eval15-bestval-finalopt-aime24/global_step_150/actor/extra_state_world_size_2_rank_1.ptWeights15.3 KB 607e21e80715
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-8b-len20480-overlong4k-pf1p0-dp2-step150-b64-mb64-save30-eval15-bestval-finalopt-aime24/global_step_150/actor/model_world_size_2_rank_0.ptWeights16.4 GB d77f975069dc
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-8b-len20480-overlong4k-pf1p0-dp2-step150-b64-mb64-save30-eval15-bestval-finalopt-aime24/global_step_150/actor/model_world_size_2_rank_1.ptWeights16.4 GB b4a2adbfa642
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-8b-len20480-overlong4k-pf1p0-dp2-step150-b64-mb64-save30-eval15-bestval-finalopt-aime24/global_step_150/actor/optim_world_size_2_rank_0.ptWeights32.8 GB ca8d300edfad
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-8b-len20480-overlong4k-pf1p0-dp2-step150-b64-mb64-save30-eval15-bestval-finalopt-aime24/global_step_150/actor/optim_world_size_2_rank_1.ptWeights32.8 GB 8d762dbb44cd
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-8b-len20480-overlong4k-pf1p0-dp2-step150-b64-mb64-save30-eval15-bestval-finalopt-aime24/global_step_150/data.ptWeights7.0 KB 6d96285c52da
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-8b-len20480-overlong4k-pf1p0-dp2-step150-b64-mb64-save30-eval15-bestval-finalopt-aime24/global_step_30/actor/extra_state_world_size_2_rank_0.ptWeights15.3 KB 79df8c685e02
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-8b-len20480-overlong4k-pf1p0-dp2-step150-b64-mb64-save30-eval15-bestval-finalopt-aime24/global_step_30/actor/extra_state_world_size_2_rank_1.ptWeights15.3 KB 6908f89f3c28
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-8b-len20480-overlong4k-pf1p0-dp2-step150-b64-mb64-save30-eval15-bestval-finalopt-aime24/global_step_30/actor/model_world_size_2_rank_0.ptWeights16.4 GB 1112ddc15595
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-8b-len20480-overlong4k-pf1p0-dp2-step150-b64-mb64-save30-eval15-bestval-finalopt-aime24/global_step_30/actor/model_world_size_2_rank_1.ptWeights16.4 GB df9e1fb60208
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-8b-len20480-overlong4k-pf1p0-dp2-step150-b64-mb64-save30-eval15-bestval-finalopt-aime24/global_step_30/data.ptWeights7.0 KB 3d3cf8f5fa73
experiments/weak_to_strong/math/distill_baseline/260723-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_120/actor/distill_resume_state_world_size_2_rank_0.ptWeights1.7 KB 7a717f925edd
experiments/weak_to_strong/math/distill_baseline/260723-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_120/actor/distill_resume_state_world_size_2_rank_1.ptWeights1.7 KB 609fbe569b4d
experiments/weak_to_strong/math/distill_baseline/260723-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_120/actor/distill_teacher_world_size_2_rank_0.ptWeights16.4 GB 14e8652f74b7
experiments/weak_to_strong/math/distill_baseline/260723-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_120/actor/distill_teacher_world_size_2_rank_1.ptWeights16.4 GB d8a98415e804
experiments/weak_to_strong/math/distill_baseline/260723-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_120/actor/extra_state_world_size_2_rank_0.ptWeights15.2 KB eb57bb1d793d
experiments/weak_to_strong/math/distill_baseline/260723-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_120/actor/extra_state_world_size_2_rank_1.ptWeights15.2 KB d35b9a349bfb
experiments/weak_to_strong/math/distill_baseline/260723-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_120/actor/model_world_size_2_rank_0.ptWeights4.1 GB 40e2ceb90458
experiments/weak_to_strong/math/distill_baseline/260723-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_120/actor/model_world_size_2_rank_1.ptWeights4.1 GB ff5cad9bc9bb
experiments/weak_to_strong/math/distill_baseline/260723-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_120/data.ptWeights7.0 KB a66fc981d533
experiments/weak_to_strong/math/distill_baseline/260723-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_150/actor/distill_resume_state_world_size_2_rank_0.ptWeights1.7 KB 7a717f925edd
experiments/weak_to_strong/math/distill_baseline/260723-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_150/actor/distill_resume_state_world_size_2_rank_1.ptWeights1.7 KB 609fbe569b4d
experiments/weak_to_strong/math/distill_baseline/260723-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_150/actor/distill_teacher_world_size_2_rank_0.ptWeights16.4 GB 14e8652f74b7
experiments/weak_to_strong/math/distill_baseline/260723-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_150/actor/distill_teacher_world_size_2_rank_1.ptWeights16.4 GB d8a98415e804
experiments/weak_to_strong/math/distill_baseline/260723-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_150/actor/extra_state_world_size_2_rank_0.ptWeights15.2 KB 517def2c841d
experiments/weak_to_strong/math/distill_baseline/260723-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_150/actor/extra_state_world_size_2_rank_1.ptWeights15.2 KB 5525366f40c7
experiments/weak_to_strong/math/distill_baseline/260723-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_150/actor/model_world_size_2_rank_0.ptWeights4.1 GB 389bcf9cafc4
experiments/weak_to_strong/math/distill_baseline/260723-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_150/actor/model_world_size_2_rank_1.ptWeights4.1 GB f433015023cb
experiments/weak_to_strong/math/distill_baseline/260723-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_150/actor/optim_world_size_2_rank_0.ptWeights6.9 GB 90957b1c136d
experiments/weak_to_strong/math/distill_baseline/260723-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_150/actor/optim_world_size_2_rank_1.ptWeights6.9 GB fa69667ce426
experiments/weak_to_strong/math/distill_baseline/260723-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_150/data.ptWeights7.0 KB 6d96285c52da
experiments/weak_to_strong/math/distill_baseline/260723-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_30/actor/distill_resume_state_world_size_2_rank_0.ptWeights1.7 KB 47cdb7d781ed
experiments/weak_to_strong/math/distill_baseline/260723-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_30/actor/distill_resume_state_world_size_2_rank_1.ptWeights1.7 KB 85d441f6a404
experiments/weak_to_strong/math/distill_baseline/260723-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_30/actor/distill_teacher_world_size_2_rank_0.ptWeights16.4 GB 0ea66cd5263f
experiments/weak_to_strong/math/distill_baseline/260723-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_30/actor/distill_teacher_world_size_2_rank_1.ptWeights16.4 GB 22205407ebf2
experiments/weak_to_strong/math/distill_baseline/260723-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_30/actor/extra_state_world_size_2_rank_0.ptWeights15.2 KB 8b17513a0dfd
experiments/weak_to_strong/math/distill_baseline/260723-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_30/actor/extra_state_world_size_2_rank_1.ptWeights15.2 KB e964b4dfb990
experiments/weak_to_strong/math/distill_baseline/260723-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_30/actor/model_world_size_2_rank_0.ptWeights4.1 GB df9dcc736fbd
experiments/weak_to_strong/math/distill_baseline/260723-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_30/actor/model_world_size_2_rank_1.ptWeights4.1 GB a1c7eebed150
experiments/weak_to_strong/math/distill_baseline/260723-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_30/data.ptWeights7.0 KB 3d3cf8f5fa73
experiments/weak_to_strong/math/distill_baseline/260723-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_60/actor/distill_resume_state_world_size_2_rank_0.ptWeights1.7 KB 47cdb7d781ed
experiments/weak_to_strong/math/distill_baseline/260723-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_60/actor/distill_resume_state_world_size_2_rank_1.ptWeights1.7 KB 85d441f6a404
experiments/weak_to_strong/math/distill_baseline/260723-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_60/actor/distill_teacher_world_size_2_rank_0.ptWeights16.4 GB 0ea66cd5263f
experiments/weak_to_strong/math/distill_baseline/260723-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_60/actor/distill_teacher_world_size_2_rank_1.ptWeights16.4 GB 22205407ebf2
experiments/weak_to_strong/math/distill_baseline/260723-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_60/actor/extra_state_world_size_2_rank_0.ptWeights15.2 KB 22b3704c3d2a
experiments/weak_to_strong/math/distill_baseline/260723-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_60/actor/extra_state_world_size_2_rank_1.ptWeights15.2 KB 148c08847397
experiments/weak_to_strong/math/distill_baseline/260723-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_60/actor/model_world_size_2_rank_0.ptWeights4.1 GB 068edc034c61
experiments/weak_to_strong/math/distill_baseline/260723-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_60/actor/model_world_size_2_rank_1.ptWeights4.1 GB 24f5728aff15
experiments/weak_to_strong/math/distill_baseline/260723-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_60/data.ptWeights7.0 KB fbed549ebe24
experiments/weak_to_strong/math/distill_baseline/260723-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_90/actor/distill_resume_state_world_size_2_rank_0.ptWeights1.7 KB 47cdb7d781ed
experiments/weak_to_strong/math/distill_baseline/260723-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_90/actor/distill_resume_state_world_size_2_rank_1.ptWeights1.7 KB 85d441f6a404
experiments/weak_to_strong/math/distill_baseline/260723-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_90/actor/distill_teacher_world_size_2_rank_0.ptWeights16.4 GB 0ea66cd5263f
experiments/weak_to_strong/math/distill_baseline/260723-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_90/actor/distill_teacher_world_size_2_rank_1.ptWeights16.4 GB 22205407ebf2
experiments/weak_to_strong/math/distill_baseline/260723-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_90/actor/extra_state_world_size_2_rank_0.ptWeights15.2 KB e65ab0e4c11a
experiments/weak_to_strong/math/distill_baseline/260723-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_90/actor/extra_state_world_size_2_rank_1.ptWeights15.2 KB 5f8eb152afda
experiments/weak_to_strong/math/distill_baseline/260723-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_90/actor/model_world_size_2_rank_0.ptWeights4.1 GB acbd72d8a87f
experiments/weak_to_strong/math/distill_baseline/260723-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_90/actor/model_world_size_2_rank_1.ptWeights4.1 GB 150a3b20da67
experiments/weak_to_strong/math/distill_baseline/260723-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_90/data.ptWeights7.0 KB cbda6dcb9d24
experiments/weak_to_strong/math/distill_baseline/260724-kdrl-annealing-b5e3-min1e3-d1e4-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_120/actor/extra_state_world_size_2_rank_0.ptWeights15.2 KB 70eb2ac78a0e
experiments/weak_to_strong/math/distill_baseline/260724-kdrl-annealing-b5e3-min1e3-d1e4-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_120/actor/extra_state_world_size_2_rank_1.ptWeights15.2 KB 5397cd8f6813
experiments/weak_to_strong/math/distill_baseline/260724-kdrl-annealing-b5e3-min1e3-d1e4-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_120/actor/model_world_size_2_rank_0.ptWeights4.1 GB 762cbe0c0654
experiments/weak_to_strong/math/distill_baseline/260724-kdrl-annealing-b5e3-min1e3-d1e4-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_120/actor/model_world_size_2_rank_1.ptWeights4.1 GB 8e9023281fc7
experiments/weak_to_strong/math/distill_baseline/260724-kdrl-annealing-b5e3-min1e3-d1e4-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_120/data.ptWeights7.0 KB a66fc981d533
experiments/weak_to_strong/math/distill_baseline/260724-kdrl-annealing-b5e3-min1e3-d1e4-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_150/actor/extra_state_world_size_2_rank_0.ptWeights15.2 KB 399e586bf496
experiments/weak_to_strong/math/distill_baseline/260724-kdrl-annealing-b5e3-min1e3-d1e4-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_150/actor/extra_state_world_size_2_rank_1.ptWeights15.2 KB 81e4ea872ba1
experiments/weak_to_strong/math/distill_baseline/260724-kdrl-annealing-b5e3-min1e3-d1e4-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_150/actor/model_world_size_2_rank_0.ptWeights4.1 GB b12bc176fa64
experiments/weak_to_strong/math/distill_baseline/260724-kdrl-annealing-b5e3-min1e3-d1e4-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_150/actor/model_world_size_2_rank_1.ptWeights4.1 GB 55d4fffc8a93
experiments/weak_to_strong/math/distill_baseline/260724-kdrl-annealing-b5e3-min1e3-d1e4-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_150/actor/optim_world_size_2_rank_0.ptWeights6.9 GB 3ecc02427203
experiments/weak_to_strong/math/distill_baseline/260724-kdrl-annealing-b5e3-min1e3-d1e4-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_150/actor/optim_world_size_2_rank_1.ptWeights6.9 GB f32b232c062c
experiments/weak_to_strong/math/distill_baseline/260724-kdrl-annealing-b5e3-min1e3-d1e4-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_150/data.ptWeights7.0 KB 6d96285c52da
experiments/weak_to_strong/math/distill_baseline/260724-kdrl-annealing-b5e3-min1e3-d1e4-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_30/actor/extra_state_world_size_2_rank_0.ptWeights15.2 KB 9d16655e24af
experiments/weak_to_strong/math/distill_baseline/260724-kdrl-annealing-b5e3-min1e3-d1e4-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_30/actor/extra_state_world_size_2_rank_1.ptWeights15.2 KB 8498974b6c92
experiments/weak_to_strong/math/distill_baseline/260724-kdrl-annealing-b5e3-min1e3-d1e4-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_30/actor/model_world_size_2_rank_0.ptWeights4.1 GB 87af6e95d833
experiments/weak_to_strong/math/distill_baseline/260724-kdrl-annealing-b5e3-min1e3-d1e4-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_30/actor/model_world_size_2_rank_1.ptWeights4.1 GB bfcf2678823b
experiments/weak_to_strong/math/distill_baseline/260724-kdrl-annealing-b5e3-min1e3-d1e4-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_30/data.ptWeights7.0 KB 3d3cf8f5fa73
experiments/weak_to_strong/math/distill_baseline/260724-kdrl-annealing-b5e3-min1e3-d1e4-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_60/actor/extra_state_world_size_2_rank_0.ptWeights15.2 KB 064a80298eff
experiments/weak_to_strong/math/distill_baseline/260724-kdrl-annealing-b5e3-min1e3-d1e4-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_60/actor/extra_state_world_size_2_rank_1.ptWeights15.2 KB 2cf7088cac8a
experiments/weak_to_strong/math/distill_baseline/260724-kdrl-annealing-b5e3-min1e3-d1e4-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_60/actor/model_world_size_2_rank_0.ptWeights4.1 GB ee45fc4f75a8
experiments/weak_to_strong/math/distill_baseline/260724-kdrl-annealing-b5e3-min1e3-d1e4-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_60/actor/model_world_size_2_rank_1.ptWeights4.1 GB ff2439635770
experiments/weak_to_strong/math/distill_baseline/260724-kdrl-annealing-b5e3-min1e3-d1e4-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_60/data.ptWeights7.0 KB fbed549ebe24
experiments/weak_to_strong/math/distill_baseline/260724-kdrl-annealing-b5e3-min1e3-d1e4-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_90/actor/extra_state_world_size_2_rank_0.ptWeights15.2 KB 8ae1be4b1e8b
experiments/weak_to_strong/math/distill_baseline/260724-kdrl-annealing-b5e3-min1e3-d1e4-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_90/actor/extra_state_world_size_2_rank_1.ptWeights15.2 KB 028176e8aa61
experiments/weak_to_strong/math/distill_baseline/260724-kdrl-annealing-b5e3-min1e3-d1e4-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_90/actor/model_world_size_2_rank_0.ptWeights4.1 GB aa4449954be4
experiments/weak_to_strong/math/distill_baseline/260724-kdrl-annealing-b5e3-min1e3-d1e4-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_90/actor/model_world_size_2_rank_1.ptWeights4.1 GB e64ff7e9af33
experiments/weak_to_strong/math/distill_baseline/260724-kdrl-annealing-b5e3-min1e3-d1e4-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_90/data.ptWeights7.0 KB cbda6dcb9d24
experiments/weak_to_strong/math/distill_baseline/260724-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_120/actor/distill_resume_state_world_size_2_rank_0.ptWeights1.7 KB 646007d2f53e
experiments/weak_to_strong/math/distill_baseline/260724-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_120/actor/distill_resume_state_world_size_2_rank_1.ptWeights1.7 KB b6d81c48231e
experiments/weak_to_strong/math/distill_baseline/260724-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_120/actor/distill_teacher_world_size_2_rank_0.ptWeights8.8 GB 0097c17a278c
experiments/weak_to_strong/math/distill_baseline/260724-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_120/actor/distill_teacher_world_size_2_rank_1.ptWeights8.8 GB 714ab0223551
experiments/weak_to_strong/math/distill_baseline/260724-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_120/actor/extra_state_world_size_2_rank_0.ptWeights15.2 KB 9bf07e87562f
experiments/weak_to_strong/math/distill_baseline/260724-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_120/actor/extra_state_world_size_2_rank_1.ptWeights15.2 KB 56c5ca595dba
experiments/weak_to_strong/math/distill_baseline/260724-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_120/actor/model_world_size_2_rank_0.ptWeights16.4 GB bbb6efab623d
experiments/weak_to_strong/math/distill_baseline/260724-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_120/actor/model_world_size_2_rank_1.ptWeights16.4 GB bd2bfda2390e
experiments/weak_to_strong/math/distill_baseline/260724-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_120/data.ptWeights7.0 KB a66fc981d533
experiments/weak_to_strong/math/distill_baseline/260724-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_150/actor/distill_resume_state_world_size_2_rank_0.ptWeights1.7 KB 646007d2f53e
experiments/weak_to_strong/math/distill_baseline/260724-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_150/actor/distill_resume_state_world_size_2_rank_1.ptWeights1.7 KB b6d81c48231e
experiments/weak_to_strong/math/distill_baseline/260724-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_150/actor/distill_teacher_world_size_2_rank_0.ptWeights8.8 GB 0097c17a278c
experiments/weak_to_strong/math/distill_baseline/260724-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_150/actor/distill_teacher_world_size_2_rank_1.ptWeights8.8 GB 714ab0223551
experiments/weak_to_strong/math/distill_baseline/260724-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_150/actor/extra_state_world_size_2_rank_0.ptWeights15.2 KB 64b31b7da35f
experiments/weak_to_strong/math/distill_baseline/260724-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_150/actor/extra_state_world_size_2_rank_1.ptWeights15.2 KB 1fbde96ed65c
experiments/weak_to_strong/math/distill_baseline/260724-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_150/actor/model_world_size_2_rank_0.ptWeights16.4 GB d9e3836cce99
experiments/weak_to_strong/math/distill_baseline/260724-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_150/actor/model_world_size_2_rank_1.ptWeights16.4 GB 6f1854f73e48
experiments/weak_to_strong/math/distill_baseline/260724-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_150/actor/optim_world_size_2_rank_0.ptWeights32.8 GB 2f9cbf4273e4
experiments/weak_to_strong/math/distill_baseline/260724-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_150/actor/optim_world_size_2_rank_1.ptWeights32.8 GB 0e4972ebdae3
experiments/weak_to_strong/math/distill_baseline/260724-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_150/data.ptWeights7.0 KB 6d96285c52da
experiments/weak_to_strong/math/distill_baseline/260724-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_30/actor/distill_resume_state_world_size_2_rank_0.ptWeights1.7 KB 646007d2f53e
experiments/weak_to_strong/math/distill_baseline/260724-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_30/actor/distill_resume_state_world_size_2_rank_1.ptWeights1.7 KB b6d81c48231e
experiments/weak_to_strong/math/distill_baseline/260724-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_30/actor/distill_teacher_world_size_2_rank_0.ptWeights8.8 GB 0097c17a278c
experiments/weak_to_strong/math/distill_baseline/260724-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_30/actor/distill_teacher_world_size_2_rank_1.ptWeights8.8 GB 714ab0223551
experiments/weak_to_strong/math/distill_baseline/260724-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_30/actor/extra_state_world_size_2_rank_0.ptWeights15.2 KB 9986b91f7cdf
experiments/weak_to_strong/math/distill_baseline/260724-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_30/actor/extra_state_world_size_2_rank_1.ptWeights15.2 KB a820a79f53e8
experiments/weak_to_strong/math/distill_baseline/260724-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_30/actor/model_world_size_2_rank_0.ptWeights16.4 GB cc192edd0647
experiments/weak_to_strong/math/distill_baseline/260724-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_30/actor/model_world_size_2_rank_1.ptWeights16.4 GB 667c8f01b415
experiments/weak_to_strong/math/distill_baseline/260724-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_30/data.ptWeights7.0 KB 3d3cf8f5fa73
experiments/weak_to_strong/math/distill_baseline/260724-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_60/actor/distill_resume_state_world_size_2_rank_0.ptWeights1.7 KB 646007d2f53e
experiments/weak_to_strong/math/distill_baseline/260724-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_60/actor/distill_resume_state_world_size_2_rank_1.ptWeights1.7 KB b6d81c48231e
experiments/weak_to_strong/math/distill_baseline/260724-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_60/actor/distill_teacher_world_size_2_rank_0.ptWeights8.8 GB 0097c17a278c
experiments/weak_to_strong/math/distill_baseline/260724-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_60/actor/distill_teacher_world_size_2_rank_1.ptWeights8.8 GB 714ab0223551
experiments/weak_to_strong/math/distill_baseline/260724-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_60/actor/extra_state_world_size_2_rank_0.ptWeights15.2 KB 89d56da7b2e6
experiments/weak_to_strong/math/distill_baseline/260724-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_60/actor/extra_state_world_size_2_rank_1.ptWeights15.2 KB 3f84b6a2a4e5
experiments/weak_to_strong/math/distill_baseline/260724-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_60/actor/model_world_size_2_rank_0.ptWeights16.4 GB 984b52cbb3f1
experiments/weak_to_strong/math/distill_baseline/260724-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_60/actor/model_world_size_2_rank_1.ptWeights16.4 GB e4f2da99d056
experiments/weak_to_strong/math/distill_baseline/260724-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_60/data.ptWeights7.0 KB fbed549ebe24
experiments/weak_to_strong/math/distill_baseline/260724-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_90/actor/distill_resume_state_world_size_2_rank_0.ptWeights1.7 KB 646007d2f53e
experiments/weak_to_strong/math/distill_baseline/260724-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_90/actor/distill_resume_state_world_size_2_rank_1.ptWeights1.7 KB b6d81c48231e
experiments/weak_to_strong/math/distill_baseline/260724-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_90/actor/distill_teacher_world_size_2_rank_0.ptWeights8.8 GB 0097c17a278c
experiments/weak_to_strong/math/distill_baseline/260724-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_90/actor/distill_teacher_world_size_2_rank_1.ptWeights8.8 GB 714ab0223551
experiments/weak_to_strong/math/distill_baseline/260724-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_90/actor/extra_state_world_size_2_rank_0.ptWeights15.2 KB e3d5dcdfa291
experiments/weak_to_strong/math/distill_baseline/260724-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_90/actor/extra_state_world_size_2_rank_1.ptWeights15.2 KB d4d9412e69b3
experiments/weak_to_strong/math/distill_baseline/260724-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_90/actor/model_world_size_2_rank_0.ptWeights16.4 GB f622be9e4a1f
experiments/weak_to_strong/math/distill_baseline/260724-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_90/actor/model_world_size_2_rank_1.ptWeights16.4 GB 9d58a4ddcc1d
experiments/weak_to_strong/math/distill_baseline/260724-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_90/data.ptWeights7.0 KB cbda6dcb9d24
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched30-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_120/actor/extra_state_world_size_2_rank_0.ptWeights15.3 KB 95baaee40e56
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched30-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_120/actor/extra_state_world_size_2_rank_1.ptWeights15.3 KB d551ce83462f
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched30-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_120/actor/model_world_size_2_rank_0.ptWeights16.4 GB 95b679aec075
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched30-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_120/actor/model_world_size_2_rank_1.ptWeights16.4 GB 56a050c0a707
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched30-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_120/data.ptWeights7.0 KB a66fc981d533
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched30-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_150/actor/extra_state_world_size_2_rank_0.ptWeights15.3 KB 74c422afa130
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched30-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_150/actor/extra_state_world_size_2_rank_1.ptWeights15.3 KB 088b7ce2e32b
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched30-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_150/actor/model_world_size_2_rank_0.ptWeights16.4 GB 0e7468f7d87f
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched30-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_150/actor/model_world_size_2_rank_1.ptWeights16.4 GB 3e7177701634
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched30-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_150/actor/optim_world_size_2_rank_0.ptWeights32.8 GB c10b42e7992e
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched30-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_150/actor/optim_world_size_2_rank_1.ptWeights32.8 GB ee09f37cc964
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched30-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_150/data.ptWeights7.0 KB 6d96285c52da
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched30-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_30/actor/extra_state_world_size_2_rank_0.ptWeights15.3 KB 7c2c7692f7ae
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched30-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_30/actor/extra_state_world_size_2_rank_1.ptWeights15.3 KB 89759b845b48
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched30-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_30/actor/model_world_size_2_rank_0.ptWeights16.4 GB 0909b99fb07d
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched30-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_30/actor/model_world_size_2_rank_1.ptWeights16.4 GB 0e6d70e1607f
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched30-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_30/data.ptWeights7.0 KB 3d3cf8f5fa73
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched30-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_60/actor/extra_state_world_size_2_rank_0.ptWeights15.3 KB 407e6b7c50b2
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched30-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_60/actor/extra_state_world_size_2_rank_1.ptWeights15.3 KB 7c3eb1f9186b
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched30-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_60/actor/model_world_size_2_rank_0.ptWeights16.4 GB 14527904108d
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched30-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_60/actor/model_world_size_2_rank_1.ptWeights16.4 GB da8e519c35c7
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched30-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_60/data.ptWeights7.0 KB fbed549ebe24
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched30-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_90/actor/extra_state_world_size_2_rank_0.ptWeights15.3 KB 0630b2dc4f7d
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched30-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_90/actor/extra_state_world_size_2_rank_1.ptWeights15.3 KB 768e1dabec5c
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched30-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_90/actor/model_world_size_2_rank_0.ptWeights16.4 GB 7b342669c0fd
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched30-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_90/actor/model_world_size_2_rank_1.ptWeights16.4 GB 6f70012918d4
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched30-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_90/data.ptWeights7.0 KB cbda6dcb9d24
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched45-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_120/actor/extra_state_world_size_2_rank_0.ptWeights15.2 KB 0848ee7c3edc
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched45-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_120/actor/extra_state_world_size_2_rank_1.ptWeights15.2 KB be12bc30001d
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched45-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_120/actor/model_world_size_2_rank_0.ptWeights4.1 GB 31630f844d58
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched45-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_120/actor/model_world_size_2_rank_1.ptWeights4.1 GB 191976d24dac
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched45-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_120/data.ptWeights7.0 KB a66fc981d533
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched45-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_150/actor/extra_state_world_size_2_rank_0.ptWeights15.2 KB 28e5e1373a6d
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched45-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_150/actor/extra_state_world_size_2_rank_1.ptWeights15.2 KB 6f09a97ac0da
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched45-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_150/actor/model_world_size_2_rank_0.ptWeights4.1 GB daaf0d18cb15
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched45-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_150/actor/model_world_size_2_rank_1.ptWeights4.1 GB e03e55af160a
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched45-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_150/actor/optim_world_size_2_rank_0.ptWeights6.9 GB 11f6878ca498
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched45-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_150/actor/optim_world_size_2_rank_1.ptWeights6.9 GB 31609723b3bb
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched45-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_150/data.ptWeights7.0 KB 6d96285c52da
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched45-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_30/actor/extra_state_world_size_2_rank_0.ptWeights15.3 KB c45f34c01e8a
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched45-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_30/actor/extra_state_world_size_2_rank_1.ptWeights15.3 KB f5931cb8da77
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched45-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_30/actor/model_world_size_2_rank_0.ptWeights4.1 GB 3e867e5d2489
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched45-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_30/actor/model_world_size_2_rank_1.ptWeights4.1 GB b6b2501557ec
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched45-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_30/data.ptWeights7.0 KB 3d3cf8f5fa73
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched45-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_60/actor/extra_state_world_size_2_rank_0.ptWeights15.3 KB c40493746f8f
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched45-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_60/actor/extra_state_world_size_2_rank_1.ptWeights15.3 KB 35acdb563b18
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched45-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_60/actor/model_world_size_2_rank_0.ptWeights4.1 GB 3815cbb44287
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched45-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_60/actor/model_world_size_2_rank_1.ptWeights4.1 GB ce9999e33dcb
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched45-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_60/data.ptWeights7.0 KB fbed549ebe24
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched45-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_90/actor/extra_state_world_size_2_rank_0.ptWeights15.3 KB b03e37e4109a
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched45-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_90/actor/extra_state_world_size_2_rank_1.ptWeights15.3 KB 908ef76b36b6
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched45-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_90/actor/model_world_size_2_rank_0.ptWeights4.1 GB 97ea56771180
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched45-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_90/actor/model_world_size_2_rank_1.ptWeights4.1 GB 99bba24cec3c
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched45-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_90/data.ptWeights7.0 KB cbda6dcb9d24
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched75-overlong4k-len20480-dapo-math17k-qwen3-8b-base-teacher4b-base-step90-mb32-nosystem-save30-eval15-latestopt-2gpu/global_step_120/actor/extra_state_world_size_2_rank_0.ptWeights15.3 KB dbd48ad3fcc4
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched75-overlong4k-len20480-dapo-math17k-qwen3-8b-base-teacher4b-base-step90-mb32-nosystem-save30-eval15-latestopt-2gpu/global_step_120/actor/extra_state_world_size_2_rank_1.ptWeights15.3 KB a4b6f7ca6ea5
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched75-overlong4k-len20480-dapo-math17k-qwen3-8b-base-teacher4b-base-step90-mb32-nosystem-save30-eval15-latestopt-2gpu/global_step_120/actor/model_world_size_2_rank_0.ptWeights16.4 GB 37ed4c4ba946
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched75-overlong4k-len20480-dapo-math17k-qwen3-8b-base-teacher4b-base-step90-mb32-nosystem-save30-eval15-latestopt-2gpu/global_step_120/actor/model_world_size_2_rank_1.ptWeights16.4 GB 2ec107673cbb
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched75-overlong4k-len20480-dapo-math17k-qwen3-8b-base-teacher4b-base-step90-mb32-nosystem-save30-eval15-latestopt-2gpu/global_step_120/data.ptWeights7.0 KB a66fc981d533
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched75-overlong4k-len20480-dapo-math17k-qwen3-8b-base-teacher4b-base-step90-mb32-nosystem-save30-eval15-latestopt-2gpu/global_step_150/actor/extra_state_world_size_2_rank_0.ptWeights15.3 KB 2dfb450d7ddd
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched75-overlong4k-len20480-dapo-math17k-qwen3-8b-base-teacher4b-base-step90-mb32-nosystem-save30-eval15-latestopt-2gpu/global_step_150/actor/extra_state_world_size_2_rank_1.ptWeights15.3 KB efe8030784ad
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched75-overlong4k-len20480-dapo-math17k-qwen3-8b-base-teacher4b-base-step90-mb32-nosystem-save30-eval15-latestopt-2gpu/global_step_150/actor/model_world_size_2_rank_0.ptWeights16.4 GB 08d8d79f3173
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched75-overlong4k-len20480-dapo-math17k-qwen3-8b-base-teacher4b-base-step90-mb32-nosystem-save30-eval15-latestopt-2gpu/global_step_150/actor/model_world_size_2_rank_1.ptWeights16.4 GB eca56f1817a8
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched75-overlong4k-len20480-dapo-math17k-qwen3-8b-base-teacher4b-base-step90-mb32-nosystem-save30-eval15-latestopt-2gpu/global_step_150/actor/optim_world_size_2_rank_0.ptWeights32.8 GB e05394d11b9f
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched75-overlong4k-len20480-dapo-math17k-qwen3-8b-base-teacher4b-base-step90-mb32-nosystem-save30-eval15-latestopt-2gpu/global_step_150/actor/optim_world_size_2_rank_1.ptWeights32.8 GB a377050ff739
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched75-overlong4k-len20480-dapo-math17k-qwen3-8b-base-teacher4b-base-step90-mb32-nosystem-save30-eval15-latestopt-2gpu/global_step_150/data.ptWeights7.0 KB 6d96285c52da
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched75-overlong4k-len20480-dapo-math17k-qwen3-8b-base-teacher4b-base-step90-mb32-nosystem-save30-eval15-latestopt-2gpu/global_step_30/actor/extra_state_world_size_2_rank_0.ptWeights15.2 KB 5c45da498076
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched75-overlong4k-len20480-dapo-math17k-qwen3-8b-base-teacher4b-base-step90-mb32-nosystem-save30-eval15-latestopt-2gpu/global_step_30/actor/extra_state_world_size_2_rank_1.ptWeights15.2 KB fc4175be617a
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched75-overlong4k-len20480-dapo-math17k-qwen3-8b-base-teacher4b-base-step90-mb32-nosystem-save30-eval15-latestopt-2gpu/global_step_30/actor/model_world_size_2_rank_0.ptWeights16.4 GB 6d9867b517b9
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched75-overlong4k-len20480-dapo-math17k-qwen3-8b-base-teacher4b-base-step90-mb32-nosystem-save30-eval15-latestopt-2gpu/global_step_30/actor/model_world_size_2_rank_1.ptWeights16.4 GB c4dfd5f09b6e
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched75-overlong4k-len20480-dapo-math17k-qwen3-8b-base-teacher4b-base-step90-mb32-nosystem-save30-eval15-latestopt-2gpu/global_step_30/data.ptWeights7.0 KB 3d3cf8f5fa73
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched75-overlong4k-len20480-dapo-math17k-qwen3-8b-base-teacher4b-base-step90-mb32-nosystem-save30-eval15-latestopt-2gpu/global_step_60/actor/extra_state_world_size_2_rank_0.ptWeights15.3 KB 67564e14ab83
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched75-overlong4k-len20480-dapo-math17k-qwen3-8b-base-teacher4b-base-step90-mb32-nosystem-save30-eval15-latestopt-2gpu/global_step_60/actor/extra_state_world_size_2_rank_1.ptWeights15.3 KB e05ba81ee2da
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched75-overlong4k-len20480-dapo-math17k-qwen3-8b-base-teacher4b-base-step90-mb32-nosystem-save30-eval15-latestopt-2gpu/global_step_60/actor/model_world_size_2_rank_0.ptWeights16.4 GB 4082155ad6d9
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched75-overlong4k-len20480-dapo-math17k-qwen3-8b-base-teacher4b-base-step90-mb32-nosystem-save30-eval15-latestopt-2gpu/global_step_60/actor/model_world_size_2_rank_1.ptWeights16.4 GB 83dc3294c155
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched75-overlong4k-len20480-dapo-math17k-qwen3-8b-base-teacher4b-base-step90-mb32-nosystem-save30-eval15-latestopt-2gpu/global_step_60/data.ptWeights7.0 KB fbed549ebe24
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched75-overlong4k-len20480-dapo-math17k-qwen3-8b-base-teacher4b-base-step90-mb32-nosystem-save30-eval15-latestopt-2gpu/global_step_90/actor/extra_state_world_size_2_rank_0.ptWeights15.3 KB 5395c80028a6
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched75-overlong4k-len20480-dapo-math17k-qwen3-8b-base-teacher4b-base-step90-mb32-nosystem-save30-eval15-latestopt-2gpu/global_step_90/actor/extra_state_world_size_2_rank_1.ptWeights15.3 KB 25fd267c7870
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched75-overlong4k-len20480-dapo-math17k-qwen3-8b-base-teacher4b-base-step90-mb32-nosystem-save30-eval15-latestopt-2gpu/global_step_90/actor/model_world_size_2_rank_0.ptWeights16.4 GB 96aad90b42db
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched75-overlong4k-len20480-dapo-math17k-qwen3-8b-base-teacher4b-base-step90-mb32-nosystem-save30-eval15-latestopt-2gpu/global_step_90/actor/model_world_size_2_rank_1.ptWeights16.4 GB d714aa22b9a2
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched75-overlong4k-len20480-dapo-math17k-qwen3-8b-base-teacher4b-base-step90-mb32-nosystem-save30-eval15-latestopt-2gpu/global_step_90/data.ptWeights7.0 KB cbda6dcb9d24
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_120/actor/extra_state_world_size_4_rank_0.ptWeights15.3 KB 4ec745ec9aee
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_120/actor/extra_state_world_size_4_rank_1.ptWeights15.3 KB 6136abf69021
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_120/actor/extra_state_world_size_4_rank_2.ptWeights15.3 KB 991623a6fb94
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_120/actor/extra_state_world_size_4_rank_3.ptWeights15.3 KB c108b44de3bc
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_120/actor/model_world_size_4_rank_0.ptWeights8.2 GB 3b4f141c5f20
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_120/actor/model_world_size_4_rank_1.ptWeights8.2 GB 10e6942f56ea
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_120/actor/model_world_size_4_rank_2.ptWeights8.2 GB 8741090942e6
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_120/actor/model_world_size_4_rank_3.ptWeights8.2 GB 6a8f9901035a
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_120/data.ptWeights7.0 KB a66fc981d533
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_135/actor/extra_state_world_size_4_rank_0.ptWeights15.3 KB 2e818e0dae31
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_135/actor/extra_state_world_size_4_rank_1.ptWeights15.3 KB c835642e09d4
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_135/actor/extra_state_world_size_4_rank_2.ptWeights15.3 KB 327633b9f4f4
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_135/actor/extra_state_world_size_4_rank_3.ptWeights15.3 KB ab4516e2251f
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_135/actor/model_world_size_4_rank_0.ptWeights8.2 GB 6fb2c4054311
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_135/actor/model_world_size_4_rank_1.ptWeights8.2 GB fd12199a34fe
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_135/actor/model_world_size_4_rank_2.ptWeights8.2 GB 6b9883ef6995
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_135/actor/model_world_size_4_rank_3.ptWeights8.2 GB 17a16317aa66
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_135/data.ptWeights7.0 KB 30fa55d9f0ad
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_150/actor/extra_state_world_size_4_rank_0.ptWeights15.3 KB 5585f8a5c3ab
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_150/actor/extra_state_world_size_4_rank_1.ptWeights15.3 KB 65c7cf7d2340
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_150/actor/extra_state_world_size_4_rank_2.ptWeights15.3 KB cb5c821170c1
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_150/actor/extra_state_world_size_4_rank_3.ptWeights15.3 KB a6d2a2322c27
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_150/actor/model_world_size_4_rank_0.ptWeights8.2 GB 07218fdee0c6
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_150/actor/model_world_size_4_rank_1.ptWeights8.2 GB 5818710eb1a1
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_150/actor/model_world_size_4_rank_2.ptWeights8.2 GB 3a97f97915d7
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_150/actor/model_world_size_4_rank_3.ptWeights8.2 GB fcb1b839d508
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_150/actor/optim_world_size_4_rank_0.ptWeights16.4 GB aeaf81c51b9b
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_150/actor/optim_world_size_4_rank_1.ptWeights16.4 GB 0494a516b603
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_150/actor/optim_world_size_4_rank_2.ptWeights16.4 GB 36a7712cdb8d
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_150/actor/optim_world_size_4_rank_3.ptWeights16.4 GB a2d8e380505a
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_150/data.ptWeights7.0 KB 6d96285c52da
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_30/actor/extra_state_world_size_4_rank_0.ptWeights15.3 KB 76a9d4c2dcbc
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_30/actor/extra_state_world_size_4_rank_1.ptWeights15.3 KB 0e0e3a337689
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_30/actor/extra_state_world_size_4_rank_2.ptWeights15.3 KB 6e217ced1ba5
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_30/actor/extra_state_world_size_4_rank_3.ptWeights15.3 KB 1df1c3b1f03e
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_30/actor/model_world_size_4_rank_0.ptWeights8.2 GB 9e5e02f82151
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_30/actor/model_world_size_4_rank_1.ptWeights8.2 GB bc4ad3c3653c
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_30/actor/model_world_size_4_rank_2.ptWeights8.2 GB f56fab2142d3
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_30/actor/model_world_size_4_rank_3.ptWeights8.2 GB 1fe6252a5820
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_30/data.ptWeights7.0 KB 3d3cf8f5fa73
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_60/actor/extra_state_world_size_4_rank_0.ptWeights15.3 KB e7cf86fb8520
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_60/actor/extra_state_world_size_4_rank_1.ptWeights15.3 KB 9dacc0264baa
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_60/actor/extra_state_world_size_4_rank_2.ptWeights15.3 KB c0e798568baa
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_60/actor/extra_state_world_size_4_rank_3.ptWeights15.3 KB 0f9c96187aa6
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_60/actor/model_world_size_4_rank_0.ptWeights8.2 GB 0f7d43fa963a
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_60/actor/model_world_size_4_rank_1.ptWeights8.2 GB afb8ced6fd90
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_60/actor/model_world_size_4_rank_2.ptWeights8.2 GB 29b7b2996002
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_60/actor/model_world_size_4_rank_3.ptWeights8.2 GB 6c09f704a391
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_60/data.ptWeights7.0 KB fbed549ebe24
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_90/actor/extra_state_world_size_4_rank_0.ptWeights15.3 KB aa9439f3a161
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_90/actor/extra_state_world_size_4_rank_1.ptWeights15.3 KB b65e764f3cef
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_90/actor/extra_state_world_size_4_rank_2.ptWeights15.3 KB b5da3c2eb9b7
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_90/actor/extra_state_world_size_4_rank_3.ptWeights15.3 KB 0f2fd8174f07
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_90/actor/model_world_size_4_rank_0.ptWeights8.2 GB c28a17e30bf4
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_90/actor/model_world_size_4_rank_1.ptWeights8.2 GB c9157f89a029
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_90/actor/model_world_size_4_rank_2.ptWeights8.2 GB 6f1c05da6db7
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_90/actor/model_world_size_4_rank_3.ptWeights8.2 GB 5126d4b999bb
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_90/data.ptWeights7.0 KB cbda6dcb9d24
experiments/weak_to_strong/reasoning/binary_matrix/baseline/260727-grpo-binary_matrix-q3-8b-base-s150-tr8k-va8k-seed1234-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp4/global_step_120/actor/extra_state_world_size_4_rank_0.ptWeights15.3 KB 16279dcba730
experiments/weak_to_strong/reasoning/binary_matrix/baseline/260727-grpo-binary_matrix-q3-8b-base-s150-tr8k-va8k-seed1234-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp4/global_step_120/actor/extra_state_world_size_4_rank_1.ptWeights15.3 KB ebe5b096a8cb
experiments/weak_to_strong/reasoning/binary_matrix/baseline/260727-grpo-binary_matrix-q3-8b-base-s150-tr8k-va8k-seed1234-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp4/global_step_120/actor/extra_state_world_size_4_rank_2.ptWeights15.3 KB f161e0bc24e6
experiments/weak_to_strong/reasoning/binary_matrix/baseline/260727-grpo-binary_matrix-q3-8b-base-s150-tr8k-va8k-seed1234-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp4/global_step_120/actor/extra_state_world_size_4_rank_3.ptWeights15.3 KB 1260efa8db87
experiments/weak_to_strong/reasoning/binary_matrix/baseline/260727-grpo-binary_matrix-q3-8b-base-s150-tr8k-va8k-seed1234-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp4/global_step_120/actor/model_world_size_4_rank_0.ptWeights8.2 GB c317a5f13914
experiments/weak_to_strong/reasoning/binary_matrix/baseline/260727-grpo-binary_matrix-q3-8b-base-s150-tr8k-va8k-seed1234-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp4/global_step_120/actor/model_world_size_4_rank_1.ptWeights8.2 GB f69ddc749fc0
experiments/weak_to_strong/reasoning/binary_matrix/baseline/260727-grpo-binary_matrix-q3-8b-base-s150-tr8k-va8k-seed1234-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp4/global_step_120/actor/model_world_size_4_rank_2.ptWeights8.2 GB ab9a0aca5ec8
experiments/weak_to_strong/reasoning/binary_matrix/baseline/260727-grpo-binary_matrix-q3-8b-base-s150-tr8k-va8k-seed1234-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp4/global_step_120/actor/model_world_size_4_rank_3.ptWeights8.2 GB d0c6e9d5d6d0
experiments/weak_to_strong/reasoning/binary_matrix/baseline/260727-grpo-binary_matrix-q3-8b-base-s150-tr8k-va8k-seed1234-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp4/global_step_120/data.ptWeights7.0 KB ed5c416be2ad
experiments/weak_to_strong/reasoning/binary_matrix/baseline/260727-grpo-binary_matrix-q3-8b-base-s150-tr8k-va8k-seed1234-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp4/global_step_150/actor/extra_state_world_size_4_rank_0.ptWeights15.3 KB 120359b8a77f
experiments/weak_to_strong/reasoning/binary_matrix/baseline/260727-grpo-binary_matrix-q3-8b-base-s150-tr8k-va8k-seed1234-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp4/global_step_150/actor/extra_state_world_size_4_rank_1.ptWeights15.3 KB 31f1dd257f56
experiments/weak_to_strong/reasoning/binary_matrix/baseline/260727-grpo-binary_matrix-q3-8b-base-s150-tr8k-va8k-seed1234-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp4/global_step_150/actor/extra_state_world_size_4_rank_2.ptWeights15.3 KB faf7ece48744
experiments/weak_to_strong/reasoning/binary_matrix/baseline/260727-grpo-binary_matrix-q3-8b-base-s150-tr8k-va8k-seed1234-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp4/global_step_150/actor/extra_state_world_size_4_rank_3.ptWeights15.3 KB 408f285951be
experiments/weak_to_strong/reasoning/binary_matrix/baseline/260727-grpo-binary_matrix-q3-8b-base-s150-tr8k-va8k-seed1234-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp4/global_step_150/actor/model_world_size_4_rank_0.ptWeights8.2 GB 8eca0dbc2fb9
experiments/weak_to_strong/reasoning/binary_matrix/baseline/260727-grpo-binary_matrix-q3-8b-base-s150-tr8k-va8k-seed1234-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp4/global_step_150/actor/model_world_size_4_rank_1.ptWeights8.2 GB 9f095dbd9a8c
experiments/weak_to_strong/reasoning/binary_matrix/baseline/260727-grpo-binary_matrix-q3-8b-base-s150-tr8k-va8k-seed1234-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp4/global_step_150/actor/model_world_size_4_rank_2.ptWeights8.2 GB 48ee99bd56fa
experiments/weak_to_strong/reasoning/binary_matrix/baseline/260727-grpo-binary_matrix-q3-8b-base-s150-tr8k-va8k-seed1234-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp4/global_step_150/actor/model_world_size_4_rank_3.ptWeights8.2 GB 2da929ea16e9
experiments/weak_to_strong/reasoning/binary_matrix/baseline/260727-grpo-binary_matrix-q3-8b-base-s150-tr8k-va8k-seed1234-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp4/global_step_150/data.ptWeights7.0 KB 4582c532075e
experiments/weak_to_strong/reasoning/binary_matrix/baseline/260727-grpo-binary_matrix-q3-8b-base-s150-tr8k-va8k-seed1234-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp4/global_step_90/actor/extra_state_world_size_4_rank_0.ptWeights15.3 KB 4a94b5997227
experiments/weak_to_strong/reasoning/binary_matrix/baseline/260727-grpo-binary_matrix-q3-8b-base-s150-tr8k-va8k-seed1234-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp4/global_step_90/actor/extra_state_world_size_4_rank_1.ptWeights15.3 KB 061d4249301e
experiments/weak_to_strong/reasoning/binary_matrix/baseline/260727-grpo-binary_matrix-q3-8b-base-s150-tr8k-va8k-seed1234-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp4/global_step_90/actor/extra_state_world_size_4_rank_2.ptWeights15.3 KB 37071f4bdc3d
experiments/weak_to_strong/reasoning/binary_matrix/baseline/260727-grpo-binary_matrix-q3-8b-base-s150-tr8k-va8k-seed1234-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp4/global_step_90/actor/extra_state_world_size_4_rank_3.ptWeights15.3 KB d0f443da3e0d
experiments/weak_to_strong/reasoning/binary_matrix/baseline/260727-grpo-binary_matrix-q3-8b-base-s150-tr8k-va8k-seed1234-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp4/global_step_90/actor/model_world_size_4_rank_0.ptWeights8.2 GB 957b088a5590
experiments/weak_to_strong/reasoning/binary_matrix/baseline/260727-grpo-binary_matrix-q3-8b-base-s150-tr8k-va8k-seed1234-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp4/global_step_90/actor/model_world_size_4_rank_1.ptWeights8.2 GB e9e6d9a0cab4
experiments/weak_to_strong/reasoning/binary_matrix/baseline/260727-grpo-binary_matrix-q3-8b-base-s150-tr8k-va8k-seed1234-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp4/global_step_90/actor/model_world_size_4_rank_2.ptWeights8.2 GB c97c4b024845
experiments/weak_to_strong/reasoning/binary_matrix/baseline/260727-grpo-binary_matrix-q3-8b-base-s150-tr8k-va8k-seed1234-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp4/global_step_90/actor/model_world_size_4_rank_3.ptWeights8.2 GB 8321710fa916
experiments/weak_to_strong/reasoning/binary_matrix/baseline/260727-grpo-binary_matrix-q3-8b-base-s150-tr8k-va8k-seed1234-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp4/global_step_90/data.ptWeights7.0 KB be7eaded59c3
experiments/weak_to_strong/reasoning/binary_matrix/distill_baseline/260731-kdrl-b5e3-d6p6667e5-min0-sched75-binary_matrix-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-finalopt-static10k-tistoken-clip0p2-0p28-seed1234-b64-mb32-dp2/global_step_120/actor/extra_state_world_size_2_rank_0.ptWeights15.2 KB d79de4b04c7c
experiments/weak_to_strong/reasoning/binary_matrix/distill_baseline/260731-kdrl-b5e3-d6p6667e5-min0-sched75-binary_matrix-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-finalopt-static10k-tistoken-clip0p2-0p28-seed1234-b64-mb32-dp2/global_step_120/actor/extra_state_world_size_2_rank_1.ptWeights15.2 KB 6922c162e1a1
experiments/weak_to_strong/reasoning/binary_matrix/distill_baseline/260731-kdrl-b5e3-d6p6667e5-min0-sched75-binary_matrix-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-finalopt-static10k-tistoken-clip0p2-0p28-seed1234-b64-mb32-dp2/global_step_120/actor/model_world_size_2_rank_0.ptWeights16.4 GB 6eef0fd2bf4c
experiments/weak_to_strong/reasoning/binary_matrix/distill_baseline/260731-kdrl-b5e3-d6p6667e5-min0-sched75-binary_matrix-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-finalopt-static10k-tistoken-clip0p2-0p28-seed1234-b64-mb32-dp2/global_step_120/actor/model_world_size_2_rank_1.ptWeights16.4 GB 4ac1531066ac
experiments/weak_to_strong/reasoning/binary_matrix/distill_baseline/260731-kdrl-b5e3-d6p6667e5-min0-sched75-binary_matrix-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-finalopt-static10k-tistoken-clip0p2-0p28-seed1234-b64-mb32-dp2/global_step_120/data.ptWeights7.0 KB ed5c416be2ad
experiments/weak_to_strong/reasoning/binary_matrix/distill_baseline/260731-kdrl-b5e3-d6p6667e5-min0-sched75-binary_matrix-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-finalopt-static10k-tistoken-clip0p2-0p28-seed1234-b64-mb32-dp2/global_step_135/actor/extra_state_world_size_2_rank_0.ptWeights15.2 KB 59b37d9c06d1
experiments/weak_to_strong/reasoning/binary_matrix/distill_baseline/260731-kdrl-b5e3-d6p6667e5-min0-sched75-binary_matrix-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-finalopt-static10k-tistoken-clip0p2-0p28-seed1234-b64-mb32-dp2/global_step_135/actor/extra_state_world_size_2_rank_1.ptWeights15.2 KB e141999889ba
experiments/weak_to_strong/reasoning/binary_matrix/distill_baseline/260731-kdrl-b5e3-d6p6667e5-min0-sched75-binary_matrix-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-finalopt-static10k-tistoken-clip0p2-0p28-seed1234-b64-mb32-dp2/global_step_135/actor/model_world_size_2_rank_0.ptWeights16.4 GB 3ec9f6171c70
experiments/weak_to_strong/reasoning/binary_matrix/distill_baseline/260731-kdrl-b5e3-d6p6667e5-min0-sched75-binary_matrix-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-finalopt-static10k-tistoken-clip0p2-0p28-seed1234-b64-mb32-dp2/global_step_135/actor/model_world_size_2_rank_1.ptWeights16.4 GB d430eccdebe7
experiments/weak_to_strong/reasoning/binary_matrix/distill_baseline/260731-kdrl-b5e3-d6p6667e5-min0-sched75-binary_matrix-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-finalopt-static10k-tistoken-clip0p2-0p28-seed1234-b64-mb32-dp2/global_step_135/data.ptWeights7.0 KB 286b1cea3ac3
experiments/weak_to_strong/reasoning/binary_matrix/distill_baseline/260731-kdrl-b5e3-d6p6667e5-min0-sched75-binary_matrix-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-finalopt-static10k-tistoken-clip0p2-0p28-seed1234-b64-mb32-dp2/global_step_150/actor/extra_state_world_size_2_rank_0.ptWeights15.2 KB 5fa2a7897421
experiments/weak_to_strong/reasoning/binary_matrix/distill_baseline/260731-kdrl-b5e3-d6p6667e5-min0-sched75-binary_matrix-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-finalopt-static10k-tistoken-clip0p2-0p28-seed1234-b64-mb32-dp2/global_step_150/actor/extra_state_world_size_2_rank_1.ptWeights15.2 KB 1f5c68b1b146
experiments/weak_to_strong/reasoning/binary_matrix/distill_baseline/260731-kdrl-b5e3-d6p6667e5-min0-sched75-binary_matrix-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-finalopt-static10k-tistoken-clip0p2-0p28-seed1234-b64-mb32-dp2/global_step_150/actor/model_world_size_2_rank_0.ptWeights16.4 GB 07d8b2204cea
experiments/weak_to_strong/reasoning/binary_matrix/distill_baseline/260731-kdrl-b5e3-d6p6667e5-min0-sched75-binary_matrix-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-finalopt-static10k-tistoken-clip0p2-0p28-seed1234-b64-mb32-dp2/global_step_150/actor/model_world_size_2_rank_1.ptWeights16.4 GB eb7c64c299eb
experiments/weak_to_strong/reasoning/binary_matrix/distill_baseline/260731-kdrl-b5e3-d6p6667e5-min0-sched75-binary_matrix-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-finalopt-static10k-tistoken-clip0p2-0p28-seed1234-b64-mb32-dp2/global_step_150/data.ptWeights7.0 KB 4582c532075e
experiments/weak_to_strong/reasoning/binary_matrix/ours/260728-rcd-binary_matrix-q3-8b-base-t4b-s105-lp0p5fixed-lm0to0p5-s75-tr8k-save30-best-finalopt-tistoken-seed1234-b64-mb32-dp4/global_step_120/actor/extra_state_world_size_4_rank_0.ptWeights15.3 KB 569d64b367b2
experiments/weak_to_strong/reasoning/binary_matrix/ours/260728-rcd-binary_matrix-q3-8b-base-t4b-s105-lp0p5fixed-lm0to0p5-s75-tr8k-save30-best-finalopt-tistoken-seed1234-b64-mb32-dp4/global_step_120/actor/extra_state_world_size_4_rank_1.ptWeights15.3 KB e2625f4c3b57
experiments/weak_to_strong/reasoning/binary_matrix/ours/260728-rcd-binary_matrix-q3-8b-base-t4b-s105-lp0p5fixed-lm0to0p5-s75-tr8k-save30-best-finalopt-tistoken-seed1234-b64-mb32-dp4/global_step_120/actor/extra_state_world_size_4_rank_2.ptWeights15.3 KB f6b829863db1
experiments/weak_to_strong/reasoning/binary_matrix/ours/260728-rcd-binary_matrix-q3-8b-base-t4b-s105-lp0p5fixed-lm0to0p5-s75-tr8k-save30-best-finalopt-tistoken-seed1234-b64-mb32-dp4/global_step_120/actor/extra_state_world_size_4_rank_3.ptWeights15.3 KB 4e8efa16ea8b
experiments/weak_to_strong/reasoning/binary_matrix/ours/260728-rcd-binary_matrix-q3-8b-base-t4b-s105-lp0p5fixed-lm0to0p5-s75-tr8k-save30-best-finalopt-tistoken-seed1234-b64-mb32-dp4/global_step_120/actor/model_world_size_4_rank_0.ptWeights8.2 GB 8e60c40a59f2
experiments/weak_to_strong/reasoning/binary_matrix/ours/260728-rcd-binary_matrix-q3-8b-base-t4b-s105-lp0p5fixed-lm0to0p5-s75-tr8k-save30-best-finalopt-tistoken-seed1234-b64-mb32-dp4/global_step_120/actor/model_world_size_4_rank_1.ptWeights8.2 GB 93c210a2e4d5
experiments/weak_to_strong/reasoning/binary_matrix/ours/260728-rcd-binary_matrix-q3-8b-base-t4b-s105-lp0p5fixed-lm0to0p5-s75-tr8k-save30-best-finalopt-tistoken-seed1234-b64-mb32-dp4/global_step_120/actor/model_world_size_4_rank_2.ptWeights8.2 GB d7ff6edbe716
experiments/weak_to_strong/reasoning/binary_matrix/ours/260728-rcd-binary_matrix-q3-8b-base-t4b-s105-lp0p5fixed-lm0to0p5-s75-tr8k-save30-best-finalopt-tistoken-seed1234-b64-mb32-dp4/global_step_120/actor/model_world_size_4_rank_3.ptWeights8.2 GB da6b6d4ef860
experiments/weak_to_strong/reasoning/binary_matrix/ours/260728-rcd-binary_matrix-q3-8b-base-t4b-s105-lp0p5fixed-lm0to0p5-s75-tr8k-save30-best-finalopt-tistoken-seed1234-b64-mb32-dp4/global_step_120/data.ptWeights7.0 KB ed5c416be2ad
experiments/weak_to_strong/reasoning/binary_matrix/ours/260728-rcd-binary_matrix-q3-8b-base-t4b-s105-lp0p5fixed-lm0to0p5-s75-tr8k-save30-best-finalopt-tistoken-seed1234-b64-mb32-dp4/global_step_150/actor/extra_state_world_size_4_rank_0.ptWeights15.3 KB f904fff00e51
experiments/weak_to_strong/reasoning/binary_matrix/ours/260728-rcd-binary_matrix-q3-8b-base-t4b-s105-lp0p5fixed-lm0to0p5-s75-tr8k-save30-best-finalopt-tistoken-seed1234-b64-mb32-dp4/global_step_150/actor/extra_state_world_size_4_rank_1.ptWeights15.3 KB 81de70f4ccc7
experiments/weak_to_strong/reasoning/binary_matrix/ours/260728-rcd-binary_matrix-q3-8b-base-t4b-s105-lp0p5fixed-lm0to0p5-s75-tr8k-save30-best-finalopt-tistoken-seed1234-b64-mb32-dp4/global_step_150/actor/extra_state_world_size_4_rank_2.ptWeights15.3 KB 7059e48203cf
experiments/weak_to_strong/reasoning/binary_matrix/ours/260728-rcd-binary_matrix-q3-8b-base-t4b-s105-lp0p5fixed-lm0to0p5-s75-tr8k-save30-best-finalopt-tistoken-seed1234-b64-mb32-dp4/global_step_150/actor/extra_state_world_size_4_rank_3.ptWeights15.3 KB 19b3e3e4fbd9
experiments/weak_to_strong/reasoning/binary_matrix/ours/260728-rcd-binary_matrix-q3-8b-base-t4b-s105-lp0p5fixed-lm0to0p5-s75-tr8k-save30-best-finalopt-tistoken-seed1234-b64-mb32-dp4/global_step_150/actor/model_world_size_4_rank_0.ptWeights8.2 GB 6594a916cf2c
experiments/weak_to_strong/reasoning/binary_matrix/ours/260728-rcd-binary_matrix-q3-8b-base-t4b-s105-lp0p5fixed-lm0to0p5-s75-tr8k-save30-best-finalopt-tistoken-seed1234-b64-mb32-dp4/global_step_150/actor/model_world_size_4_rank_1.ptWeights8.2 GB 37d35edab7b6
experiments/weak_to_strong/reasoning/binary_matrix/ours/260728-rcd-binary_matrix-q3-8b-base-t4b-s105-lp0p5fixed-lm0to0p5-s75-tr8k-save30-best-finalopt-tistoken-seed1234-b64-mb32-dp4/global_step_150/actor/model_world_size_4_rank_2.ptWeights8.2 GB c2814bd1a9f0
experiments/weak_to_strong/reasoning/binary_matrix/ours/260728-rcd-binary_matrix-q3-8b-base-t4b-s105-lp0p5fixed-lm0to0p5-s75-tr8k-save30-best-finalopt-tistoken-seed1234-b64-mb32-dp4/global_step_150/actor/model_world_size_4_rank_3.ptWeights8.2 GB c81a36855af7
experiments/weak_to_strong/reasoning/binary_matrix/ours/260728-rcd-binary_matrix-q3-8b-base-t4b-s105-lp0p5fixed-lm0to0p5-s75-tr8k-save30-best-finalopt-tistoken-seed1234-b64-mb32-dp4/global_step_150/data.ptWeights7.0 KB 4582c532075e
experiments/weak_to_strong/reasoning/binary_matrix/ours/260728-rcd-binary_matrix-q3-8b-base-t4b-s105-lp0p5fixed-lm0to0p5-s75-tr8k-save30-best-finalopt-tistoken-seed1234-b64-mb32-dp4/global_step_90/actor/extra_state_world_size_4_rank_0.ptWeights15.3 KB 912daed3ce1c
experiments/weak_to_strong/reasoning/binary_matrix/ours/260728-rcd-binary_matrix-q3-8b-base-t4b-s105-lp0p5fixed-lm0to0p5-s75-tr8k-save30-best-finalopt-tistoken-seed1234-b64-mb32-dp4/global_step_90/actor/extra_state_world_size_4_rank_1.ptWeights15.3 KB 7bc120b492a8
experiments/weak_to_strong/reasoning/binary_matrix/ours/260728-rcd-binary_matrix-q3-8b-base-t4b-s105-lp0p5fixed-lm0to0p5-s75-tr8k-save30-best-finalopt-tistoken-seed1234-b64-mb32-dp4/global_step_90/actor/extra_state_world_size_4_rank_2.ptWeights15.3 KB 9dbda226f7c3
experiments/weak_to_strong/reasoning/binary_matrix/ours/260728-rcd-binary_matrix-q3-8b-base-t4b-s105-lp0p5fixed-lm0to0p5-s75-tr8k-save30-best-finalopt-tistoken-seed1234-b64-mb32-dp4/global_step_90/actor/extra_state_world_size_4_rank_3.ptWeights15.3 KB a42d7ec1caf4
experiments/weak_to_strong/reasoning/binary_matrix/ours/260728-rcd-binary_matrix-q3-8b-base-t4b-s105-lp0p5fixed-lm0to0p5-s75-tr8k-save30-best-finalopt-tistoken-seed1234-b64-mb32-dp4/global_step_90/actor/model_world_size_4_rank_0.ptWeights8.2 GB 886298baede2
experiments/weak_to_strong/reasoning/binary_matrix/ours/260728-rcd-binary_matrix-q3-8b-base-t4b-s105-lp0p5fixed-lm0to0p5-s75-tr8k-save30-best-finalopt-tistoken-seed1234-b64-mb32-dp4/global_step_90/actor/model_world_size_4_rank_1.ptWeights8.2 GB 6b36f1ce9303
experiments/weak_to_strong/reasoning/binary_matrix/ours/260728-rcd-binary_matrix-q3-8b-base-t4b-s105-lp0p5fixed-lm0to0p5-s75-tr8k-save30-best-finalopt-tistoken-seed1234-b64-mb32-dp4/global_step_90/actor/model_world_size_4_rank_2.ptWeights8.2 GB ad9fae7bcf7e
experiments/weak_to_strong/reasoning/binary_matrix/ours/260728-rcd-binary_matrix-q3-8b-base-t4b-s105-lp0p5fixed-lm0to0p5-s75-tr8k-save30-best-finalopt-tistoken-seed1234-b64-mb32-dp4/global_step_90/actor/model_world_size_4_rank_3.ptWeights8.2 GB 1b70929981a0
experiments/weak_to_strong/reasoning/binary_matrix/ours/260728-rcd-binary_matrix-q3-8b-base-t4b-s105-lp0p5fixed-lm0to0p5-s75-tr8k-save30-best-finalopt-tistoken-seed1234-b64-mb32-dp4/global_step_90/data.ptWeights7.0 KB be7eaded59c3
experiments/weak_to_strong/reasoning/binary_matrix/ours/260731-rcd-binary_matrix-q3-8b-base-t4b-s105-h1b-s45-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_120/actor/extra_state_world_size_2_rank_0.ptWeights15.3 KB 7aec01a334e9
experiments/weak_to_strong/reasoning/binary_matrix/ours/260731-rcd-binary_matrix-q3-8b-base-t4b-s105-h1b-s45-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_120/actor/extra_state_world_size_2_rank_1.ptWeights15.3 KB bcb2cf021bab
experiments/weak_to_strong/reasoning/binary_matrix/ours/260731-rcd-binary_matrix-q3-8b-base-t4b-s105-h1b-s45-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_120/actor/model_world_size_2_rank_0.ptWeights16.4 GB a6b2c6c72345
experiments/weak_to_strong/reasoning/binary_matrix/ours/260731-rcd-binary_matrix-q3-8b-base-t4b-s105-h1b-s45-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_120/actor/model_world_size_2_rank_1.ptWeights16.4 GB 3a443c474702
experiments/weak_to_strong/reasoning/binary_matrix/ours/260731-rcd-binary_matrix-q3-8b-base-t4b-s105-h1b-s45-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_120/data.ptWeights7.0 KB ed5c416be2ad
experiments/weak_to_strong/reasoning/binary_matrix/ours/260731-rcd-binary_matrix-q3-8b-base-t4b-s105-h1b-s45-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_150/actor/extra_state_world_size_2_rank_0.ptWeights15.3 KB 27d77b9bba0f
experiments/weak_to_strong/reasoning/binary_matrix/ours/260731-rcd-binary_matrix-q3-8b-base-t4b-s105-h1b-s45-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_150/actor/extra_state_world_size_2_rank_1.ptWeights15.3 KB 5b44af7648ef
experiments/weak_to_strong/reasoning/binary_matrix/ours/260731-rcd-binary_matrix-q3-8b-base-t4b-s105-h1b-s45-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_150/actor/model_world_size_2_rank_0.ptWeights16.4 GB a58126cad7d2
experiments/weak_to_strong/reasoning/binary_matrix/ours/260731-rcd-binary_matrix-q3-8b-base-t4b-s105-h1b-s45-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_150/actor/model_world_size_2_rank_1.ptWeights16.4 GB 1a4fbc03cba1
experiments/weak_to_strong/reasoning/binary_matrix/ours/260731-rcd-binary_matrix-q3-8b-base-t4b-s105-h1b-s45-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_150/data.ptWeights7.0 KB 4582c532075e
experiments/weak_to_strong/reasoning/binary_matrix/ours/260731-rcd-binary_matrix-q3-8b-base-t4b-s105-h1b-s45-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_90/actor/extra_state_world_size_2_rank_0.ptWeights15.3 KB 08e614dc2c62
experiments/weak_to_strong/reasoning/binary_matrix/ours/260731-rcd-binary_matrix-q3-8b-base-t4b-s105-h1b-s45-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_90/actor/extra_state_world_size_2_rank_1.ptWeights15.3 KB d336576356cb
experiments/weak_to_strong/reasoning/binary_matrix/ours/260731-rcd-binary_matrix-q3-8b-base-t4b-s105-h1b-s45-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_90/actor/model_world_size_2_rank_0.ptWeights16.4 GB 07cb278b7ce8
experiments/weak_to_strong/reasoning/binary_matrix/ours/260731-rcd-binary_matrix-q3-8b-base-t4b-s105-h1b-s45-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_90/actor/model_world_size_2_rank_1.ptWeights16.4 GB 904940214940
experiments/weak_to_strong/reasoning/binary_matrix/ours/260731-rcd-binary_matrix-q3-8b-base-t4b-s105-h1b-s45-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_90/data.ptWeights7.0 KB be7eaded59c3
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-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.ptWeights15.2 KB 1f53a6387870
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-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.ptWeights15.2 KB 06bea4d6f1c0
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_150/actor/model_world_size_2_rank_0.ptWeights8.8 GB 381d81e9e7dc
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_150/actor/model_world_size_2_rank_1.ptWeights8.8 GB 8ae7b7f667fb
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_150/actor/optim_world_size_2_rank_0.ptWeights16.1 GB a9cc707453f4
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_120/actor/extra_state_world_size_2_rank_0.ptWeights15.3 KB 1563be8a073e
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_120/actor/extra_state_world_size_2_rank_1.ptWeights15.3 KB b00e21ab02ec
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_120/data.ptWeights7.0 KB a66fc981d533
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_135/actor/extra_state_world_size_2_rank_0.ptWeights15.3 KB 14110e872214
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_135/actor/extra_state_world_size_2_rank_1.ptWeights15.3 KB 1dbaa7338287
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_135/data.ptWeights7.0 KB 30fa55d9f0ad
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_150/actor/extra_state_world_size_2_rank_0.ptWeights15.3 KB cbf1fe5562ad
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_150/actor/extra_state_world_size_2_rank_1.ptWeights15.3 KB f7fbdb0fdd43
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_150/actor/model_world_size_2_rank_0.ptWeights16.4 GB 2fc5611b1d69
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_150/data.ptWeights7.0 KB 6d96285c52da
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_30/actor/extra_state_world_size_2_rank_0.ptWeights15.3 KB 46c2c58f5f64
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_30/actor/extra_state_world_size_2_rank_1.ptWeights15.3 KB 6f264d07c861
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_30/data.ptWeights7.0 KB 3d3cf8f5fa73
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_60/actor/extra_state_world_size_2_rank_0.ptWeights15.3 KB d65bc4b1de1f
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_60/actor/extra_state_world_size_2_rank_1.ptWeights15.3 KB 9ec98ae48cb7
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_60/data.ptWeights7.0 KB fbed549ebe24
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_90/actor/extra_state_world_size_2_rank_0.ptWeights15.3 KB 9ce893852291
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_90/actor/extra_state_world_size_2_rank_1.ptWeights15.3 KB 243d7c837ede
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_90/data.ptWeights7.0 KB cbda6dcb9d24
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260730-sampledrkl-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_105/actor/distill_resume_state_world_size_2_rank_0.ptWeights1.7 KB 108fe00ad721
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260730-sampledrkl-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_105/actor/distill_resume_state_world_size_2_rank_1.ptWeights1.7 KB f9c806678c77
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260730-sampledrkl-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_105/actor/extra_state_world_size_2_rank_0.ptWeights15.2 KB bd323bcb62b1
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260730-sampledrkl-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_105/actor/extra_state_world_size_2_rank_1.ptWeights15.2 KB 7fddf50a6085
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260730-sampledrkl-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_105/data.ptWeights7.0 KB 09a40d508dab
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260730-sampledrkl-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_120/actor/distill_resume_state_world_size_2_rank_0.ptWeights1.7 KB 108fe00ad721
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260730-sampledrkl-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_120/actor/distill_resume_state_world_size_2_rank_1.ptWeights1.7 KB f9c806678c77
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260730-sampledrkl-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_120/actor/extra_state_world_size_2_rank_0.ptWeights15.2 KB 89b6dac0b472
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260730-sampledrkl-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_120/actor/extra_state_world_size_2_rank_1.ptWeights15.2 KB 6afe107d7402
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260730-sampledrkl-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_120/data.ptWeights7.0 KB a66fc981d533
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260730-sampledrkl-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_150/actor/distill_resume_state_world_size_2_rank_0.ptWeights1.7 KB 108fe00ad721
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260730-sampledrkl-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_150/actor/distill_resume_state_world_size_2_rank_1.ptWeights1.7 KB f9c806678c77
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260730-sampledrkl-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_150/actor/extra_state_world_size_2_rank_0.ptWeights15.2 KB 04f829c1e0e1
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260730-sampledrkl-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_150/actor/extra_state_world_size_2_rank_1.ptWeights15.2 KB c4b1bf765ab3
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260730-sampledrkl-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_150/actor/model_world_size_2_rank_0.ptWeights16.4 GB 2207746f6261
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260730-sampledrkl-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_150/data.ptWeights7.0 KB 6d96285c52da
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260730-sampledrkl-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_30/actor/distill_resume_state_world_size_2_rank_0.ptWeights1.7 KB 108fe00ad721
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260730-sampledrkl-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_30/actor/distill_resume_state_world_size_2_rank_1.ptWeights1.7 KB f9c806678c77
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260730-sampledrkl-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_30/actor/extra_state_world_size_2_rank_0.ptWeights15.2 KB 944d279d18a8
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260730-sampledrkl-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_30/actor/extra_state_world_size_2_rank_1.ptWeights15.2 KB b23b1c1d4a4b
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260730-sampledrkl-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_30/data.ptWeights7.0 KB 3d3cf8f5fa73
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260730-sampledrkl-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_60/actor/distill_resume_state_world_size_2_rank_0.ptWeights1.7 KB 108fe00ad721
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260730-sampledrkl-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_60/actor/distill_resume_state_world_size_2_rank_1.ptWeights1.7 KB f9c806678c77
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260730-sampledrkl-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_60/actor/extra_state_world_size_2_rank_0.ptWeights15.2 KB d86ab38cb1d8
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260730-sampledrkl-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_60/actor/extra_state_world_size_2_rank_1.ptWeights15.2 KB 5d1ffb6a09e3
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260730-sampledrkl-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_60/data.ptWeights7.0 KB fbed549ebe24
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260730-sampledrkl-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_90/actor/distill_resume_state_world_size_2_rank_0.ptWeights1.7 KB 108fe00ad721
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260730-sampledrkl-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_90/actor/distill_resume_state_world_size_2_rank_1.ptWeights1.7 KB f9c806678c77
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260730-sampledrkl-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_90/actor/extra_state_world_size_2_rank_0.ptWeights15.2 KB 864a2f7e0367
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260730-sampledrkl-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_90/actor/extra_state_world_size_2_rank_1.ptWeights15.2 KB 2e91b18f27ea
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260730-sampledrkl-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_90/data.ptWeights7.0 KB cbda6dcb9d24
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260731-rerun1-kdrl-b5e3-d6p6667e5-min0-sched75-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-finalopt-static10k-tistoken-clip0p2-0p28-seed42-fastvllm-b64-mb32-dp4/global_step_120/data.ptWeights7.0 KB a66fc981d533
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260731-rerun1-kdrl-b5e3-d6p6667e5-min0-sched75-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-finalopt-static10k-tistoken-clip0p2-0p28-seed42-fastvllm-b64-mb32-dp4/global_step_135/data.ptWeights7.0 KB 30fa55d9f0ad
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260731-rerun1-kdrl-b5e3-d6p6667e5-min0-sched75-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-finalopt-static10k-tistoken-clip0p2-0p28-seed42-fastvllm-b64-mb32-dp4/global_step_150/data.ptWeights7.0 KB 6d96285c52da
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260731-rerun1-kdrl-b5e3-d6p6667e5-min0-sched75-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-finalopt-static10k-tistoken-clip0p2-0p28-seed42-fastvllm-b64-mb32-dp4/global_step_30/data.ptWeights7.0 KB 3d3cf8f5fa73
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260731-rerun1-kdrl-b5e3-d6p6667e5-min0-sched75-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-finalopt-static10k-tistoken-clip0p2-0p28-seed42-fastvllm-b64-mb32-dp4/global_step_45/data.ptWeights7.0 KB fc55ca80ba58
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260731-rerun1-kdrl-b5e3-d6p6667e5-min0-sched75-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-finalopt-static10k-tistoken-clip0p2-0p28-seed42-fastvllm-b64-mb32-dp4/global_step_60/data.ptWeights7.0 KB fbed549ebe24
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260731-rerun1-kdrl-b5e3-d6p6667e5-min0-sched75-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-finalopt-static10k-tistoken-clip0p2-0p28-seed42-fastvllm-b64-mb32-dp4/global_step_90/data.ptWeights7.0 KB cbda6dcb9d24
experiments/weak_to_strong/reasoning/countdown/baseline/260721-grpo-countdown-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_135/actor/extra_state_world_size_4_rank_0.ptWeights15.3 KB 4e67a5282c48
experiments/weak_to_strong/reasoning/countdown/baseline/260721-grpo-countdown-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_135/actor/extra_state_world_size_4_rank_1.ptWeights15.3 KB da2ec3ddb63a
experiments/weak_to_strong/reasoning/countdown/baseline/260721-grpo-countdown-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_135/actor/extra_state_world_size_4_rank_2.ptWeights15.3 KB e8fecc40d20a
experiments/weak_to_strong/reasoning/countdown/baseline/260721-grpo-countdown-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_135/actor/extra_state_world_size_4_rank_3.ptWeights15.3 KB af68bc7081b5
experiments/weak_to_strong/reasoning/countdown/baseline/260721-grpo-countdown-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_135/actor/model_world_size_4_rank_0.ptWeights8.2 GB ebc426380adb
experiments/weak_to_strong/reasoning/countdown/baseline/260721-grpo-countdown-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_135/actor/model_world_size_4_rank_1.ptWeights8.2 GB ea50aac0814a
experiments/weak_to_strong/reasoning/countdown/baseline/260721-grpo-countdown-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_135/actor/model_world_size_4_rank_2.ptWeights8.2 GB 08aec2cb0964
experiments/weak_to_strong/reasoning/countdown/baseline/260721-grpo-countdown-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_135/actor/model_world_size_4_rank_3.ptWeights8.2 GB 4ec88eced742
experiments/weak_to_strong/reasoning/countdown/baseline/260721-grpo-countdown-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_135/data.ptWeights7.0 KB 30fa55d9f0ad
experiments/weak_to_strong/reasoning/countdown/baseline/260721-grpo-countdown-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_150/actor/extra_state_world_size_4_rank_0.ptWeights15.3 KB 9efcf1fa0e53
experiments/weak_to_strong/reasoning/countdown/baseline/260721-grpo-countdown-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_150/actor/extra_state_world_size_4_rank_1.ptWeights15.3 KB 665a42b56ef3
experiments/weak_to_strong/reasoning/countdown/baseline/260721-grpo-countdown-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_150/actor/extra_state_world_size_4_rank_2.ptWeights15.3 KB b210b5c067b2
experiments/weak_to_strong/reasoning/countdown/baseline/260721-grpo-countdown-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_150/actor/extra_state_world_size_4_rank_3.ptWeights15.3 KB 962b0a4a1e69
experiments/weak_to_strong/reasoning/countdown/baseline/260721-grpo-countdown-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_150/actor/model_world_size_4_rank_0.ptWeights8.2 GB deb058be2eeb
experiments/weak_to_strong/reasoning/countdown/baseline/260721-grpo-countdown-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_150/actor/model_world_size_4_rank_1.ptWeights8.2 GB 8ccc8e8595c0
experiments/weak_to_strong/reasoning/countdown/baseline/260721-grpo-countdown-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_150/actor/model_world_size_4_rank_2.ptWeights8.2 GB cbe6ea1e982d
experiments/weak_to_strong/reasoning/countdown/baseline/260721-grpo-countdown-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_150/actor/model_world_size_4_rank_3.ptWeights8.2 GB 574c2dd60c69
experiments/weak_to_strong/reasoning/countdown/baseline/260721-grpo-countdown-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_150/actor/optim_world_size_4_rank_0.ptWeights16.4 GB 7a8fbc47a9d4
experiments/weak_to_strong/reasoning/countdown/baseline/260721-grpo-countdown-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_150/actor/optim_world_size_4_rank_1.ptWeights16.4 GB 67fad5363b31
experiments/weak_to_strong/reasoning/countdown/baseline/260721-grpo-countdown-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_150/actor/optim_world_size_4_rank_2.ptWeights16.4 GB 754f41e7f81a
experiments/weak_to_strong/reasoning/countdown/baseline/260721-grpo-countdown-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_150/actor/optim_world_size_4_rank_3.ptWeights16.4 GB 0747559a61bb
experiments/weak_to_strong/reasoning/countdown/baseline/260721-grpo-countdown-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_150/data.ptWeights7.0 KB 6d96285c52da
experiments/weak_to_strong/reasoning/countdown/distill_baseline/260730-sampledrkl-countdown-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_15/actor/distill_resume_state_world_size_2_rank_0.ptWeights1.7 KB e2842b11c31a
experiments/weak_to_strong/reasoning/countdown/distill_baseline/260730-sampledrkl-countdown-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_15/actor/distill_resume_state_world_size_2_rank_1.ptWeights1.7 KB 3054804825a6
experiments/weak_to_strong/reasoning/countdown/distill_baseline/260730-sampledrkl-countdown-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_15/actor/extra_state_world_size_2_rank_0.ptWeights15.2 KB 1945da4045b7
experiments/weak_to_strong/reasoning/countdown/distill_baseline/260730-sampledrkl-countdown-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_15/actor/extra_state_world_size_2_rank_1.ptWeights15.2 KB 74e59f259b32
experiments/weak_to_strong/reasoning/countdown/distill_baseline/260730-sampledrkl-countdown-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_15/data.ptWeights7.0 KB dd157db893bc
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_100/actor/extra_state_world_size_4_rank_0.ptWeights15.3 KB 1749b1d81a0a
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_100/actor/extra_state_world_size_4_rank_1.ptWeights15.3 KB ba1640757da5
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_100/actor/extra_state_world_size_4_rank_2.ptWeights15.3 KB 18cae106e0e0
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_100/actor/extra_state_world_size_4_rank_3.ptWeights15.3 KB 4f21adc7d27b
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_100/actor/model_world_size_4_rank_1.ptWeights8.2 GB 9be6ed2bf027
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_100/actor/model_world_size_4_rank_2.ptWeights8.2 GB 381fd3216fd6
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_100/actor/model_world_size_4_rank_3.ptWeights8.2 GB 2551dcd1c411
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_100/data.ptWeights7.0 KB 09ed80b85ea1
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_105/actor/extra_state_world_size_4_rank_0.ptWeights15.3 KB 74dd338c14ae
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_105/actor/extra_state_world_size_4_rank_1.ptWeights15.3 KB 68a15e617e7b
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_105/actor/extra_state_world_size_4_rank_2.ptWeights15.3 KB b72554d42873
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_105/actor/extra_state_world_size_4_rank_3.ptWeights15.3 KB 838c33ea1f06
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_105/actor/model_world_size_4_rank_0.ptWeights8.2 GB 02ded7905e99
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_105/actor/model_world_size_4_rank_1.ptWeights8.2 GB ae110a01b209
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_105/actor/model_world_size_4_rank_2.ptWeights8.2 GB 77b886509876
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_105/actor/model_world_size_4_rank_3.ptWeights8.2 GB 4894a99d4524
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_105/data.ptWeights7.0 KB 09a40d508dab
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_120/actor/extra_state_world_size_4_rank_0.ptWeights15.3 KB 5ff93557ce5a
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_120/actor/extra_state_world_size_4_rank_1.ptWeights15.3 KB cde733bb7461
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_120/actor/extra_state_world_size_4_rank_2.ptWeights15.3 KB 7fa94ecea2db
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_120/actor/extra_state_world_size_4_rank_3.ptWeights15.3 KB 5408f2155b89
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_120/actor/model_world_size_4_rank_0.ptWeights8.2 GB 690a3a88f6af
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_120/actor/model_world_size_4_rank_1.ptWeights8.2 GB 4cd7ae62c787
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_120/actor/model_world_size_4_rank_2.ptWeights8.2 GB b6e0fdd7a9c1
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_120/data.ptWeights7.0 KB a66fc981d533
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_135/actor/extra_state_world_size_4_rank_0.ptWeights15.3 KB 26f5f87bcef8
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_135/actor/extra_state_world_size_4_rank_1.ptWeights15.3 KB d7f38eea69d8
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_135/actor/extra_state_world_size_4_rank_2.ptWeights15.3 KB a710d02a393b
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_135/actor/extra_state_world_size_4_rank_3.ptWeights15.3 KB b15ca0b57f23
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_135/actor/model_world_size_4_rank_0.ptWeights8.2 GB 8de03b7e8ab9
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_135/actor/model_world_size_4_rank_1.ptWeights8.2 GB fffe7e01b424
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_135/actor/model_world_size_4_rank_2.ptWeights8.2 GB 1a67ca793cd3
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_135/actor/model_world_size_4_rank_3.ptWeights8.2 GB 5e132c814a5d
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_135/data.ptWeights7.0 KB 30fa55d9f0ad
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_15/actor/extra_state_world_size_4_rank_0.ptWeights15.3 KB 4e8b37db0992
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_15/actor/extra_state_world_size_4_rank_1.ptWeights15.3 KB 2187257fff6e
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_15/actor/extra_state_world_size_4_rank_2.ptWeights15.3 KB 5858924d244e
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_15/actor/extra_state_world_size_4_rank_3.ptWeights15.3 KB ac7def1379a6
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_15/actor/model_world_size_4_rank_0.ptWeights8.2 GB 60f16923f8a0
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_15/actor/model_world_size_4_rank_1.ptWeights8.2 GB 3a1e1b782a5d
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_15/actor/model_world_size_4_rank_2.ptWeights8.2 GB 06c7620ea9c0
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_15/actor/model_world_size_4_rank_3.ptWeights8.2 GB 8d4c3110171a
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_15/data.ptWeights7.0 KB dd157db893bc
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_150/actor/extra_state_world_size_4_rank_0.ptWeights15.3 KB 8b670eecf612
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_150/actor/extra_state_world_size_4_rank_1.ptWeights15.3 KB 9b297ef5bed6
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_150/actor/extra_state_world_size_4_rank_2.ptWeights15.3 KB cf0b2a891efc
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_150/actor/extra_state_world_size_4_rank_3.ptWeights15.3 KB 48fbd95fbca2
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_150/actor/model_world_size_4_rank_0.ptWeights8.2 GB 594f58f91f94
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_150/actor/model_world_size_4_rank_1.ptWeights8.2 GB 7faad42e0662
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_150/actor/model_world_size_4_rank_2.ptWeights8.2 GB b279b9067eaf
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_150/actor/model_world_size_4_rank_3.ptWeights8.2 GB cdd97da765df
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_150/actor/optim_world_size_4_rank_0.ptWeights16.4 GB 42f7b7065994
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_150/actor/optim_world_size_4_rank_1.ptWeights16.4 GB 84020bb8460a
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_150/actor/optim_world_size_4_rank_2.ptWeights16.4 GB 39b44b4a9189
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_150/actor/optim_world_size_4_rank_3.ptWeights16.4 GB 95299e21bf04
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_150/data.ptWeights7.0 KB 6d96285c52da
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_30/actor/extra_state_world_size_4_rank_0.ptWeights15.3 KB 3199ad1dbd1b
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_30/actor/extra_state_world_size_4_rank_1.ptWeights15.3 KB 4d041630a7f6
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_30/actor/extra_state_world_size_4_rank_2.ptWeights15.3 KB b8094274b77e
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_30/actor/extra_state_world_size_4_rank_3.ptWeights15.3 KB 05b469fa543e
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_30/actor/model_world_size_4_rank_0.ptWeights8.2 GB 1e7c0c725a61
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_30/actor/model_world_size_4_rank_1.ptWeights8.2 GB a7596f104744
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_30/actor/model_world_size_4_rank_2.ptWeights8.2 GB 7d21c062d092
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_30/actor/model_world_size_4_rank_3.ptWeights8.2 GB 06919d3199ca
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_45/actor/extra_state_world_size_4_rank_0.ptWeights15.3 KB 46851db0df23
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_45/actor/extra_state_world_size_4_rank_1.ptWeights15.3 KB d6eaa0095434
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_45/actor/extra_state_world_size_4_rank_2.ptWeights15.3 KB 1599c7ace749
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_45/actor/extra_state_world_size_4_rank_3.ptWeights15.3 KB 4f5b26f588b2
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_45/actor/model_world_size_4_rank_0.ptWeights8.2 GB a3951028b579
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_45/actor/model_world_size_4_rank_1.ptWeights8.2 GB 574a050bc20e
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_45/actor/model_world_size_4_rank_2.ptWeights8.2 GB 6a08c417d094
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_45/actor/model_world_size_4_rank_3.ptWeights8.2 GB e523a18e0abb
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_45/data.ptWeights7.0 KB fc55ca80ba58
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_50/actor/extra_state_world_size_4_rank_0.ptWeights15.3 KB 797b42f1dea4
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_50/actor/extra_state_world_size_4_rank_1.ptWeights15.3 KB 004b97892d49
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_50/actor/extra_state_world_size_4_rank_2.ptWeights15.3 KB 571f74b227a1
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_50/actor/extra_state_world_size_4_rank_3.ptWeights15.3 KB 1ead95ddb8e1
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_50/actor/model_world_size_4_rank_0.ptWeights8.2 GB 3940403592f1
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_50/actor/model_world_size_4_rank_1.ptWeights8.2 GB 174593e198cc
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_50/actor/model_world_size_4_rank_2.ptWeights8.2 GB 96f40b31bf17
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_50/actor/model_world_size_4_rank_3.ptWeights8.2 GB a369a3051741
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_50/data.ptWeights7.0 KB 715447bc8d43
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_60/actor/extra_state_world_size_4_rank_0.ptWeights15.3 KB 8e213321a522
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_60/actor/extra_state_world_size_4_rank_1.ptWeights15.3 KB ce42aecf4277
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_60/actor/extra_state_world_size_4_rank_2.ptWeights15.3 KB d930897c25c0
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_60/actor/extra_state_world_size_4_rank_3.ptWeights15.3 KB 764547b5b981
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_60/actor/model_world_size_4_rank_0.ptWeights8.2 GB 5fbae8d99755
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_60/actor/model_world_size_4_rank_1.ptWeights8.2 GB e36aad0b7ae8
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_60/actor/model_world_size_4_rank_2.ptWeights8.2 GB 69ed5a72cff2
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_60/actor/model_world_size_4_rank_3.ptWeights8.2 GB 4769fa553300
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_60/data.ptWeights7.0 KB fbed549ebe24
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_75/actor/extra_state_world_size_4_rank_0.ptWeights15.3 KB 0a2e8b7f792f
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_75/actor/extra_state_world_size_4_rank_1.ptWeights15.3 KB 98167b309706
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_75/actor/extra_state_world_size_4_rank_2.ptWeights15.3 KB 0a6a414eb0ad
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_75/actor/extra_state_world_size_4_rank_3.ptWeights15.3 KB 79e9a82526b4
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_75/actor/model_world_size_4_rank_0.ptWeights8.2 GB f64bc0fe0ab1
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_75/actor/model_world_size_4_rank_1.ptWeights8.2 GB 0d53ecf13d28
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_75/actor/model_world_size_4_rank_2.ptWeights8.2 GB 74a49de76f29
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_75/actor/model_world_size_4_rank_3.ptWeights8.2 GB 8765f0fad19c
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_75/data.ptWeights7.0 KB 24aeb2207229
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_90/actor/extra_state_world_size_4_rank_0.ptWeights15.3 KB e20b7e6416e2
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_90/actor/extra_state_world_size_4_rank_1.ptWeights15.3 KB 7b1bb075a841
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_90/actor/extra_state_world_size_4_rank_2.ptWeights15.3 KB fe173608fecd
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_90/actor/extra_state_world_size_4_rank_3.ptWeights15.3 KB 1bd5778cc2e4
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_90/actor/model_world_size_4_rank_0.ptWeights8.2 GB 8e5d83e953d5
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_90/actor/model_world_size_4_rank_1.ptWeights8.2 GB 84f5c9e7b90a
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_90/actor/model_world_size_4_rank_2.ptWeights8.2 GB 37a9de9c9fbe
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_90/actor/model_world_size_4_rank_3.ptWeights8.2 GB 204d0c441b76
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_90/data.ptWeights7.0 KB cbda6dcb9d24
diagnostics/DCTN-0915155925/260922_pixel_3b_upload_check.jsonConfiguration199 B —
experiments/distillation/reasoning/binary_matrix/baseline/260716-grpo-binary_matrix-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/best_validation_checkpoint.jsonConfiguration226 B —
experiments/distillation/reasoning/binary_matrix/baseline/260716-grpo-binary_matrix-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_150/actor/.async_checkpoint_ready_world_size_2_rank_0.jsonConfiguration370 B —
experiments/distillation/reasoning/binary_matrix/baseline/260716-grpo-binary_matrix-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_150/actor/.async_checkpoint_ready_world_size_2_rank_1.jsonConfiguration183 B —
experiments/distillation/reasoning/binary_matrix/baseline/260716-grpo-binary_matrix-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_150/actor/.async_checkpoint_started_world_size_2_rank_0.jsonConfiguration62 B —
experiments/distillation/reasoning/binary_matrix/baseline/260716-grpo-binary_matrix-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_150/actor/.async_checkpoint_started_world_size_2_rank_1.jsonConfiguration62 B —
experiments/distillation/reasoning/binary_matrix/baseline/260716-grpo-binary_matrix-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_150/actor/.checkpoint_complete.jsonConfiguration51 B —
experiments/distillation/reasoning/binary_matrix/baseline/260716-grpo-binary_matrix-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_150/actor/.worker_sidecars_ready_world_size_2_rank_0.jsonConfiguration84 B —
experiments/distillation/reasoning/binary_matrix/baseline/260716-grpo-binary_matrix-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_150/actor/.worker_sidecars_ready_world_size_2_rank_1.jsonConfiguration84 B —
experiments/distillation/reasoning/binary_matrix/baseline/260716-grpo-binary_matrix-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_150/actor/fsdp_config.jsonConfiguration46 B —
experiments/distillation/reasoning/binary_matrix/baseline/260716-grpo-binary_matrix-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_150/actor/huggingface/config.jsonConfiguration1.6 KB —
experiments/distillation/reasoning/binary_matrix/baseline/260716-grpo-binary_matrix-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_150/actor/huggingface/generation_config.jsonConfiguration139 B —
experiments/distillation/reasoning/binary_matrix/baseline/260716-grpo-binary_matrix-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/latest_checkpoint.jsonConfiguration243 B —
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/best_validation_checkpoint.jsonConfiguration222 B —
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_105/actor/.async_checkpoint_ready_world_size_2_rank_0.jsonConfiguration370 B —
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_105/actor/.async_checkpoint_ready_world_size_2_rank_1.jsonConfiguration183 B —
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_105/actor/.async_checkpoint_started_world_size_2_rank_0.jsonConfiguration62 B —
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_105/actor/.async_checkpoint_started_world_size_2_rank_1.jsonConfiguration62 B —
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_105/actor/.checkpoint_complete.jsonConfiguration51 B —
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_105/actor/.worker_sidecars_ready_world_size_2_rank_0.jsonConfiguration84 B —
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_105/actor/.worker_sidecars_ready_world_size_2_rank_1.jsonConfiguration84 B —
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_105/actor/fsdp_config.jsonConfiguration46 B —
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_105/actor/huggingface/config.jsonConfiguration1.6 KB —
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_105/actor/huggingface/generation_config.jsonConfiguration139 B —
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_120/actor/.async_checkpoint_ready_world_size_2_rank_0.jsonConfiguration370 B —
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_120/actor/.async_checkpoint_ready_world_size_2_rank_1.jsonConfiguration183 B —
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_120/actor/.async_checkpoint_started_world_size_2_rank_0.jsonConfiguration62 B —
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_120/actor/.async_checkpoint_started_world_size_2_rank_1.jsonConfiguration62 B —
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_120/actor/.checkpoint_complete.jsonConfiguration51 B —
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_120/actor/.worker_sidecars_ready_world_size_2_rank_0.jsonConfiguration84 B —
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_120/actor/.worker_sidecars_ready_world_size_2_rank_1.jsonConfiguration84 B —
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_120/actor/fsdp_config.jsonConfiguration46 B —
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_120/actor/huggingface/config.jsonConfiguration1.6 KB —
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_120/actor/huggingface/generation_config.jsonConfiguration139 B —
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_135/actor/.async_checkpoint_ready_world_size_2_rank_0.jsonConfiguration370 B —
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_135/actor/.async_checkpoint_ready_world_size_2_rank_1.jsonConfiguration183 B —
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_135/actor/.async_checkpoint_started_world_size_2_rank_0.jsonConfiguration62 B —
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_135/actor/.async_checkpoint_started_world_size_2_rank_1.jsonConfiguration62 B —
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_135/actor/.checkpoint_complete.jsonConfiguration51 B —
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_135/actor/.worker_sidecars_ready_world_size_2_rank_0.jsonConfiguration84 B —
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_135/actor/.worker_sidecars_ready_world_size_2_rank_1.jsonConfiguration84 B —
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_135/actor/fsdp_config.jsonConfiguration46 B —
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_135/actor/huggingface/config.jsonConfiguration1.6 KB —
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_135/actor/huggingface/generation_config.jsonConfiguration139 B —
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_15/actor/.async_checkpoint_ready_world_size_2_rank_0.jsonConfiguration369 B —
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_15/actor/.async_checkpoint_ready_world_size_2_rank_1.jsonConfiguration182 B —
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_15/actor/.async_checkpoint_started_world_size_2_rank_0.jsonConfiguration61 B —
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_15/actor/.async_checkpoint_started_world_size_2_rank_1.jsonConfiguration61 B —
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_15/actor/.checkpoint_complete.jsonConfiguration50 B —
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_15/actor/.worker_sidecars_ready_world_size_2_rank_0.jsonConfiguration83 B —
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_15/actor/.worker_sidecars_ready_world_size_2_rank_1.jsonConfiguration83 B —
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_15/actor/fsdp_config.jsonConfiguration46 B —
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_15/actor/huggingface/config.jsonConfiguration1.6 KB —
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_15/actor/huggingface/generation_config.jsonConfiguration139 B —
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_150/actor/.async_checkpoint_ready_world_size_2_rank_0.jsonConfiguration370 B —
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_150/actor/.async_checkpoint_ready_world_size_2_rank_1.jsonConfiguration183 B —
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_150/actor/.async_checkpoint_started_world_size_2_rank_0.jsonConfiguration62 B —
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_150/actor/.async_checkpoint_started_world_size_2_rank_1.jsonConfiguration62 B —
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_150/actor/.checkpoint_complete.jsonConfiguration51 B —
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_150/actor/.worker_sidecars_ready_world_size_2_rank_0.jsonConfiguration84 B —
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_150/actor/.worker_sidecars_ready_world_size_2_rank_1.jsonConfiguration84 B —
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_150/actor/fsdp_config.jsonConfiguration46 B —
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_150/actor/huggingface/config.jsonConfiguration1.6 KB —
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_150/actor/huggingface/generation_config.jsonConfiguration139 B —
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_30/actor/.async_checkpoint_ready_world_size_2_rank_0.jsonConfiguration369 B —
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_30/actor/.async_checkpoint_ready_world_size_2_rank_1.jsonConfiguration182 B —
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_30/actor/.async_checkpoint_started_world_size_2_rank_0.jsonConfiguration61 B —
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_30/actor/.async_checkpoint_started_world_size_2_rank_1.jsonConfiguration61 B —
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_30/actor/.checkpoint_complete.jsonConfiguration50 B —
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_30/actor/.worker_sidecars_ready_world_size_2_rank_0.jsonConfiguration83 B —
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_30/actor/.worker_sidecars_ready_world_size_2_rank_1.jsonConfiguration83 B —
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_30/actor/fsdp_config.jsonConfiguration46 B —
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_30/actor/huggingface/config.jsonConfiguration1.6 KB —
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_30/actor/huggingface/generation_config.jsonConfiguration139 B —
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_45/actor/.async_checkpoint_ready_world_size_2_rank_0.jsonConfiguration369 B —
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_45/actor/.async_checkpoint_ready_world_size_2_rank_1.jsonConfiguration182 B —
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_45/actor/.async_checkpoint_started_world_size_2_rank_0.jsonConfiguration61 B —
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_45/actor/.async_checkpoint_started_world_size_2_rank_1.jsonConfiguration61 B —
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_45/actor/.checkpoint_complete.jsonConfiguration50 B —
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_45/actor/.worker_sidecars_ready_world_size_2_rank_0.jsonConfiguration83 B —
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_45/actor/.worker_sidecars_ready_world_size_2_rank_1.jsonConfiguration83 B —
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_45/actor/fsdp_config.jsonConfiguration46 B —
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_45/actor/huggingface/config.jsonConfiguration1.6 KB —
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_45/actor/huggingface/generation_config.jsonConfiguration139 B —
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_60/actor/.async_checkpoint_ready_world_size_2_rank_0.jsonConfiguration369 B —
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_60/actor/.async_checkpoint_ready_world_size_2_rank_1.jsonConfiguration182 B —
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_60/actor/.async_checkpoint_started_world_size_2_rank_0.jsonConfiguration61 B —
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_60/actor/.async_checkpoint_started_world_size_2_rank_1.jsonConfiguration61 B —
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_60/actor/.checkpoint_complete.jsonConfiguration50 B —
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_60/actor/.worker_sidecars_ready_world_size_2_rank_0.jsonConfiguration83 B —
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_60/actor/.worker_sidecars_ready_world_size_2_rank_1.jsonConfiguration83 B —
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_60/actor/fsdp_config.jsonConfiguration46 B —
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_60/actor/huggingface/config.jsonConfiguration1.6 KB —
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_60/actor/huggingface/generation_config.jsonConfiguration139 B —
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_75/actor/.async_checkpoint_ready_world_size_2_rank_0.jsonConfiguration369 B —
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_75/actor/.async_checkpoint_ready_world_size_2_rank_1.jsonConfiguration182 B —
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_75/actor/.async_checkpoint_started_world_size_2_rank_0.jsonConfiguration61 B —
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_75/actor/.async_checkpoint_started_world_size_2_rank_1.jsonConfiguration61 B —
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_75/actor/.checkpoint_complete.jsonConfiguration50 B —
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_75/actor/.worker_sidecars_ready_world_size_2_rank_0.jsonConfiguration83 B —
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_75/actor/.worker_sidecars_ready_world_size_2_rank_1.jsonConfiguration83 B —
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_75/actor/fsdp_config.jsonConfiguration46 B —
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_75/actor/huggingface/config.jsonConfiguration1.6 KB —
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_75/actor/huggingface/generation_config.jsonConfiguration139 B —
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_90/actor/.async_checkpoint_ready_world_size_2_rank_0.jsonConfiguration369 B —
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_90/actor/.async_checkpoint_ready_world_size_2_rank_1.jsonConfiguration182 B —
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_90/actor/.async_checkpoint_started_world_size_2_rank_0.jsonConfiguration61 B —
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_90/actor/.async_checkpoint_started_world_size_2_rank_1.jsonConfiguration61 B —
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_90/actor/.checkpoint_complete.jsonConfiguration50 B —
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_90/actor/.worker_sidecars_ready_world_size_2_rank_0.jsonConfiguration83 B —
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_90/actor/.worker_sidecars_ready_world_size_2_rank_1.jsonConfiguration83 B —
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_90/actor/fsdp_config.jsonConfiguration46 B —
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_90/actor/huggingface/config.jsonConfiguration1.6 KB —
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/global_step_90/actor/huggingface/generation_config.jsonConfiguration139 B —
experiments/distillation/reasoning/countdown/baseline/260716-grpo-countdown-q3-4b-base-s150-tr8k-va8k-save15-b64-mb32-dp2/latest_checkpoint.jsonConfiguration331 B —
experiments/weak_to_strong/agent/baseline/260917-pixel-qwen25vl-3b-grpo-b64-n8-step150-2gpu/global_step_30/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/agent/baseline/260917-pixel-qwen25vl-3b-grpo-b64-n8-step150-2gpu/global_step_30/actor/huggingface/added_tokens.jsonConfiguration605 B —
experiments/weak_to_strong/agent/baseline/260917-pixel-qwen25vl-3b-grpo-b64-n8-step150-2gpu/global_step_30/actor/huggingface/config.jsonConfiguration3.4 KB —
experiments/weak_to_strong/agent/baseline/260917-pixel-qwen25vl-3b-grpo-b64-n8-step150-2gpu/global_step_30/actor/huggingface/generation_config.jsonConfiguration214 B —
experiments/weak_to_strong/agent/baseline/260917-pixel-qwen25vl-3b-grpo-b64-n8-step150-2gpu/global_step_30/actor/huggingface/model.safetensors.index.jsonConfiguration65.5 KB —
experiments/weak_to_strong/agent/baseline/260917-pixel-qwen25vl-3b-grpo-b64-n8-step150-2gpu/global_step_30/actor/huggingface/preprocessor_config.jsonConfiguration829 B —
experiments/weak_to_strong/agent/baseline/260917-pixel-qwen25vl-3b-grpo-b64-n8-step150-2gpu/global_step_30/actor/huggingface/special_tokens_map.jsonConfiguration613 B —
experiments/weak_to_strong/agent/baseline/260917-pixel-qwen25vl-3b-grpo-b64-n8-step150-2gpu/global_step_30/actor/huggingface/video_preprocessor_config.jsonConfiguration955 B —
experiments/weak_to_strong/agent/baseline/260917-pixel-qwen25vl-3b-grpo-b64-n8-step150-2gpu/global_step_30/resolved_config.yamlConfiguration17.6 KB —
experiments/weak_to_strong/agent/baseline/260917-pixel-qwen25vl-3b-grpo-b64-n8-step150-2gpu/global_step_60/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/agent/baseline/260917-pixel-qwen25vl-3b-grpo-b64-n8-step150-2gpu/global_step_60/actor/huggingface/added_tokens.jsonConfiguration605 B —
experiments/weak_to_strong/agent/baseline/260917-pixel-qwen25vl-3b-grpo-b64-n8-step150-2gpu/global_step_60/actor/huggingface/config.jsonConfiguration3.4 KB —
experiments/weak_to_strong/agent/baseline/260917-pixel-qwen25vl-3b-grpo-b64-n8-step150-2gpu/global_step_60/actor/huggingface/generation_config.jsonConfiguration214 B —
experiments/weak_to_strong/agent/baseline/260917-pixel-qwen25vl-3b-grpo-b64-n8-step150-2gpu/global_step_60/actor/huggingface/model.safetensors.index.jsonConfiguration65.5 KB —
experiments/weak_to_strong/agent/baseline/260917-pixel-qwen25vl-3b-grpo-b64-n8-step150-2gpu/global_step_60/actor/huggingface/preprocessor_config.jsonConfiguration829 B —
experiments/weak_to_strong/agent/baseline/260917-pixel-qwen25vl-3b-grpo-b64-n8-step150-2gpu/global_step_60/actor/huggingface/special_tokens_map.jsonConfiguration613 B —
experiments/weak_to_strong/agent/baseline/260917-pixel-qwen25vl-3b-grpo-b64-n8-step150-2gpu/global_step_60/actor/huggingface/video_preprocessor_config.jsonConfiguration955 B —
experiments/weak_to_strong/agent/baseline/260917-pixel-qwen25vl-3b-grpo-b64-n8-step150-2gpu/global_step_60/resolved_config.yamlConfiguration17.6 KB —
experiments/weak_to_strong/agent/baseline/260917-pixel-qwen25vl-3b-grpo-b64-n8-step150-2gpu/latest_checkpoint.jsonConfiguration233 B —
experiments/weak_to_strong/agent/baseline/260917-pixel-qwen25vl-3b-grpo-b64-n8-step150/resolved_config.yamlConfiguration17.5 KB —
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen25vl-3b-grpo-b64-mb32-n8-sysv1-step150-2gpu-fp32/global_step_30/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen25vl-3b-grpo-b64-mb32-n8-sysv1-step150-2gpu-fp32/global_step_30/actor/huggingface/added_tokens.jsonConfiguration605 B —
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen25vl-3b-grpo-b64-mb32-n8-sysv1-step150-2gpu-fp32/global_step_30/actor/huggingface/config.jsonConfiguration3.4 KB —
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen25vl-3b-grpo-b64-mb32-n8-sysv1-step150-2gpu-fp32/global_step_30/actor/huggingface/generation_config.jsonConfiguration214 B —
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen25vl-3b-grpo-b64-mb32-n8-sysv1-step150-2gpu-fp32/global_step_30/actor/huggingface/model.safetensors.index.jsonConfiguration65.5 KB —
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen25vl-3b-grpo-b64-mb32-n8-sysv1-step150-2gpu-fp32/global_step_30/actor/huggingface/preprocessor_config.jsonConfiguration829 B —
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen25vl-3b-grpo-b64-mb32-n8-sysv1-step150-2gpu-fp32/global_step_30/actor/huggingface/special_tokens_map.jsonConfiguration613 B —
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen25vl-3b-grpo-b64-mb32-n8-sysv1-step150-2gpu-fp32/global_step_30/actor/huggingface/video_preprocessor_config.jsonConfiguration955 B —
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen25vl-3b-grpo-b64-mb32-n8-sysv1-step150-2gpu-fp32/global_step_30/resolved_config.yamlConfiguration17.8 KB —
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen25vl-3b-grpo-b64-mb32-n8-sysv1-step150-2gpu-fp32/latest_checkpoint.jsonConfiguration249 B —
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen25vl-3b-grpo-b64-mb64-n8-sysv1-step150-2gpu-fp32/global_step_120/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen25vl-3b-grpo-b64-mb64-n8-sysv1-step150-2gpu-fp32/global_step_120/actor/huggingface/added_tokens.jsonConfiguration605 B —
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen25vl-3b-grpo-b64-mb64-n8-sysv1-step150-2gpu-fp32/global_step_120/actor/huggingface/config.jsonConfiguration3.4 KB —
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen25vl-3b-grpo-b64-mb64-n8-sysv1-step150-2gpu-fp32/global_step_120/actor/huggingface/generation_config.jsonConfiguration214 B —
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen25vl-3b-grpo-b64-mb64-n8-sysv1-step150-2gpu-fp32/global_step_120/actor/huggingface/model.safetensors.index.jsonConfiguration65.5 KB —
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen25vl-3b-grpo-b64-mb64-n8-sysv1-step150-2gpu-fp32/global_step_120/actor/huggingface/preprocessor_config.jsonConfiguration829 B —
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen25vl-3b-grpo-b64-mb64-n8-sysv1-step150-2gpu-fp32/global_step_120/actor/huggingface/special_tokens_map.jsonConfiguration613 B —
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen25vl-3b-grpo-b64-mb64-n8-sysv1-step150-2gpu-fp32/global_step_120/actor/huggingface/video_preprocessor_config.jsonConfiguration955 B —
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen25vl-3b-grpo-b64-mb64-n8-sysv1-step150-2gpu-fp32/global_step_120/resolved_config.yamlConfiguration17.8 KB —
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen25vl-3b-grpo-b64-mb64-n8-sysv1-step150-2gpu-fp32/global_step_150/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen25vl-3b-grpo-b64-mb64-n8-sysv1-step150-2gpu-fp32/global_step_150/actor/huggingface/added_tokens.jsonConfiguration605 B —
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen25vl-3b-grpo-b64-mb64-n8-sysv1-step150-2gpu-fp32/global_step_150/actor/huggingface/config.jsonConfiguration3.4 KB —
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen25vl-3b-grpo-b64-mb64-n8-sysv1-step150-2gpu-fp32/global_step_150/actor/huggingface/generation_config.jsonConfiguration214 B —
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen25vl-3b-grpo-b64-mb64-n8-sysv1-step150-2gpu-fp32/global_step_150/actor/huggingface/model.safetensors.index.jsonConfiguration65.5 KB —
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen25vl-3b-grpo-b64-mb64-n8-sysv1-step150-2gpu-fp32/global_step_150/actor/huggingface/preprocessor_config.jsonConfiguration829 B —
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen25vl-3b-grpo-b64-mb64-n8-sysv1-step150-2gpu-fp32/global_step_150/actor/huggingface/special_tokens_map.jsonConfiguration613 B —
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen25vl-3b-grpo-b64-mb64-n8-sysv1-step150-2gpu-fp32/global_step_150/actor/huggingface/video_preprocessor_config.jsonConfiguration955 B —
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen25vl-3b-grpo-b64-mb64-n8-sysv1-step150-2gpu-fp32/global_step_150/resolved_config.yamlConfiguration17.8 KB —
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen25vl-3b-grpo-b64-mb64-n8-sysv1-step150-2gpu-fp32/global_step_30/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen25vl-3b-grpo-b64-mb64-n8-sysv1-step150-2gpu-fp32/global_step_30/actor/huggingface/added_tokens.jsonConfiguration605 B —
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen25vl-3b-grpo-b64-mb64-n8-sysv1-step150-2gpu-fp32/global_step_30/actor/huggingface/config.jsonConfiguration3.4 KB —
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen25vl-3b-grpo-b64-mb64-n8-sysv1-step150-2gpu-fp32/global_step_30/actor/huggingface/generation_config.jsonConfiguration214 B —
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen25vl-3b-grpo-b64-mb64-n8-sysv1-step150-2gpu-fp32/global_step_30/actor/huggingface/model.safetensors.index.jsonConfiguration65.5 KB —
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen25vl-3b-grpo-b64-mb64-n8-sysv1-step150-2gpu-fp32/global_step_30/actor/huggingface/preprocessor_config.jsonConfiguration829 B —
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen25vl-3b-grpo-b64-mb64-n8-sysv1-step150-2gpu-fp32/global_step_30/actor/huggingface/special_tokens_map.jsonConfiguration613 B —
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen25vl-3b-grpo-b64-mb64-n8-sysv1-step150-2gpu-fp32/global_step_30/actor/huggingface/video_preprocessor_config.jsonConfiguration955 B —
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen25vl-3b-grpo-b64-mb64-n8-sysv1-step150-2gpu-fp32/global_step_30/resolved_config.yamlConfiguration17.8 KB —
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen25vl-3b-grpo-b64-mb64-n8-sysv1-step150-2gpu-fp32/global_step_60/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen25vl-3b-grpo-b64-mb64-n8-sysv1-step150-2gpu-fp32/global_step_60/actor/huggingface/added_tokens.jsonConfiguration605 B —
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen25vl-3b-grpo-b64-mb64-n8-sysv1-step150-2gpu-fp32/global_step_60/actor/huggingface/config.jsonConfiguration3.4 KB —
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen25vl-3b-grpo-b64-mb64-n8-sysv1-step150-2gpu-fp32/global_step_60/actor/huggingface/generation_config.jsonConfiguration214 B —
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen25vl-3b-grpo-b64-mb64-n8-sysv1-step150-2gpu-fp32/global_step_60/actor/huggingface/model.safetensors.index.jsonConfiguration65.5 KB —
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen25vl-3b-grpo-b64-mb64-n8-sysv1-step150-2gpu-fp32/global_step_60/actor/huggingface/preprocessor_config.jsonConfiguration829 B —
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen25vl-3b-grpo-b64-mb64-n8-sysv1-step150-2gpu-fp32/global_step_60/actor/huggingface/special_tokens_map.jsonConfiguration613 B —
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen25vl-3b-grpo-b64-mb64-n8-sysv1-step150-2gpu-fp32/global_step_60/actor/huggingface/video_preprocessor_config.jsonConfiguration955 B —
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen25vl-3b-grpo-b64-mb64-n8-sysv1-step150-2gpu-fp32/global_step_60/resolved_config.yamlConfiguration17.8 KB —
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen25vl-3b-grpo-b64-mb64-n8-sysv1-step150-2gpu-fp32/global_step_90/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen25vl-3b-grpo-b64-mb64-n8-sysv1-step150-2gpu-fp32/global_step_90/actor/huggingface/added_tokens.jsonConfiguration605 B —
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen25vl-3b-grpo-b64-mb64-n8-sysv1-step150-2gpu-fp32/global_step_90/actor/huggingface/config.jsonConfiguration3.4 KB —
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen25vl-3b-grpo-b64-mb64-n8-sysv1-step150-2gpu-fp32/global_step_90/actor/huggingface/generation_config.jsonConfiguration214 B —
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen25vl-3b-grpo-b64-mb64-n8-sysv1-step150-2gpu-fp32/global_step_90/actor/huggingface/model.safetensors.index.jsonConfiguration65.5 KB —
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen25vl-3b-grpo-b64-mb64-n8-sysv1-step150-2gpu-fp32/global_step_90/actor/huggingface/preprocessor_config.jsonConfiguration829 B —
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen25vl-3b-grpo-b64-mb64-n8-sysv1-step150-2gpu-fp32/global_step_90/actor/huggingface/special_tokens_map.jsonConfiguration613 B —
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen25vl-3b-grpo-b64-mb64-n8-sysv1-step150-2gpu-fp32/global_step_90/actor/huggingface/video_preprocessor_config.jsonConfiguration955 B —
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen25vl-3b-grpo-b64-mb64-n8-sysv1-step150-2gpu-fp32/global_step_90/resolved_config.yamlConfiguration17.8 KB —
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen25vl-3b-grpo-b64-mb64-n8-sysv1-step150-2gpu-fp32/latest_checkpoint.jsonConfiguration251 B —
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen3vl-4b-instruct-grpo-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_30/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen3vl-4b-instruct-grpo-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_30/actor/huggingface/added_tokens.jsonConfiguration707 B —
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen3vl-4b-instruct-grpo-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_30/actor/huggingface/config.jsonConfiguration1.6 KB —
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen3vl-4b-instruct-grpo-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_30/actor/huggingface/generation_config.jsonConfiguration213 B —
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen3vl-4b-instruct-grpo-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_30/actor/huggingface/model.safetensors.index.jsonConfiguration64.8 KB —
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen3vl-4b-instruct-grpo-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_30/actor/huggingface/preprocessor_config.jsonConfiguration782 B —
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen3vl-4b-instruct-grpo-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_30/actor/huggingface/special_tokens_map.jsonConfiguration613 B —
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen3vl-4b-instruct-grpo-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_30/actor/huggingface/video_preprocessor_config.jsonConfiguration817 B —
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen3vl-4b-instruct-grpo-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_30/resolved_config.yamlConfiguration18.0 KB —
experiments/weak_to_strong/agent/baseline/260919-pixel-qwen3vl-4b-instruct-grpo-b64-mb64-n8-sysv1-step150-4gpu-fp32/latest_checkpoint.jsonConfiguration261 B —
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen25vl-3b-sft-grpo-b64-mb64-n8-alpha1-sysv1-step150-4gpu-fp32/global_step_30/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen25vl-3b-sft-grpo-b64-mb64-n8-alpha1-sysv1-step150-4gpu-fp32/global_step_30/actor/huggingface/added_tokens.jsonConfiguration605 B —
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen25vl-3b-sft-grpo-b64-mb64-n8-alpha1-sysv1-step150-4gpu-fp32/global_step_30/actor/huggingface/config.jsonConfiguration3.4 KB —
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen25vl-3b-sft-grpo-b64-mb64-n8-alpha1-sysv1-step150-4gpu-fp32/global_step_30/actor/huggingface/generation_config.jsonConfiguration214 B —
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen25vl-3b-sft-grpo-b64-mb64-n8-alpha1-sysv1-step150-4gpu-fp32/global_step_30/actor/huggingface/model.safetensors.index.jsonConfiguration65.5 KB —
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen25vl-3b-sft-grpo-b64-mb64-n8-alpha1-sysv1-step150-4gpu-fp32/global_step_30/actor/huggingface/preprocessor_config.jsonConfiguration829 B —
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen25vl-3b-sft-grpo-b64-mb64-n8-alpha1-sysv1-step150-4gpu-fp32/global_step_30/actor/huggingface/special_tokens_map.jsonConfiguration613 B —
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen25vl-3b-sft-grpo-b64-mb64-n8-alpha1-sysv1-step150-4gpu-fp32/global_step_30/actor/huggingface/video_preprocessor_config.jsonConfiguration955 B —
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen25vl-3b-sft-grpo-b64-mb64-n8-alpha1-sysv1-step150-4gpu-fp32/global_step_30/resolved_config.yamlConfiguration18.3 KB —
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen25vl-3b-sft-grpo-b64-mb64-n8-alpha1-sysv1-step150-4gpu-fp32/latest_checkpoint.jsonConfiguration256 B —
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_120/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_120/actor/huggingface/added_tokens.jsonConfiguration605 B —
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_120/actor/huggingface/config.jsonConfiguration3.2 KB —
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_120/actor/huggingface/generation_config.jsonConfiguration282 B —
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_120/actor/huggingface/model.safetensors.index.jsonConfiguration57.7 KB —
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_120/actor/huggingface/preprocessor_config.jsonConfiguration827 B —
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_120/actor/huggingface/special_tokens_map.jsonConfiguration613 B —
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_120/actor/huggingface/video_preprocessor_config.jsonConfiguration911 B —
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_120/resolved_config.yamlConfiguration18.3 KB —
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_30/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_30/actor/huggingface/added_tokens.jsonConfiguration605 B —
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_30/actor/huggingface/config.jsonConfiguration3.2 KB —
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_30/actor/huggingface/generation_config.jsonConfiguration282 B —
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_30/actor/huggingface/model.safetensors.index.jsonConfiguration57.7 KB —
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_30/actor/huggingface/preprocessor_config.jsonConfiguration827 B —
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_30/actor/huggingface/special_tokens_map.jsonConfiguration613 B —
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_30/actor/huggingface/video_preprocessor_config.jsonConfiguration911 B —
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_30/resolved_config.yamlConfiguration18.3 KB —
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_60/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_60/actor/huggingface/added_tokens.jsonConfiguration605 B —
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_60/actor/huggingface/config.jsonConfiguration3.2 KB —
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_60/actor/huggingface/generation_config.jsonConfiguration282 B —
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_60/actor/huggingface/model.safetensors.index.jsonConfiguration57.7 KB —
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_60/actor/huggingface/preprocessor_config.jsonConfiguration827 B —
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_60/actor/huggingface/special_tokens_map.jsonConfiguration613 B —
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_60/actor/huggingface/video_preprocessor_config.jsonConfiguration911 B —
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_60/resolved_config.yamlConfiguration18.3 KB —
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_90/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_90/actor/huggingface/added_tokens.jsonConfiguration605 B —
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_90/actor/huggingface/config.jsonConfiguration3.2 KB —
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_90/actor/huggingface/generation_config.jsonConfiguration282 B —
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_90/actor/huggingface/model.safetensors.index.jsonConfiguration57.7 KB —
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_90/actor/huggingface/preprocessor_config.jsonConfiguration827 B —
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_90/actor/huggingface/special_tokens_map.jsonConfiguration613 B —
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_90/actor/huggingface/video_preprocessor_config.jsonConfiguration911 B —
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_90/resolved_config.yamlConfiguration18.3 KB —
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-sysv1-step150-4gpu-fp32/latest_checkpoint.jsonConfiguration257 B —
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen3vl-4b-instruct-grpo-b64-mb64-n8-alpha2-sysv1-step150-4gpu-fp32/global_step_30/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen3vl-4b-instruct-grpo-b64-mb64-n8-alpha2-sysv1-step150-4gpu-fp32/global_step_30/actor/huggingface/added_tokens.jsonConfiguration707 B —
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen3vl-4b-instruct-grpo-b64-mb64-n8-alpha2-sysv1-step150-4gpu-fp32/global_step_30/actor/huggingface/config.jsonConfiguration1.6 KB —
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen3vl-4b-instruct-grpo-b64-mb64-n8-alpha2-sysv1-step150-4gpu-fp32/global_step_30/actor/huggingface/generation_config.jsonConfiguration213 B —
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen3vl-4b-instruct-grpo-b64-mb64-n8-alpha2-sysv1-step150-4gpu-fp32/global_step_30/actor/huggingface/model.safetensors.index.jsonConfiguration64.8 KB —
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen3vl-4b-instruct-grpo-b64-mb64-n8-alpha2-sysv1-step150-4gpu-fp32/global_step_30/actor/huggingface/preprocessor_config.jsonConfiguration782 B —
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen3vl-4b-instruct-grpo-b64-mb64-n8-alpha2-sysv1-step150-4gpu-fp32/global_step_30/actor/huggingface/special_tokens_map.jsonConfiguration613 B —
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen3vl-4b-instruct-grpo-b64-mb64-n8-alpha2-sysv1-step150-4gpu-fp32/global_step_30/actor/huggingface/video_preprocessor_config.jsonConfiguration817 B —
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen3vl-4b-instruct-grpo-b64-mb64-n8-alpha2-sysv1-step150-4gpu-fp32/global_step_30/resolved_config.yamlConfiguration18.1 KB —
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen3vl-4b-instruct-grpo-b64-mb64-n8-alpha2-sysv1-step150-4gpu-fp32/global_step_60/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen3vl-4b-instruct-grpo-b64-mb64-n8-alpha2-sysv1-step150-4gpu-fp32/global_step_60/actor/huggingface/added_tokens.jsonConfiguration707 B —
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen3vl-4b-instruct-grpo-b64-mb64-n8-alpha2-sysv1-step150-4gpu-fp32/global_step_60/actor/huggingface/config.jsonConfiguration1.6 KB —
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen3vl-4b-instruct-grpo-b64-mb64-n8-alpha2-sysv1-step150-4gpu-fp32/global_step_60/actor/huggingface/generation_config.jsonConfiguration213 B —
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen3vl-4b-instruct-grpo-b64-mb64-n8-alpha2-sysv1-step150-4gpu-fp32/global_step_60/actor/huggingface/model.safetensors.index.jsonConfiguration64.8 KB —
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen3vl-4b-instruct-grpo-b64-mb64-n8-alpha2-sysv1-step150-4gpu-fp32/global_step_60/actor/huggingface/preprocessor_config.jsonConfiguration782 B —
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen3vl-4b-instruct-grpo-b64-mb64-n8-alpha2-sysv1-step150-4gpu-fp32/global_step_60/actor/huggingface/special_tokens_map.jsonConfiguration613 B —
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen3vl-4b-instruct-grpo-b64-mb64-n8-alpha2-sysv1-step150-4gpu-fp32/global_step_60/actor/huggingface/video_preprocessor_config.jsonConfiguration817 B —
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen3vl-4b-instruct-grpo-b64-mb64-n8-alpha2-sysv1-step150-4gpu-fp32/global_step_60/resolved_config.yamlConfiguration18.1 KB —
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen3vl-4b-instruct-grpo-b64-mb64-n8-alpha2-sysv1-step150-4gpu-fp32/global_step_75/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen3vl-4b-instruct-grpo-b64-mb64-n8-alpha2-sysv1-step150-4gpu-fp32/global_step_75/actor/huggingface/added_tokens.jsonConfiguration707 B —
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen3vl-4b-instruct-grpo-b64-mb64-n8-alpha2-sysv1-step150-4gpu-fp32/global_step_75/actor/huggingface/config.jsonConfiguration1.6 KB —
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen3vl-4b-instruct-grpo-b64-mb64-n8-alpha2-sysv1-step150-4gpu-fp32/global_step_75/actor/huggingface/generation_config.jsonConfiguration213 B —
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen3vl-4b-instruct-grpo-b64-mb64-n8-alpha2-sysv1-step150-4gpu-fp32/global_step_75/actor/huggingface/model.safetensors.index.jsonConfiguration64.8 KB —
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen3vl-4b-instruct-grpo-b64-mb64-n8-alpha2-sysv1-step150-4gpu-fp32/global_step_75/actor/huggingface/preprocessor_config.jsonConfiguration782 B —
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen3vl-4b-instruct-grpo-b64-mb64-n8-alpha2-sysv1-step150-4gpu-fp32/global_step_75/actor/huggingface/special_tokens_map.jsonConfiguration613 B —
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen3vl-4b-instruct-grpo-b64-mb64-n8-alpha2-sysv1-step150-4gpu-fp32/global_step_75/actor/huggingface/video_preprocessor_config.jsonConfiguration817 B —
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen3vl-4b-instruct-grpo-b64-mb64-n8-alpha2-sysv1-step150-4gpu-fp32/global_step_75/resolved_config.yamlConfiguration18.1 KB —
experiments/weak_to_strong/agent/baseline/260920-pixel-qwen3vl-4b-instruct-grpo-b64-mb64-n8-alpha2-sysv1-step150-4gpu-fp32/latest_checkpoint.jsonConfiguration268 B —
experiments/weak_to_strong/agent/baseline/260921-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-normalized-source-v1-turn4k-step150-4gpu-fp32/latest_checkpoint.jsonConfiguration284 B —
experiments/weak_to_strong/agent/ours/260920-pixel-qwen25vl-7b-warmstart-oprd-t3b-step90-lp0p5-lm0to0p5-s45-b64-mb64-n8-sysv1-step150-4gpu-fp32-toolmatch-v2/global_step_30/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/agent/ours/260920-pixel-qwen25vl-7b-warmstart-oprd-t3b-step90-lp0p5-lm0to0p5-s45-b64-mb64-n8-sysv1-step150-4gpu-fp32-toolmatch-v2/global_step_30/actor/huggingface/added_tokens.jsonConfiguration605 B —
experiments/weak_to_strong/agent/ours/260920-pixel-qwen25vl-7b-warmstart-oprd-t3b-step90-lp0p5-lm0to0p5-s45-b64-mb64-n8-sysv1-step150-4gpu-fp32-toolmatch-v2/global_step_30/actor/huggingface/config.jsonConfiguration3.2 KB —
experiments/weak_to_strong/agent/ours/260920-pixel-qwen25vl-7b-warmstart-oprd-t3b-step90-lp0p5-lm0to0p5-s45-b64-mb64-n8-sysv1-step150-4gpu-fp32-toolmatch-v2/global_step_30/actor/huggingface/generation_config.jsonConfiguration282 B —
experiments/weak_to_strong/agent/ours/260920-pixel-qwen25vl-7b-warmstart-oprd-t3b-step90-lp0p5-lm0to0p5-s45-b64-mb64-n8-sysv1-step150-4gpu-fp32-toolmatch-v2/global_step_30/actor/huggingface/model.safetensors.index.jsonConfiguration57.7 KB —
experiments/weak_to_strong/agent/ours/260920-pixel-qwen25vl-7b-warmstart-oprd-t3b-step90-lp0p5-lm0to0p5-s45-b64-mb64-n8-sysv1-step150-4gpu-fp32-toolmatch-v2/global_step_30/actor/huggingface/preprocessor_config.jsonConfiguration827 B —
experiments/weak_to_strong/agent/ours/260920-pixel-qwen25vl-7b-warmstart-oprd-t3b-step90-lp0p5-lm0to0p5-s45-b64-mb64-n8-sysv1-step150-4gpu-fp32-toolmatch-v2/global_step_30/actor/huggingface/special_tokens_map.jsonConfiguration613 B —
experiments/weak_to_strong/agent/ours/260920-pixel-qwen25vl-7b-warmstart-oprd-t3b-step90-lp0p5-lm0to0p5-s45-b64-mb64-n8-sysv1-step150-4gpu-fp32-toolmatch-v2/global_step_30/actor/huggingface/video_preprocessor_config.jsonConfiguration911 B —
experiments/weak_to_strong/agent/ours/260920-pixel-qwen25vl-7b-warmstart-oprd-t3b-step90-lp0p5-lm0to0p5-s45-b64-mb64-n8-sysv1-step150-4gpu-fp32-toolmatch-v2/global_step_30/resolved_config.yamlConfiguration19.3 KB —
experiments/weak_to_strong/agent/ours/260920-pixel-qwen25vl-7b-warmstart-oprd-t3b-step90-lp0p5-lm0to0p5-s45-b64-mb64-n8-sysv1-step150-4gpu-fp32-toolmatch-v2/latest_checkpoint.jsonConfiguration310 B —
experiments/weak_to_strong/agent/ours/260920-pixel-qwen25vl-7b-warmstart-oprd-t3b-step90-lp0p5-lm0to0p5-s45-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_15/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/agent/ours/260920-pixel-qwen25vl-7b-warmstart-oprd-t3b-step90-lp0p5-lm0to0p5-s45-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_15/actor/huggingface/added_tokens.jsonConfiguration605 B —
experiments/weak_to_strong/agent/ours/260920-pixel-qwen25vl-7b-warmstart-oprd-t3b-step90-lp0p5-lm0to0p5-s45-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_15/actor/huggingface/config.jsonConfiguration3.2 KB —
experiments/weak_to_strong/agent/ours/260920-pixel-qwen25vl-7b-warmstart-oprd-t3b-step90-lp0p5-lm0to0p5-s45-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_15/actor/huggingface/generation_config.jsonConfiguration282 B —
experiments/weak_to_strong/agent/ours/260920-pixel-qwen25vl-7b-warmstart-oprd-t3b-step90-lp0p5-lm0to0p5-s45-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_15/actor/huggingface/model.safetensors.index.jsonConfiguration57.7 KB —
experiments/weak_to_strong/agent/ours/260920-pixel-qwen25vl-7b-warmstart-oprd-t3b-step90-lp0p5-lm0to0p5-s45-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_15/actor/huggingface/preprocessor_config.jsonConfiguration827 B —
experiments/weak_to_strong/agent/ours/260920-pixel-qwen25vl-7b-warmstart-oprd-t3b-step90-lp0p5-lm0to0p5-s45-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_15/actor/huggingface/special_tokens_map.jsonConfiguration613 B —
experiments/weak_to_strong/agent/ours/260920-pixel-qwen25vl-7b-warmstart-oprd-t3b-step90-lp0p5-lm0to0p5-s45-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_15/actor/huggingface/video_preprocessor_config.jsonConfiguration911 B —
experiments/weak_to_strong/agent/ours/260920-pixel-qwen25vl-7b-warmstart-oprd-t3b-step90-lp0p5-lm0to0p5-s45-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_15/resolved_config.yamlConfiguration19.0 KB —
experiments/weak_to_strong/agent/ours/260920-pixel-qwen25vl-7b-warmstart-oprd-t3b-step90-lp0p5-lm0to0p5-s45-b64-mb64-n8-sysv1-step150-4gpu-fp32/latest_checkpoint.jsonConfiguration285 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/best_validation_checkpoint.jsonConfiguration224 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_105/actor/.async_checkpoint_ready_world_size_2_rank_0.jsonConfiguration370 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_105/actor/.async_checkpoint_ready_world_size_2_rank_1.jsonConfiguration183 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_105/actor/.async_checkpoint_started_world_size_2_rank_0.jsonConfiguration62 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_105/actor/.async_checkpoint_started_world_size_2_rank_1.jsonConfiguration62 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_105/actor/.checkpoint_complete.jsonConfiguration51 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_105/actor/.worker_sidecars_ready_world_size_2_rank_0.jsonConfiguration84 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_105/actor/.worker_sidecars_ready_world_size_2_rank_1.jsonConfiguration84 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_105/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_105/actor/huggingface/config.jsonConfiguration1.5 KB —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_105/actor/huggingface/generation_config.jsonConfiguration214 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_120/actor/.async_checkpoint_ready_world_size_2_rank_0.jsonConfiguration370 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_120/actor/.async_checkpoint_ready_world_size_2_rank_1.jsonConfiguration183 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_120/actor/.async_checkpoint_started_world_size_2_rank_0.jsonConfiguration62 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_120/actor/.async_checkpoint_started_world_size_2_rank_1.jsonConfiguration62 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_120/actor/.checkpoint_complete.jsonConfiguration51 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_120/actor/.worker_sidecars_ready_world_size_2_rank_0.jsonConfiguration84 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_120/actor/.worker_sidecars_ready_world_size_2_rank_1.jsonConfiguration84 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_120/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_120/actor/huggingface/config.jsonConfiguration1.5 KB —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_120/actor/huggingface/generation_config.jsonConfiguration214 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_135/actor/.async_checkpoint_ready_world_size_2_rank_0.jsonConfiguration370 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_135/actor/.async_checkpoint_ready_world_size_2_rank_1.jsonConfiguration183 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_135/actor/.async_checkpoint_started_world_size_2_rank_0.jsonConfiguration62 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_135/actor/.async_checkpoint_started_world_size_2_rank_1.jsonConfiguration62 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_135/actor/.checkpoint_complete.jsonConfiguration51 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_135/actor/.worker_sidecars_ready_world_size_2_rank_0.jsonConfiguration84 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_135/actor/.worker_sidecars_ready_world_size_2_rank_1.jsonConfiguration84 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_135/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_135/actor/huggingface/config.jsonConfiguration1.5 KB —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_135/actor/huggingface/generation_config.jsonConfiguration214 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_15/actor/.async_checkpoint_ready_world_size_2_rank_0.jsonConfiguration369 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_15/actor/.async_checkpoint_ready_world_size_2_rank_1.jsonConfiguration182 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_15/actor/.async_checkpoint_started_world_size_2_rank_0.jsonConfiguration61 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_15/actor/.async_checkpoint_started_world_size_2_rank_1.jsonConfiguration61 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_15/actor/.checkpoint_complete.jsonConfiguration50 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_15/actor/.worker_sidecars_ready_world_size_2_rank_0.jsonConfiguration83 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_15/actor/.worker_sidecars_ready_world_size_2_rank_1.jsonConfiguration83 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_15/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_15/actor/huggingface/config.jsonConfiguration1.5 KB —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_15/actor/huggingface/generation_config.jsonConfiguration214 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_150/actor/.async_checkpoint_ready_world_size_2_rank_0.jsonConfiguration370 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_150/actor/.async_checkpoint_ready_world_size_2_rank_1.jsonConfiguration183 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_150/actor/.async_checkpoint_started_world_size_2_rank_0.jsonConfiguration62 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_150/actor/.async_checkpoint_started_world_size_2_rank_1.jsonConfiguration62 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_150/actor/.checkpoint_complete.jsonConfiguration51 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_150/actor/.worker_sidecars_ready_world_size_2_rank_0.jsonConfiguration84 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_150/actor/.worker_sidecars_ready_world_size_2_rank_1.jsonConfiguration84 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_150/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_150/actor/huggingface/config.jsonConfiguration1.5 KB —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_150/actor/huggingface/generation_config.jsonConfiguration214 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_180/actor/.async_checkpoint_ready_world_size_2_rank_0.jsonConfiguration370 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_180/actor/.async_checkpoint_ready_world_size_2_rank_1.jsonConfiguration183 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_180/actor/.async_checkpoint_started_world_size_2_rank_0.jsonConfiguration62 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_180/actor/.async_checkpoint_started_world_size_2_rank_1.jsonConfiguration62 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_180/actor/.checkpoint_complete.jsonConfiguration51 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_180/actor/.worker_sidecars_ready_world_size_2_rank_0.jsonConfiguration84 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_180/actor/.worker_sidecars_ready_world_size_2_rank_1.jsonConfiguration84 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_180/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_180/actor/huggingface/config.jsonConfiguration1.5 KB —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_180/actor/huggingface/generation_config.jsonConfiguration214 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_210/actor/.async_checkpoint_ready_world_size_2_rank_0.jsonConfiguration370 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_210/actor/.async_checkpoint_ready_world_size_2_rank_1.jsonConfiguration183 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_210/actor/.async_checkpoint_started_world_size_2_rank_0.jsonConfiguration62 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_210/actor/.async_checkpoint_started_world_size_2_rank_1.jsonConfiguration62 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_210/actor/.checkpoint_complete.jsonConfiguration51 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_210/actor/.worker_sidecars_ready_world_size_2_rank_0.jsonConfiguration84 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_210/actor/.worker_sidecars_ready_world_size_2_rank_1.jsonConfiguration84 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_210/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_210/actor/huggingface/config.jsonConfiguration1.5 KB —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_210/actor/huggingface/generation_config.jsonConfiguration214 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_240/actor/.async_checkpoint_ready_world_size_2_rank_0.jsonConfiguration370 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_240/actor/.async_checkpoint_ready_world_size_2_rank_1.jsonConfiguration183 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_240/actor/.async_checkpoint_started_world_size_2_rank_0.jsonConfiguration62 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_240/actor/.async_checkpoint_started_world_size_2_rank_1.jsonConfiguration62 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_240/actor/.checkpoint_complete.jsonConfiguration51 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_240/actor/.worker_sidecars_ready_world_size_2_rank_0.jsonConfiguration84 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_240/actor/.worker_sidecars_ready_world_size_2_rank_1.jsonConfiguration84 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_240/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_240/actor/huggingface/config.jsonConfiguration1.5 KB —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_240/actor/huggingface/generation_config.jsonConfiguration214 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_30/actor/.async_checkpoint_ready_world_size_2_rank_0.jsonConfiguration369 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_30/actor/.async_checkpoint_ready_world_size_2_rank_1.jsonConfiguration182 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_30/actor/.async_checkpoint_started_world_size_2_rank_0.jsonConfiguration61 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_30/actor/.async_checkpoint_started_world_size_2_rank_1.jsonConfiguration61 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_30/actor/.checkpoint_complete.jsonConfiguration50 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_30/actor/.worker_sidecars_ready_world_size_2_rank_0.jsonConfiguration83 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_30/actor/.worker_sidecars_ready_world_size_2_rank_1.jsonConfiguration83 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_30/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_30/actor/huggingface/config.jsonConfiguration1.5 KB —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_30/actor/huggingface/generation_config.jsonConfiguration214 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_45/actor/.async_checkpoint_ready_world_size_2_rank_0.jsonConfiguration369 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_45/actor/.async_checkpoint_ready_world_size_2_rank_1.jsonConfiguration182 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_45/actor/.async_checkpoint_started_world_size_2_rank_0.jsonConfiguration61 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_45/actor/.async_checkpoint_started_world_size_2_rank_1.jsonConfiguration61 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_45/actor/.checkpoint_complete.jsonConfiguration50 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_45/actor/.worker_sidecars_ready_world_size_2_rank_0.jsonConfiguration83 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_45/actor/.worker_sidecars_ready_world_size_2_rank_1.jsonConfiguration83 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_45/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_45/actor/huggingface/config.jsonConfiguration1.5 KB —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_45/actor/huggingface/generation_config.jsonConfiguration214 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_60/actor/.async_checkpoint_ready_world_size_2_rank_0.jsonConfiguration369 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_60/actor/.async_checkpoint_ready_world_size_2_rank_1.jsonConfiguration182 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_60/actor/.async_checkpoint_started_world_size_2_rank_0.jsonConfiguration61 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_60/actor/.async_checkpoint_started_world_size_2_rank_1.jsonConfiguration61 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_60/actor/.checkpoint_complete.jsonConfiguration50 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_60/actor/.worker_sidecars_ready_world_size_2_rank_0.jsonConfiguration83 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_60/actor/.worker_sidecars_ready_world_size_2_rank_1.jsonConfiguration83 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_60/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_60/actor/huggingface/config.jsonConfiguration1.5 KB —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_60/actor/huggingface/generation_config.jsonConfiguration214 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_75/actor/.async_checkpoint_ready_world_size_2_rank_0.jsonConfiguration369 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_75/actor/.async_checkpoint_ready_world_size_2_rank_1.jsonConfiguration182 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_75/actor/.async_checkpoint_started_world_size_2_rank_0.jsonConfiguration61 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_75/actor/.async_checkpoint_started_world_size_2_rank_1.jsonConfiguration61 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_75/actor/.checkpoint_complete.jsonConfiguration50 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_75/actor/.worker_sidecars_ready_world_size_2_rank_0.jsonConfiguration83 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_75/actor/.worker_sidecars_ready_world_size_2_rank_1.jsonConfiguration83 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_75/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_75/actor/huggingface/config.jsonConfiguration1.5 KB —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_75/actor/huggingface/generation_config.jsonConfiguration214 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_90/actor/.async_checkpoint_ready_world_size_2_rank_0.jsonConfiguration369 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_90/actor/.async_checkpoint_ready_world_size_2_rank_1.jsonConfiguration182 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_90/actor/.async_checkpoint_started_world_size_2_rank_0.jsonConfiguration61 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_90/actor/.async_checkpoint_started_world_size_2_rank_1.jsonConfiguration61 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_90/actor/.checkpoint_complete.jsonConfiguration50 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_90/actor/.worker_sidecars_ready_world_size_2_rank_0.jsonConfiguration83 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_90/actor/.worker_sidecars_ready_world_size_2_rank_1.jsonConfiguration83 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_90/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_90/actor/huggingface/config.jsonConfiguration1.5 KB —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/global_step_90/actor/huggingface/generation_config.jsonConfiguration214 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-1-7b-len20480-overlong4k-pf1p0-dp2-step300-b64-mb64-save15then30-finalopt-aime24/latest_checkpoint.jsonConfiguration265 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-4b-base-len20480-overlong4k-pf1p0-dp2-step150-b64-mb32-nosystem-save15-eval15-bestval-finalopt-aime24/best_validation_checkpoint.jsonConfiguration236 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-4b-base-len20480-overlong4k-pf1p0-dp2-step150-b64-mb32-nosystem-save15-eval15-bestval-finalopt-aime24/global_step_150/actor/.async_checkpoint_ready_world_size_2_rank_0.jsonConfiguration370 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-4b-base-len20480-overlong4k-pf1p0-dp2-step150-b64-mb32-nosystem-save15-eval15-bestval-finalopt-aime24/global_step_150/actor/.async_checkpoint_ready_world_size_2_rank_1.jsonConfiguration183 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-4b-base-len20480-overlong4k-pf1p0-dp2-step150-b64-mb32-nosystem-save15-eval15-bestval-finalopt-aime24/global_step_150/actor/.async_checkpoint_started_world_size_2_rank_0.jsonConfiguration62 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-4b-base-len20480-overlong4k-pf1p0-dp2-step150-b64-mb32-nosystem-save15-eval15-bestval-finalopt-aime24/global_step_150/actor/.async_checkpoint_started_world_size_2_rank_1.jsonConfiguration62 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-4b-base-len20480-overlong4k-pf1p0-dp2-step150-b64-mb32-nosystem-save15-eval15-bestval-finalopt-aime24/global_step_150/actor/.checkpoint_complete.jsonConfiguration51 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-4b-base-len20480-overlong4k-pf1p0-dp2-step150-b64-mb32-nosystem-save15-eval15-bestval-finalopt-aime24/global_step_150/actor/.worker_sidecars_ready_world_size_2_rank_0.jsonConfiguration84 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-4b-base-len20480-overlong4k-pf1p0-dp2-step150-b64-mb32-nosystem-save15-eval15-bestval-finalopt-aime24/global_step_150/actor/.worker_sidecars_ready_world_size_2_rank_1.jsonConfiguration84 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-4b-base-len20480-overlong4k-pf1p0-dp2-step150-b64-mb32-nosystem-save15-eval15-bestval-finalopt-aime24/global_step_150/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-4b-base-len20480-overlong4k-pf1p0-dp2-step150-b64-mb32-nosystem-save15-eval15-bestval-finalopt-aime24/global_step_150/actor/huggingface/config.jsonConfiguration1.6 KB —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-4b-base-len20480-overlong4k-pf1p0-dp2-step150-b64-mb32-nosystem-save15-eval15-bestval-finalopt-aime24/global_step_150/actor/huggingface/generation_config.jsonConfiguration139 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-4b-base-len20480-overlong4k-pf1p0-dp2-step150-b64-mb32-nosystem-save15-eval15-bestval-finalopt-aime24/latest_checkpoint.jsonConfiguration378 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-4b-len20480-overlong4k-pf1p0-dp2-step150-b64-mb64-save15-eval15-bestval-finalopt-aime24/best_validation_checkpoint.jsonConfiguration235 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-4b-len20480-overlong4k-pf1p0-dp2-step150-b64-mb64-save15-eval15-bestval-finalopt-aime24/global_step_150/actor/.async_checkpoint_ready_world_size_2_rank_0.jsonConfiguration370 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-4b-len20480-overlong4k-pf1p0-dp2-step150-b64-mb64-save15-eval15-bestval-finalopt-aime24/global_step_150/actor/.async_checkpoint_ready_world_size_2_rank_1.jsonConfiguration183 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-4b-len20480-overlong4k-pf1p0-dp2-step150-b64-mb64-save15-eval15-bestval-finalopt-aime24/global_step_150/actor/.async_checkpoint_started_world_size_2_rank_0.jsonConfiguration62 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-4b-len20480-overlong4k-pf1p0-dp2-step150-b64-mb64-save15-eval15-bestval-finalopt-aime24/global_step_150/actor/.async_checkpoint_started_world_size_2_rank_1.jsonConfiguration62 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-4b-len20480-overlong4k-pf1p0-dp2-step150-b64-mb64-save15-eval15-bestval-finalopt-aime24/global_step_150/actor/.checkpoint_complete.jsonConfiguration51 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-4b-len20480-overlong4k-pf1p0-dp2-step150-b64-mb64-save15-eval15-bestval-finalopt-aime24/global_step_150/actor/.worker_sidecars_ready_world_size_2_rank_0.jsonConfiguration84 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-4b-len20480-overlong4k-pf1p0-dp2-step150-b64-mb64-save15-eval15-bestval-finalopt-aime24/global_step_150/actor/.worker_sidecars_ready_world_size_2_rank_1.jsonConfiguration84 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-4b-len20480-overlong4k-pf1p0-dp2-step150-b64-mb64-save15-eval15-bestval-finalopt-aime24/global_step_150/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-4b-len20480-overlong4k-pf1p0-dp2-step150-b64-mb64-save15-eval15-bestval-finalopt-aime24/global_step_150/actor/huggingface/config.jsonConfiguration1.6 KB —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-4b-len20480-overlong4k-pf1p0-dp2-step150-b64-mb64-save15-eval15-bestval-finalopt-aime24/global_step_150/actor/huggingface/generation_config.jsonConfiguration214 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-4b-len20480-overlong4k-pf1p0-dp2-step150-b64-mb64-save15-eval15-bestval-finalopt-aime24/latest_checkpoint.jsonConfiguration345 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-8b-base-len20480-overlong4k-pf1p0-dp2-step150-b64-mb32-nosystem-save30-eval15-bestval-finalopt-aime24/best_validation_checkpoint.jsonConfiguration236 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-8b-base-len20480-overlong4k-pf1p0-dp2-step150-b64-mb32-nosystem-save30-eval15-bestval-finalopt-aime24/global_step_150/actor/.async_checkpoint_ready_world_size_2_rank_0.jsonConfiguration370 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-8b-base-len20480-overlong4k-pf1p0-dp2-step150-b64-mb32-nosystem-save30-eval15-bestval-finalopt-aime24/global_step_150/actor/.async_checkpoint_ready_world_size_2_rank_1.jsonConfiguration183 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-8b-base-len20480-overlong4k-pf1p0-dp2-step150-b64-mb32-nosystem-save30-eval15-bestval-finalopt-aime24/global_step_150/actor/.async_checkpoint_started_world_size_2_rank_0.jsonConfiguration62 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-8b-base-len20480-overlong4k-pf1p0-dp2-step150-b64-mb32-nosystem-save30-eval15-bestval-finalopt-aime24/global_step_150/actor/.async_checkpoint_started_world_size_2_rank_1.jsonConfiguration62 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-8b-base-len20480-overlong4k-pf1p0-dp2-step150-b64-mb32-nosystem-save30-eval15-bestval-finalopt-aime24/global_step_150/actor/.checkpoint_complete.jsonConfiguration51 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-8b-base-len20480-overlong4k-pf1p0-dp2-step150-b64-mb32-nosystem-save30-eval15-bestval-finalopt-aime24/global_step_150/actor/.worker_sidecars_ready_world_size_2_rank_0.jsonConfiguration84 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-8b-base-len20480-overlong4k-pf1p0-dp2-step150-b64-mb32-nosystem-save30-eval15-bestval-finalopt-aime24/global_step_150/actor/.worker_sidecars_ready_world_size_2_rank_1.jsonConfiguration84 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-8b-base-len20480-overlong4k-pf1p0-dp2-step150-b64-mb32-nosystem-save30-eval15-bestval-finalopt-aime24/global_step_150/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-8b-base-len20480-overlong4k-pf1p0-dp2-step150-b64-mb32-nosystem-save30-eval15-bestval-finalopt-aime24/global_step_150/actor/huggingface/config.jsonConfiguration1.6 KB —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-8b-base-len20480-overlong4k-pf1p0-dp2-step150-b64-mb32-nosystem-save30-eval15-bestval-finalopt-aime24/global_step_150/actor/huggingface/generation_config.jsonConfiguration139 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-8b-base-len20480-overlong4k-pf1p0-dp2-step150-b64-mb32-nosystem-save30-eval15-bestval-finalopt-aime24/global_step_30/actor/.async_checkpoint_ready_world_size_2_rank_0.jsonConfiguration369 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-8b-base-len20480-overlong4k-pf1p0-dp2-step150-b64-mb32-nosystem-save30-eval15-bestval-finalopt-aime24/global_step_30/actor/.async_checkpoint_ready_world_size_2_rank_1.jsonConfiguration182 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-8b-base-len20480-overlong4k-pf1p0-dp2-step150-b64-mb32-nosystem-save30-eval15-bestval-finalopt-aime24/global_step_30/actor/.async_checkpoint_started_world_size_2_rank_0.jsonConfiguration61 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-8b-base-len20480-overlong4k-pf1p0-dp2-step150-b64-mb32-nosystem-save30-eval15-bestval-finalopt-aime24/global_step_30/actor/.async_checkpoint_started_world_size_2_rank_1.jsonConfiguration61 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-8b-base-len20480-overlong4k-pf1p0-dp2-step150-b64-mb32-nosystem-save30-eval15-bestval-finalopt-aime24/global_step_30/actor/.checkpoint_complete.jsonConfiguration50 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-8b-base-len20480-overlong4k-pf1p0-dp2-step150-b64-mb32-nosystem-save30-eval15-bestval-finalopt-aime24/global_step_30/actor/.worker_sidecars_ready_world_size_2_rank_0.jsonConfiguration83 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-8b-base-len20480-overlong4k-pf1p0-dp2-step150-b64-mb32-nosystem-save30-eval15-bestval-finalopt-aime24/global_step_30/actor/.worker_sidecars_ready_world_size_2_rank_1.jsonConfiguration83 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-8b-base-len20480-overlong4k-pf1p0-dp2-step150-b64-mb32-nosystem-save30-eval15-bestval-finalopt-aime24/global_step_30/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-8b-base-len20480-overlong4k-pf1p0-dp2-step150-b64-mb32-nosystem-save30-eval15-bestval-finalopt-aime24/global_step_30/actor/huggingface/config.jsonConfiguration1.6 KB —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-8b-base-len20480-overlong4k-pf1p0-dp2-step150-b64-mb32-nosystem-save30-eval15-bestval-finalopt-aime24/global_step_30/actor/huggingface/generation_config.jsonConfiguration139 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-8b-base-len20480-overlong4k-pf1p0-dp2-step150-b64-mb32-nosystem-save30-eval15-bestval-finalopt-aime24/latest_checkpoint.jsonConfiguration378 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-8b-len20480-overlong4k-pf1p0-dp2-step150-b64-mb64-save30-eval15-bestval-finalopt-aime24/best_validation_checkpoint.jsonConfiguration235 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-8b-len20480-overlong4k-pf1p0-dp2-step150-b64-mb64-save30-eval15-bestval-finalopt-aime24/global_step_135/actor/.async_checkpoint_ready_world_size_2_rank_0.jsonConfiguration370 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-8b-len20480-overlong4k-pf1p0-dp2-step150-b64-mb64-save30-eval15-bestval-finalopt-aime24/global_step_135/actor/.async_checkpoint_ready_world_size_2_rank_1.jsonConfiguration183 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-8b-len20480-overlong4k-pf1p0-dp2-step150-b64-mb64-save30-eval15-bestval-finalopt-aime24/global_step_135/actor/.async_checkpoint_started_world_size_2_rank_0.jsonConfiguration62 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-8b-len20480-overlong4k-pf1p0-dp2-step150-b64-mb64-save30-eval15-bestval-finalopt-aime24/global_step_135/actor/.async_checkpoint_started_world_size_2_rank_1.jsonConfiguration62 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-8b-len20480-overlong4k-pf1p0-dp2-step150-b64-mb64-save30-eval15-bestval-finalopt-aime24/global_step_135/actor/.checkpoint_complete.jsonConfiguration51 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-8b-len20480-overlong4k-pf1p0-dp2-step150-b64-mb64-save30-eval15-bestval-finalopt-aime24/global_step_135/actor/.worker_sidecars_ready_world_size_2_rank_0.jsonConfiguration84 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-8b-len20480-overlong4k-pf1p0-dp2-step150-b64-mb64-save30-eval15-bestval-finalopt-aime24/global_step_135/actor/.worker_sidecars_ready_world_size_2_rank_1.jsonConfiguration84 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-8b-len20480-overlong4k-pf1p0-dp2-step150-b64-mb64-save30-eval15-bestval-finalopt-aime24/global_step_135/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-8b-len20480-overlong4k-pf1p0-dp2-step150-b64-mb64-save30-eval15-bestval-finalopt-aime24/global_step_135/actor/huggingface/config.jsonConfiguration1.6 KB —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-8b-len20480-overlong4k-pf1p0-dp2-step150-b64-mb64-save30-eval15-bestval-finalopt-aime24/global_step_135/actor/huggingface/generation_config.jsonConfiguration214 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-8b-len20480-overlong4k-pf1p0-dp2-step150-b64-mb64-save30-eval15-bestval-finalopt-aime24/global_step_150/actor/.async_checkpoint_ready_world_size_2_rank_0.jsonConfiguration370 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-8b-len20480-overlong4k-pf1p0-dp2-step150-b64-mb64-save30-eval15-bestval-finalopt-aime24/global_step_150/actor/.async_checkpoint_ready_world_size_2_rank_1.jsonConfiguration183 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-8b-len20480-overlong4k-pf1p0-dp2-step150-b64-mb64-save30-eval15-bestval-finalopt-aime24/global_step_150/actor/.async_checkpoint_started_world_size_2_rank_0.jsonConfiguration62 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-8b-len20480-overlong4k-pf1p0-dp2-step150-b64-mb64-save30-eval15-bestval-finalopt-aime24/global_step_150/actor/.async_checkpoint_started_world_size_2_rank_1.jsonConfiguration62 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-8b-len20480-overlong4k-pf1p0-dp2-step150-b64-mb64-save30-eval15-bestval-finalopt-aime24/global_step_150/actor/.checkpoint_complete.jsonConfiguration51 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-8b-len20480-overlong4k-pf1p0-dp2-step150-b64-mb64-save30-eval15-bestval-finalopt-aime24/global_step_150/actor/.worker_sidecars_ready_world_size_2_rank_0.jsonConfiguration84 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-8b-len20480-overlong4k-pf1p0-dp2-step150-b64-mb64-save30-eval15-bestval-finalopt-aime24/global_step_150/actor/.worker_sidecars_ready_world_size_2_rank_1.jsonConfiguration84 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-8b-len20480-overlong4k-pf1p0-dp2-step150-b64-mb64-save30-eval15-bestval-finalopt-aime24/global_step_150/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-8b-len20480-overlong4k-pf1p0-dp2-step150-b64-mb64-save30-eval15-bestval-finalopt-aime24/global_step_150/actor/huggingface/config.jsonConfiguration1.6 KB —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-8b-len20480-overlong4k-pf1p0-dp2-step150-b64-mb64-save30-eval15-bestval-finalopt-aime24/global_step_150/actor/huggingface/generation_config.jsonConfiguration214 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-8b-len20480-overlong4k-pf1p0-dp2-step150-b64-mb64-save30-eval15-bestval-finalopt-aime24/global_step_30/actor/.async_checkpoint_ready_world_size_2_rank_0.jsonConfiguration369 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-8b-len20480-overlong4k-pf1p0-dp2-step150-b64-mb64-save30-eval15-bestval-finalopt-aime24/global_step_30/actor/.async_checkpoint_ready_world_size_2_rank_1.jsonConfiguration182 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-8b-len20480-overlong4k-pf1p0-dp2-step150-b64-mb64-save30-eval15-bestval-finalopt-aime24/global_step_30/actor/.async_checkpoint_started_world_size_2_rank_0.jsonConfiguration61 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-8b-len20480-overlong4k-pf1p0-dp2-step150-b64-mb64-save30-eval15-bestval-finalopt-aime24/global_step_30/actor/.async_checkpoint_started_world_size_2_rank_1.jsonConfiguration61 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-8b-len20480-overlong4k-pf1p0-dp2-step150-b64-mb64-save30-eval15-bestval-finalopt-aime24/global_step_30/actor/.checkpoint_complete.jsonConfiguration50 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-8b-len20480-overlong4k-pf1p0-dp2-step150-b64-mb64-save30-eval15-bestval-finalopt-aime24/global_step_30/actor/.worker_sidecars_ready_world_size_2_rank_0.jsonConfiguration83 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-8b-len20480-overlong4k-pf1p0-dp2-step150-b64-mb64-save30-eval15-bestval-finalopt-aime24/global_step_30/actor/.worker_sidecars_ready_world_size_2_rank_1.jsonConfiguration83 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-8b-len20480-overlong4k-pf1p0-dp2-step150-b64-mb64-save30-eval15-bestval-finalopt-aime24/global_step_30/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-8b-len20480-overlong4k-pf1p0-dp2-step150-b64-mb64-save30-eval15-bestval-finalopt-aime24/global_step_30/actor/huggingface/config.jsonConfiguration1.6 KB —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-8b-len20480-overlong4k-pf1p0-dp2-step150-b64-mb64-save30-eval15-bestval-finalopt-aime24/global_step_30/actor/huggingface/generation_config.jsonConfiguration214 B —
experiments/weak_to_strong/math/baseline/260722-grpo-dapo-math17k-qwen3-8b-len20480-overlong4k-pf1p0-dp2-step150-b64-mb64-save30-eval15-bestval-finalopt-aime24/latest_checkpoint.jsonConfiguration345 B —
experiments/weak_to_strong/math/distill_baseline/260723-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_120/actor/.async_checkpoint_ready_world_size_2_rank_0.jsonConfiguration370 B —
experiments/weak_to_strong/math/distill_baseline/260723-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_120/actor/.async_checkpoint_ready_world_size_2_rank_1.jsonConfiguration183 B —
experiments/weak_to_strong/math/distill_baseline/260723-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_120/actor/.async_checkpoint_started_world_size_2_rank_0.jsonConfiguration62 B —
experiments/weak_to_strong/math/distill_baseline/260723-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_120/actor/.async_checkpoint_started_world_size_2_rank_1.jsonConfiguration62 B —
experiments/weak_to_strong/math/distill_baseline/260723-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_120/actor/.checkpoint_complete.jsonConfiguration51 B —
experiments/weak_to_strong/math/distill_baseline/260723-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_120/actor/.worker_sidecars_ready_world_size_2_rank_0.jsonConfiguration171 B —
experiments/weak_to_strong/math/distill_baseline/260723-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_120/actor/.worker_sidecars_ready_world_size_2_rank_1.jsonConfiguration171 B —
experiments/weak_to_strong/math/distill_baseline/260723-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_120/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/math/distill_baseline/260723-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_120/actor/huggingface/config.jsonConfiguration1.5 KB —
experiments/weak_to_strong/math/distill_baseline/260723-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_120/actor/huggingface/generation_config.jsonConfiguration214 B —
experiments/weak_to_strong/math/distill_baseline/260723-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_150/actor/.async_checkpoint_ready_world_size_2_rank_0.jsonConfiguration370 B —
experiments/weak_to_strong/math/distill_baseline/260723-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_150/actor/.async_checkpoint_ready_world_size_2_rank_1.jsonConfiguration183 B —
experiments/weak_to_strong/math/distill_baseline/260723-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_150/actor/.async_checkpoint_started_world_size_2_rank_0.jsonConfiguration62 B —
experiments/weak_to_strong/math/distill_baseline/260723-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_150/actor/.async_checkpoint_started_world_size_2_rank_1.jsonConfiguration62 B —
experiments/weak_to_strong/math/distill_baseline/260723-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_150/actor/.checkpoint_complete.jsonConfiguration51 B —
experiments/weak_to_strong/math/distill_baseline/260723-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_150/actor/.worker_sidecars_ready_world_size_2_rank_0.jsonConfiguration171 B —
experiments/weak_to_strong/math/distill_baseline/260723-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_150/actor/.worker_sidecars_ready_world_size_2_rank_1.jsonConfiguration171 B —
experiments/weak_to_strong/math/distill_baseline/260723-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_150/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/math/distill_baseline/260723-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_150/actor/huggingface/config.jsonConfiguration1.5 KB —
experiments/weak_to_strong/math/distill_baseline/260723-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_150/actor/huggingface/generation_config.jsonConfiguration214 B —
experiments/weak_to_strong/math/distill_baseline/260723-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_30/actor/.async_checkpoint_ready_world_size_2_rank_0.jsonConfiguration369 B —
experiments/weak_to_strong/math/distill_baseline/260723-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_30/actor/.async_checkpoint_ready_world_size_2_rank_1.jsonConfiguration182 B —
experiments/weak_to_strong/math/distill_baseline/260723-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_30/actor/.async_checkpoint_started_world_size_2_rank_0.jsonConfiguration61 B —
experiments/weak_to_strong/math/distill_baseline/260723-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_30/actor/.async_checkpoint_started_world_size_2_rank_1.jsonConfiguration61 B —
experiments/weak_to_strong/math/distill_baseline/260723-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_30/actor/.checkpoint_complete.jsonConfiguration50 B —
experiments/weak_to_strong/math/distill_baseline/260723-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_30/actor/.worker_sidecars_ready_world_size_2_rank_0.jsonConfiguration170 B —
experiments/weak_to_strong/math/distill_baseline/260723-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_30/actor/.worker_sidecars_ready_world_size_2_rank_1.jsonConfiguration170 B —
experiments/weak_to_strong/math/distill_baseline/260723-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_30/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/math/distill_baseline/260723-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_30/actor/huggingface/config.jsonConfiguration1.5 KB —
experiments/weak_to_strong/math/distill_baseline/260723-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_30/actor/huggingface/generation_config.jsonConfiguration214 B —
experiments/weak_to_strong/math/distill_baseline/260723-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_60/actor/.async_checkpoint_ready_world_size_2_rank_0.jsonConfiguration369 B —
experiments/weak_to_strong/math/distill_baseline/260723-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_60/actor/.async_checkpoint_ready_world_size_2_rank_1.jsonConfiguration182 B —
experiments/weak_to_strong/math/distill_baseline/260723-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_60/actor/.async_checkpoint_started_world_size_2_rank_0.jsonConfiguration61 B —
experiments/weak_to_strong/math/distill_baseline/260723-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_60/actor/.async_checkpoint_started_world_size_2_rank_1.jsonConfiguration61 B —
experiments/weak_to_strong/math/distill_baseline/260723-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_60/actor/.checkpoint_complete.jsonConfiguration50 B —
experiments/weak_to_strong/math/distill_baseline/260723-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_60/actor/.worker_sidecars_ready_world_size_2_rank_0.jsonConfiguration170 B —
experiments/weak_to_strong/math/distill_baseline/260723-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_60/actor/.worker_sidecars_ready_world_size_2_rank_1.jsonConfiguration170 B —
experiments/weak_to_strong/math/distill_baseline/260723-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_60/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/math/distill_baseline/260723-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_60/actor/huggingface/config.jsonConfiguration1.5 KB —
experiments/weak_to_strong/math/distill_baseline/260723-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_60/actor/huggingface/generation_config.jsonConfiguration214 B —
experiments/weak_to_strong/math/distill_baseline/260723-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_90/actor/.async_checkpoint_ready_world_size_2_rank_0.jsonConfiguration369 B —
experiments/weak_to_strong/math/distill_baseline/260723-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_90/actor/.async_checkpoint_ready_world_size_2_rank_1.jsonConfiguration182 B —
experiments/weak_to_strong/math/distill_baseline/260723-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_90/actor/.async_checkpoint_started_world_size_2_rank_0.jsonConfiguration61 B —
experiments/weak_to_strong/math/distill_baseline/260723-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_90/actor/.async_checkpoint_started_world_size_2_rank_1.jsonConfiguration61 B —
experiments/weak_to_strong/math/distill_baseline/260723-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_90/actor/.checkpoint_complete.jsonConfiguration50 B —
experiments/weak_to_strong/math/distill_baseline/260723-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_90/actor/.worker_sidecars_ready_world_size_2_rank_0.jsonConfiguration170 B —
experiments/weak_to_strong/math/distill_baseline/260723-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_90/actor/.worker_sidecars_ready_world_size_2_rank_1.jsonConfiguration170 B —
experiments/weak_to_strong/math/distill_baseline/260723-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_90/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/math/distill_baseline/260723-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_90/actor/huggingface/config.jsonConfiguration1.5 KB —
experiments/weak_to_strong/math/distill_baseline/260723-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_90/actor/huggingface/generation_config.jsonConfiguration214 B —
experiments/weak_to_strong/math/distill_baseline/260723-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/latest_checkpoint.jsonConfiguration501 B —
experiments/weak_to_strong/math/distill_baseline/260724-kdrl-annealing-b5e3-min1e3-d1e4-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/best_validation_checkpoint.jsonConfiguration222 B —
experiments/weak_to_strong/math/distill_baseline/260724-kdrl-annealing-b5e3-min1e3-d1e4-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_120/actor/.async_checkpoint_ready_world_size_2_rank_0.jsonConfiguration370 B —
experiments/weak_to_strong/math/distill_baseline/260724-kdrl-annealing-b5e3-min1e3-d1e4-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_120/actor/.async_checkpoint_ready_world_size_2_rank_1.jsonConfiguration183 B —
experiments/weak_to_strong/math/distill_baseline/260724-kdrl-annealing-b5e3-min1e3-d1e4-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_120/actor/.async_checkpoint_started_world_size_2_rank_0.jsonConfiguration62 B —
experiments/weak_to_strong/math/distill_baseline/260724-kdrl-annealing-b5e3-min1e3-d1e4-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_120/actor/.async_checkpoint_started_world_size_2_rank_1.jsonConfiguration62 B —
experiments/weak_to_strong/math/distill_baseline/260724-kdrl-annealing-b5e3-min1e3-d1e4-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_120/actor/.checkpoint_complete.jsonConfiguration51 B —
experiments/weak_to_strong/math/distill_baseline/260724-kdrl-annealing-b5e3-min1e3-d1e4-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_120/actor/.worker_sidecars_ready_world_size_2_rank_0.jsonConfiguration84 B —
experiments/weak_to_strong/math/distill_baseline/260724-kdrl-annealing-b5e3-min1e3-d1e4-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_120/actor/.worker_sidecars_ready_world_size_2_rank_1.jsonConfiguration84 B —
experiments/weak_to_strong/math/distill_baseline/260724-kdrl-annealing-b5e3-min1e3-d1e4-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_120/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/math/distill_baseline/260724-kdrl-annealing-b5e3-min1e3-d1e4-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_120/actor/huggingface/config.jsonConfiguration1.5 KB —
experiments/weak_to_strong/math/distill_baseline/260724-kdrl-annealing-b5e3-min1e3-d1e4-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_120/actor/huggingface/generation_config.jsonConfiguration214 B —
experiments/weak_to_strong/math/distill_baseline/260724-kdrl-annealing-b5e3-min1e3-d1e4-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_150/actor/.async_checkpoint_ready_world_size_2_rank_0.jsonConfiguration370 B —
experiments/weak_to_strong/math/distill_baseline/260724-kdrl-annealing-b5e3-min1e3-d1e4-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_150/actor/.async_checkpoint_ready_world_size_2_rank_1.jsonConfiguration183 B —
experiments/weak_to_strong/math/distill_baseline/260724-kdrl-annealing-b5e3-min1e3-d1e4-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_150/actor/.async_checkpoint_started_world_size_2_rank_0.jsonConfiguration62 B —
experiments/weak_to_strong/math/distill_baseline/260724-kdrl-annealing-b5e3-min1e3-d1e4-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_150/actor/.async_checkpoint_started_world_size_2_rank_1.jsonConfiguration62 B —
experiments/weak_to_strong/math/distill_baseline/260724-kdrl-annealing-b5e3-min1e3-d1e4-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_150/actor/.checkpoint_complete.jsonConfiguration51 B —
experiments/weak_to_strong/math/distill_baseline/260724-kdrl-annealing-b5e3-min1e3-d1e4-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_150/actor/.worker_sidecars_ready_world_size_2_rank_0.jsonConfiguration84 B —
experiments/weak_to_strong/math/distill_baseline/260724-kdrl-annealing-b5e3-min1e3-d1e4-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_150/actor/.worker_sidecars_ready_world_size_2_rank_1.jsonConfiguration84 B —
experiments/weak_to_strong/math/distill_baseline/260724-kdrl-annealing-b5e3-min1e3-d1e4-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_150/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/math/distill_baseline/260724-kdrl-annealing-b5e3-min1e3-d1e4-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_150/actor/huggingface/config.jsonConfiguration1.5 KB —
experiments/weak_to_strong/math/distill_baseline/260724-kdrl-annealing-b5e3-min1e3-d1e4-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_150/actor/huggingface/generation_config.jsonConfiguration214 B —
experiments/weak_to_strong/math/distill_baseline/260724-kdrl-annealing-b5e3-min1e3-d1e4-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_30/actor/.async_checkpoint_ready_world_size_2_rank_0.jsonConfiguration369 B —
experiments/weak_to_strong/math/distill_baseline/260724-kdrl-annealing-b5e3-min1e3-d1e4-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_30/actor/.async_checkpoint_ready_world_size_2_rank_1.jsonConfiguration182 B —
experiments/weak_to_strong/math/distill_baseline/260724-kdrl-annealing-b5e3-min1e3-d1e4-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_30/actor/.async_checkpoint_started_world_size_2_rank_0.jsonConfiguration61 B —
experiments/weak_to_strong/math/distill_baseline/260724-kdrl-annealing-b5e3-min1e3-d1e4-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_30/actor/.async_checkpoint_started_world_size_2_rank_1.jsonConfiguration61 B —
experiments/weak_to_strong/math/distill_baseline/260724-kdrl-annealing-b5e3-min1e3-d1e4-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_30/actor/.checkpoint_complete.jsonConfiguration50 B —
experiments/weak_to_strong/math/distill_baseline/260724-kdrl-annealing-b5e3-min1e3-d1e4-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_30/actor/.worker_sidecars_ready_world_size_2_rank_0.jsonConfiguration83 B —
experiments/weak_to_strong/math/distill_baseline/260724-kdrl-annealing-b5e3-min1e3-d1e4-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_30/actor/.worker_sidecars_ready_world_size_2_rank_1.jsonConfiguration83 B —
experiments/weak_to_strong/math/distill_baseline/260724-kdrl-annealing-b5e3-min1e3-d1e4-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_30/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/math/distill_baseline/260724-kdrl-annealing-b5e3-min1e3-d1e4-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_30/actor/huggingface/config.jsonConfiguration1.5 KB —
experiments/weak_to_strong/math/distill_baseline/260724-kdrl-annealing-b5e3-min1e3-d1e4-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_30/actor/huggingface/generation_config.jsonConfiguration214 B —
experiments/weak_to_strong/math/distill_baseline/260724-kdrl-annealing-b5e3-min1e3-d1e4-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_60/actor/.async_checkpoint_ready_world_size_2_rank_0.jsonConfiguration369 B —
experiments/weak_to_strong/math/distill_baseline/260724-kdrl-annealing-b5e3-min1e3-d1e4-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_60/actor/.async_checkpoint_ready_world_size_2_rank_1.jsonConfiguration182 B —
experiments/weak_to_strong/math/distill_baseline/260724-kdrl-annealing-b5e3-min1e3-d1e4-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_60/actor/.async_checkpoint_started_world_size_2_rank_0.jsonConfiguration61 B —
experiments/weak_to_strong/math/distill_baseline/260724-kdrl-annealing-b5e3-min1e3-d1e4-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_60/actor/.async_checkpoint_started_world_size_2_rank_1.jsonConfiguration61 B —
experiments/weak_to_strong/math/distill_baseline/260724-kdrl-annealing-b5e3-min1e3-d1e4-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_60/actor/.checkpoint_complete.jsonConfiguration50 B —
experiments/weak_to_strong/math/distill_baseline/260724-kdrl-annealing-b5e3-min1e3-d1e4-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_60/actor/.worker_sidecars_ready_world_size_2_rank_0.jsonConfiguration83 B —
experiments/weak_to_strong/math/distill_baseline/260724-kdrl-annealing-b5e3-min1e3-d1e4-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_60/actor/.worker_sidecars_ready_world_size_2_rank_1.jsonConfiguration83 B —
experiments/weak_to_strong/math/distill_baseline/260724-kdrl-annealing-b5e3-min1e3-d1e4-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_60/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/math/distill_baseline/260724-kdrl-annealing-b5e3-min1e3-d1e4-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_60/actor/huggingface/config.jsonConfiguration1.5 KB —
experiments/weak_to_strong/math/distill_baseline/260724-kdrl-annealing-b5e3-min1e3-d1e4-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_60/actor/huggingface/generation_config.jsonConfiguration214 B —
experiments/weak_to_strong/math/distill_baseline/260724-kdrl-annealing-b5e3-min1e3-d1e4-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_90/actor/.async_checkpoint_ready_world_size_2_rank_0.jsonConfiguration369 B —
experiments/weak_to_strong/math/distill_baseline/260724-kdrl-annealing-b5e3-min1e3-d1e4-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_90/actor/.async_checkpoint_ready_world_size_2_rank_1.jsonConfiguration182 B —
experiments/weak_to_strong/math/distill_baseline/260724-kdrl-annealing-b5e3-min1e3-d1e4-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_90/actor/.async_checkpoint_started_world_size_2_rank_0.jsonConfiguration61 B —
experiments/weak_to_strong/math/distill_baseline/260724-kdrl-annealing-b5e3-min1e3-d1e4-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_90/actor/.async_checkpoint_started_world_size_2_rank_1.jsonConfiguration61 B —
experiments/weak_to_strong/math/distill_baseline/260724-kdrl-annealing-b5e3-min1e3-d1e4-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_90/actor/.checkpoint_complete.jsonConfiguration50 B —
experiments/weak_to_strong/math/distill_baseline/260724-kdrl-annealing-b5e3-min1e3-d1e4-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_90/actor/.worker_sidecars_ready_world_size_2_rank_0.jsonConfiguration83 B —
experiments/weak_to_strong/math/distill_baseline/260724-kdrl-annealing-b5e3-min1e3-d1e4-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_90/actor/.worker_sidecars_ready_world_size_2_rank_1.jsonConfiguration83 B —
experiments/weak_to_strong/math/distill_baseline/260724-kdrl-annealing-b5e3-min1e3-d1e4-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_90/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/math/distill_baseline/260724-kdrl-annealing-b5e3-min1e3-d1e4-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_90/actor/huggingface/config.jsonConfiguration1.5 KB —
experiments/weak_to_strong/math/distill_baseline/260724-kdrl-annealing-b5e3-min1e3-d1e4-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_90/actor/huggingface/generation_config.jsonConfiguration214 B —
experiments/weak_to_strong/math/distill_baseline/260724-kdrl-annealing-b5e3-min1e3-d1e4-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/latest_checkpoint.jsonConfiguration422 B —
experiments/weak_to_strong/math/distill_baseline/260724-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/best_validation_checkpoint.jsonConfiguration220 B —
experiments/weak_to_strong/math/distill_baseline/260724-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_120/actor/.async_checkpoint_ready_world_size_2_rank_0.jsonConfiguration370 B —
experiments/weak_to_strong/math/distill_baseline/260724-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_120/actor/.async_checkpoint_ready_world_size_2_rank_1.jsonConfiguration183 B —
experiments/weak_to_strong/math/distill_baseline/260724-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_120/actor/.async_checkpoint_started_world_size_2_rank_0.jsonConfiguration62 B —
experiments/weak_to_strong/math/distill_baseline/260724-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_120/actor/.async_checkpoint_started_world_size_2_rank_1.jsonConfiguration62 B —
experiments/weak_to_strong/math/distill_baseline/260724-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_120/actor/.checkpoint_complete.jsonConfiguration51 B —
experiments/weak_to_strong/math/distill_baseline/260724-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_120/actor/.worker_sidecars_ready_world_size_2_rank_0.jsonConfiguration171 B —
experiments/weak_to_strong/math/distill_baseline/260724-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_120/actor/.worker_sidecars_ready_world_size_2_rank_1.jsonConfiguration171 B —
experiments/weak_to_strong/math/distill_baseline/260724-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_120/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/math/distill_baseline/260724-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_120/actor/huggingface/config.jsonConfiguration1.6 KB —
experiments/weak_to_strong/math/distill_baseline/260724-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_120/actor/huggingface/generation_config.jsonConfiguration214 B —
experiments/weak_to_strong/math/distill_baseline/260724-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_150/actor/.async_checkpoint_ready_world_size_2_rank_0.jsonConfiguration370 B —
experiments/weak_to_strong/math/distill_baseline/260724-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_150/actor/.async_checkpoint_ready_world_size_2_rank_1.jsonConfiguration183 B —
experiments/weak_to_strong/math/distill_baseline/260724-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_150/actor/.async_checkpoint_started_world_size_2_rank_0.jsonConfiguration62 B —
experiments/weak_to_strong/math/distill_baseline/260724-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_150/actor/.async_checkpoint_started_world_size_2_rank_1.jsonConfiguration62 B —
experiments/weak_to_strong/math/distill_baseline/260724-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_150/actor/.checkpoint_complete.jsonConfiguration51 B —
experiments/weak_to_strong/math/distill_baseline/260724-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_150/actor/.worker_sidecars_ready_world_size_2_rank_0.jsonConfiguration171 B —
experiments/weak_to_strong/math/distill_baseline/260724-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_150/actor/.worker_sidecars_ready_world_size_2_rank_1.jsonConfiguration171 B —
experiments/weak_to_strong/math/distill_baseline/260724-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_150/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/math/distill_baseline/260724-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_150/actor/huggingface/config.jsonConfiguration1.6 KB —
experiments/weak_to_strong/math/distill_baseline/260724-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_150/actor/huggingface/generation_config.jsonConfiguration214 B —
experiments/weak_to_strong/math/distill_baseline/260724-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_30/actor/.async_checkpoint_ready_world_size_2_rank_0.jsonConfiguration369 B —
experiments/weak_to_strong/math/distill_baseline/260724-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_30/actor/.async_checkpoint_ready_world_size_2_rank_1.jsonConfiguration182 B —
experiments/weak_to_strong/math/distill_baseline/260724-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_30/actor/.async_checkpoint_started_world_size_2_rank_0.jsonConfiguration61 B —
experiments/weak_to_strong/math/distill_baseline/260724-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_30/actor/.async_checkpoint_started_world_size_2_rank_1.jsonConfiguration61 B —
experiments/weak_to_strong/math/distill_baseline/260724-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_30/actor/.checkpoint_complete.jsonConfiguration50 B —
experiments/weak_to_strong/math/distill_baseline/260724-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_30/actor/.worker_sidecars_ready_world_size_2_rank_0.jsonConfiguration170 B —
experiments/weak_to_strong/math/distill_baseline/260724-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_30/actor/.worker_sidecars_ready_world_size_2_rank_1.jsonConfiguration170 B —
experiments/weak_to_strong/math/distill_baseline/260724-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_30/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/math/distill_baseline/260724-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_30/actor/huggingface/config.jsonConfiguration1.6 KB —
experiments/weak_to_strong/math/distill_baseline/260724-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_30/actor/huggingface/generation_config.jsonConfiguration214 B —
experiments/weak_to_strong/math/distill_baseline/260724-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_60/actor/.async_checkpoint_ready_world_size_2_rank_0.jsonConfiguration369 B —
experiments/weak_to_strong/math/distill_baseline/260724-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_60/actor/.async_checkpoint_ready_world_size_2_rank_1.jsonConfiguration182 B —
experiments/weak_to_strong/math/distill_baseline/260724-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_60/actor/.async_checkpoint_started_world_size_2_rank_0.jsonConfiguration61 B —
experiments/weak_to_strong/math/distill_baseline/260724-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_60/actor/.async_checkpoint_started_world_size_2_rank_1.jsonConfiguration61 B —
experiments/weak_to_strong/math/distill_baseline/260724-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_60/actor/.checkpoint_complete.jsonConfiguration50 B —
experiments/weak_to_strong/math/distill_baseline/260724-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_60/actor/.worker_sidecars_ready_world_size_2_rank_0.jsonConfiguration170 B —
experiments/weak_to_strong/math/distill_baseline/260724-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_60/actor/.worker_sidecars_ready_world_size_2_rank_1.jsonConfiguration170 B —
experiments/weak_to_strong/math/distill_baseline/260724-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_60/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/math/distill_baseline/260724-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_60/actor/huggingface/config.jsonConfiguration1.6 KB —
experiments/weak_to_strong/math/distill_baseline/260724-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_60/actor/huggingface/generation_config.jsonConfiguration214 B —
experiments/weak_to_strong/math/distill_baseline/260724-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_90/actor/.async_checkpoint_ready_world_size_2_rank_0.jsonConfiguration369 B —
experiments/weak_to_strong/math/distill_baseline/260724-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_90/actor/.async_checkpoint_ready_world_size_2_rank_1.jsonConfiguration182 B —
experiments/weak_to_strong/math/distill_baseline/260724-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_90/actor/.async_checkpoint_started_world_size_2_rank_0.jsonConfiguration61 B —
experiments/weak_to_strong/math/distill_baseline/260724-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_90/actor/.async_checkpoint_started_world_size_2_rank_1.jsonConfiguration61 B —
experiments/weak_to_strong/math/distill_baseline/260724-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_90/actor/.checkpoint_complete.jsonConfiguration50 B —
experiments/weak_to_strong/math/distill_baseline/260724-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_90/actor/.worker_sidecars_ready_world_size_2_rank_0.jsonConfiguration170 B —
experiments/weak_to_strong/math/distill_baseline/260724-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_90/actor/.worker_sidecars_ready_world_size_2_rank_1.jsonConfiguration170 B —
experiments/weak_to_strong/math/distill_baseline/260724-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_90/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/math/distill_baseline/260724-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_90/actor/huggingface/config.jsonConfiguration1.6 KB —
experiments/weak_to_strong/math/distill_baseline/260724-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_90/actor/huggingface/generation_config.jsonConfiguration214 B —
experiments/weak_to_strong/math/distill_baseline/260724-sampledrkl-opd150-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/latest_checkpoint.jsonConfiguration458 B —
experiments/weak_to_strong/math/distill_baseline/260821-direct-opd-topk16-dapo-math17k-q3-8b-t4b-s75-s150-len20480-save30-eval15-b64-n8-mb64-dp4/global_step_150/actor/.async_checkpoint_ready_world_size_4_rank_0.jsonConfiguration370 B —
experiments/weak_to_strong/math/distill_baseline/260821-direct-opd-topk16-dapo-math17k-q3-8b-t4b-s75-s150-len20480-save30-eval15-b64-n8-mb64-dp4/global_step_150/actor/.async_checkpoint_ready_world_size_4_rank_1.jsonConfiguration183 B —
experiments/weak_to_strong/math/distill_baseline/260821-direct-opd-topk16-dapo-math17k-q3-8b-t4b-s75-s150-len20480-save30-eval15-b64-n8-mb64-dp4/global_step_150/actor/.async_checkpoint_ready_world_size_4_rank_2.jsonConfiguration183 B —
experiments/weak_to_strong/math/distill_baseline/260821-direct-opd-topk16-dapo-math17k-q3-8b-t4b-s75-s150-len20480-save30-eval15-b64-n8-mb64-dp4/global_step_150/actor/.async_checkpoint_ready_world_size_4_rank_3.jsonConfiguration183 B —
experiments/weak_to_strong/math/distill_baseline/260821-direct-opd-topk16-dapo-math17k-q3-8b-t4b-s75-s150-len20480-save30-eval15-b64-n8-mb64-dp4/global_step_150/actor/.async_checkpoint_started_world_size_4_rank_0.jsonConfiguration62 B —
experiments/weak_to_strong/math/distill_baseline/260821-direct-opd-topk16-dapo-math17k-q3-8b-t4b-s75-s150-len20480-save30-eval15-b64-n8-mb64-dp4/global_step_150/actor/.async_checkpoint_started_world_size_4_rank_1.jsonConfiguration62 B —
experiments/weak_to_strong/math/distill_baseline/260821-direct-opd-topk16-dapo-math17k-q3-8b-t4b-s75-s150-len20480-save30-eval15-b64-n8-mb64-dp4/global_step_150/actor/.async_checkpoint_started_world_size_4_rank_2.jsonConfiguration62 B —
experiments/weak_to_strong/math/distill_baseline/260821-direct-opd-topk16-dapo-math17k-q3-8b-t4b-s75-s150-len20480-save30-eval15-b64-n8-mb64-dp4/global_step_150/actor/.async_checkpoint_started_world_size_4_rank_3.jsonConfiguration62 B —
experiments/weak_to_strong/math/distill_baseline/260821-direct-opd-topk16-dapo-math17k-q3-8b-t4b-s75-s150-len20480-save30-eval15-b64-n8-mb64-dp4/global_step_150/actor/.checkpoint_complete.jsonConfiguration51 B —
experiments/weak_to_strong/math/distill_baseline/260821-direct-opd-topk16-dapo-math17k-q3-8b-t4b-s75-s150-len20480-save30-eval15-b64-n8-mb64-dp4/global_step_150/actor/.worker_sidecars_ready_world_size_4_rank_0.jsonConfiguration171 B —
experiments/weak_to_strong/math/distill_baseline/260821-direct-opd-topk16-dapo-math17k-q3-8b-t4b-s75-s150-len20480-save30-eval15-b64-n8-mb64-dp4/global_step_150/actor/.worker_sidecars_ready_world_size_4_rank_1.jsonConfiguration171 B —
experiments/weak_to_strong/math/distill_baseline/260821-direct-opd-topk16-dapo-math17k-q3-8b-t4b-s75-s150-len20480-save30-eval15-b64-n8-mb64-dp4/global_step_150/actor/.worker_sidecars_ready_world_size_4_rank_2.jsonConfiguration171 B —
experiments/weak_to_strong/math/distill_baseline/260821-direct-opd-topk16-dapo-math17k-q3-8b-t4b-s75-s150-len20480-save30-eval15-b64-n8-mb64-dp4/global_step_150/actor/.worker_sidecars_ready_world_size_4_rank_3.jsonConfiguration171 B —
experiments/weak_to_strong/math/distill_baseline/260821-direct-opd-topk16-dapo-math17k-q3-8b-t4b-s75-s150-len20480-save30-eval15-b64-n8-mb64-dp4/global_step_150/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched30-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/best_validation_checkpoint.jsonConfiguration234 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched30-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_120/actor/.async_checkpoint_ready_world_size_2_rank_0.jsonConfiguration370 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched30-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_120/actor/.async_checkpoint_ready_world_size_2_rank_1.jsonConfiguration183 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched30-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_120/actor/.async_checkpoint_started_world_size_2_rank_0.jsonConfiguration62 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched30-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_120/actor/.async_checkpoint_started_world_size_2_rank_1.jsonConfiguration62 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched30-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_120/actor/.checkpoint_complete.jsonConfiguration51 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched30-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_120/actor/.worker_sidecars_ready_world_size_2_rank_0.jsonConfiguration84 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched30-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_120/actor/.worker_sidecars_ready_world_size_2_rank_1.jsonConfiguration84 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched30-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_120/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched30-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_120/actor/huggingface/config.jsonConfiguration1.6 KB —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched30-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_120/actor/huggingface/generation_config.jsonConfiguration214 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched30-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_150/actor/.async_checkpoint_ready_world_size_2_rank_0.jsonConfiguration370 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched30-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_150/actor/.async_checkpoint_ready_world_size_2_rank_1.jsonConfiguration183 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched30-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_150/actor/.async_checkpoint_started_world_size_2_rank_0.jsonConfiguration62 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched30-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_150/actor/.async_checkpoint_started_world_size_2_rank_1.jsonConfiguration62 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched30-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_150/actor/.checkpoint_complete.jsonConfiguration51 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched30-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_150/actor/.worker_sidecars_ready_world_size_2_rank_0.jsonConfiguration84 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched30-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_150/actor/.worker_sidecars_ready_world_size_2_rank_1.jsonConfiguration84 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched30-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_150/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched30-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_150/actor/huggingface/config.jsonConfiguration1.6 KB —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched30-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_150/actor/huggingface/generation_config.jsonConfiguration214 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched30-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_30/actor/.async_checkpoint_ready_world_size_2_rank_0.jsonConfiguration369 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched30-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_30/actor/.async_checkpoint_ready_world_size_2_rank_1.jsonConfiguration182 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched30-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_30/actor/.async_checkpoint_started_world_size_2_rank_0.jsonConfiguration61 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched30-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_30/actor/.async_checkpoint_started_world_size_2_rank_1.jsonConfiguration61 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched30-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_30/actor/.checkpoint_complete.jsonConfiguration50 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched30-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_30/actor/.worker_sidecars_ready_world_size_2_rank_0.jsonConfiguration83 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched30-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_30/actor/.worker_sidecars_ready_world_size_2_rank_1.jsonConfiguration83 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched30-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_30/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched30-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_30/actor/huggingface/config.jsonConfiguration1.6 KB —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched30-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_30/actor/huggingface/generation_config.jsonConfiguration214 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched30-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_60/actor/.async_checkpoint_ready_world_size_2_rank_0.jsonConfiguration369 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched30-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_60/actor/.async_checkpoint_ready_world_size_2_rank_1.jsonConfiguration182 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched30-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_60/actor/.async_checkpoint_started_world_size_2_rank_0.jsonConfiguration61 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched30-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_60/actor/.async_checkpoint_started_world_size_2_rank_1.jsonConfiguration61 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched30-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_60/actor/.checkpoint_complete.jsonConfiguration50 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched30-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_60/actor/.worker_sidecars_ready_world_size_2_rank_0.jsonConfiguration83 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched30-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_60/actor/.worker_sidecars_ready_world_size_2_rank_1.jsonConfiguration83 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched30-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_60/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched30-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_60/actor/huggingface/config.jsonConfiguration1.6 KB —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched30-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_60/actor/huggingface/generation_config.jsonConfiguration214 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched30-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_90/actor/.async_checkpoint_ready_world_size_2_rank_0.jsonConfiguration369 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched30-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_90/actor/.async_checkpoint_ready_world_size_2_rank_1.jsonConfiguration182 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched30-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_90/actor/.async_checkpoint_started_world_size_2_rank_0.jsonConfiguration61 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched30-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_90/actor/.async_checkpoint_started_world_size_2_rank_1.jsonConfiguration61 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched30-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_90/actor/.checkpoint_complete.jsonConfiguration50 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched30-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_90/actor/.worker_sidecars_ready_world_size_2_rank_0.jsonConfiguration83 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched30-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_90/actor/.worker_sidecars_ready_world_size_2_rank_1.jsonConfiguration83 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched30-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_90/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched30-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_90/actor/huggingface/config.jsonConfiguration1.6 KB —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched30-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/global_step_90/actor/huggingface/generation_config.jsonConfiguration214 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched30-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-2gpu/latest_checkpoint.jsonConfiguration453 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched45-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_120/actor/.async_checkpoint_ready_world_size_2_rank_0.jsonConfiguration370 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched45-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_120/actor/.async_checkpoint_ready_world_size_2_rank_1.jsonConfiguration183 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched45-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_120/actor/.async_checkpoint_started_world_size_2_rank_0.jsonConfiguration62 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched45-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_120/actor/.async_checkpoint_started_world_size_2_rank_1.jsonConfiguration62 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched45-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_120/actor/.checkpoint_complete.jsonConfiguration51 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched45-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_120/actor/.worker_sidecars_ready_world_size_2_rank_0.jsonConfiguration84 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched45-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_120/actor/.worker_sidecars_ready_world_size_2_rank_1.jsonConfiguration84 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched45-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_120/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched45-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_120/actor/huggingface/config.jsonConfiguration1.5 KB —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched45-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_120/actor/huggingface/generation_config.jsonConfiguration214 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched45-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_150/actor/.async_checkpoint_ready_world_size_2_rank_0.jsonConfiguration370 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched45-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_150/actor/.async_checkpoint_ready_world_size_2_rank_1.jsonConfiguration183 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched45-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_150/actor/.async_checkpoint_started_world_size_2_rank_0.jsonConfiguration62 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched45-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_150/actor/.async_checkpoint_started_world_size_2_rank_1.jsonConfiguration62 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched45-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_150/actor/.checkpoint_complete.jsonConfiguration51 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched45-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_150/actor/.worker_sidecars_ready_world_size_2_rank_0.jsonConfiguration84 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched45-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_150/actor/.worker_sidecars_ready_world_size_2_rank_1.jsonConfiguration84 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched45-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_150/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched45-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_150/actor/huggingface/config.jsonConfiguration1.5 KB —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched45-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_150/actor/huggingface/generation_config.jsonConfiguration214 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched45-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_30/actor/.async_checkpoint_ready_world_size_2_rank_0.jsonConfiguration369 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched45-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_30/actor/.async_checkpoint_ready_world_size_2_rank_1.jsonConfiguration182 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched45-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_30/actor/.async_checkpoint_started_world_size_2_rank_0.jsonConfiguration61 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched45-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_30/actor/.async_checkpoint_started_world_size_2_rank_1.jsonConfiguration61 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched45-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_30/actor/.checkpoint_complete.jsonConfiguration50 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched45-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_30/actor/.worker_sidecars_ready_world_size_2_rank_0.jsonConfiguration83 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched45-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_30/actor/.worker_sidecars_ready_world_size_2_rank_1.jsonConfiguration83 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched45-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_30/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched45-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_30/actor/huggingface/config.jsonConfiguration1.5 KB —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched45-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_30/actor/huggingface/generation_config.jsonConfiguration214 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched45-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_60/actor/.async_checkpoint_ready_world_size_2_rank_0.jsonConfiguration369 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched45-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_60/actor/.async_checkpoint_ready_world_size_2_rank_1.jsonConfiguration182 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched45-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_60/actor/.async_checkpoint_started_world_size_2_rank_0.jsonConfiguration61 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched45-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_60/actor/.async_checkpoint_started_world_size_2_rank_1.jsonConfiguration61 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched45-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_60/actor/.checkpoint_complete.jsonConfiguration50 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched45-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_60/actor/.worker_sidecars_ready_world_size_2_rank_0.jsonConfiguration83 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched45-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_60/actor/.worker_sidecars_ready_world_size_2_rank_1.jsonConfiguration83 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched45-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_60/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched45-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_60/actor/huggingface/config.jsonConfiguration1.5 KB —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched45-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_60/actor/huggingface/generation_config.jsonConfiguration214 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched45-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_90/actor/.async_checkpoint_ready_world_size_2_rank_0.jsonConfiguration369 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched45-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_90/actor/.async_checkpoint_ready_world_size_2_rank_1.jsonConfiguration182 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched45-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_90/actor/.async_checkpoint_started_world_size_2_rank_0.jsonConfiguration61 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched45-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_90/actor/.async_checkpoint_started_world_size_2_rank_1.jsonConfiguration61 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched45-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_90/actor/.checkpoint_complete.jsonConfiguration50 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched45-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_90/actor/.worker_sidecars_ready_world_size_2_rank_0.jsonConfiguration83 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched45-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_90/actor/.worker_sidecars_ready_world_size_2_rank_1.jsonConfiguration83 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched45-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_90/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched45-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_90/actor/huggingface/config.jsonConfiguration1.5 KB —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched45-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/global_step_90/actor/huggingface/generation_config.jsonConfiguration214 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched45-overlong4k-len20480-dapo-math17k-qwen3-1p7b-teacher8b-wtsstep105-save30-eval15-latestopt-2gpu/latest_checkpoint.jsonConfiguration467 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched75-overlong4k-len20480-dapo-math17k-qwen3-8b-base-teacher4b-base-step90-mb32-nosystem-save30-eval15-latestopt-2gpu/best_validation_checkpoint.jsonConfiguration235 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched75-overlong4k-len20480-dapo-math17k-qwen3-8b-base-teacher4b-base-step90-mb32-nosystem-save30-eval15-latestopt-2gpu/global_step_120/actor/.async_checkpoint_ready_world_size_2_rank_0.jsonConfiguration370 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched75-overlong4k-len20480-dapo-math17k-qwen3-8b-base-teacher4b-base-step90-mb32-nosystem-save30-eval15-latestopt-2gpu/global_step_120/actor/.async_checkpoint_ready_world_size_2_rank_1.jsonConfiguration183 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched75-overlong4k-len20480-dapo-math17k-qwen3-8b-base-teacher4b-base-step90-mb32-nosystem-save30-eval15-latestopt-2gpu/global_step_120/actor/.async_checkpoint_started_world_size_2_rank_0.jsonConfiguration62 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched75-overlong4k-len20480-dapo-math17k-qwen3-8b-base-teacher4b-base-step90-mb32-nosystem-save30-eval15-latestopt-2gpu/global_step_120/actor/.async_checkpoint_started_world_size_2_rank_1.jsonConfiguration62 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched75-overlong4k-len20480-dapo-math17k-qwen3-8b-base-teacher4b-base-step90-mb32-nosystem-save30-eval15-latestopt-2gpu/global_step_120/actor/.checkpoint_complete.jsonConfiguration51 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched75-overlong4k-len20480-dapo-math17k-qwen3-8b-base-teacher4b-base-step90-mb32-nosystem-save30-eval15-latestopt-2gpu/global_step_120/actor/.worker_sidecars_ready_world_size_2_rank_0.jsonConfiguration84 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched75-overlong4k-len20480-dapo-math17k-qwen3-8b-base-teacher4b-base-step90-mb32-nosystem-save30-eval15-latestopt-2gpu/global_step_120/actor/.worker_sidecars_ready_world_size_2_rank_1.jsonConfiguration84 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched75-overlong4k-len20480-dapo-math17k-qwen3-8b-base-teacher4b-base-step90-mb32-nosystem-save30-eval15-latestopt-2gpu/global_step_120/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched75-overlong4k-len20480-dapo-math17k-qwen3-8b-base-teacher4b-base-step90-mb32-nosystem-save30-eval15-latestopt-2gpu/global_step_120/actor/huggingface/config.jsonConfiguration1.6 KB —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched75-overlong4k-len20480-dapo-math17k-qwen3-8b-base-teacher4b-base-step90-mb32-nosystem-save30-eval15-latestopt-2gpu/global_step_120/actor/huggingface/generation_config.jsonConfiguration139 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched75-overlong4k-len20480-dapo-math17k-qwen3-8b-base-teacher4b-base-step90-mb32-nosystem-save30-eval15-latestopt-2gpu/global_step_150/actor/.async_checkpoint_ready_world_size_2_rank_0.jsonConfiguration370 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched75-overlong4k-len20480-dapo-math17k-qwen3-8b-base-teacher4b-base-step90-mb32-nosystem-save30-eval15-latestopt-2gpu/global_step_150/actor/.async_checkpoint_ready_world_size_2_rank_1.jsonConfiguration183 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched75-overlong4k-len20480-dapo-math17k-qwen3-8b-base-teacher4b-base-step90-mb32-nosystem-save30-eval15-latestopt-2gpu/global_step_150/actor/.async_checkpoint_started_world_size_2_rank_0.jsonConfiguration62 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched75-overlong4k-len20480-dapo-math17k-qwen3-8b-base-teacher4b-base-step90-mb32-nosystem-save30-eval15-latestopt-2gpu/global_step_150/actor/.async_checkpoint_started_world_size_2_rank_1.jsonConfiguration62 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched75-overlong4k-len20480-dapo-math17k-qwen3-8b-base-teacher4b-base-step90-mb32-nosystem-save30-eval15-latestopt-2gpu/global_step_150/actor/.checkpoint_complete.jsonConfiguration51 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched75-overlong4k-len20480-dapo-math17k-qwen3-8b-base-teacher4b-base-step90-mb32-nosystem-save30-eval15-latestopt-2gpu/global_step_150/actor/.worker_sidecars_ready_world_size_2_rank_0.jsonConfiguration84 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched75-overlong4k-len20480-dapo-math17k-qwen3-8b-base-teacher4b-base-step90-mb32-nosystem-save30-eval15-latestopt-2gpu/global_step_150/actor/.worker_sidecars_ready_world_size_2_rank_1.jsonConfiguration84 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched75-overlong4k-len20480-dapo-math17k-qwen3-8b-base-teacher4b-base-step90-mb32-nosystem-save30-eval15-latestopt-2gpu/global_step_150/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched75-overlong4k-len20480-dapo-math17k-qwen3-8b-base-teacher4b-base-step90-mb32-nosystem-save30-eval15-latestopt-2gpu/global_step_150/actor/huggingface/config.jsonConfiguration1.6 KB —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched75-overlong4k-len20480-dapo-math17k-qwen3-8b-base-teacher4b-base-step90-mb32-nosystem-save30-eval15-latestopt-2gpu/global_step_150/actor/huggingface/generation_config.jsonConfiguration139 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched75-overlong4k-len20480-dapo-math17k-qwen3-8b-base-teacher4b-base-step90-mb32-nosystem-save30-eval15-latestopt-2gpu/global_step_30/actor/.async_checkpoint_ready_world_size_2_rank_0.jsonConfiguration369 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched75-overlong4k-len20480-dapo-math17k-qwen3-8b-base-teacher4b-base-step90-mb32-nosystem-save30-eval15-latestopt-2gpu/global_step_30/actor/.async_checkpoint_ready_world_size_2_rank_1.jsonConfiguration182 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched75-overlong4k-len20480-dapo-math17k-qwen3-8b-base-teacher4b-base-step90-mb32-nosystem-save30-eval15-latestopt-2gpu/global_step_30/actor/.async_checkpoint_started_world_size_2_rank_0.jsonConfiguration61 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched75-overlong4k-len20480-dapo-math17k-qwen3-8b-base-teacher4b-base-step90-mb32-nosystem-save30-eval15-latestopt-2gpu/global_step_30/actor/.async_checkpoint_started_world_size_2_rank_1.jsonConfiguration61 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched75-overlong4k-len20480-dapo-math17k-qwen3-8b-base-teacher4b-base-step90-mb32-nosystem-save30-eval15-latestopt-2gpu/global_step_30/actor/.checkpoint_complete.jsonConfiguration50 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched75-overlong4k-len20480-dapo-math17k-qwen3-8b-base-teacher4b-base-step90-mb32-nosystem-save30-eval15-latestopt-2gpu/global_step_30/actor/.worker_sidecars_ready_world_size_2_rank_0.jsonConfiguration83 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched75-overlong4k-len20480-dapo-math17k-qwen3-8b-base-teacher4b-base-step90-mb32-nosystem-save30-eval15-latestopt-2gpu/global_step_30/actor/.worker_sidecars_ready_world_size_2_rank_1.jsonConfiguration83 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched75-overlong4k-len20480-dapo-math17k-qwen3-8b-base-teacher4b-base-step90-mb32-nosystem-save30-eval15-latestopt-2gpu/global_step_30/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched75-overlong4k-len20480-dapo-math17k-qwen3-8b-base-teacher4b-base-step90-mb32-nosystem-save30-eval15-latestopt-2gpu/global_step_30/actor/huggingface/config.jsonConfiguration1.6 KB —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched75-overlong4k-len20480-dapo-math17k-qwen3-8b-base-teacher4b-base-step90-mb32-nosystem-save30-eval15-latestopt-2gpu/global_step_30/actor/huggingface/generation_config.jsonConfiguration139 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched75-overlong4k-len20480-dapo-math17k-qwen3-8b-base-teacher4b-base-step90-mb32-nosystem-save30-eval15-latestopt-2gpu/global_step_60/actor/.async_checkpoint_ready_world_size_2_rank_0.jsonConfiguration369 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched75-overlong4k-len20480-dapo-math17k-qwen3-8b-base-teacher4b-base-step90-mb32-nosystem-save30-eval15-latestopt-2gpu/global_step_60/actor/.async_checkpoint_ready_world_size_2_rank_1.jsonConfiguration182 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched75-overlong4k-len20480-dapo-math17k-qwen3-8b-base-teacher4b-base-step90-mb32-nosystem-save30-eval15-latestopt-2gpu/global_step_60/actor/.async_checkpoint_started_world_size_2_rank_0.jsonConfiguration61 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched75-overlong4k-len20480-dapo-math17k-qwen3-8b-base-teacher4b-base-step90-mb32-nosystem-save30-eval15-latestopt-2gpu/global_step_60/actor/.async_checkpoint_started_world_size_2_rank_1.jsonConfiguration61 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched75-overlong4k-len20480-dapo-math17k-qwen3-8b-base-teacher4b-base-step90-mb32-nosystem-save30-eval15-latestopt-2gpu/global_step_60/actor/.checkpoint_complete.jsonConfiguration50 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched75-overlong4k-len20480-dapo-math17k-qwen3-8b-base-teacher4b-base-step90-mb32-nosystem-save30-eval15-latestopt-2gpu/global_step_60/actor/.worker_sidecars_ready_world_size_2_rank_0.jsonConfiguration83 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched75-overlong4k-len20480-dapo-math17k-qwen3-8b-base-teacher4b-base-step90-mb32-nosystem-save30-eval15-latestopt-2gpu/global_step_60/actor/.worker_sidecars_ready_world_size_2_rank_1.jsonConfiguration83 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched75-overlong4k-len20480-dapo-math17k-qwen3-8b-base-teacher4b-base-step90-mb32-nosystem-save30-eval15-latestopt-2gpu/global_step_60/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched75-overlong4k-len20480-dapo-math17k-qwen3-8b-base-teacher4b-base-step90-mb32-nosystem-save30-eval15-latestopt-2gpu/global_step_60/actor/huggingface/config.jsonConfiguration1.6 KB —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched75-overlong4k-len20480-dapo-math17k-qwen3-8b-base-teacher4b-base-step90-mb32-nosystem-save30-eval15-latestopt-2gpu/global_step_60/actor/huggingface/generation_config.jsonConfiguration139 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched75-overlong4k-len20480-dapo-math17k-qwen3-8b-base-teacher4b-base-step90-mb32-nosystem-save30-eval15-latestopt-2gpu/global_step_90/actor/.async_checkpoint_ready_world_size_2_rank_0.jsonConfiguration369 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched75-overlong4k-len20480-dapo-math17k-qwen3-8b-base-teacher4b-base-step90-mb32-nosystem-save30-eval15-latestopt-2gpu/global_step_90/actor/.async_checkpoint_ready_world_size_2_rank_1.jsonConfiguration182 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched75-overlong4k-len20480-dapo-math17k-qwen3-8b-base-teacher4b-base-step90-mb32-nosystem-save30-eval15-latestopt-2gpu/global_step_90/actor/.async_checkpoint_started_world_size_2_rank_0.jsonConfiguration61 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched75-overlong4k-len20480-dapo-math17k-qwen3-8b-base-teacher4b-base-step90-mb32-nosystem-save30-eval15-latestopt-2gpu/global_step_90/actor/.async_checkpoint_started_world_size_2_rank_1.jsonConfiguration61 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched75-overlong4k-len20480-dapo-math17k-qwen3-8b-base-teacher4b-base-step90-mb32-nosystem-save30-eval15-latestopt-2gpu/global_step_90/actor/.checkpoint_complete.jsonConfiguration50 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched75-overlong4k-len20480-dapo-math17k-qwen3-8b-base-teacher4b-base-step90-mb32-nosystem-save30-eval15-latestopt-2gpu/global_step_90/actor/.worker_sidecars_ready_world_size_2_rank_0.jsonConfiguration83 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched75-overlong4k-len20480-dapo-math17k-qwen3-8b-base-teacher4b-base-step90-mb32-nosystem-save30-eval15-latestopt-2gpu/global_step_90/actor/.worker_sidecars_ready_world_size_2_rank_1.jsonConfiguration83 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched75-overlong4k-len20480-dapo-math17k-qwen3-8b-base-teacher4b-base-step90-mb32-nosystem-save30-eval15-latestopt-2gpu/global_step_90/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched75-overlong4k-len20480-dapo-math17k-qwen3-8b-base-teacher4b-base-step90-mb32-nosystem-save30-eval15-latestopt-2gpu/global_step_90/actor/huggingface/config.jsonConfiguration1.6 KB —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched75-overlong4k-len20480-dapo-math17k-qwen3-8b-base-teacher4b-base-step90-mb32-nosystem-save30-eval15-latestopt-2gpu/global_step_90/actor/huggingface/generation_config.jsonConfiguration139 B —
experiments/weak_to_strong/math/ours/260723-rcd-signedlambda-plus0p5-minus0to0p5-sched75-overlong4k-len20480-dapo-math17k-qwen3-8b-base-teacher4b-base-step90-mb32-nosystem-save30-eval15-latestopt-2gpu/latest_checkpoint.jsonConfiguration403 B —
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/best_validation_checkpoint.jsonConfiguration234 B —
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_120/actor/.async_checkpoint_ready_world_size_4_rank_0.jsonConfiguration370 B —
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_120/actor/.async_checkpoint_ready_world_size_4_rank_1.jsonConfiguration183 B —
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_120/actor/.async_checkpoint_ready_world_size_4_rank_2.jsonConfiguration183 B —
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_120/actor/.async_checkpoint_ready_world_size_4_rank_3.jsonConfiguration183 B —
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_120/actor/.async_checkpoint_started_world_size_4_rank_0.jsonConfiguration62 B —
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_120/actor/.async_checkpoint_started_world_size_4_rank_1.jsonConfiguration62 B —
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_120/actor/.async_checkpoint_started_world_size_4_rank_2.jsonConfiguration62 B —
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_120/actor/.async_checkpoint_started_world_size_4_rank_3.jsonConfiguration62 B —
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_120/actor/.checkpoint_complete.jsonConfiguration51 B —
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_120/actor/.worker_sidecars_ready_world_size_4_rank_0.jsonConfiguration84 B —
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_120/actor/.worker_sidecars_ready_world_size_4_rank_1.jsonConfiguration84 B —
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_120/actor/.worker_sidecars_ready_world_size_4_rank_2.jsonConfiguration84 B —
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_120/actor/.worker_sidecars_ready_world_size_4_rank_3.jsonConfiguration84 B —
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_120/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_120/actor/huggingface/config.jsonConfiguration1.6 KB —
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_120/actor/huggingface/generation_config.jsonConfiguration214 B —
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_135/actor/.async_checkpoint_ready_world_size_4_rank_0.jsonConfiguration370 B —
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_135/actor/.async_checkpoint_ready_world_size_4_rank_1.jsonConfiguration183 B —
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_135/actor/.async_checkpoint_ready_world_size_4_rank_2.jsonConfiguration183 B —
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_135/actor/.async_checkpoint_ready_world_size_4_rank_3.jsonConfiguration183 B —
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_135/actor/.async_checkpoint_started_world_size_4_rank_0.jsonConfiguration62 B —
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_135/actor/.async_checkpoint_started_world_size_4_rank_1.jsonConfiguration62 B —
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_135/actor/.async_checkpoint_started_world_size_4_rank_2.jsonConfiguration62 B —
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_135/actor/.async_checkpoint_started_world_size_4_rank_3.jsonConfiguration62 B —
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_135/actor/.checkpoint_complete.jsonConfiguration51 B —
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_135/actor/.worker_sidecars_ready_world_size_4_rank_0.jsonConfiguration84 B —
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_135/actor/.worker_sidecars_ready_world_size_4_rank_1.jsonConfiguration84 B —
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_135/actor/.worker_sidecars_ready_world_size_4_rank_2.jsonConfiguration84 B —
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_135/actor/.worker_sidecars_ready_world_size_4_rank_3.jsonConfiguration84 B —
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_135/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_135/actor/huggingface/config.jsonConfiguration1.6 KB —
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_135/actor/huggingface/generation_config.jsonConfiguration214 B —
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_150/actor/.async_checkpoint_ready_world_size_4_rank_0.jsonConfiguration370 B —
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_150/actor/.async_checkpoint_ready_world_size_4_rank_1.jsonConfiguration183 B —
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_150/actor/.async_checkpoint_ready_world_size_4_rank_2.jsonConfiguration183 B —
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_150/actor/.async_checkpoint_ready_world_size_4_rank_3.jsonConfiguration183 B —
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_150/actor/.async_checkpoint_started_world_size_4_rank_0.jsonConfiguration62 B —
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_150/actor/.async_checkpoint_started_world_size_4_rank_1.jsonConfiguration62 B —
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_150/actor/.async_checkpoint_started_world_size_4_rank_2.jsonConfiguration62 B —
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_150/actor/.async_checkpoint_started_world_size_4_rank_3.jsonConfiguration62 B —
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_150/actor/.checkpoint_complete.jsonConfiguration51 B —
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_150/actor/.worker_sidecars_ready_world_size_4_rank_0.jsonConfiguration84 B —
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_150/actor/.worker_sidecars_ready_world_size_4_rank_1.jsonConfiguration84 B —
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_150/actor/.worker_sidecars_ready_world_size_4_rank_2.jsonConfiguration84 B —
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_150/actor/.worker_sidecars_ready_world_size_4_rank_3.jsonConfiguration84 B —
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_150/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_150/actor/huggingface/config.jsonConfiguration1.6 KB —
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_150/actor/huggingface/generation_config.jsonConfiguration214 B —
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_30/actor/.async_checkpoint_ready_world_size_4_rank_0.jsonConfiguration369 B —
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_30/actor/.async_checkpoint_ready_world_size_4_rank_1.jsonConfiguration182 B —
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_30/actor/.async_checkpoint_ready_world_size_4_rank_2.jsonConfiguration182 B —
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_30/actor/.async_checkpoint_ready_world_size_4_rank_3.jsonConfiguration182 B —
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_30/actor/.async_checkpoint_started_world_size_4_rank_0.jsonConfiguration61 B —
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_30/actor/.async_checkpoint_started_world_size_4_rank_1.jsonConfiguration61 B —
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_30/actor/.async_checkpoint_started_world_size_4_rank_2.jsonConfiguration61 B —
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_30/actor/.async_checkpoint_started_world_size_4_rank_3.jsonConfiguration61 B —
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_30/actor/.checkpoint_complete.jsonConfiguration50 B —
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_30/actor/.worker_sidecars_ready_world_size_4_rank_0.jsonConfiguration83 B —
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_30/actor/.worker_sidecars_ready_world_size_4_rank_1.jsonConfiguration83 B —
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_30/actor/.worker_sidecars_ready_world_size_4_rank_2.jsonConfiguration83 B —
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_30/actor/.worker_sidecars_ready_world_size_4_rank_3.jsonConfiguration83 B —
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_30/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_30/actor/huggingface/config.jsonConfiguration1.6 KB —
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_30/actor/huggingface/generation_config.jsonConfiguration214 B —
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_60/actor/.async_checkpoint_ready_world_size_4_rank_0.jsonConfiguration369 B —
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_60/actor/.async_checkpoint_ready_world_size_4_rank_1.jsonConfiguration182 B —
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_60/actor/.async_checkpoint_ready_world_size_4_rank_2.jsonConfiguration182 B —
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_60/actor/.async_checkpoint_ready_world_size_4_rank_3.jsonConfiguration182 B —
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_60/actor/.async_checkpoint_started_world_size_4_rank_0.jsonConfiguration61 B —
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_60/actor/.async_checkpoint_started_world_size_4_rank_1.jsonConfiguration61 B —
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_60/actor/.async_checkpoint_started_world_size_4_rank_2.jsonConfiguration61 B —
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_60/actor/.async_checkpoint_started_world_size_4_rank_3.jsonConfiguration61 B —
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_60/actor/.checkpoint_complete.jsonConfiguration50 B —
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_60/actor/.worker_sidecars_ready_world_size_4_rank_0.jsonConfiguration83 B —
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_60/actor/.worker_sidecars_ready_world_size_4_rank_1.jsonConfiguration83 B —
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_60/actor/.worker_sidecars_ready_world_size_4_rank_2.jsonConfiguration83 B —
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_60/actor/.worker_sidecars_ready_world_size_4_rank_3.jsonConfiguration83 B —
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_60/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_60/actor/huggingface/config.jsonConfiguration1.6 KB —
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_60/actor/huggingface/generation_config.jsonConfiguration214 B —
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_90/actor/.async_checkpoint_ready_world_size_4_rank_0.jsonConfiguration369 B —
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_90/actor/.async_checkpoint_ready_world_size_4_rank_1.jsonConfiguration182 B —
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_90/actor/.async_checkpoint_ready_world_size_4_rank_2.jsonConfiguration182 B —
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_90/actor/.async_checkpoint_ready_world_size_4_rank_3.jsonConfiguration182 B —
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_90/actor/.async_checkpoint_started_world_size_4_rank_0.jsonConfiguration61 B —
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_90/actor/.async_checkpoint_started_world_size_4_rank_1.jsonConfiguration61 B —
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_90/actor/.async_checkpoint_started_world_size_4_rank_2.jsonConfiguration61 B —
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_90/actor/.async_checkpoint_started_world_size_4_rank_3.jsonConfiguration61 B —
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_90/actor/.checkpoint_complete.jsonConfiguration50 B —
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_90/actor/.worker_sidecars_ready_world_size_4_rank_0.jsonConfiguration83 B —
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_90/actor/.worker_sidecars_ready_world_size_4_rank_1.jsonConfiguration83 B —
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_90/actor/.worker_sidecars_ready_world_size_4_rank_2.jsonConfiguration83 B —
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_90/actor/.worker_sidecars_ready_world_size_4_rank_3.jsonConfiguration83 B —
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_90/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_90/actor/huggingface/config.jsonConfiguration1.6 KB —
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/global_step_90/actor/huggingface/generation_config.jsonConfiguration214 B —
experiments/weak_to_strong/math/ours/260808-rcd-signedlambda-plus0p5-minus0to0p5-sched15-overlong4k-len20480-dapo-math17k-qwen3-8b-teacher4b-step75-save30-eval15-latestopt-4gpu-dp4/latest_checkpoint.jsonConfiguration461 B —
experiments/weak_to_strong/math/ours/260815-math-q3-8b-rcd-lp0p5to0-lm0fixed-s30-t4b75-4bbase-b64-mb64-dp4/best_validation_checkpoint.jsonConfiguration235 B —
experiments/weak_to_strong/math/ours/260815-math-q3-8b-rcd-lp0p5to0-lm0fixed-s30-t4b75-4bbase-b64-mb64-dp4/global_step_120/actor/.async_checkpoint_ready_world_size_4_rank_0.jsonConfiguration370 B —
experiments/weak_to_strong/math/ours/260815-math-q3-8b-rcd-lp0p5to0-lm0fixed-s30-t4b75-4bbase-b64-mb64-dp4/global_step_120/actor/.async_checkpoint_ready_world_size_4_rank_1.jsonConfiguration183 B —
experiments/weak_to_strong/math/ours/260815-math-q3-8b-rcd-lp0p5to0-lm0fixed-s30-t4b75-4bbase-b64-mb64-dp4/global_step_120/actor/.async_checkpoint_ready_world_size_4_rank_2.jsonConfiguration183 B —
experiments/weak_to_strong/math/ours/260815-math-q3-8b-rcd-lp0p5to0-lm0fixed-s30-t4b75-4bbase-b64-mb64-dp4/global_step_120/actor/.async_checkpoint_ready_world_size_4_rank_3.jsonConfiguration183 B —
experiments/weak_to_strong/math/ours/260815-math-q3-8b-rcd-lp0p5to0-lm0fixed-s30-t4b75-4bbase-b64-mb64-dp4/global_step_120/actor/.async_checkpoint_started_world_size_4_rank_0.jsonConfiguration62 B —
experiments/weak_to_strong/math/ours/260815-math-q3-8b-rcd-lp0p5to0-lm0fixed-s30-t4b75-4bbase-b64-mb64-dp4/global_step_120/actor/.async_checkpoint_started_world_size_4_rank_1.jsonConfiguration62 B —
experiments/weak_to_strong/math/ours/260815-math-q3-8b-rcd-lp0p5to0-lm0fixed-s30-t4b75-4bbase-b64-mb64-dp4/global_step_120/actor/.async_checkpoint_started_world_size_4_rank_2.jsonConfiguration62 B —
experiments/weak_to_strong/math/ours/260815-math-q3-8b-rcd-lp0p5to0-lm0fixed-s30-t4b75-4bbase-b64-mb64-dp4/global_step_120/actor/.async_checkpoint_started_world_size_4_rank_3.jsonConfiguration62 B —
experiments/weak_to_strong/math/ours/260815-math-q3-8b-rcd-lp0p5to0-lm0fixed-s30-t4b75-4bbase-b64-mb64-dp4/global_step_120/actor/.checkpoint_complete.jsonConfiguration51 B —
experiments/weak_to_strong/math/ours/260815-math-q3-8b-rcd-lp0p5to0-lm0fixed-s30-t4b75-4bbase-b64-mb64-dp4/global_step_120/actor/.worker_sidecars_ready_world_size_4_rank_0.jsonConfiguration84 B —
experiments/weak_to_strong/math/ours/260815-math-q3-8b-rcd-lp0p5to0-lm0fixed-s30-t4b75-4bbase-b64-mb64-dp4/global_step_120/actor/.worker_sidecars_ready_world_size_4_rank_1.jsonConfiguration84 B —
experiments/weak_to_strong/math/ours/260815-math-q3-8b-rcd-lp0p5to0-lm0fixed-s30-t4b75-4bbase-b64-mb64-dp4/global_step_120/actor/.worker_sidecars_ready_world_size_4_rank_2.jsonConfiguration84 B —
experiments/weak_to_strong/math/ours/260815-math-q3-8b-rcd-lp0p5to0-lm0fixed-s30-t4b75-4bbase-b64-mb64-dp4/global_step_120/actor/.worker_sidecars_ready_world_size_4_rank_3.jsonConfiguration84 B —
experiments/weak_to_strong/math/ours/260815-math-q3-8b-rcd-lp0p5to0-lm0fixed-s30-t4b75-4bbase-b64-mb64-dp4/global_step_120/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/math/ours/260815-math-q3-8b-rcd-lp0p5to0-lm0fixed-s30-t4b75-4bbase-b64-mb64-dp4/global_step_120/actor/huggingface/config.jsonConfiguration1.6 KB —
experiments/weak_to_strong/math/ours/260815-math-q3-8b-rcd-lp0p5to0-lm0fixed-s30-t4b75-4bbase-b64-mb64-dp4/global_step_120/actor/huggingface/generation_config.jsonConfiguration214 B —
experiments/weak_to_strong/math/ours/260815-math-q3-8b-rcd-lp0p5to0-lm0fixed-s30-t4b75-4bbase-b64-mb64-dp4/global_step_150/actor/.async_checkpoint_ready_world_size_4_rank_0.jsonConfiguration370 B —
experiments/weak_to_strong/math/ours/260815-math-q3-8b-rcd-lp0p5to0-lm0fixed-s30-t4b75-4bbase-b64-mb64-dp4/global_step_150/actor/.async_checkpoint_ready_world_size_4_rank_1.jsonConfiguration183 B —
experiments/weak_to_strong/math/ours/260815-math-q3-8b-rcd-lp0p5to0-lm0fixed-s30-t4b75-4bbase-b64-mb64-dp4/global_step_150/actor/.async_checkpoint_ready_world_size_4_rank_2.jsonConfiguration183 B —
experiments/weak_to_strong/math/ours/260815-math-q3-8b-rcd-lp0p5to0-lm0fixed-s30-t4b75-4bbase-b64-mb64-dp4/global_step_150/actor/.async_checkpoint_ready_world_size_4_rank_3.jsonConfiguration183 B —
experiments/weak_to_strong/math/ours/260815-math-q3-8b-rcd-lp0p5to0-lm0fixed-s30-t4b75-4bbase-b64-mb64-dp4/global_step_150/actor/.async_checkpoint_started_world_size_4_rank_0.jsonConfiguration62 B —
experiments/weak_to_strong/math/ours/260815-math-q3-8b-rcd-lp0p5to0-lm0fixed-s30-t4b75-4bbase-b64-mb64-dp4/global_step_150/actor/.async_checkpoint_started_world_size_4_rank_1.jsonConfiguration62 B —
experiments/weak_to_strong/math/ours/260815-math-q3-8b-rcd-lp0p5to0-lm0fixed-s30-t4b75-4bbase-b64-mb64-dp4/global_step_150/actor/.async_checkpoint_started_world_size_4_rank_2.jsonConfiguration62 B —
experiments/weak_to_strong/math/ours/260815-math-q3-8b-rcd-lp0p5to0-lm0fixed-s30-t4b75-4bbase-b64-mb64-dp4/global_step_150/actor/.async_checkpoint_started_world_size_4_rank_3.jsonConfiguration62 B —
experiments/weak_to_strong/math/ours/260815-math-q3-8b-rcd-lp0p5to0-lm0fixed-s30-t4b75-4bbase-b64-mb64-dp4/global_step_150/actor/.checkpoint_complete.jsonConfiguration51 B —
experiments/weak_to_strong/math/ours/260815-math-q3-8b-rcd-lp0p5to0-lm0fixed-s30-t4b75-4bbase-b64-mb64-dp4/global_step_150/actor/.worker_sidecars_ready_world_size_4_rank_0.jsonConfiguration84 B —
experiments/weak_to_strong/math/ours/260815-math-q3-8b-rcd-lp0p5to0-lm0fixed-s30-t4b75-4bbase-b64-mb64-dp4/global_step_150/actor/.worker_sidecars_ready_world_size_4_rank_1.jsonConfiguration84 B —
experiments/weak_to_strong/math/ours/260815-math-q3-8b-rcd-lp0p5to0-lm0fixed-s30-t4b75-4bbase-b64-mb64-dp4/global_step_150/actor/.worker_sidecars_ready_world_size_4_rank_2.jsonConfiguration84 B —
experiments/weak_to_strong/math/ours/260815-math-q3-8b-rcd-lp0p5to0-lm0fixed-s30-t4b75-4bbase-b64-mb64-dp4/global_step_150/actor/.worker_sidecars_ready_world_size_4_rank_3.jsonConfiguration84 B —
experiments/weak_to_strong/math/ours/260815-math-q3-8b-rcd-lp0p5to0-lm0fixed-s30-t4b75-4bbase-b64-mb64-dp4/global_step_150/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/math/ours/260815-math-q3-8b-rcd-lp0p5to0-lm0fixed-s30-t4b75-4bbase-b64-mb64-dp4/global_step_150/actor/huggingface/config.jsonConfiguration1.6 KB —
experiments/weak_to_strong/math/ours/260815-math-q3-8b-rcd-lp0p5to0-lm0fixed-s30-t4b75-4bbase-b64-mb64-dp4/global_step_150/actor/huggingface/generation_config.jsonConfiguration214 B —
experiments/weak_to_strong/math/ours/260815-math-q3-8b-rcd-lp0p5to0-lm0fixed-s30-t4b75-4bbase-b64-mb64-dp4/global_step_30/actor/.async_checkpoint_ready_world_size_4_rank_0.jsonConfiguration369 B —
experiments/weak_to_strong/math/ours/260815-math-q3-8b-rcd-lp0p5to0-lm0fixed-s30-t4b75-4bbase-b64-mb64-dp4/global_step_30/actor/.async_checkpoint_ready_world_size_4_rank_1.jsonConfiguration182 B —
experiments/weak_to_strong/math/ours/260815-math-q3-8b-rcd-lp0p5to0-lm0fixed-s30-t4b75-4bbase-b64-mb64-dp4/global_step_30/actor/.async_checkpoint_ready_world_size_4_rank_2.jsonConfiguration182 B —
experiments/weak_to_strong/math/ours/260815-math-q3-8b-rcd-lp0p5to0-lm0fixed-s30-t4b75-4bbase-b64-mb64-dp4/global_step_30/actor/.async_checkpoint_ready_world_size_4_rank_3.jsonConfiguration182 B —
experiments/weak_to_strong/math/ours/260815-math-q3-8b-rcd-lp0p5to0-lm0fixed-s30-t4b75-4bbase-b64-mb64-dp4/global_step_30/actor/.async_checkpoint_started_world_size_4_rank_0.jsonConfiguration61 B —
experiments/weak_to_strong/math/ours/260815-math-q3-8b-rcd-lp0p5to0-lm0fixed-s30-t4b75-4bbase-b64-mb64-dp4/global_step_30/actor/.async_checkpoint_started_world_size_4_rank_1.jsonConfiguration61 B —
experiments/weak_to_strong/math/ours/260815-math-q3-8b-rcd-lp0p5to0-lm0fixed-s30-t4b75-4bbase-b64-mb64-dp4/global_step_30/actor/.async_checkpoint_started_world_size_4_rank_2.jsonConfiguration61 B —
experiments/weak_to_strong/math/ours/260815-math-q3-8b-rcd-lp0p5to0-lm0fixed-s30-t4b75-4bbase-b64-mb64-dp4/global_step_30/actor/.async_checkpoint_started_world_size_4_rank_3.jsonConfiguration61 B —
experiments/weak_to_strong/math/ours/260815-math-q3-8b-rcd-lp0p5to0-lm0fixed-s30-t4b75-4bbase-b64-mb64-dp4/global_step_30/actor/.checkpoint_complete.jsonConfiguration50 B —
experiments/weak_to_strong/math/ours/260815-math-q3-8b-rcd-lp0p5to0-lm0fixed-s30-t4b75-4bbase-b64-mb64-dp4/global_step_30/actor/.worker_sidecars_ready_world_size_4_rank_0.jsonConfiguration83 B —
experiments/weak_to_strong/math/ours/260815-math-q3-8b-rcd-lp0p5to0-lm0fixed-s30-t4b75-4bbase-b64-mb64-dp4/global_step_30/actor/.worker_sidecars_ready_world_size_4_rank_1.jsonConfiguration83 B —
experiments/weak_to_strong/math/ours/260815-math-q3-8b-rcd-lp0p5to0-lm0fixed-s30-t4b75-4bbase-b64-mb64-dp4/global_step_30/actor/.worker_sidecars_ready_world_size_4_rank_2.jsonConfiguration83 B —
experiments/weak_to_strong/math/ours/260815-math-q3-8b-rcd-lp0p5to0-lm0fixed-s30-t4b75-4bbase-b64-mb64-dp4/global_step_30/actor/.worker_sidecars_ready_world_size_4_rank_3.jsonConfiguration83 B —
experiments/weak_to_strong/math/ours/260815-math-q3-8b-rcd-lp0p5to0-lm0fixed-s30-t4b75-4bbase-b64-mb64-dp4/global_step_30/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/math/ours/260815-math-q3-8b-rcd-lp0p5to0-lm0fixed-s30-t4b75-4bbase-b64-mb64-dp4/global_step_30/actor/huggingface/config.jsonConfiguration1.6 KB —
experiments/weak_to_strong/math/ours/260815-math-q3-8b-rcd-lp0p5to0-lm0fixed-s30-t4b75-4bbase-b64-mb64-dp4/global_step_30/actor/huggingface/generation_config.jsonConfiguration214 B —
experiments/weak_to_strong/math/ours/260815-math-q3-8b-rcd-lp0p5to0-lm0fixed-s30-t4b75-4bbase-b64-mb64-dp4/global_step_60/actor/.async_checkpoint_ready_world_size_4_rank_0.jsonConfiguration369 B —
experiments/weak_to_strong/math/ours/260815-math-q3-8b-rcd-lp0p5to0-lm0fixed-s30-t4b75-4bbase-b64-mb64-dp4/global_step_60/actor/.async_checkpoint_ready_world_size_4_rank_1.jsonConfiguration182 B —
experiments/weak_to_strong/math/ours/260815-math-q3-8b-rcd-lp0p5to0-lm0fixed-s30-t4b75-4bbase-b64-mb64-dp4/global_step_60/actor/.async_checkpoint_ready_world_size_4_rank_2.jsonConfiguration182 B —
experiments/weak_to_strong/math/ours/260815-math-q3-8b-rcd-lp0p5to0-lm0fixed-s30-t4b75-4bbase-b64-mb64-dp4/global_step_60/actor/.async_checkpoint_ready_world_size_4_rank_3.jsonConfiguration182 B —
experiments/weak_to_strong/math/ours/260815-math-q3-8b-rcd-lp0p5to0-lm0fixed-s30-t4b75-4bbase-b64-mb64-dp4/global_step_60/actor/.async_checkpoint_started_world_size_4_rank_0.jsonConfiguration61 B —
experiments/weak_to_strong/math/ours/260815-math-q3-8b-rcd-lp0p5to0-lm0fixed-s30-t4b75-4bbase-b64-mb64-dp4/global_step_60/actor/.async_checkpoint_started_world_size_4_rank_1.jsonConfiguration61 B —
experiments/weak_to_strong/math/ours/260815-math-q3-8b-rcd-lp0p5to0-lm0fixed-s30-t4b75-4bbase-b64-mb64-dp4/global_step_60/actor/.async_checkpoint_started_world_size_4_rank_2.jsonConfiguration61 B —
experiments/weak_to_strong/math/ours/260815-math-q3-8b-rcd-lp0p5to0-lm0fixed-s30-t4b75-4bbase-b64-mb64-dp4/global_step_60/actor/.async_checkpoint_started_world_size_4_rank_3.jsonConfiguration61 B —
experiments/weak_to_strong/math/ours/260815-math-q3-8b-rcd-lp0p5to0-lm0fixed-s30-t4b75-4bbase-b64-mb64-dp4/global_step_60/actor/.checkpoint_complete.jsonConfiguration50 B —
experiments/weak_to_strong/math/ours/260815-math-q3-8b-rcd-lp0p5to0-lm0fixed-s30-t4b75-4bbase-b64-mb64-dp4/global_step_60/actor/.worker_sidecars_ready_world_size_4_rank_0.jsonConfiguration83 B —
experiments/weak_to_strong/math/ours/260815-math-q3-8b-rcd-lp0p5to0-lm0fixed-s30-t4b75-4bbase-b64-mb64-dp4/global_step_60/actor/.worker_sidecars_ready_world_size_4_rank_1.jsonConfiguration83 B —
experiments/weak_to_strong/math/ours/260815-math-q3-8b-rcd-lp0p5to0-lm0fixed-s30-t4b75-4bbase-b64-mb64-dp4/global_step_60/actor/.worker_sidecars_ready_world_size_4_rank_2.jsonConfiguration83 B —
experiments/weak_to_strong/math/ours/260815-math-q3-8b-rcd-lp0p5to0-lm0fixed-s30-t4b75-4bbase-b64-mb64-dp4/global_step_60/actor/.worker_sidecars_ready_world_size_4_rank_3.jsonConfiguration83 B —
experiments/weak_to_strong/math/ours/260815-math-q3-8b-rcd-lp0p5to0-lm0fixed-s30-t4b75-4bbase-b64-mb64-dp4/global_step_60/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/math/ours/260815-math-q3-8b-rcd-lp0p5to0-lm0fixed-s30-t4b75-4bbase-b64-mb64-dp4/global_step_60/actor/huggingface/config.jsonConfiguration1.6 KB —
experiments/weak_to_strong/math/ours/260815-math-q3-8b-rcd-lp0p5to0-lm0fixed-s30-t4b75-4bbase-b64-mb64-dp4/global_step_60/actor/huggingface/generation_config.jsonConfiguration214 B —
experiments/weak_to_strong/math/ours/260815-math-q3-8b-rcd-lp0p5to0-lm0fixed-s30-t4b75-4bbase-b64-mb64-dp4/global_step_90/actor/.async_checkpoint_ready_world_size_4_rank_0.jsonConfiguration369 B —
experiments/weak_to_strong/math/ours/260815-math-q3-8b-rcd-lp0p5to0-lm0fixed-s30-t4b75-4bbase-b64-mb64-dp4/global_step_90/actor/.async_checkpoint_ready_world_size_4_rank_1.jsonConfiguration182 B —
experiments/weak_to_strong/math/ours/260815-math-q3-8b-rcd-lp0p5to0-lm0fixed-s30-t4b75-4bbase-b64-mb64-dp4/global_step_90/actor/.async_checkpoint_ready_world_size_4_rank_2.jsonConfiguration182 B —
experiments/weak_to_strong/math/ours/260815-math-q3-8b-rcd-lp0p5to0-lm0fixed-s30-t4b75-4bbase-b64-mb64-dp4/global_step_90/actor/.async_checkpoint_ready_world_size_4_rank_3.jsonConfiguration182 B —
experiments/weak_to_strong/math/ours/260815-math-q3-8b-rcd-lp0p5to0-lm0fixed-s30-t4b75-4bbase-b64-mb64-dp4/global_step_90/actor/.async_checkpoint_started_world_size_4_rank_0.jsonConfiguration61 B —
experiments/weak_to_strong/math/ours/260815-math-q3-8b-rcd-lp0p5to0-lm0fixed-s30-t4b75-4bbase-b64-mb64-dp4/global_step_90/actor/.async_checkpoint_started_world_size_4_rank_1.jsonConfiguration61 B —
experiments/weak_to_strong/math/ours/260815-math-q3-8b-rcd-lp0p5to0-lm0fixed-s30-t4b75-4bbase-b64-mb64-dp4/global_step_90/actor/.async_checkpoint_started_world_size_4_rank_2.jsonConfiguration61 B —
experiments/weak_to_strong/math/ours/260815-math-q3-8b-rcd-lp0p5to0-lm0fixed-s30-t4b75-4bbase-b64-mb64-dp4/global_step_90/actor/.async_checkpoint_started_world_size_4_rank_3.jsonConfiguration61 B —
experiments/weak_to_strong/math/ours/260815-math-q3-8b-rcd-lp0p5to0-lm0fixed-s30-t4b75-4bbase-b64-mb64-dp4/global_step_90/actor/.checkpoint_complete.jsonConfiguration50 B —
experiments/weak_to_strong/math/ours/260815-math-q3-8b-rcd-lp0p5to0-lm0fixed-s30-t4b75-4bbase-b64-mb64-dp4/global_step_90/actor/.worker_sidecars_ready_world_size_4_rank_0.jsonConfiguration83 B —
experiments/weak_to_strong/math/ours/260815-math-q3-8b-rcd-lp0p5to0-lm0fixed-s30-t4b75-4bbase-b64-mb64-dp4/global_step_90/actor/.worker_sidecars_ready_world_size_4_rank_1.jsonConfiguration83 B —
experiments/weak_to_strong/math/ours/260815-math-q3-8b-rcd-lp0p5to0-lm0fixed-s30-t4b75-4bbase-b64-mb64-dp4/global_step_90/actor/.worker_sidecars_ready_world_size_4_rank_2.jsonConfiguration83 B —
experiments/weak_to_strong/math/ours/260815-math-q3-8b-rcd-lp0p5to0-lm0fixed-s30-t4b75-4bbase-b64-mb64-dp4/global_step_90/actor/.worker_sidecars_ready_world_size_4_rank_3.jsonConfiguration83 B —
experiments/weak_to_strong/math/ours/260815-math-q3-8b-rcd-lp0p5to0-lm0fixed-s30-t4b75-4bbase-b64-mb64-dp4/global_step_90/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/math/ours/260815-math-q3-8b-rcd-lp0p5to0-lm0fixed-s30-t4b75-4bbase-b64-mb64-dp4/global_step_90/actor/huggingface/config.jsonConfiguration1.6 KB —
experiments/weak_to_strong/math/ours/260815-math-q3-8b-rcd-lp0p5to0-lm0fixed-s30-t4b75-4bbase-b64-mb64-dp4/global_step_90/actor/huggingface/generation_config.jsonConfiguration214 B —
experiments/weak_to_strong/math/ours/260815-math-q3-8b-rcd-lp0p5to0-lm0fixed-s30-t4b75-4bbase-b64-mb64-dp4/latest_checkpoint.jsonConfiguration385 B —
experiments/weak_to_strong/math/ours/260816-math-rcd-opdgrad-lp0p5-lm0to0p5-s30-qwen3-8b-t4b-step75-tk10-b64-mb64-dp4/best_validation_checkpoint.jsonConfiguration235 B —
experiments/weak_to_strong/math/ours/260816-math-rcd-opdgrad-lp0p5-lm0to0p5-s30-qwen3-8b-t4b-step75-tk10-b64-mb64-dp4/global_step_120/actor/.async_checkpoint_ready_world_size_4_rank_0.jsonConfiguration370 B —
experiments/weak_to_strong/math/ours/260816-math-rcd-opdgrad-lp0p5-lm0to0p5-s30-qwen3-8b-t4b-step75-tk10-b64-mb64-dp4/global_step_120/actor/.async_checkpoint_ready_world_size_4_rank_1.jsonConfiguration183 B —
experiments/weak_to_strong/math/ours/260816-math-rcd-opdgrad-lp0p5-lm0to0p5-s30-qwen3-8b-t4b-step75-tk10-b64-mb64-dp4/global_step_120/actor/.async_checkpoint_ready_world_size_4_rank_2.jsonConfiguration183 B —
experiments/weak_to_strong/math/ours/260816-math-rcd-opdgrad-lp0p5-lm0to0p5-s30-qwen3-8b-t4b-step75-tk10-b64-mb64-dp4/global_step_120/actor/.async_checkpoint_ready_world_size_4_rank_3.jsonConfiguration183 B —
experiments/weak_to_strong/math/ours/260816-math-rcd-opdgrad-lp0p5-lm0to0p5-s30-qwen3-8b-t4b-step75-tk10-b64-mb64-dp4/global_step_120/actor/.async_checkpoint_started_world_size_4_rank_0.jsonConfiguration62 B —
experiments/weak_to_strong/math/ours/260816-math-rcd-opdgrad-lp0p5-lm0to0p5-s30-qwen3-8b-t4b-step75-tk10-b64-mb64-dp4/global_step_120/actor/.async_checkpoint_started_world_size_4_rank_1.jsonConfiguration62 B —
experiments/weak_to_strong/math/ours/260816-math-rcd-opdgrad-lp0p5-lm0to0p5-s30-qwen3-8b-t4b-step75-tk10-b64-mb64-dp4/global_step_120/actor/.async_checkpoint_started_world_size_4_rank_2.jsonConfiguration62 B —
experiments/weak_to_strong/math/ours/260816-math-rcd-opdgrad-lp0p5-lm0to0p5-s30-qwen3-8b-t4b-step75-tk10-b64-mb64-dp4/global_step_120/actor/.async_checkpoint_started_world_size_4_rank_3.jsonConfiguration62 B —
experiments/weak_to_strong/math/ours/260816-math-rcd-opdgrad-lp0p5-lm0to0p5-s30-qwen3-8b-t4b-step75-tk10-b64-mb64-dp4/global_step_120/actor/.checkpoint_complete.jsonConfiguration51 B —
experiments/weak_to_strong/math/ours/260816-math-rcd-opdgrad-lp0p5-lm0to0p5-s30-qwen3-8b-t4b-step75-tk10-b64-mb64-dp4/global_step_120/actor/.worker_sidecars_ready_world_size_4_rank_0.jsonConfiguration84 B —
experiments/weak_to_strong/math/ours/260816-math-rcd-opdgrad-lp0p5-lm0to0p5-s30-qwen3-8b-t4b-step75-tk10-b64-mb64-dp4/global_step_120/actor/.worker_sidecars_ready_world_size_4_rank_1.jsonConfiguration84 B —
experiments/weak_to_strong/math/ours/260816-math-rcd-opdgrad-lp0p5-lm0to0p5-s30-qwen3-8b-t4b-step75-tk10-b64-mb64-dp4/global_step_120/actor/.worker_sidecars_ready_world_size_4_rank_2.jsonConfiguration84 B —
experiments/weak_to_strong/math/ours/260816-math-rcd-opdgrad-lp0p5-lm0to0p5-s30-qwen3-8b-t4b-step75-tk10-b64-mb64-dp4/global_step_120/actor/.worker_sidecars_ready_world_size_4_rank_3.jsonConfiguration84 B —
experiments/weak_to_strong/math/ours/260816-math-rcd-opdgrad-lp0p5-lm0to0p5-s30-qwen3-8b-t4b-step75-tk10-b64-mb64-dp4/global_step_120/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/math/ours/260816-math-rcd-opdgrad-lp0p5-lm0to0p5-s30-qwen3-8b-t4b-step75-tk10-b64-mb64-dp4/global_step_120/actor/huggingface/config.jsonConfiguration1.6 KB —
experiments/weak_to_strong/math/ours/260816-math-rcd-opdgrad-lp0p5-lm0to0p5-s30-qwen3-8b-t4b-step75-tk10-b64-mb64-dp4/global_step_120/actor/huggingface/generation_config.jsonConfiguration214 B —
experiments/weak_to_strong/math/ours/260816-math-rcd-opdgrad-lp0p5-lm0to0p5-s30-qwen3-8b-t4b-step75-tk10-b64-mb64-dp4/global_step_150/actor/.async_checkpoint_ready_world_size_4_rank_0.jsonConfiguration370 B —
experiments/weak_to_strong/math/ours/260816-math-rcd-opdgrad-lp0p5-lm0to0p5-s30-qwen3-8b-t4b-step75-tk10-b64-mb64-dp4/global_step_150/actor/.async_checkpoint_ready_world_size_4_rank_1.jsonConfiguration183 B —
experiments/weak_to_strong/math/ours/260816-math-rcd-opdgrad-lp0p5-lm0to0p5-s30-qwen3-8b-t4b-step75-tk10-b64-mb64-dp4/global_step_150/actor/.async_checkpoint_ready_world_size_4_rank_2.jsonConfiguration183 B —
experiments/weak_to_strong/math/ours/260816-math-rcd-opdgrad-lp0p5-lm0to0p5-s30-qwen3-8b-t4b-step75-tk10-b64-mb64-dp4/global_step_150/actor/.async_checkpoint_ready_world_size_4_rank_3.jsonConfiguration183 B —
experiments/weak_to_strong/math/ours/260816-math-rcd-opdgrad-lp0p5-lm0to0p5-s30-qwen3-8b-t4b-step75-tk10-b64-mb64-dp4/global_step_150/actor/.async_checkpoint_started_world_size_4_rank_0.jsonConfiguration62 B —
experiments/weak_to_strong/math/ours/260816-math-rcd-opdgrad-lp0p5-lm0to0p5-s30-qwen3-8b-t4b-step75-tk10-b64-mb64-dp4/global_step_150/actor/.async_checkpoint_started_world_size_4_rank_1.jsonConfiguration62 B —
experiments/weak_to_strong/math/ours/260816-math-rcd-opdgrad-lp0p5-lm0to0p5-s30-qwen3-8b-t4b-step75-tk10-b64-mb64-dp4/global_step_150/actor/.async_checkpoint_started_world_size_4_rank_2.jsonConfiguration62 B —
experiments/weak_to_strong/math/ours/260816-math-rcd-opdgrad-lp0p5-lm0to0p5-s30-qwen3-8b-t4b-step75-tk10-b64-mb64-dp4/global_step_150/actor/.async_checkpoint_started_world_size_4_rank_3.jsonConfiguration62 B —
experiments/weak_to_strong/math/ours/260816-math-rcd-opdgrad-lp0p5-lm0to0p5-s30-qwen3-8b-t4b-step75-tk10-b64-mb64-dp4/global_step_150/actor/.checkpoint_complete.jsonConfiguration51 B —
experiments/weak_to_strong/math/ours/260816-math-rcd-opdgrad-lp0p5-lm0to0p5-s30-qwen3-8b-t4b-step75-tk10-b64-mb64-dp4/global_step_150/actor/.worker_sidecars_ready_world_size_4_rank_0.jsonConfiguration84 B —
experiments/weak_to_strong/math/ours/260816-math-rcd-opdgrad-lp0p5-lm0to0p5-s30-qwen3-8b-t4b-step75-tk10-b64-mb64-dp4/global_step_150/actor/.worker_sidecars_ready_world_size_4_rank_1.jsonConfiguration84 B —
experiments/weak_to_strong/math/ours/260816-math-rcd-opdgrad-lp0p5-lm0to0p5-s30-qwen3-8b-t4b-step75-tk10-b64-mb64-dp4/global_step_150/actor/.worker_sidecars_ready_world_size_4_rank_2.jsonConfiguration84 B —
experiments/weak_to_strong/math/ours/260816-math-rcd-opdgrad-lp0p5-lm0to0p5-s30-qwen3-8b-t4b-step75-tk10-b64-mb64-dp4/global_step_150/actor/.worker_sidecars_ready_world_size_4_rank_3.jsonConfiguration84 B —
experiments/weak_to_strong/math/ours/260816-math-rcd-opdgrad-lp0p5-lm0to0p5-s30-qwen3-8b-t4b-step75-tk10-b64-mb64-dp4/global_step_150/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/math/ours/260816-math-rcd-opdgrad-lp0p5-lm0to0p5-s30-qwen3-8b-t4b-step75-tk10-b64-mb64-dp4/global_step_150/actor/huggingface/config.jsonConfiguration1.6 KB —
experiments/weak_to_strong/math/ours/260816-math-rcd-opdgrad-lp0p5-lm0to0p5-s30-qwen3-8b-t4b-step75-tk10-b64-mb64-dp4/global_step_150/actor/huggingface/generation_config.jsonConfiguration214 B —
experiments/weak_to_strong/math/ours/260816-math-rcd-opdgrad-lp0p5-lm0to0p5-s30-qwen3-8b-t4b-step75-tk10-b64-mb64-dp4/global_step_30/actor/.async_checkpoint_ready_world_size_4_rank_0.jsonConfiguration369 B —
experiments/weak_to_strong/math/ours/260816-math-rcd-opdgrad-lp0p5-lm0to0p5-s30-qwen3-8b-t4b-step75-tk10-b64-mb64-dp4/global_step_30/actor/.async_checkpoint_ready_world_size_4_rank_1.jsonConfiguration182 B —
experiments/weak_to_strong/math/ours/260816-math-rcd-opdgrad-lp0p5-lm0to0p5-s30-qwen3-8b-t4b-step75-tk10-b64-mb64-dp4/global_step_30/actor/.async_checkpoint_ready_world_size_4_rank_2.jsonConfiguration182 B —
experiments/weak_to_strong/math/ours/260816-math-rcd-opdgrad-lp0p5-lm0to0p5-s30-qwen3-8b-t4b-step75-tk10-b64-mb64-dp4/global_step_30/actor/.async_checkpoint_ready_world_size_4_rank_3.jsonConfiguration182 B —
experiments/weak_to_strong/math/ours/260816-math-rcd-opdgrad-lp0p5-lm0to0p5-s30-qwen3-8b-t4b-step75-tk10-b64-mb64-dp4/global_step_30/actor/.async_checkpoint_started_world_size_4_rank_0.jsonConfiguration61 B —
experiments/weak_to_strong/math/ours/260816-math-rcd-opdgrad-lp0p5-lm0to0p5-s30-qwen3-8b-t4b-step75-tk10-b64-mb64-dp4/global_step_30/actor/.async_checkpoint_started_world_size_4_rank_1.jsonConfiguration61 B —
experiments/weak_to_strong/math/ours/260816-math-rcd-opdgrad-lp0p5-lm0to0p5-s30-qwen3-8b-t4b-step75-tk10-b64-mb64-dp4/global_step_30/actor/.async_checkpoint_started_world_size_4_rank_2.jsonConfiguration61 B —
experiments/weak_to_strong/math/ours/260816-math-rcd-opdgrad-lp0p5-lm0to0p5-s30-qwen3-8b-t4b-step75-tk10-b64-mb64-dp4/global_step_30/actor/.async_checkpoint_started_world_size_4_rank_3.jsonConfiguration61 B —
experiments/weak_to_strong/math/ours/260816-math-rcd-opdgrad-lp0p5-lm0to0p5-s30-qwen3-8b-t4b-step75-tk10-b64-mb64-dp4/global_step_30/actor/.checkpoint_complete.jsonConfiguration50 B —
experiments/weak_to_strong/math/ours/260816-math-rcd-opdgrad-lp0p5-lm0to0p5-s30-qwen3-8b-t4b-step75-tk10-b64-mb64-dp4/global_step_30/actor/.worker_sidecars_ready_world_size_4_rank_0.jsonConfiguration83 B —
experiments/weak_to_strong/math/ours/260816-math-rcd-opdgrad-lp0p5-lm0to0p5-s30-qwen3-8b-t4b-step75-tk10-b64-mb64-dp4/global_step_30/actor/.worker_sidecars_ready_world_size_4_rank_1.jsonConfiguration83 B —
experiments/weak_to_strong/math/ours/260816-math-rcd-opdgrad-lp0p5-lm0to0p5-s30-qwen3-8b-t4b-step75-tk10-b64-mb64-dp4/global_step_30/actor/.worker_sidecars_ready_world_size_4_rank_2.jsonConfiguration83 B —
experiments/weak_to_strong/math/ours/260816-math-rcd-opdgrad-lp0p5-lm0to0p5-s30-qwen3-8b-t4b-step75-tk10-b64-mb64-dp4/global_step_30/actor/.worker_sidecars_ready_world_size_4_rank_3.jsonConfiguration83 B —
experiments/weak_to_strong/math/ours/260816-math-rcd-opdgrad-lp0p5-lm0to0p5-s30-qwen3-8b-t4b-step75-tk10-b64-mb64-dp4/global_step_30/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/math/ours/260816-math-rcd-opdgrad-lp0p5-lm0to0p5-s30-qwen3-8b-t4b-step75-tk10-b64-mb64-dp4/global_step_30/actor/huggingface/config.jsonConfiguration1.6 KB —
experiments/weak_to_strong/math/ours/260816-math-rcd-opdgrad-lp0p5-lm0to0p5-s30-qwen3-8b-t4b-step75-tk10-b64-mb64-dp4/global_step_30/actor/huggingface/generation_config.jsonConfiguration214 B —
experiments/weak_to_strong/math/ours/260816-math-rcd-opdgrad-lp0p5-lm0to0p5-s30-qwen3-8b-t4b-step75-tk10-b64-mb64-dp4/global_step_60/actor/.async_checkpoint_ready_world_size_4_rank_0.jsonConfiguration369 B —
experiments/weak_to_strong/math/ours/260816-math-rcd-opdgrad-lp0p5-lm0to0p5-s30-qwen3-8b-t4b-step75-tk10-b64-mb64-dp4/global_step_60/actor/.async_checkpoint_ready_world_size_4_rank_1.jsonConfiguration182 B —
experiments/weak_to_strong/math/ours/260816-math-rcd-opdgrad-lp0p5-lm0to0p5-s30-qwen3-8b-t4b-step75-tk10-b64-mb64-dp4/global_step_60/actor/.async_checkpoint_ready_world_size_4_rank_2.jsonConfiguration182 B —
experiments/weak_to_strong/math/ours/260816-math-rcd-opdgrad-lp0p5-lm0to0p5-s30-qwen3-8b-t4b-step75-tk10-b64-mb64-dp4/global_step_60/actor/.async_checkpoint_ready_world_size_4_rank_3.jsonConfiguration182 B —
experiments/weak_to_strong/math/ours/260816-math-rcd-opdgrad-lp0p5-lm0to0p5-s30-qwen3-8b-t4b-step75-tk10-b64-mb64-dp4/global_step_60/actor/.async_checkpoint_started_world_size_4_rank_0.jsonConfiguration61 B —
experiments/weak_to_strong/math/ours/260816-math-rcd-opdgrad-lp0p5-lm0to0p5-s30-qwen3-8b-t4b-step75-tk10-b64-mb64-dp4/global_step_60/actor/.async_checkpoint_started_world_size_4_rank_1.jsonConfiguration61 B —
experiments/weak_to_strong/math/ours/260816-math-rcd-opdgrad-lp0p5-lm0to0p5-s30-qwen3-8b-t4b-step75-tk10-b64-mb64-dp4/global_step_60/actor/.async_checkpoint_started_world_size_4_rank_2.jsonConfiguration61 B —
experiments/weak_to_strong/math/ours/260816-math-rcd-opdgrad-lp0p5-lm0to0p5-s30-qwen3-8b-t4b-step75-tk10-b64-mb64-dp4/global_step_60/actor/.async_checkpoint_started_world_size_4_rank_3.jsonConfiguration61 B —
experiments/weak_to_strong/math/ours/260816-math-rcd-opdgrad-lp0p5-lm0to0p5-s30-qwen3-8b-t4b-step75-tk10-b64-mb64-dp4/global_step_60/actor/.checkpoint_complete.jsonConfiguration50 B —
experiments/weak_to_strong/math/ours/260816-math-rcd-opdgrad-lp0p5-lm0to0p5-s30-qwen3-8b-t4b-step75-tk10-b64-mb64-dp4/global_step_60/actor/.worker_sidecars_ready_world_size_4_rank_0.jsonConfiguration83 B —
experiments/weak_to_strong/math/ours/260816-math-rcd-opdgrad-lp0p5-lm0to0p5-s30-qwen3-8b-t4b-step75-tk10-b64-mb64-dp4/global_step_60/actor/.worker_sidecars_ready_world_size_4_rank_1.jsonConfiguration83 B —
experiments/weak_to_strong/math/ours/260816-math-rcd-opdgrad-lp0p5-lm0to0p5-s30-qwen3-8b-t4b-step75-tk10-b64-mb64-dp4/global_step_60/actor/.worker_sidecars_ready_world_size_4_rank_2.jsonConfiguration83 B —
experiments/weak_to_strong/math/ours/260816-math-rcd-opdgrad-lp0p5-lm0to0p5-s30-qwen3-8b-t4b-step75-tk10-b64-mb64-dp4/global_step_60/actor/.worker_sidecars_ready_world_size_4_rank_3.jsonConfiguration83 B —
experiments/weak_to_strong/math/ours/260816-math-rcd-opdgrad-lp0p5-lm0to0p5-s30-qwen3-8b-t4b-step75-tk10-b64-mb64-dp4/global_step_60/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/math/ours/260816-math-rcd-opdgrad-lp0p5-lm0to0p5-s30-qwen3-8b-t4b-step75-tk10-b64-mb64-dp4/global_step_60/actor/huggingface/config.jsonConfiguration1.6 KB —
experiments/weak_to_strong/math/ours/260816-math-rcd-opdgrad-lp0p5-lm0to0p5-s30-qwen3-8b-t4b-step75-tk10-b64-mb64-dp4/global_step_60/actor/huggingface/generation_config.jsonConfiguration214 B —
experiments/weak_to_strong/math/ours/260816-math-rcd-opdgrad-lp0p5-lm0to0p5-s30-qwen3-8b-t4b-step75-tk10-b64-mb64-dp4/global_step_90/actor/.async_checkpoint_ready_world_size_4_rank_0.jsonConfiguration369 B —
experiments/weak_to_strong/math/ours/260816-math-rcd-opdgrad-lp0p5-lm0to0p5-s30-qwen3-8b-t4b-step75-tk10-b64-mb64-dp4/global_step_90/actor/.async_checkpoint_ready_world_size_4_rank_1.jsonConfiguration182 B —
experiments/weak_to_strong/math/ours/260816-math-rcd-opdgrad-lp0p5-lm0to0p5-s30-qwen3-8b-t4b-step75-tk10-b64-mb64-dp4/global_step_90/actor/.async_checkpoint_ready_world_size_4_rank_2.jsonConfiguration182 B —
experiments/weak_to_strong/math/ours/260816-math-rcd-opdgrad-lp0p5-lm0to0p5-s30-qwen3-8b-t4b-step75-tk10-b64-mb64-dp4/global_step_90/actor/.async_checkpoint_ready_world_size_4_rank_3.jsonConfiguration182 B —
experiments/weak_to_strong/math/ours/260816-math-rcd-opdgrad-lp0p5-lm0to0p5-s30-qwen3-8b-t4b-step75-tk10-b64-mb64-dp4/global_step_90/actor/.async_checkpoint_started_world_size_4_rank_0.jsonConfiguration61 B —
experiments/weak_to_strong/math/ours/260816-math-rcd-opdgrad-lp0p5-lm0to0p5-s30-qwen3-8b-t4b-step75-tk10-b64-mb64-dp4/global_step_90/actor/.async_checkpoint_started_world_size_4_rank_1.jsonConfiguration61 B —
experiments/weak_to_strong/math/ours/260816-math-rcd-opdgrad-lp0p5-lm0to0p5-s30-qwen3-8b-t4b-step75-tk10-b64-mb64-dp4/global_step_90/actor/.async_checkpoint_started_world_size_4_rank_2.jsonConfiguration61 B —
experiments/weak_to_strong/math/ours/260816-math-rcd-opdgrad-lp0p5-lm0to0p5-s30-qwen3-8b-t4b-step75-tk10-b64-mb64-dp4/global_step_90/actor/.async_checkpoint_started_world_size_4_rank_3.jsonConfiguration61 B —
experiments/weak_to_strong/math/ours/260816-math-rcd-opdgrad-lp0p5-lm0to0p5-s30-qwen3-8b-t4b-step75-tk10-b64-mb64-dp4/global_step_90/actor/.checkpoint_complete.jsonConfiguration50 B —
experiments/weak_to_strong/math/ours/260816-math-rcd-opdgrad-lp0p5-lm0to0p5-s30-qwen3-8b-t4b-step75-tk10-b64-mb64-dp4/global_step_90/actor/.worker_sidecars_ready_world_size_4_rank_0.jsonConfiguration83 B —
experiments/weak_to_strong/math/ours/260816-math-rcd-opdgrad-lp0p5-lm0to0p5-s30-qwen3-8b-t4b-step75-tk10-b64-mb64-dp4/global_step_90/actor/.worker_sidecars_ready_world_size_4_rank_1.jsonConfiguration83 B —
experiments/weak_to_strong/math/ours/260816-math-rcd-opdgrad-lp0p5-lm0to0p5-s30-qwen3-8b-t4b-step75-tk10-b64-mb64-dp4/global_step_90/actor/.worker_sidecars_ready_world_size_4_rank_2.jsonConfiguration83 B —
experiments/weak_to_strong/math/ours/260816-math-rcd-opdgrad-lp0p5-lm0to0p5-s30-qwen3-8b-t4b-step75-tk10-b64-mb64-dp4/global_step_90/actor/.worker_sidecars_ready_world_size_4_rank_3.jsonConfiguration83 B —
experiments/weak_to_strong/math/ours/260816-math-rcd-opdgrad-lp0p5-lm0to0p5-s30-qwen3-8b-t4b-step75-tk10-b64-mb64-dp4/global_step_90/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/math/ours/260816-math-rcd-opdgrad-lp0p5-lm0to0p5-s30-qwen3-8b-t4b-step75-tk10-b64-mb64-dp4/global_step_90/actor/huggingface/config.jsonConfiguration1.6 KB —
experiments/weak_to_strong/math/ours/260816-math-rcd-opdgrad-lp0p5-lm0to0p5-s30-qwen3-8b-t4b-step75-tk10-b64-mb64-dp4/global_step_90/actor/huggingface/generation_config.jsonConfiguration214 B —
experiments/weak_to_strong/math/ours/260816-math-rcd-opdgrad-lp0p5-lm0to0p5-s30-qwen3-8b-t4b-step75-tk10-b64-mb64-dp4/latest_checkpoint.jsonConfiguration370 B —
experiments/weak_to_strong/reasoning/binary_matrix/baseline/260727-grpo-binary_matrix-q3-8b-base-s150-tr8k-va8k-seed1234-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp4/best_validation_checkpoint.jsonConfiguration226 B —
experiments/weak_to_strong/reasoning/binary_matrix/baseline/260727-grpo-binary_matrix-q3-8b-base-s150-tr8k-va8k-seed1234-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp4/global_step_120/actor/.async_checkpoint_ready_world_size_4_rank_0.jsonConfiguration370 B —
experiments/weak_to_strong/reasoning/binary_matrix/baseline/260727-grpo-binary_matrix-q3-8b-base-s150-tr8k-va8k-seed1234-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp4/global_step_120/actor/.async_checkpoint_ready_world_size_4_rank_1.jsonConfiguration183 B —
experiments/weak_to_strong/reasoning/binary_matrix/baseline/260727-grpo-binary_matrix-q3-8b-base-s150-tr8k-va8k-seed1234-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp4/global_step_120/actor/.async_checkpoint_ready_world_size_4_rank_2.jsonConfiguration183 B —
experiments/weak_to_strong/reasoning/binary_matrix/baseline/260727-grpo-binary_matrix-q3-8b-base-s150-tr8k-va8k-seed1234-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp4/global_step_120/actor/.async_checkpoint_ready_world_size_4_rank_3.jsonConfiguration183 B —
experiments/weak_to_strong/reasoning/binary_matrix/baseline/260727-grpo-binary_matrix-q3-8b-base-s150-tr8k-va8k-seed1234-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp4/global_step_120/actor/.async_checkpoint_started_world_size_4_rank_0.jsonConfiguration62 B —
experiments/weak_to_strong/reasoning/binary_matrix/baseline/260727-grpo-binary_matrix-q3-8b-base-s150-tr8k-va8k-seed1234-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp4/global_step_120/actor/.async_checkpoint_started_world_size_4_rank_1.jsonConfiguration62 B —
experiments/weak_to_strong/reasoning/binary_matrix/baseline/260727-grpo-binary_matrix-q3-8b-base-s150-tr8k-va8k-seed1234-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp4/global_step_120/actor/.async_checkpoint_started_world_size_4_rank_2.jsonConfiguration62 B —
experiments/weak_to_strong/reasoning/binary_matrix/baseline/260727-grpo-binary_matrix-q3-8b-base-s150-tr8k-va8k-seed1234-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp4/global_step_120/actor/.async_checkpoint_started_world_size_4_rank_3.jsonConfiguration62 B —
experiments/weak_to_strong/reasoning/binary_matrix/baseline/260727-grpo-binary_matrix-q3-8b-base-s150-tr8k-va8k-seed1234-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp4/global_step_120/actor/.checkpoint_complete.jsonConfiguration51 B —
experiments/weak_to_strong/reasoning/binary_matrix/baseline/260727-grpo-binary_matrix-q3-8b-base-s150-tr8k-va8k-seed1234-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp4/global_step_120/actor/.worker_sidecars_ready_world_size_4_rank_0.jsonConfiguration84 B —
experiments/weak_to_strong/reasoning/binary_matrix/baseline/260727-grpo-binary_matrix-q3-8b-base-s150-tr8k-va8k-seed1234-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp4/global_step_120/actor/.worker_sidecars_ready_world_size_4_rank_1.jsonConfiguration84 B —
experiments/weak_to_strong/reasoning/binary_matrix/baseline/260727-grpo-binary_matrix-q3-8b-base-s150-tr8k-va8k-seed1234-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp4/global_step_120/actor/.worker_sidecars_ready_world_size_4_rank_2.jsonConfiguration84 B —
experiments/weak_to_strong/reasoning/binary_matrix/baseline/260727-grpo-binary_matrix-q3-8b-base-s150-tr8k-va8k-seed1234-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp4/global_step_120/actor/.worker_sidecars_ready_world_size_4_rank_3.jsonConfiguration84 B —
experiments/weak_to_strong/reasoning/binary_matrix/baseline/260727-grpo-binary_matrix-q3-8b-base-s150-tr8k-va8k-seed1234-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp4/global_step_120/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/reasoning/binary_matrix/baseline/260727-grpo-binary_matrix-q3-8b-base-s150-tr8k-va8k-seed1234-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp4/global_step_120/actor/huggingface/config.jsonConfiguration1.6 KB —
experiments/weak_to_strong/reasoning/binary_matrix/baseline/260727-grpo-binary_matrix-q3-8b-base-s150-tr8k-va8k-seed1234-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp4/global_step_120/actor/huggingface/generation_config.jsonConfiguration139 B —
experiments/weak_to_strong/reasoning/binary_matrix/baseline/260727-grpo-binary_matrix-q3-8b-base-s150-tr8k-va8k-seed1234-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp4/global_step_150/actor/.async_checkpoint_ready_world_size_4_rank_0.jsonConfiguration370 B —
experiments/weak_to_strong/reasoning/binary_matrix/baseline/260727-grpo-binary_matrix-q3-8b-base-s150-tr8k-va8k-seed1234-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp4/global_step_150/actor/.async_checkpoint_ready_world_size_4_rank_1.jsonConfiguration183 B —
experiments/weak_to_strong/reasoning/binary_matrix/baseline/260727-grpo-binary_matrix-q3-8b-base-s150-tr8k-va8k-seed1234-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp4/global_step_150/actor/.async_checkpoint_ready_world_size_4_rank_2.jsonConfiguration183 B —
experiments/weak_to_strong/reasoning/binary_matrix/baseline/260727-grpo-binary_matrix-q3-8b-base-s150-tr8k-va8k-seed1234-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp4/global_step_150/actor/.async_checkpoint_ready_world_size_4_rank_3.jsonConfiguration183 B —
experiments/weak_to_strong/reasoning/binary_matrix/baseline/260727-grpo-binary_matrix-q3-8b-base-s150-tr8k-va8k-seed1234-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp4/global_step_150/actor/.async_checkpoint_started_world_size_4_rank_0.jsonConfiguration62 B —
experiments/weak_to_strong/reasoning/binary_matrix/baseline/260727-grpo-binary_matrix-q3-8b-base-s150-tr8k-va8k-seed1234-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp4/global_step_150/actor/.async_checkpoint_started_world_size_4_rank_1.jsonConfiguration62 B —
experiments/weak_to_strong/reasoning/binary_matrix/baseline/260727-grpo-binary_matrix-q3-8b-base-s150-tr8k-va8k-seed1234-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp4/global_step_150/actor/.async_checkpoint_started_world_size_4_rank_2.jsonConfiguration62 B —
experiments/weak_to_strong/reasoning/binary_matrix/baseline/260727-grpo-binary_matrix-q3-8b-base-s150-tr8k-va8k-seed1234-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp4/global_step_150/actor/.async_checkpoint_started_world_size_4_rank_3.jsonConfiguration62 B —
experiments/weak_to_strong/reasoning/binary_matrix/baseline/260727-grpo-binary_matrix-q3-8b-base-s150-tr8k-va8k-seed1234-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp4/global_step_150/actor/.checkpoint_complete.jsonConfiguration51 B —
experiments/weak_to_strong/reasoning/binary_matrix/baseline/260727-grpo-binary_matrix-q3-8b-base-s150-tr8k-va8k-seed1234-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp4/global_step_150/actor/.worker_sidecars_ready_world_size_4_rank_0.jsonConfiguration84 B —
experiments/weak_to_strong/reasoning/binary_matrix/baseline/260727-grpo-binary_matrix-q3-8b-base-s150-tr8k-va8k-seed1234-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp4/global_step_150/actor/.worker_sidecars_ready_world_size_4_rank_1.jsonConfiguration84 B —
experiments/weak_to_strong/reasoning/binary_matrix/baseline/260727-grpo-binary_matrix-q3-8b-base-s150-tr8k-va8k-seed1234-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp4/global_step_150/actor/.worker_sidecars_ready_world_size_4_rank_2.jsonConfiguration84 B —
experiments/weak_to_strong/reasoning/binary_matrix/baseline/260727-grpo-binary_matrix-q3-8b-base-s150-tr8k-va8k-seed1234-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp4/global_step_150/actor/.worker_sidecars_ready_world_size_4_rank_3.jsonConfiguration84 B —
experiments/weak_to_strong/reasoning/binary_matrix/baseline/260727-grpo-binary_matrix-q3-8b-base-s150-tr8k-va8k-seed1234-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp4/global_step_150/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/reasoning/binary_matrix/baseline/260727-grpo-binary_matrix-q3-8b-base-s150-tr8k-va8k-seed1234-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp4/global_step_150/actor/huggingface/config.jsonConfiguration1.6 KB —
experiments/weak_to_strong/reasoning/binary_matrix/baseline/260727-grpo-binary_matrix-q3-8b-base-s150-tr8k-va8k-seed1234-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp4/global_step_150/actor/huggingface/generation_config.jsonConfiguration139 B —
experiments/weak_to_strong/reasoning/binary_matrix/baseline/260727-grpo-binary_matrix-q3-8b-base-s150-tr8k-va8k-seed1234-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp4/global_step_90/actor/.async_checkpoint_ready_world_size_4_rank_0.jsonConfiguration369 B —
experiments/weak_to_strong/reasoning/binary_matrix/baseline/260727-grpo-binary_matrix-q3-8b-base-s150-tr8k-va8k-seed1234-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp4/global_step_90/actor/.async_checkpoint_ready_world_size_4_rank_1.jsonConfiguration182 B —
experiments/weak_to_strong/reasoning/binary_matrix/baseline/260727-grpo-binary_matrix-q3-8b-base-s150-tr8k-va8k-seed1234-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp4/global_step_90/actor/.async_checkpoint_ready_world_size_4_rank_2.jsonConfiguration182 B —
experiments/weak_to_strong/reasoning/binary_matrix/baseline/260727-grpo-binary_matrix-q3-8b-base-s150-tr8k-va8k-seed1234-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp4/global_step_90/actor/.async_checkpoint_ready_world_size_4_rank_3.jsonConfiguration182 B —
experiments/weak_to_strong/reasoning/binary_matrix/baseline/260727-grpo-binary_matrix-q3-8b-base-s150-tr8k-va8k-seed1234-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp4/global_step_90/actor/.async_checkpoint_started_world_size_4_rank_0.jsonConfiguration61 B —
experiments/weak_to_strong/reasoning/binary_matrix/baseline/260727-grpo-binary_matrix-q3-8b-base-s150-tr8k-va8k-seed1234-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp4/global_step_90/actor/.async_checkpoint_started_world_size_4_rank_1.jsonConfiguration61 B —
experiments/weak_to_strong/reasoning/binary_matrix/baseline/260727-grpo-binary_matrix-q3-8b-base-s150-tr8k-va8k-seed1234-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp4/global_step_90/actor/.async_checkpoint_started_world_size_4_rank_2.jsonConfiguration61 B —
experiments/weak_to_strong/reasoning/binary_matrix/baseline/260727-grpo-binary_matrix-q3-8b-base-s150-tr8k-va8k-seed1234-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp4/global_step_90/actor/.async_checkpoint_started_world_size_4_rank_3.jsonConfiguration61 B —
experiments/weak_to_strong/reasoning/binary_matrix/baseline/260727-grpo-binary_matrix-q3-8b-base-s150-tr8k-va8k-seed1234-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp4/global_step_90/actor/.checkpoint_complete.jsonConfiguration50 B —
experiments/weak_to_strong/reasoning/binary_matrix/baseline/260727-grpo-binary_matrix-q3-8b-base-s150-tr8k-va8k-seed1234-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp4/global_step_90/actor/.worker_sidecars_ready_world_size_4_rank_0.jsonConfiguration83 B —
experiments/weak_to_strong/reasoning/binary_matrix/baseline/260727-grpo-binary_matrix-q3-8b-base-s150-tr8k-va8k-seed1234-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp4/global_step_90/actor/.worker_sidecars_ready_world_size_4_rank_1.jsonConfiguration83 B —
experiments/weak_to_strong/reasoning/binary_matrix/baseline/260727-grpo-binary_matrix-q3-8b-base-s150-tr8k-va8k-seed1234-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp4/global_step_90/actor/.worker_sidecars_ready_world_size_4_rank_2.jsonConfiguration83 B —
experiments/weak_to_strong/reasoning/binary_matrix/baseline/260727-grpo-binary_matrix-q3-8b-base-s150-tr8k-va8k-seed1234-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp4/global_step_90/actor/.worker_sidecars_ready_world_size_4_rank_3.jsonConfiguration83 B —
experiments/weak_to_strong/reasoning/binary_matrix/baseline/260727-grpo-binary_matrix-q3-8b-base-s150-tr8k-va8k-seed1234-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp4/global_step_90/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/reasoning/binary_matrix/baseline/260727-grpo-binary_matrix-q3-8b-base-s150-tr8k-va8k-seed1234-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp4/global_step_90/actor/huggingface/config.jsonConfiguration1.6 KB —
experiments/weak_to_strong/reasoning/binary_matrix/baseline/260727-grpo-binary_matrix-q3-8b-base-s150-tr8k-va8k-seed1234-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp4/global_step_90/actor/huggingface/generation_config.jsonConfiguration139 B —
experiments/weak_to_strong/reasoning/binary_matrix/baseline/260727-grpo-binary_matrix-q3-8b-base-s150-tr8k-va8k-seed1234-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp4/latest_checkpoint.jsonConfiguration431 B —
experiments/weak_to_strong/reasoning/binary_matrix/distill_baseline/260731-kdrl-b5e3-d6p6667e5-min0-sched75-binary_matrix-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-finalopt-static10k-tistoken-clip0p2-0p28-seed1234-b64-mb32-dp2/best_validation_checkpoint.jsonConfiguration226 B —
experiments/weak_to_strong/reasoning/binary_matrix/distill_baseline/260731-kdrl-b5e3-d6p6667e5-min0-sched75-binary_matrix-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-finalopt-static10k-tistoken-clip0p2-0p28-seed1234-b64-mb32-dp2/global_step_120/actor/.async_checkpoint_ready_world_size_2_rank_0.jsonConfiguration370 B —
experiments/weak_to_strong/reasoning/binary_matrix/distill_baseline/260731-kdrl-b5e3-d6p6667e5-min0-sched75-binary_matrix-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-finalopt-static10k-tistoken-clip0p2-0p28-seed1234-b64-mb32-dp2/global_step_120/actor/.async_checkpoint_ready_world_size_2_rank_1.jsonConfiguration183 B —
experiments/weak_to_strong/reasoning/binary_matrix/distill_baseline/260731-kdrl-b5e3-d6p6667e5-min0-sched75-binary_matrix-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-finalopt-static10k-tistoken-clip0p2-0p28-seed1234-b64-mb32-dp2/global_step_120/actor/.async_checkpoint_started_world_size_2_rank_0.jsonConfiguration62 B —
experiments/weak_to_strong/reasoning/binary_matrix/distill_baseline/260731-kdrl-b5e3-d6p6667e5-min0-sched75-binary_matrix-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-finalopt-static10k-tistoken-clip0p2-0p28-seed1234-b64-mb32-dp2/global_step_120/actor/.async_checkpoint_started_world_size_2_rank_1.jsonConfiguration62 B —
experiments/weak_to_strong/reasoning/binary_matrix/distill_baseline/260731-kdrl-b5e3-d6p6667e5-min0-sched75-binary_matrix-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-finalopt-static10k-tistoken-clip0p2-0p28-seed1234-b64-mb32-dp2/global_step_120/actor/.checkpoint_complete.jsonConfiguration51 B —
experiments/weak_to_strong/reasoning/binary_matrix/distill_baseline/260731-kdrl-b5e3-d6p6667e5-min0-sched75-binary_matrix-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-finalopt-static10k-tistoken-clip0p2-0p28-seed1234-b64-mb32-dp2/global_step_120/actor/.worker_sidecars_ready_world_size_2_rank_0.jsonConfiguration84 B —
experiments/weak_to_strong/reasoning/binary_matrix/distill_baseline/260731-kdrl-b5e3-d6p6667e5-min0-sched75-binary_matrix-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-finalopt-static10k-tistoken-clip0p2-0p28-seed1234-b64-mb32-dp2/global_step_120/actor/.worker_sidecars_ready_world_size_2_rank_1.jsonConfiguration84 B —
experiments/weak_to_strong/reasoning/binary_matrix/distill_baseline/260731-kdrl-b5e3-d6p6667e5-min0-sched75-binary_matrix-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-finalopt-static10k-tistoken-clip0p2-0p28-seed1234-b64-mb32-dp2/global_step_120/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/reasoning/binary_matrix/distill_baseline/260731-kdrl-b5e3-d6p6667e5-min0-sched75-binary_matrix-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-finalopt-static10k-tistoken-clip0p2-0p28-seed1234-b64-mb32-dp2/global_step_120/actor/huggingface/config.jsonConfiguration1.6 KB —
experiments/weak_to_strong/reasoning/binary_matrix/distill_baseline/260731-kdrl-b5e3-d6p6667e5-min0-sched75-binary_matrix-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-finalopt-static10k-tistoken-clip0p2-0p28-seed1234-b64-mb32-dp2/global_step_120/actor/huggingface/generation_config.jsonConfiguration139 B —
experiments/weak_to_strong/reasoning/binary_matrix/distill_baseline/260731-kdrl-b5e3-d6p6667e5-min0-sched75-binary_matrix-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-finalopt-static10k-tistoken-clip0p2-0p28-seed1234-b64-mb32-dp2/global_step_135/actor/.async_checkpoint_ready_world_size_2_rank_0.jsonConfiguration370 B —
experiments/weak_to_strong/reasoning/binary_matrix/distill_baseline/260731-kdrl-b5e3-d6p6667e5-min0-sched75-binary_matrix-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-finalopt-static10k-tistoken-clip0p2-0p28-seed1234-b64-mb32-dp2/global_step_135/actor/.async_checkpoint_ready_world_size_2_rank_1.jsonConfiguration183 B —
experiments/weak_to_strong/reasoning/binary_matrix/distill_baseline/260731-kdrl-b5e3-d6p6667e5-min0-sched75-binary_matrix-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-finalopt-static10k-tistoken-clip0p2-0p28-seed1234-b64-mb32-dp2/global_step_135/actor/.async_checkpoint_started_world_size_2_rank_0.jsonConfiguration62 B —
experiments/weak_to_strong/reasoning/binary_matrix/distill_baseline/260731-kdrl-b5e3-d6p6667e5-min0-sched75-binary_matrix-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-finalopt-static10k-tistoken-clip0p2-0p28-seed1234-b64-mb32-dp2/global_step_135/actor/.async_checkpoint_started_world_size_2_rank_1.jsonConfiguration62 B —
experiments/weak_to_strong/reasoning/binary_matrix/distill_baseline/260731-kdrl-b5e3-d6p6667e5-min0-sched75-binary_matrix-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-finalopt-static10k-tistoken-clip0p2-0p28-seed1234-b64-mb32-dp2/global_step_135/actor/.checkpoint_complete.jsonConfiguration51 B —
experiments/weak_to_strong/reasoning/binary_matrix/distill_baseline/260731-kdrl-b5e3-d6p6667e5-min0-sched75-binary_matrix-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-finalopt-static10k-tistoken-clip0p2-0p28-seed1234-b64-mb32-dp2/global_step_135/actor/.worker_sidecars_ready_world_size_2_rank_0.jsonConfiguration84 B —
experiments/weak_to_strong/reasoning/binary_matrix/distill_baseline/260731-kdrl-b5e3-d6p6667e5-min0-sched75-binary_matrix-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-finalopt-static10k-tistoken-clip0p2-0p28-seed1234-b64-mb32-dp2/global_step_135/actor/.worker_sidecars_ready_world_size_2_rank_1.jsonConfiguration84 B —
experiments/weak_to_strong/reasoning/binary_matrix/distill_baseline/260731-kdrl-b5e3-d6p6667e5-min0-sched75-binary_matrix-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-finalopt-static10k-tistoken-clip0p2-0p28-seed1234-b64-mb32-dp2/global_step_135/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/reasoning/binary_matrix/distill_baseline/260731-kdrl-b5e3-d6p6667e5-min0-sched75-binary_matrix-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-finalopt-static10k-tistoken-clip0p2-0p28-seed1234-b64-mb32-dp2/global_step_135/actor/huggingface/config.jsonConfiguration1.6 KB —
experiments/weak_to_strong/reasoning/binary_matrix/distill_baseline/260731-kdrl-b5e3-d6p6667e5-min0-sched75-binary_matrix-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-finalopt-static10k-tistoken-clip0p2-0p28-seed1234-b64-mb32-dp2/global_step_135/actor/huggingface/generation_config.jsonConfiguration139 B —
experiments/weak_to_strong/reasoning/binary_matrix/distill_baseline/260731-kdrl-b5e3-d6p6667e5-min0-sched75-binary_matrix-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-finalopt-static10k-tistoken-clip0p2-0p28-seed1234-b64-mb32-dp2/global_step_150/actor/.async_checkpoint_ready_world_size_2_rank_0.jsonConfiguration370 B —
experiments/weak_to_strong/reasoning/binary_matrix/distill_baseline/260731-kdrl-b5e3-d6p6667e5-min0-sched75-binary_matrix-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-finalopt-static10k-tistoken-clip0p2-0p28-seed1234-b64-mb32-dp2/global_step_150/actor/.async_checkpoint_ready_world_size_2_rank_1.jsonConfiguration183 B —
experiments/weak_to_strong/reasoning/binary_matrix/distill_baseline/260731-kdrl-b5e3-d6p6667e5-min0-sched75-binary_matrix-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-finalopt-static10k-tistoken-clip0p2-0p28-seed1234-b64-mb32-dp2/global_step_150/actor/.async_checkpoint_started_world_size_2_rank_0.jsonConfiguration62 B —
experiments/weak_to_strong/reasoning/binary_matrix/distill_baseline/260731-kdrl-b5e3-d6p6667e5-min0-sched75-binary_matrix-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-finalopt-static10k-tistoken-clip0p2-0p28-seed1234-b64-mb32-dp2/global_step_150/actor/.async_checkpoint_started_world_size_2_rank_1.jsonConfiguration62 B —
experiments/weak_to_strong/reasoning/binary_matrix/distill_baseline/260731-kdrl-b5e3-d6p6667e5-min0-sched75-binary_matrix-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-finalopt-static10k-tistoken-clip0p2-0p28-seed1234-b64-mb32-dp2/global_step_150/actor/.checkpoint_complete.jsonConfiguration51 B —
experiments/weak_to_strong/reasoning/binary_matrix/distill_baseline/260731-kdrl-b5e3-d6p6667e5-min0-sched75-binary_matrix-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-finalopt-static10k-tistoken-clip0p2-0p28-seed1234-b64-mb32-dp2/global_step_150/actor/.worker_sidecars_ready_world_size_2_rank_0.jsonConfiguration84 B —
experiments/weak_to_strong/reasoning/binary_matrix/distill_baseline/260731-kdrl-b5e3-d6p6667e5-min0-sched75-binary_matrix-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-finalopt-static10k-tistoken-clip0p2-0p28-seed1234-b64-mb32-dp2/global_step_150/actor/.worker_sidecars_ready_world_size_2_rank_1.jsonConfiguration84 B —
experiments/weak_to_strong/reasoning/binary_matrix/distill_baseline/260731-kdrl-b5e3-d6p6667e5-min0-sched75-binary_matrix-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-finalopt-static10k-tistoken-clip0p2-0p28-seed1234-b64-mb32-dp2/global_step_150/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/reasoning/binary_matrix/distill_baseline/260731-kdrl-b5e3-d6p6667e5-min0-sched75-binary_matrix-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-finalopt-static10k-tistoken-clip0p2-0p28-seed1234-b64-mb32-dp2/global_step_150/actor/huggingface/config.jsonConfiguration1.6 KB —
experiments/weak_to_strong/reasoning/binary_matrix/distill_baseline/260731-kdrl-b5e3-d6p6667e5-min0-sched75-binary_matrix-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-finalopt-static10k-tistoken-clip0p2-0p28-seed1234-b64-mb32-dp2/global_step_150/actor/huggingface/generation_config.jsonConfiguration139 B —
experiments/weak_to_strong/reasoning/binary_matrix/distill_baseline/260731-kdrl-b5e3-d6p6667e5-min0-sched75-binary_matrix-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-finalopt-static10k-tistoken-clip0p2-0p28-seed1234-b64-mb32-dp2/latest_checkpoint.jsonConfiguration381 B —
experiments/weak_to_strong/reasoning/binary_matrix/ours/260728-rcd-binary_matrix-q3-8b-base-t4b-s105-lp0p5fixed-lm0to0p5-s75-tr8k-save30-best-finalopt-tistoken-seed1234-b64-mb32-dp4/best_validation_checkpoint.jsonConfiguration226 B —
experiments/weak_to_strong/reasoning/binary_matrix/ours/260728-rcd-binary_matrix-q3-8b-base-t4b-s105-lp0p5fixed-lm0to0p5-s75-tr8k-save30-best-finalopt-tistoken-seed1234-b64-mb32-dp4/global_step_120/actor/.async_checkpoint_ready_world_size_4_rank_0.jsonConfiguration370 B —
experiments/weak_to_strong/reasoning/binary_matrix/ours/260728-rcd-binary_matrix-q3-8b-base-t4b-s105-lp0p5fixed-lm0to0p5-s75-tr8k-save30-best-finalopt-tistoken-seed1234-b64-mb32-dp4/global_step_120/actor/.async_checkpoint_ready_world_size_4_rank_1.jsonConfiguration183 B —
experiments/weak_to_strong/reasoning/binary_matrix/ours/260728-rcd-binary_matrix-q3-8b-base-t4b-s105-lp0p5fixed-lm0to0p5-s75-tr8k-save30-best-finalopt-tistoken-seed1234-b64-mb32-dp4/global_step_120/actor/.async_checkpoint_ready_world_size_4_rank_2.jsonConfiguration183 B —
experiments/weak_to_strong/reasoning/binary_matrix/ours/260728-rcd-binary_matrix-q3-8b-base-t4b-s105-lp0p5fixed-lm0to0p5-s75-tr8k-save30-best-finalopt-tistoken-seed1234-b64-mb32-dp4/global_step_120/actor/.async_checkpoint_ready_world_size_4_rank_3.jsonConfiguration183 B —
experiments/weak_to_strong/reasoning/binary_matrix/ours/260728-rcd-binary_matrix-q3-8b-base-t4b-s105-lp0p5fixed-lm0to0p5-s75-tr8k-save30-best-finalopt-tistoken-seed1234-b64-mb32-dp4/global_step_120/actor/.async_checkpoint_started_world_size_4_rank_0.jsonConfiguration62 B —
experiments/weak_to_strong/reasoning/binary_matrix/ours/260728-rcd-binary_matrix-q3-8b-base-t4b-s105-lp0p5fixed-lm0to0p5-s75-tr8k-save30-best-finalopt-tistoken-seed1234-b64-mb32-dp4/global_step_120/actor/.async_checkpoint_started_world_size_4_rank_1.jsonConfiguration62 B —
experiments/weak_to_strong/reasoning/binary_matrix/ours/260728-rcd-binary_matrix-q3-8b-base-t4b-s105-lp0p5fixed-lm0to0p5-s75-tr8k-save30-best-finalopt-tistoken-seed1234-b64-mb32-dp4/global_step_120/actor/.async_checkpoint_started_world_size_4_rank_2.jsonConfiguration62 B —
experiments/weak_to_strong/reasoning/binary_matrix/ours/260728-rcd-binary_matrix-q3-8b-base-t4b-s105-lp0p5fixed-lm0to0p5-s75-tr8k-save30-best-finalopt-tistoken-seed1234-b64-mb32-dp4/global_step_120/actor/.async_checkpoint_started_world_size_4_rank_3.jsonConfiguration62 B —
experiments/weak_to_strong/reasoning/binary_matrix/ours/260728-rcd-binary_matrix-q3-8b-base-t4b-s105-lp0p5fixed-lm0to0p5-s75-tr8k-save30-best-finalopt-tistoken-seed1234-b64-mb32-dp4/global_step_120/actor/.checkpoint_complete.jsonConfiguration51 B —
experiments/weak_to_strong/reasoning/binary_matrix/ours/260728-rcd-binary_matrix-q3-8b-base-t4b-s105-lp0p5fixed-lm0to0p5-s75-tr8k-save30-best-finalopt-tistoken-seed1234-b64-mb32-dp4/global_step_120/actor/.worker_sidecars_ready_world_size_4_rank_0.jsonConfiguration84 B —
experiments/weak_to_strong/reasoning/binary_matrix/ours/260728-rcd-binary_matrix-q3-8b-base-t4b-s105-lp0p5fixed-lm0to0p5-s75-tr8k-save30-best-finalopt-tistoken-seed1234-b64-mb32-dp4/global_step_120/actor/.worker_sidecars_ready_world_size_4_rank_1.jsonConfiguration84 B —
experiments/weak_to_strong/reasoning/binary_matrix/ours/260728-rcd-binary_matrix-q3-8b-base-t4b-s105-lp0p5fixed-lm0to0p5-s75-tr8k-save30-best-finalopt-tistoken-seed1234-b64-mb32-dp4/global_step_120/actor/.worker_sidecars_ready_world_size_4_rank_2.jsonConfiguration84 B —
experiments/weak_to_strong/reasoning/binary_matrix/ours/260728-rcd-binary_matrix-q3-8b-base-t4b-s105-lp0p5fixed-lm0to0p5-s75-tr8k-save30-best-finalopt-tistoken-seed1234-b64-mb32-dp4/global_step_120/actor/.worker_sidecars_ready_world_size_4_rank_3.jsonConfiguration84 B —
experiments/weak_to_strong/reasoning/binary_matrix/ours/260728-rcd-binary_matrix-q3-8b-base-t4b-s105-lp0p5fixed-lm0to0p5-s75-tr8k-save30-best-finalopt-tistoken-seed1234-b64-mb32-dp4/global_step_120/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/reasoning/binary_matrix/ours/260728-rcd-binary_matrix-q3-8b-base-t4b-s105-lp0p5fixed-lm0to0p5-s75-tr8k-save30-best-finalopt-tistoken-seed1234-b64-mb32-dp4/global_step_120/actor/huggingface/config.jsonConfiguration1.6 KB —
experiments/weak_to_strong/reasoning/binary_matrix/ours/260728-rcd-binary_matrix-q3-8b-base-t4b-s105-lp0p5fixed-lm0to0p5-s75-tr8k-save30-best-finalopt-tistoken-seed1234-b64-mb32-dp4/global_step_120/actor/huggingface/generation_config.jsonConfiguration139 B —
experiments/weak_to_strong/reasoning/binary_matrix/ours/260728-rcd-binary_matrix-q3-8b-base-t4b-s105-lp0p5fixed-lm0to0p5-s75-tr8k-save30-best-finalopt-tistoken-seed1234-b64-mb32-dp4/global_step_150/actor/.async_checkpoint_ready_world_size_4_rank_0.jsonConfiguration370 B —
experiments/weak_to_strong/reasoning/binary_matrix/ours/260728-rcd-binary_matrix-q3-8b-base-t4b-s105-lp0p5fixed-lm0to0p5-s75-tr8k-save30-best-finalopt-tistoken-seed1234-b64-mb32-dp4/global_step_150/actor/.async_checkpoint_ready_world_size_4_rank_1.jsonConfiguration183 B —
experiments/weak_to_strong/reasoning/binary_matrix/ours/260728-rcd-binary_matrix-q3-8b-base-t4b-s105-lp0p5fixed-lm0to0p5-s75-tr8k-save30-best-finalopt-tistoken-seed1234-b64-mb32-dp4/global_step_150/actor/.async_checkpoint_ready_world_size_4_rank_2.jsonConfiguration183 B —
experiments/weak_to_strong/reasoning/binary_matrix/ours/260728-rcd-binary_matrix-q3-8b-base-t4b-s105-lp0p5fixed-lm0to0p5-s75-tr8k-save30-best-finalopt-tistoken-seed1234-b64-mb32-dp4/global_step_150/actor/.async_checkpoint_ready_world_size_4_rank_3.jsonConfiguration183 B —
experiments/weak_to_strong/reasoning/binary_matrix/ours/260728-rcd-binary_matrix-q3-8b-base-t4b-s105-lp0p5fixed-lm0to0p5-s75-tr8k-save30-best-finalopt-tistoken-seed1234-b64-mb32-dp4/global_step_150/actor/.async_checkpoint_started_world_size_4_rank_0.jsonConfiguration62 B —
experiments/weak_to_strong/reasoning/binary_matrix/ours/260728-rcd-binary_matrix-q3-8b-base-t4b-s105-lp0p5fixed-lm0to0p5-s75-tr8k-save30-best-finalopt-tistoken-seed1234-b64-mb32-dp4/global_step_150/actor/.async_checkpoint_started_world_size_4_rank_1.jsonConfiguration62 B —
experiments/weak_to_strong/reasoning/binary_matrix/ours/260728-rcd-binary_matrix-q3-8b-base-t4b-s105-lp0p5fixed-lm0to0p5-s75-tr8k-save30-best-finalopt-tistoken-seed1234-b64-mb32-dp4/global_step_150/actor/.async_checkpoint_started_world_size_4_rank_2.jsonConfiguration62 B —
experiments/weak_to_strong/reasoning/binary_matrix/ours/260728-rcd-binary_matrix-q3-8b-base-t4b-s105-lp0p5fixed-lm0to0p5-s75-tr8k-save30-best-finalopt-tistoken-seed1234-b64-mb32-dp4/global_step_150/actor/.async_checkpoint_started_world_size_4_rank_3.jsonConfiguration62 B —
experiments/weak_to_strong/reasoning/binary_matrix/ours/260728-rcd-binary_matrix-q3-8b-base-t4b-s105-lp0p5fixed-lm0to0p5-s75-tr8k-save30-best-finalopt-tistoken-seed1234-b64-mb32-dp4/global_step_150/actor/.checkpoint_complete.jsonConfiguration51 B —
experiments/weak_to_strong/reasoning/binary_matrix/ours/260728-rcd-binary_matrix-q3-8b-base-t4b-s105-lp0p5fixed-lm0to0p5-s75-tr8k-save30-best-finalopt-tistoken-seed1234-b64-mb32-dp4/global_step_150/actor/.worker_sidecars_ready_world_size_4_rank_0.jsonConfiguration84 B —
experiments/weak_to_strong/reasoning/binary_matrix/ours/260728-rcd-binary_matrix-q3-8b-base-t4b-s105-lp0p5fixed-lm0to0p5-s75-tr8k-save30-best-finalopt-tistoken-seed1234-b64-mb32-dp4/global_step_150/actor/.worker_sidecars_ready_world_size_4_rank_1.jsonConfiguration84 B —
experiments/weak_to_strong/reasoning/binary_matrix/ours/260728-rcd-binary_matrix-q3-8b-base-t4b-s105-lp0p5fixed-lm0to0p5-s75-tr8k-save30-best-finalopt-tistoken-seed1234-b64-mb32-dp4/global_step_150/actor/.worker_sidecars_ready_world_size_4_rank_2.jsonConfiguration84 B —
experiments/weak_to_strong/reasoning/binary_matrix/ours/260728-rcd-binary_matrix-q3-8b-base-t4b-s105-lp0p5fixed-lm0to0p5-s75-tr8k-save30-best-finalopt-tistoken-seed1234-b64-mb32-dp4/global_step_150/actor/.worker_sidecars_ready_world_size_4_rank_3.jsonConfiguration84 B —
experiments/weak_to_strong/reasoning/binary_matrix/ours/260728-rcd-binary_matrix-q3-8b-base-t4b-s105-lp0p5fixed-lm0to0p5-s75-tr8k-save30-best-finalopt-tistoken-seed1234-b64-mb32-dp4/global_step_150/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/reasoning/binary_matrix/ours/260728-rcd-binary_matrix-q3-8b-base-t4b-s105-lp0p5fixed-lm0to0p5-s75-tr8k-save30-best-finalopt-tistoken-seed1234-b64-mb32-dp4/global_step_150/actor/huggingface/config.jsonConfiguration1.6 KB —
experiments/weak_to_strong/reasoning/binary_matrix/ours/260728-rcd-binary_matrix-q3-8b-base-t4b-s105-lp0p5fixed-lm0to0p5-s75-tr8k-save30-best-finalopt-tistoken-seed1234-b64-mb32-dp4/global_step_150/actor/huggingface/generation_config.jsonConfiguration139 B —
experiments/weak_to_strong/reasoning/binary_matrix/ours/260728-rcd-binary_matrix-q3-8b-base-t4b-s105-lp0p5fixed-lm0to0p5-s75-tr8k-save30-best-finalopt-tistoken-seed1234-b64-mb32-dp4/global_step_90/actor/.async_checkpoint_ready_world_size_4_rank_0.jsonConfiguration369 B —
experiments/weak_to_strong/reasoning/binary_matrix/ours/260728-rcd-binary_matrix-q3-8b-base-t4b-s105-lp0p5fixed-lm0to0p5-s75-tr8k-save30-best-finalopt-tistoken-seed1234-b64-mb32-dp4/global_step_90/actor/.async_checkpoint_ready_world_size_4_rank_1.jsonConfiguration182 B —
experiments/weak_to_strong/reasoning/binary_matrix/ours/260728-rcd-binary_matrix-q3-8b-base-t4b-s105-lp0p5fixed-lm0to0p5-s75-tr8k-save30-best-finalopt-tistoken-seed1234-b64-mb32-dp4/global_step_90/actor/.async_checkpoint_ready_world_size_4_rank_2.jsonConfiguration182 B —
experiments/weak_to_strong/reasoning/binary_matrix/ours/260728-rcd-binary_matrix-q3-8b-base-t4b-s105-lp0p5fixed-lm0to0p5-s75-tr8k-save30-best-finalopt-tistoken-seed1234-b64-mb32-dp4/global_step_90/actor/.async_checkpoint_ready_world_size_4_rank_3.jsonConfiguration182 B —
experiments/weak_to_strong/reasoning/binary_matrix/ours/260728-rcd-binary_matrix-q3-8b-base-t4b-s105-lp0p5fixed-lm0to0p5-s75-tr8k-save30-best-finalopt-tistoken-seed1234-b64-mb32-dp4/global_step_90/actor/.async_checkpoint_started_world_size_4_rank_0.jsonConfiguration61 B —
experiments/weak_to_strong/reasoning/binary_matrix/ours/260728-rcd-binary_matrix-q3-8b-base-t4b-s105-lp0p5fixed-lm0to0p5-s75-tr8k-save30-best-finalopt-tistoken-seed1234-b64-mb32-dp4/global_step_90/actor/.async_checkpoint_started_world_size_4_rank_1.jsonConfiguration61 B —
experiments/weak_to_strong/reasoning/binary_matrix/ours/260728-rcd-binary_matrix-q3-8b-base-t4b-s105-lp0p5fixed-lm0to0p5-s75-tr8k-save30-best-finalopt-tistoken-seed1234-b64-mb32-dp4/global_step_90/actor/.async_checkpoint_started_world_size_4_rank_2.jsonConfiguration61 B —
experiments/weak_to_strong/reasoning/binary_matrix/ours/260728-rcd-binary_matrix-q3-8b-base-t4b-s105-lp0p5fixed-lm0to0p5-s75-tr8k-save30-best-finalopt-tistoken-seed1234-b64-mb32-dp4/global_step_90/actor/.async_checkpoint_started_world_size_4_rank_3.jsonConfiguration61 B —
experiments/weak_to_strong/reasoning/binary_matrix/ours/260728-rcd-binary_matrix-q3-8b-base-t4b-s105-lp0p5fixed-lm0to0p5-s75-tr8k-save30-best-finalopt-tistoken-seed1234-b64-mb32-dp4/global_step_90/actor/.checkpoint_complete.jsonConfiguration50 B —
experiments/weak_to_strong/reasoning/binary_matrix/ours/260728-rcd-binary_matrix-q3-8b-base-t4b-s105-lp0p5fixed-lm0to0p5-s75-tr8k-save30-best-finalopt-tistoken-seed1234-b64-mb32-dp4/global_step_90/actor/.worker_sidecars_ready_world_size_4_rank_0.jsonConfiguration83 B —
experiments/weak_to_strong/reasoning/binary_matrix/ours/260728-rcd-binary_matrix-q3-8b-base-t4b-s105-lp0p5fixed-lm0to0p5-s75-tr8k-save30-best-finalopt-tistoken-seed1234-b64-mb32-dp4/global_step_90/actor/.worker_sidecars_ready_world_size_4_rank_1.jsonConfiguration83 B —
experiments/weak_to_strong/reasoning/binary_matrix/ours/260728-rcd-binary_matrix-q3-8b-base-t4b-s105-lp0p5fixed-lm0to0p5-s75-tr8k-save30-best-finalopt-tistoken-seed1234-b64-mb32-dp4/global_step_90/actor/.worker_sidecars_ready_world_size_4_rank_2.jsonConfiguration83 B —
experiments/weak_to_strong/reasoning/binary_matrix/ours/260728-rcd-binary_matrix-q3-8b-base-t4b-s105-lp0p5fixed-lm0to0p5-s75-tr8k-save30-best-finalopt-tistoken-seed1234-b64-mb32-dp4/global_step_90/actor/.worker_sidecars_ready_world_size_4_rank_3.jsonConfiguration83 B —
experiments/weak_to_strong/reasoning/binary_matrix/ours/260728-rcd-binary_matrix-q3-8b-base-t4b-s105-lp0p5fixed-lm0to0p5-s75-tr8k-save30-best-finalopt-tistoken-seed1234-b64-mb32-dp4/global_step_90/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/reasoning/binary_matrix/ours/260728-rcd-binary_matrix-q3-8b-base-t4b-s105-lp0p5fixed-lm0to0p5-s75-tr8k-save30-best-finalopt-tistoken-seed1234-b64-mb32-dp4/global_step_90/actor/huggingface/config.jsonConfiguration1.6 KB —
experiments/weak_to_strong/reasoning/binary_matrix/ours/260728-rcd-binary_matrix-q3-8b-base-t4b-s105-lp0p5fixed-lm0to0p5-s75-tr8k-save30-best-finalopt-tistoken-seed1234-b64-mb32-dp4/global_step_90/actor/huggingface/generation_config.jsonConfiguration139 B —
experiments/weak_to_strong/reasoning/binary_matrix/ours/260728-rcd-binary_matrix-q3-8b-base-t4b-s105-lp0p5fixed-lm0to0p5-s75-tr8k-save30-best-finalopt-tistoken-seed1234-b64-mb32-dp4/latest_checkpoint.jsonConfiguration462 B —
experiments/weak_to_strong/reasoning/binary_matrix/ours/260731-rcd-binary_matrix-q3-8b-base-t4b-s105-h1b-s45-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/best_validation_checkpoint.jsonConfiguration226 B —
experiments/weak_to_strong/reasoning/binary_matrix/ours/260731-rcd-binary_matrix-q3-8b-base-t4b-s105-h1b-s45-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_120/actor/.async_checkpoint_ready_world_size_2_rank_0.jsonConfiguration370 B —
experiments/weak_to_strong/reasoning/binary_matrix/ours/260731-rcd-binary_matrix-q3-8b-base-t4b-s105-h1b-s45-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_120/actor/.async_checkpoint_ready_world_size_2_rank_1.jsonConfiguration183 B —
experiments/weak_to_strong/reasoning/binary_matrix/ours/260731-rcd-binary_matrix-q3-8b-base-t4b-s105-h1b-s45-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_120/actor/.async_checkpoint_started_world_size_2_rank_0.jsonConfiguration62 B —
experiments/weak_to_strong/reasoning/binary_matrix/ours/260731-rcd-binary_matrix-q3-8b-base-t4b-s105-h1b-s45-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_120/actor/.async_checkpoint_started_world_size_2_rank_1.jsonConfiguration62 B —
experiments/weak_to_strong/reasoning/binary_matrix/ours/260731-rcd-binary_matrix-q3-8b-base-t4b-s105-h1b-s45-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_120/actor/.checkpoint_complete.jsonConfiguration51 B —
experiments/weak_to_strong/reasoning/binary_matrix/ours/260731-rcd-binary_matrix-q3-8b-base-t4b-s105-h1b-s45-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_120/actor/.worker_sidecars_ready_world_size_2_rank_0.jsonConfiguration84 B —
experiments/weak_to_strong/reasoning/binary_matrix/ours/260731-rcd-binary_matrix-q3-8b-base-t4b-s105-h1b-s45-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_120/actor/.worker_sidecars_ready_world_size_2_rank_1.jsonConfiguration84 B —
experiments/weak_to_strong/reasoning/binary_matrix/ours/260731-rcd-binary_matrix-q3-8b-base-t4b-s105-h1b-s45-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_120/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/reasoning/binary_matrix/ours/260731-rcd-binary_matrix-q3-8b-base-t4b-s105-h1b-s45-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_120/actor/huggingface/config.jsonConfiguration1.6 KB —
experiments/weak_to_strong/reasoning/binary_matrix/ours/260731-rcd-binary_matrix-q3-8b-base-t4b-s105-h1b-s45-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_120/actor/huggingface/generation_config.jsonConfiguration139 B —
experiments/weak_to_strong/reasoning/binary_matrix/ours/260731-rcd-binary_matrix-q3-8b-base-t4b-s105-h1b-s45-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_150/actor/.async_checkpoint_ready_world_size_2_rank_0.jsonConfiguration370 B —
experiments/weak_to_strong/reasoning/binary_matrix/ours/260731-rcd-binary_matrix-q3-8b-base-t4b-s105-h1b-s45-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_150/actor/.async_checkpoint_ready_world_size_2_rank_1.jsonConfiguration183 B —
experiments/weak_to_strong/reasoning/binary_matrix/ours/260731-rcd-binary_matrix-q3-8b-base-t4b-s105-h1b-s45-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_150/actor/.async_checkpoint_started_world_size_2_rank_0.jsonConfiguration62 B —
experiments/weak_to_strong/reasoning/binary_matrix/ours/260731-rcd-binary_matrix-q3-8b-base-t4b-s105-h1b-s45-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_150/actor/.async_checkpoint_started_world_size_2_rank_1.jsonConfiguration62 B —
experiments/weak_to_strong/reasoning/binary_matrix/ours/260731-rcd-binary_matrix-q3-8b-base-t4b-s105-h1b-s45-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_150/actor/.checkpoint_complete.jsonConfiguration51 B —
experiments/weak_to_strong/reasoning/binary_matrix/ours/260731-rcd-binary_matrix-q3-8b-base-t4b-s105-h1b-s45-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_150/actor/.worker_sidecars_ready_world_size_2_rank_0.jsonConfiguration84 B —
experiments/weak_to_strong/reasoning/binary_matrix/ours/260731-rcd-binary_matrix-q3-8b-base-t4b-s105-h1b-s45-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_150/actor/.worker_sidecars_ready_world_size_2_rank_1.jsonConfiguration84 B —
experiments/weak_to_strong/reasoning/binary_matrix/ours/260731-rcd-binary_matrix-q3-8b-base-t4b-s105-h1b-s45-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_150/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/reasoning/binary_matrix/ours/260731-rcd-binary_matrix-q3-8b-base-t4b-s105-h1b-s45-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_150/actor/huggingface/config.jsonConfiguration1.6 KB —
experiments/weak_to_strong/reasoning/binary_matrix/ours/260731-rcd-binary_matrix-q3-8b-base-t4b-s105-h1b-s45-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_150/actor/huggingface/generation_config.jsonConfiguration139 B —
experiments/weak_to_strong/reasoning/binary_matrix/ours/260731-rcd-binary_matrix-q3-8b-base-t4b-s105-h1b-s45-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_90/actor/.async_checkpoint_ready_world_size_2_rank_0.jsonConfiguration369 B —
experiments/weak_to_strong/reasoning/binary_matrix/ours/260731-rcd-binary_matrix-q3-8b-base-t4b-s105-h1b-s45-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_90/actor/.async_checkpoint_ready_world_size_2_rank_1.jsonConfiguration182 B —
experiments/weak_to_strong/reasoning/binary_matrix/ours/260731-rcd-binary_matrix-q3-8b-base-t4b-s105-h1b-s45-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_90/actor/.async_checkpoint_started_world_size_2_rank_0.jsonConfiguration61 B —
experiments/weak_to_strong/reasoning/binary_matrix/ours/260731-rcd-binary_matrix-q3-8b-base-t4b-s105-h1b-s45-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_90/actor/.async_checkpoint_started_world_size_2_rank_1.jsonConfiguration61 B —
experiments/weak_to_strong/reasoning/binary_matrix/ours/260731-rcd-binary_matrix-q3-8b-base-t4b-s105-h1b-s45-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_90/actor/.checkpoint_complete.jsonConfiguration50 B —
experiments/weak_to_strong/reasoning/binary_matrix/ours/260731-rcd-binary_matrix-q3-8b-base-t4b-s105-h1b-s45-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_90/actor/.worker_sidecars_ready_world_size_2_rank_0.jsonConfiguration83 B —
experiments/weak_to_strong/reasoning/binary_matrix/ours/260731-rcd-binary_matrix-q3-8b-base-t4b-s105-h1b-s45-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_90/actor/.worker_sidecars_ready_world_size_2_rank_1.jsonConfiguration83 B —
experiments/weak_to_strong/reasoning/binary_matrix/ours/260731-rcd-binary_matrix-q3-8b-base-t4b-s105-h1b-s45-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_90/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/reasoning/binary_matrix/ours/260731-rcd-binary_matrix-q3-8b-base-t4b-s105-h1b-s45-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_90/actor/huggingface/config.jsonConfiguration1.6 KB —
experiments/weak_to_strong/reasoning/binary_matrix/ours/260731-rcd-binary_matrix-q3-8b-base-t4b-s105-h1b-s45-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_90/actor/huggingface/generation_config.jsonConfiguration139 B —
experiments/weak_to_strong/reasoning/binary_matrix/ours/260731-rcd-binary_matrix-q3-8b-base-t4b-s105-h1b-s45-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/latest_checkpoint.jsonConfiguration493 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-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.jsonConfiguration370 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-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.jsonConfiguration183 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-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.jsonConfiguration62 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-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.jsonConfiguration62 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_105/actor/.checkpoint_complete.jsonConfiguration51 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-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.jsonConfiguration84 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-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.jsonConfiguration84 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_105/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_105/actor/huggingface/config.jsonConfiguration1.6 KB —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_105/actor/huggingface/generation_config.jsonConfiguration139 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-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.jsonConfiguration370 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-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.jsonConfiguration183 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-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.jsonConfiguration62 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-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.jsonConfiguration62 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_120/actor/.checkpoint_complete.jsonConfiguration51 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-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.jsonConfiguration84 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-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.jsonConfiguration84 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_120/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_120/actor/huggingface/config.jsonConfiguration1.6 KB —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_120/actor/huggingface/generation_config.jsonConfiguration139 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-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.jsonConfiguration370 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-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.jsonConfiguration369 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-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.jsonConfiguration182 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-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.jsonConfiguration61 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-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.jsonConfiguration61 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_15/actor/.checkpoint_complete.jsonConfiguration50 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-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.jsonConfiguration83 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-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.jsonConfiguration83 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_15/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_15/actor/huggingface/config.jsonConfiguration1.6 KB —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_15/actor/huggingface/generation_config.jsonConfiguration139 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-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.jsonConfiguration370 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-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.jsonConfiguration183 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-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.jsonConfiguration62 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-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.jsonConfiguration62 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_150/actor/.checkpoint_complete.jsonConfiguration51 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-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.jsonConfiguration84 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-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.jsonConfiguration84 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_150/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_150/actor/huggingface/config.jsonConfiguration1.6 KB —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_150/actor/huggingface/generation_config.jsonConfiguration139 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-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.jsonConfiguration369 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-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.jsonConfiguration182 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-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.jsonConfiguration61 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-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.jsonConfiguration61 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_30/actor/.checkpoint_complete.jsonConfiguration50 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-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.jsonConfiguration83 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-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.jsonConfiguration83 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_30/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_30/actor/huggingface/config.jsonConfiguration1.6 KB —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_30/actor/huggingface/generation_config.jsonConfiguration139 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-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.jsonConfiguration369 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-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.jsonConfiguration182 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-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.jsonConfiguration61 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-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.jsonConfiguration61 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_45/actor/.checkpoint_complete.jsonConfiguration50 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-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.jsonConfiguration83 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-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.jsonConfiguration83 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_45/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_45/actor/huggingface/config.jsonConfiguration1.6 KB —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_45/actor/huggingface/generation_config.jsonConfiguration139 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-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.jsonConfiguration369 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-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.jsonConfiguration182 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-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.jsonConfiguration61 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-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.jsonConfiguration61 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_60/actor/.checkpoint_complete.jsonConfiguration50 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-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.jsonConfiguration83 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-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.jsonConfiguration83 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_60/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_60/actor/huggingface/config.jsonConfiguration1.6 KB —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_60/actor/huggingface/generation_config.jsonConfiguration139 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-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.jsonConfiguration369 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-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.jsonConfiguration182 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-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.jsonConfiguration61 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-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.jsonConfiguration61 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_75/actor/.checkpoint_complete.jsonConfiguration50 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-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.jsonConfiguration83 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-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.jsonConfiguration83 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_75/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_75/actor/huggingface/config.jsonConfiguration1.6 KB —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_75/actor/huggingface/generation_config.jsonConfiguration139 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-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.jsonConfiguration369 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-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.jsonConfiguration182 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-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.jsonConfiguration61 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-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.jsonConfiguration61 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_90/actor/.checkpoint_complete.jsonConfiguration50 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-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.jsonConfiguration83 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-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.jsonConfiguration83 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_90/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_90/actor/huggingface/config.jsonConfiguration1.6 KB —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-4b-base-s150-tr8k-va8k-clip0p2-0p28-save15-eval15-tistoken-b64-mb32-dp2/global_step_90/actor/huggingface/generation_config.jsonConfiguration139 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/best_validation_checkpoint.jsonConfiguration232 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_105/actor/.async_checkpoint_ready_world_size_2_rank_0.jsonConfiguration370 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_105/actor/.async_checkpoint_ready_world_size_2_rank_1.jsonConfiguration183 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_105/actor/.async_checkpoint_started_world_size_2_rank_0.jsonConfiguration62 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_105/actor/.async_checkpoint_started_world_size_2_rank_1.jsonConfiguration62 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_105/actor/.checkpoint_complete.jsonConfiguration51 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_105/actor/.worker_sidecars_ready_world_size_2_rank_0.jsonConfiguration84 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_105/actor/.worker_sidecars_ready_world_size_2_rank_1.jsonConfiguration84 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_105/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_105/actor/huggingface/config.jsonConfiguration1.6 KB —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_105/actor/huggingface/generation_config.jsonConfiguration139 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_120/actor/.async_checkpoint_ready_world_size_2_rank_0.jsonConfiguration370 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_120/actor/.async_checkpoint_ready_world_size_2_rank_1.jsonConfiguration183 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_120/actor/.async_checkpoint_started_world_size_2_rank_0.jsonConfiguration62 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_120/actor/.async_checkpoint_started_world_size_2_rank_1.jsonConfiguration62 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_120/actor/.checkpoint_complete.jsonConfiguration51 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_120/actor/.worker_sidecars_ready_world_size_2_rank_0.jsonConfiguration84 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_120/actor/.worker_sidecars_ready_world_size_2_rank_1.jsonConfiguration84 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_120/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_120/actor/huggingface/config.jsonConfiguration1.6 KB —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_120/actor/huggingface/generation_config.jsonConfiguration139 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_135/actor/.async_checkpoint_ready_world_size_2_rank_0.jsonConfiguration370 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_135/actor/.async_checkpoint_ready_world_size_2_rank_1.jsonConfiguration183 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_135/actor/.async_checkpoint_started_world_size_2_rank_0.jsonConfiguration62 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_135/actor/.async_checkpoint_started_world_size_2_rank_1.jsonConfiguration62 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_135/actor/.checkpoint_complete.jsonConfiguration51 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_135/actor/.worker_sidecars_ready_world_size_2_rank_0.jsonConfiguration84 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_135/actor/.worker_sidecars_ready_world_size_2_rank_1.jsonConfiguration84 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_135/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_135/actor/huggingface/config.jsonConfiguration1.6 KB —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_135/actor/huggingface/generation_config.jsonConfiguration139 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_15/actor/.async_checkpoint_ready_world_size_2_rank_0.jsonConfiguration369 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_15/actor/.async_checkpoint_ready_world_size_2_rank_1.jsonConfiguration182 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_15/actor/.async_checkpoint_started_world_size_2_rank_0.jsonConfiguration61 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_15/actor/.async_checkpoint_started_world_size_2_rank_1.jsonConfiguration61 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_15/actor/.checkpoint_complete.jsonConfiguration50 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_15/actor/.worker_sidecars_ready_world_size_2_rank_0.jsonConfiguration83 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_15/actor/.worker_sidecars_ready_world_size_2_rank_1.jsonConfiguration83 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_15/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_15/actor/huggingface/config.jsonConfiguration1.6 KB —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_15/actor/huggingface/generation_config.jsonConfiguration139 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_150/actor/.async_checkpoint_ready_world_size_2_rank_0.jsonConfiguration370 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_150/actor/.async_checkpoint_ready_world_size_2_rank_1.jsonConfiguration183 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_150/actor/.async_checkpoint_started_world_size_2_rank_0.jsonConfiguration62 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_150/actor/.async_checkpoint_started_world_size_2_rank_1.jsonConfiguration62 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_150/actor/.checkpoint_complete.jsonConfiguration51 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_150/actor/.worker_sidecars_ready_world_size_2_rank_0.jsonConfiguration84 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_150/actor/.worker_sidecars_ready_world_size_2_rank_1.jsonConfiguration84 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_150/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_150/actor/huggingface/config.jsonConfiguration1.6 KB —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_150/actor/huggingface/generation_config.jsonConfiguration139 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_30/actor/.async_checkpoint_ready_world_size_2_rank_0.jsonConfiguration369 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_30/actor/.async_checkpoint_ready_world_size_2_rank_1.jsonConfiguration182 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_30/actor/.async_checkpoint_started_world_size_2_rank_0.jsonConfiguration61 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_30/actor/.async_checkpoint_started_world_size_2_rank_1.jsonConfiguration61 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_30/actor/.checkpoint_complete.jsonConfiguration50 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_30/actor/.worker_sidecars_ready_world_size_2_rank_0.jsonConfiguration83 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_30/actor/.worker_sidecars_ready_world_size_2_rank_1.jsonConfiguration83 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_30/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_30/actor/huggingface/config.jsonConfiguration1.6 KB —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_30/actor/huggingface/generation_config.jsonConfiguration139 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_45/actor/.async_checkpoint_ready_world_size_2_rank_0.jsonConfiguration369 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_45/actor/.async_checkpoint_ready_world_size_2_rank_1.jsonConfiguration182 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_45/actor/.async_checkpoint_started_world_size_2_rank_0.jsonConfiguration61 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_45/actor/.async_checkpoint_started_world_size_2_rank_1.jsonConfiguration61 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_45/actor/.checkpoint_complete.jsonConfiguration50 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_45/actor/.worker_sidecars_ready_world_size_2_rank_0.jsonConfiguration83 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_45/actor/.worker_sidecars_ready_world_size_2_rank_1.jsonConfiguration83 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_45/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_45/actor/huggingface/config.jsonConfiguration1.6 KB —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_45/actor/huggingface/generation_config.jsonConfiguration139 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_60/actor/.async_checkpoint_ready_world_size_2_rank_0.jsonConfiguration369 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_60/actor/.async_checkpoint_ready_world_size_2_rank_1.jsonConfiguration182 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_60/actor/.async_checkpoint_started_world_size_2_rank_0.jsonConfiguration61 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_60/actor/.async_checkpoint_started_world_size_2_rank_1.jsonConfiguration61 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_60/actor/.checkpoint_complete.jsonConfiguration50 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_60/actor/.worker_sidecars_ready_world_size_2_rank_0.jsonConfiguration83 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_60/actor/.worker_sidecars_ready_world_size_2_rank_1.jsonConfiguration83 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_60/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_60/actor/huggingface/config.jsonConfiguration1.6 KB —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_60/actor/huggingface/generation_config.jsonConfiguration139 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_75/actor/.async_checkpoint_ready_world_size_2_rank_0.jsonConfiguration369 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_75/actor/.async_checkpoint_ready_world_size_2_rank_1.jsonConfiguration182 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_75/actor/.async_checkpoint_started_world_size_2_rank_0.jsonConfiguration61 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_75/actor/.async_checkpoint_started_world_size_2_rank_1.jsonConfiguration61 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_75/actor/.checkpoint_complete.jsonConfiguration50 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_75/actor/.worker_sidecars_ready_world_size_2_rank_0.jsonConfiguration83 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_75/actor/.worker_sidecars_ready_world_size_2_rank_1.jsonConfiguration83 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_75/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_75/actor/huggingface/config.jsonConfiguration1.6 KB —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_75/actor/huggingface/generation_config.jsonConfiguration139 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_90/actor/.async_checkpoint_ready_world_size_2_rank_0.jsonConfiguration369 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_90/actor/.async_checkpoint_ready_world_size_2_rank_1.jsonConfiguration182 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_90/actor/.async_checkpoint_started_world_size_2_rank_0.jsonConfiguration61 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_90/actor/.async_checkpoint_started_world_size_2_rank_1.jsonConfiguration61 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_90/actor/.checkpoint_complete.jsonConfiguration50 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_90/actor/.worker_sidecars_ready_world_size_2_rank_0.jsonConfiguration83 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_90/actor/.worker_sidecars_ready_world_size_2_rank_1.jsonConfiguration83 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_90/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_90/actor/huggingface/config.jsonConfiguration1.6 KB —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_90/actor/huggingface/generation_config.jsonConfiguration139 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/baseline/260729-grpo-color_cube_rotation-q3-8b-base-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/latest_checkpoint.jsonConfiguration432 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260730-sampledrkl-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/best_validation_checkpoint.jsonConfiguration232 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260730-sampledrkl-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_105/actor/.async_checkpoint_ready_world_size_2_rank_0.jsonConfiguration370 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260730-sampledrkl-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_105/actor/.async_checkpoint_ready_world_size_2_rank_1.jsonConfiguration183 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260730-sampledrkl-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_105/actor/.async_checkpoint_started_world_size_2_rank_0.jsonConfiguration62 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260730-sampledrkl-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_105/actor/.async_checkpoint_started_world_size_2_rank_1.jsonConfiguration62 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260730-sampledrkl-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_105/actor/.checkpoint_complete.jsonConfiguration51 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260730-sampledrkl-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_105/actor/.worker_sidecars_ready_world_size_2_rank_0.jsonConfiguration171 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260730-sampledrkl-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_105/actor/.worker_sidecars_ready_world_size_2_rank_1.jsonConfiguration171 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260730-sampledrkl-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_105/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260730-sampledrkl-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_105/actor/huggingface/config.jsonConfiguration1.6 KB —
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260730-sampledrkl-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_105/actor/huggingface/generation_config.jsonConfiguration139 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260730-sampledrkl-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_120/actor/.async_checkpoint_ready_world_size_2_rank_0.jsonConfiguration370 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260730-sampledrkl-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_120/actor/.async_checkpoint_ready_world_size_2_rank_1.jsonConfiguration183 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260730-sampledrkl-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_120/actor/.async_checkpoint_started_world_size_2_rank_0.jsonConfiguration62 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260730-sampledrkl-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_120/actor/.async_checkpoint_started_world_size_2_rank_1.jsonConfiguration62 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260730-sampledrkl-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_120/actor/.checkpoint_complete.jsonConfiguration51 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260730-sampledrkl-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_120/actor/.worker_sidecars_ready_world_size_2_rank_0.jsonConfiguration171 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260730-sampledrkl-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_120/actor/.worker_sidecars_ready_world_size_2_rank_1.jsonConfiguration171 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260730-sampledrkl-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_120/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260730-sampledrkl-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_120/actor/huggingface/config.jsonConfiguration1.6 KB —
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260730-sampledrkl-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_120/actor/huggingface/generation_config.jsonConfiguration139 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260730-sampledrkl-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_15/actor/.async_checkpoint_ready_world_size_2_rank_0.jsonConfiguration369 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260730-sampledrkl-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_15/actor/.async_checkpoint_ready_world_size_2_rank_1.jsonConfiguration182 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260730-sampledrkl-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_15/actor/.async_checkpoint_started_world_size_2_rank_0.jsonConfiguration61 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260730-sampledrkl-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_15/actor/.async_checkpoint_started_world_size_2_rank_1.jsonConfiguration61 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260730-sampledrkl-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_15/actor/.checkpoint_complete.jsonConfiguration50 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260730-sampledrkl-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_15/actor/.worker_sidecars_ready_world_size_2_rank_0.jsonConfiguration170 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260730-sampledrkl-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_15/actor/.worker_sidecars_ready_world_size_2_rank_1.jsonConfiguration170 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260730-sampledrkl-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_15/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260730-sampledrkl-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_15/actor/huggingface/config.jsonConfiguration1.6 KB —
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260730-sampledrkl-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_15/actor/huggingface/generation_config.jsonConfiguration139 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260730-sampledrkl-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_150/actor/.async_checkpoint_ready_world_size_2_rank_0.jsonConfiguration370 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260730-sampledrkl-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_150/actor/.async_checkpoint_ready_world_size_2_rank_1.jsonConfiguration183 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260730-sampledrkl-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_150/actor/.async_checkpoint_started_world_size_2_rank_0.jsonConfiguration62 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260730-sampledrkl-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_150/actor/.async_checkpoint_started_world_size_2_rank_1.jsonConfiguration62 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260730-sampledrkl-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_150/actor/.checkpoint_complete.jsonConfiguration51 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260730-sampledrkl-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_150/actor/.worker_sidecars_ready_world_size_2_rank_0.jsonConfiguration171 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260730-sampledrkl-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_150/actor/.worker_sidecars_ready_world_size_2_rank_1.jsonConfiguration171 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260730-sampledrkl-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_150/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260730-sampledrkl-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_150/actor/huggingface/config.jsonConfiguration1.6 KB —
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260730-sampledrkl-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_150/actor/huggingface/generation_config.jsonConfiguration139 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260730-sampledrkl-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_30/actor/.async_checkpoint_ready_world_size_2_rank_0.jsonConfiguration369 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260730-sampledrkl-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_30/actor/.async_checkpoint_ready_world_size_2_rank_1.jsonConfiguration182 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260730-sampledrkl-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_30/actor/.async_checkpoint_started_world_size_2_rank_0.jsonConfiguration61 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260730-sampledrkl-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_30/actor/.async_checkpoint_started_world_size_2_rank_1.jsonConfiguration61 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260730-sampledrkl-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_30/actor/.checkpoint_complete.jsonConfiguration50 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260730-sampledrkl-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_30/actor/.worker_sidecars_ready_world_size_2_rank_0.jsonConfiguration170 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260730-sampledrkl-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_30/actor/.worker_sidecars_ready_world_size_2_rank_1.jsonConfiguration170 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260730-sampledrkl-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_30/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260730-sampledrkl-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_30/actor/huggingface/config.jsonConfiguration1.6 KB —
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260730-sampledrkl-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_30/actor/huggingface/generation_config.jsonConfiguration139 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260730-sampledrkl-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_45/actor/.async_checkpoint_ready_world_size_2_rank_0.jsonConfiguration369 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260730-sampledrkl-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_45/actor/.async_checkpoint_ready_world_size_2_rank_1.jsonConfiguration182 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260730-sampledrkl-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_45/actor/.async_checkpoint_started_world_size_2_rank_0.jsonConfiguration61 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260730-sampledrkl-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_45/actor/.async_checkpoint_started_world_size_2_rank_1.jsonConfiguration61 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260730-sampledrkl-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_45/actor/.checkpoint_complete.jsonConfiguration50 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260730-sampledrkl-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_45/actor/.worker_sidecars_ready_world_size_2_rank_0.jsonConfiguration170 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260730-sampledrkl-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_45/actor/.worker_sidecars_ready_world_size_2_rank_1.jsonConfiguration170 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260730-sampledrkl-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_45/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260730-sampledrkl-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_45/actor/huggingface/config.jsonConfiguration1.6 KB —
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260730-sampledrkl-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_45/actor/huggingface/generation_config.jsonConfiguration139 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260730-sampledrkl-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_60/actor/.async_checkpoint_ready_world_size_2_rank_0.jsonConfiguration369 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260730-sampledrkl-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_60/actor/.async_checkpoint_ready_world_size_2_rank_1.jsonConfiguration182 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260730-sampledrkl-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_60/actor/.async_checkpoint_started_world_size_2_rank_0.jsonConfiguration61 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260730-sampledrkl-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_60/actor/.async_checkpoint_started_world_size_2_rank_1.jsonConfiguration61 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260730-sampledrkl-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_60/actor/.checkpoint_complete.jsonConfiguration50 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260730-sampledrkl-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_60/actor/.worker_sidecars_ready_world_size_2_rank_0.jsonConfiguration170 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260730-sampledrkl-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_60/actor/.worker_sidecars_ready_world_size_2_rank_1.jsonConfiguration170 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260730-sampledrkl-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_60/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260730-sampledrkl-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_60/actor/huggingface/config.jsonConfiguration1.6 KB —
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260730-sampledrkl-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_60/actor/huggingface/generation_config.jsonConfiguration139 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260730-sampledrkl-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_90/actor/.async_checkpoint_ready_world_size_2_rank_0.jsonConfiguration369 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260730-sampledrkl-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_90/actor/.async_checkpoint_ready_world_size_2_rank_1.jsonConfiguration182 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260730-sampledrkl-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_90/actor/.async_checkpoint_started_world_size_2_rank_0.jsonConfiguration61 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260730-sampledrkl-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_90/actor/.async_checkpoint_started_world_size_2_rank_1.jsonConfiguration61 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260730-sampledrkl-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_90/actor/.checkpoint_complete.jsonConfiguration50 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260730-sampledrkl-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_90/actor/.worker_sidecars_ready_world_size_2_rank_0.jsonConfiguration170 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260730-sampledrkl-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_90/actor/.worker_sidecars_ready_world_size_2_rank_1.jsonConfiguration170 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260730-sampledrkl-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_90/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260730-sampledrkl-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_90/actor/huggingface/config.jsonConfiguration1.6 KB —
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260730-sampledrkl-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_90/actor/huggingface/generation_config.jsonConfiguration139 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260730-sampledrkl-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/latest_checkpoint.jsonConfiguration479 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260731-rerun1-kdrl-b5e3-d6p6667e5-min0-sched75-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-finalopt-static10k-tistoken-clip0p2-0p28-seed42-fastvllm-b64-mb32-dp4/best_validation_checkpoint.jsonConfiguration233 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260731-rerun1-kdrl-b5e3-d6p6667e5-min0-sched75-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-finalopt-static10k-tistoken-clip0p2-0p28-seed42-fastvllm-b64-mb32-dp4/global_step_120/actor/.checkpoint_complete.jsonConfiguration51 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260731-rerun1-kdrl-b5e3-d6p6667e5-min0-sched75-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-finalopt-static10k-tistoken-clip0p2-0p28-seed42-fastvllm-b64-mb32-dp4/global_step_120/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260731-rerun1-kdrl-b5e3-d6p6667e5-min0-sched75-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-finalopt-static10k-tistoken-clip0p2-0p28-seed42-fastvllm-b64-mb32-dp4/global_step_120/actor/huggingface/config.jsonConfiguration1.6 KB —
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260731-rerun1-kdrl-b5e3-d6p6667e5-min0-sched75-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-finalopt-static10k-tistoken-clip0p2-0p28-seed42-fastvllm-b64-mb32-dp4/global_step_135/actor/.checkpoint_complete.jsonConfiguration51 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260731-rerun1-kdrl-b5e3-d6p6667e5-min0-sched75-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-finalopt-static10k-tistoken-clip0p2-0p28-seed42-fastvllm-b64-mb32-dp4/global_step_135/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260731-rerun1-kdrl-b5e3-d6p6667e5-min0-sched75-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-finalopt-static10k-tistoken-clip0p2-0p28-seed42-fastvllm-b64-mb32-dp4/global_step_135/actor/huggingface/config.jsonConfiguration1.6 KB —
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260731-rerun1-kdrl-b5e3-d6p6667e5-min0-sched75-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-finalopt-static10k-tistoken-clip0p2-0p28-seed42-fastvllm-b64-mb32-dp4/global_step_150/actor/.checkpoint_complete.jsonConfiguration51 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260731-rerun1-kdrl-b5e3-d6p6667e5-min0-sched75-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-finalopt-static10k-tistoken-clip0p2-0p28-seed42-fastvllm-b64-mb32-dp4/global_step_150/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260731-rerun1-kdrl-b5e3-d6p6667e5-min0-sched75-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-finalopt-static10k-tistoken-clip0p2-0p28-seed42-fastvllm-b64-mb32-dp4/global_step_150/actor/huggingface/config.jsonConfiguration1.6 KB —
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260731-rerun1-kdrl-b5e3-d6p6667e5-min0-sched75-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-finalopt-static10k-tistoken-clip0p2-0p28-seed42-fastvllm-b64-mb32-dp4/global_step_30/actor/.checkpoint_complete.jsonConfiguration50 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260731-rerun1-kdrl-b5e3-d6p6667e5-min0-sched75-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-finalopt-static10k-tistoken-clip0p2-0p28-seed42-fastvllm-b64-mb32-dp4/global_step_30/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260731-rerun1-kdrl-b5e3-d6p6667e5-min0-sched75-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-finalopt-static10k-tistoken-clip0p2-0p28-seed42-fastvllm-b64-mb32-dp4/global_step_30/actor/huggingface/config.jsonConfiguration1.6 KB —
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260731-rerun1-kdrl-b5e3-d6p6667e5-min0-sched75-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-finalopt-static10k-tistoken-clip0p2-0p28-seed42-fastvllm-b64-mb32-dp4/global_step_45/actor/.checkpoint_complete.jsonConfiguration50 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260731-rerun1-kdrl-b5e3-d6p6667e5-min0-sched75-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-finalopt-static10k-tistoken-clip0p2-0p28-seed42-fastvllm-b64-mb32-dp4/global_step_45/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260731-rerun1-kdrl-b5e3-d6p6667e5-min0-sched75-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-finalopt-static10k-tistoken-clip0p2-0p28-seed42-fastvllm-b64-mb32-dp4/global_step_45/actor/huggingface/config.jsonConfiguration1.6 KB —
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260731-rerun1-kdrl-b5e3-d6p6667e5-min0-sched75-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-finalopt-static10k-tistoken-clip0p2-0p28-seed42-fastvllm-b64-mb32-dp4/global_step_60/actor/.checkpoint_complete.jsonConfiguration50 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260731-rerun1-kdrl-b5e3-d6p6667e5-min0-sched75-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-finalopt-static10k-tistoken-clip0p2-0p28-seed42-fastvllm-b64-mb32-dp4/global_step_60/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260731-rerun1-kdrl-b5e3-d6p6667e5-min0-sched75-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-finalopt-static10k-tistoken-clip0p2-0p28-seed42-fastvllm-b64-mb32-dp4/global_step_60/actor/huggingface/config.jsonConfiguration1.6 KB —
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260731-rerun1-kdrl-b5e3-d6p6667e5-min0-sched75-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-finalopt-static10k-tistoken-clip0p2-0p28-seed42-fastvllm-b64-mb32-dp4/global_step_90/actor/.checkpoint_complete.jsonConfiguration50 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260731-rerun1-kdrl-b5e3-d6p6667e5-min0-sched75-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-finalopt-static10k-tistoken-clip0p2-0p28-seed42-fastvllm-b64-mb32-dp4/global_step_90/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260731-rerun1-kdrl-b5e3-d6p6667e5-min0-sched75-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-finalopt-static10k-tistoken-clip0p2-0p28-seed42-fastvllm-b64-mb32-dp4/global_step_90/actor/huggingface/config.jsonConfiguration1.6 KB —
experiments/weak_to_strong/reasoning/color_cube_rotation/distill_baseline/260731-rerun1-kdrl-b5e3-d6p6667e5-min0-sched75-color_cube_rotation-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-finalopt-static10k-tistoken-clip0p2-0p28-seed42-fastvllm-b64-mb32-dp4/latest_checkpoint.jsonConfiguration433 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-h1b-s30-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/best_validation_checkpoint.jsonConfiguration231 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-h1b-s30-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_120/actor/.async_checkpoint_ready_world_size_2_rank_0.jsonConfiguration370 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-h1b-s30-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_120/actor/.async_checkpoint_ready_world_size_2_rank_1.jsonConfiguration183 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-h1b-s30-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_120/actor/.async_checkpoint_started_world_size_2_rank_0.jsonConfiguration62 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-h1b-s30-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_120/actor/.async_checkpoint_started_world_size_2_rank_1.jsonConfiguration62 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-h1b-s30-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_120/actor/.checkpoint_complete.jsonConfiguration51 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-h1b-s30-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_120/actor/.worker_sidecars_ready_world_size_2_rank_0.jsonConfiguration84 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-h1b-s30-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_120/actor/.worker_sidecars_ready_world_size_2_rank_1.jsonConfiguration84 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-h1b-s30-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_120/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-h1b-s30-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_120/actor/huggingface/config.jsonConfiguration1.6 KB —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-h1b-s30-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_120/actor/huggingface/generation_config.jsonConfiguration139 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-h1b-s30-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_15/actor/.async_checkpoint_ready_world_size_2_rank_0.jsonConfiguration369 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-h1b-s30-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_15/actor/.async_checkpoint_ready_world_size_2_rank_1.jsonConfiguration182 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-h1b-s30-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_15/actor/.async_checkpoint_started_world_size_2_rank_0.jsonConfiguration61 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-h1b-s30-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_15/actor/.async_checkpoint_started_world_size_2_rank_1.jsonConfiguration61 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-h1b-s30-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_15/actor/.checkpoint_complete.jsonConfiguration50 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-h1b-s30-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_15/actor/.worker_sidecars_ready_world_size_2_rank_0.jsonConfiguration83 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-h1b-s30-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_15/actor/.worker_sidecars_ready_world_size_2_rank_1.jsonConfiguration83 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-h1b-s30-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_15/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-h1b-s30-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_15/actor/huggingface/config.jsonConfiguration1.6 KB —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-h1b-s30-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_15/actor/huggingface/generation_config.jsonConfiguration139 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-h1b-s30-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_150/actor/.async_checkpoint_ready_world_size_2_rank_0.jsonConfiguration370 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-h1b-s30-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_150/actor/.async_checkpoint_ready_world_size_2_rank_1.jsonConfiguration183 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-h1b-s30-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_150/actor/.async_checkpoint_started_world_size_2_rank_0.jsonConfiguration62 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-h1b-s30-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_150/actor/.async_checkpoint_started_world_size_2_rank_1.jsonConfiguration62 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-h1b-s30-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_150/actor/.checkpoint_complete.jsonConfiguration51 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-h1b-s30-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_150/actor/.worker_sidecars_ready_world_size_2_rank_0.jsonConfiguration84 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-h1b-s30-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_150/actor/.worker_sidecars_ready_world_size_2_rank_1.jsonConfiguration84 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-h1b-s30-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_150/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-h1b-s30-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_150/actor/huggingface/config.jsonConfiguration1.6 KB —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-h1b-s30-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_150/actor/huggingface/generation_config.jsonConfiguration139 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-h1b-s30-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_30/actor/.async_checkpoint_ready_world_size_2_rank_0.jsonConfiguration369 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-h1b-s30-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_30/actor/.async_checkpoint_ready_world_size_2_rank_1.jsonConfiguration182 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-h1b-s30-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_30/actor/.async_checkpoint_started_world_size_2_rank_0.jsonConfiguration61 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-h1b-s30-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_30/actor/.async_checkpoint_started_world_size_2_rank_1.jsonConfiguration61 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-h1b-s30-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_30/actor/.checkpoint_complete.jsonConfiguration50 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-h1b-s30-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_30/actor/.worker_sidecars_ready_world_size_2_rank_0.jsonConfiguration83 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-h1b-s30-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_30/actor/.worker_sidecars_ready_world_size_2_rank_1.jsonConfiguration83 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-h1b-s30-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_30/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-h1b-s30-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_30/actor/huggingface/config.jsonConfiguration1.6 KB —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-h1b-s30-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_30/actor/huggingface/generation_config.jsonConfiguration139 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-h1b-s30-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.jsonConfiguration369 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-h1b-s30-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.jsonConfiguration182 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-h1b-s30-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.jsonConfiguration61 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-h1b-s30-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.jsonConfiguration61 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-h1b-s30-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_45/actor/.checkpoint_complete.jsonConfiguration50 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-h1b-s30-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.jsonConfiguration83 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-h1b-s30-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.jsonConfiguration83 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-h1b-s30-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_45/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-h1b-s30-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_45/actor/huggingface/config.jsonConfiguration1.6 KB —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-h1b-s30-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_45/actor/huggingface/generation_config.jsonConfiguration139 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-h1b-s30-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_60/actor/.async_checkpoint_ready_world_size_2_rank_0.jsonConfiguration369 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-h1b-s30-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_60/actor/.async_checkpoint_ready_world_size_2_rank_1.jsonConfiguration182 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-h1b-s30-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_60/actor/.async_checkpoint_started_world_size_2_rank_0.jsonConfiguration61 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-h1b-s30-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_60/actor/.async_checkpoint_started_world_size_2_rank_1.jsonConfiguration61 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-h1b-s30-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_60/actor/.checkpoint_complete.jsonConfiguration50 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-h1b-s30-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_60/actor/.worker_sidecars_ready_world_size_2_rank_0.jsonConfiguration83 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-h1b-s30-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_60/actor/.worker_sidecars_ready_world_size_2_rank_1.jsonConfiguration83 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-h1b-s30-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_60/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-h1b-s30-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_60/actor/huggingface/config.jsonConfiguration1.6 KB —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-h1b-s30-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_60/actor/huggingface/generation_config.jsonConfiguration139 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-h1b-s30-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_75/actor/.async_checkpoint_ready_world_size_2_rank_0.jsonConfiguration369 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-h1b-s30-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_75/actor/.async_checkpoint_ready_world_size_2_rank_1.jsonConfiguration182 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-h1b-s30-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_75/actor/.async_checkpoint_started_world_size_2_rank_0.jsonConfiguration61 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-h1b-s30-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_75/actor/.async_checkpoint_started_world_size_2_rank_1.jsonConfiguration61 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-h1b-s30-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_75/actor/.checkpoint_complete.jsonConfiguration50 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-h1b-s30-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_75/actor/.worker_sidecars_ready_world_size_2_rank_0.jsonConfiguration83 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-h1b-s30-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_75/actor/.worker_sidecars_ready_world_size_2_rank_1.jsonConfiguration83 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-h1b-s30-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_75/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-h1b-s30-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_75/actor/huggingface/config.jsonConfiguration1.6 KB —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-h1b-s30-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_75/actor/huggingface/generation_config.jsonConfiguration139 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-h1b-s30-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_90/actor/.async_checkpoint_ready_world_size_2_rank_0.jsonConfiguration369 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-h1b-s30-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_90/actor/.async_checkpoint_ready_world_size_2_rank_1.jsonConfiguration182 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-h1b-s30-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_90/actor/.async_checkpoint_started_world_size_2_rank_0.jsonConfiguration61 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-h1b-s30-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_90/actor/.async_checkpoint_started_world_size_2_rank_1.jsonConfiguration61 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-h1b-s30-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_90/actor/.checkpoint_complete.jsonConfiguration50 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-h1b-s30-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_90/actor/.worker_sidecars_ready_world_size_2_rank_0.jsonConfiguration83 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-h1b-s30-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_90/actor/.worker_sidecars_ready_world_size_2_rank_1.jsonConfiguration83 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-h1b-s30-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_90/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-h1b-s30-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_90/actor/huggingface/config.jsonConfiguration1.6 KB —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-h1b-s30-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_90/actor/huggingface/generation_config.jsonConfiguration139 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-h1b-s30-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/latest_checkpoint.jsonConfiguration512 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/best_validation_checkpoint.jsonConfiguration231 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_120/actor/.async_checkpoint_ready_world_size_2_rank_0.jsonConfiguration370 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_120/actor/.async_checkpoint_ready_world_size_2_rank_1.jsonConfiguration183 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_120/actor/.async_checkpoint_started_world_size_2_rank_0.jsonConfiguration62 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_120/actor/.async_checkpoint_started_world_size_2_rank_1.jsonConfiguration62 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_120/actor/.checkpoint_complete.jsonConfiguration51 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_120/actor/.worker_sidecars_ready_world_size_2_rank_0.jsonConfiguration84 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_120/actor/.worker_sidecars_ready_world_size_2_rank_1.jsonConfiguration84 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_120/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_120/actor/huggingface/config.jsonConfiguration1.6 KB —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_120/actor/huggingface/generation_config.jsonConfiguration139 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_135/actor/.async_checkpoint_ready_world_size_2_rank_0.jsonConfiguration370 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_135/actor/.async_checkpoint_ready_world_size_2_rank_1.jsonConfiguration183 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_135/actor/.async_checkpoint_started_world_size_2_rank_0.jsonConfiguration62 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_135/actor/.async_checkpoint_started_world_size_2_rank_1.jsonConfiguration62 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_135/actor/.checkpoint_complete.jsonConfiguration51 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_135/actor/.worker_sidecars_ready_world_size_2_rank_0.jsonConfiguration84 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_135/actor/.worker_sidecars_ready_world_size_2_rank_1.jsonConfiguration84 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_135/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_135/actor/huggingface/config.jsonConfiguration1.6 KB —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_135/actor/huggingface/generation_config.jsonConfiguration139 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_15/actor/.async_checkpoint_ready_world_size_2_rank_0.jsonConfiguration369 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_15/actor/.async_checkpoint_ready_world_size_2_rank_1.jsonConfiguration182 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_15/actor/.async_checkpoint_started_world_size_2_rank_0.jsonConfiguration61 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_15/actor/.async_checkpoint_started_world_size_2_rank_1.jsonConfiguration61 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_15/actor/.checkpoint_complete.jsonConfiguration50 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_15/actor/.worker_sidecars_ready_world_size_2_rank_0.jsonConfiguration83 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_15/actor/.worker_sidecars_ready_world_size_2_rank_1.jsonConfiguration83 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_15/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_15/actor/huggingface/config.jsonConfiguration1.6 KB —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_15/actor/huggingface/generation_config.jsonConfiguration139 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_150/actor/.async_checkpoint_ready_world_size_2_rank_0.jsonConfiguration370 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_150/actor/.async_checkpoint_ready_world_size_2_rank_1.jsonConfiguration183 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_150/actor/.async_checkpoint_started_world_size_2_rank_0.jsonConfiguration62 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_150/actor/.async_checkpoint_started_world_size_2_rank_1.jsonConfiguration62 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_150/actor/.checkpoint_complete.jsonConfiguration51 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_150/actor/.worker_sidecars_ready_world_size_2_rank_0.jsonConfiguration84 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_150/actor/.worker_sidecars_ready_world_size_2_rank_1.jsonConfiguration84 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_150/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_150/actor/huggingface/config.jsonConfiguration1.6 KB —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_150/actor/huggingface/generation_config.jsonConfiguration139 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_30/actor/.async_checkpoint_ready_world_size_2_rank_0.jsonConfiguration369 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_30/actor/.async_checkpoint_ready_world_size_2_rank_1.jsonConfiguration182 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_30/actor/.async_checkpoint_started_world_size_2_rank_0.jsonConfiguration61 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_30/actor/.async_checkpoint_started_world_size_2_rank_1.jsonConfiguration61 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_30/actor/.checkpoint_complete.jsonConfiguration50 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_30/actor/.worker_sidecars_ready_world_size_2_rank_0.jsonConfiguration83 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_30/actor/.worker_sidecars_ready_world_size_2_rank_1.jsonConfiguration83 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_30/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_30/actor/huggingface/config.jsonConfiguration1.6 KB —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_30/actor/huggingface/generation_config.jsonConfiguration139 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_60/actor/.async_checkpoint_ready_world_size_2_rank_0.jsonConfiguration369 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_60/actor/.async_checkpoint_ready_world_size_2_rank_1.jsonConfiguration182 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_60/actor/.async_checkpoint_started_world_size_2_rank_0.jsonConfiguration61 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_60/actor/.async_checkpoint_started_world_size_2_rank_1.jsonConfiguration61 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_60/actor/.checkpoint_complete.jsonConfiguration50 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_60/actor/.worker_sidecars_ready_world_size_2_rank_0.jsonConfiguration83 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_60/actor/.worker_sidecars_ready_world_size_2_rank_1.jsonConfiguration83 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_60/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_60/actor/huggingface/config.jsonConfiguration1.6 KB —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_60/actor/huggingface/generation_config.jsonConfiguration139 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_75/actor/.async_checkpoint_ready_world_size_2_rank_0.jsonConfiguration369 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_75/actor/.async_checkpoint_ready_world_size_2_rank_1.jsonConfiguration182 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_75/actor/.async_checkpoint_started_world_size_2_rank_0.jsonConfiguration61 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_75/actor/.async_checkpoint_started_world_size_2_rank_1.jsonConfiguration61 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_75/actor/.checkpoint_complete.jsonConfiguration50 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_75/actor/.worker_sidecars_ready_world_size_2_rank_0.jsonConfiguration83 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_75/actor/.worker_sidecars_ready_world_size_2_rank_1.jsonConfiguration83 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_75/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_75/actor/huggingface/config.jsonConfiguration1.6 KB —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_75/actor/huggingface/generation_config.jsonConfiguration139 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_90/actor/.async_checkpoint_ready_world_size_2_rank_0.jsonConfiguration369 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_90/actor/.async_checkpoint_ready_world_size_2_rank_1.jsonConfiguration182 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_90/actor/.async_checkpoint_started_world_size_2_rank_0.jsonConfiguration61 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_90/actor/.async_checkpoint_started_world_size_2_rank_1.jsonConfiguration61 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_90/actor/.checkpoint_complete.jsonConfiguration50 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_90/actor/.worker_sidecars_ready_world_size_2_rank_0.jsonConfiguration83 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_90/actor/.worker_sidecars_ready_world_size_2_rank_1.jsonConfiguration83 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_90/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_90/actor/huggingface/config.jsonConfiguration1.6 KB —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/global_step_90/actor/huggingface/generation_config.jsonConfiguration139 B —
experiments/weak_to_strong/reasoning/color_cube_rotation/ours/260730-rcd-color_cube_rotation-q3-8b-base-t4b-s105-lp0p5-lm0to0p5-s75-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb32-dp2/latest_checkpoint.jsonConfiguration507 B —
experiments/weak_to_strong/reasoning/countdown/baseline/260721-grpo-countdown-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_135/actor/.async_checkpoint_ready_world_size_4_rank_0.jsonConfiguration370 B —
experiments/weak_to_strong/reasoning/countdown/baseline/260721-grpo-countdown-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_135/actor/.async_checkpoint_ready_world_size_4_rank_1.jsonConfiguration183 B —
experiments/weak_to_strong/reasoning/countdown/baseline/260721-grpo-countdown-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_135/actor/.async_checkpoint_ready_world_size_4_rank_2.jsonConfiguration183 B —
experiments/weak_to_strong/reasoning/countdown/baseline/260721-grpo-countdown-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_135/actor/.async_checkpoint_ready_world_size_4_rank_3.jsonConfiguration183 B —
experiments/weak_to_strong/reasoning/countdown/baseline/260721-grpo-countdown-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_135/actor/.async_checkpoint_started_world_size_4_rank_0.jsonConfiguration62 B —
experiments/weak_to_strong/reasoning/countdown/baseline/260721-grpo-countdown-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_135/actor/.async_checkpoint_started_world_size_4_rank_1.jsonConfiguration62 B —
experiments/weak_to_strong/reasoning/countdown/baseline/260721-grpo-countdown-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_135/actor/.async_checkpoint_started_world_size_4_rank_2.jsonConfiguration62 B —
experiments/weak_to_strong/reasoning/countdown/baseline/260721-grpo-countdown-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_135/actor/.async_checkpoint_started_world_size_4_rank_3.jsonConfiguration62 B —
experiments/weak_to_strong/reasoning/countdown/baseline/260721-grpo-countdown-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_135/actor/.checkpoint_complete.jsonConfiguration51 B —
experiments/weak_to_strong/reasoning/countdown/baseline/260721-grpo-countdown-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_135/actor/.worker_sidecars_ready_world_size_4_rank_0.jsonConfiguration84 B —
experiments/weak_to_strong/reasoning/countdown/baseline/260721-grpo-countdown-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_135/actor/.worker_sidecars_ready_world_size_4_rank_1.jsonConfiguration84 B —
experiments/weak_to_strong/reasoning/countdown/baseline/260721-grpo-countdown-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_135/actor/.worker_sidecars_ready_world_size_4_rank_2.jsonConfiguration84 B —
experiments/weak_to_strong/reasoning/countdown/baseline/260721-grpo-countdown-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_135/actor/.worker_sidecars_ready_world_size_4_rank_3.jsonConfiguration84 B —
experiments/weak_to_strong/reasoning/countdown/baseline/260721-grpo-countdown-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_135/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/reasoning/countdown/baseline/260721-grpo-countdown-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_135/actor/huggingface/config.jsonConfiguration1.6 KB —
experiments/weak_to_strong/reasoning/countdown/baseline/260721-grpo-countdown-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_135/actor/huggingface/generation_config.jsonConfiguration139 B —
experiments/weak_to_strong/reasoning/countdown/baseline/260721-grpo-countdown-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_150/actor/.async_checkpoint_ready_world_size_4_rank_0.jsonConfiguration370 B —
experiments/weak_to_strong/reasoning/countdown/baseline/260721-grpo-countdown-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_150/actor/.async_checkpoint_ready_world_size_4_rank_1.jsonConfiguration183 B —
experiments/weak_to_strong/reasoning/countdown/baseline/260721-grpo-countdown-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_150/actor/.async_checkpoint_ready_world_size_4_rank_2.jsonConfiguration183 B —
experiments/weak_to_strong/reasoning/countdown/baseline/260721-grpo-countdown-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_150/actor/.async_checkpoint_ready_world_size_4_rank_3.jsonConfiguration183 B —
experiments/weak_to_strong/reasoning/countdown/baseline/260721-grpo-countdown-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_150/actor/.async_checkpoint_started_world_size_4_rank_0.jsonConfiguration62 B —
experiments/weak_to_strong/reasoning/countdown/baseline/260721-grpo-countdown-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_150/actor/.async_checkpoint_started_world_size_4_rank_1.jsonConfiguration62 B —
experiments/weak_to_strong/reasoning/countdown/baseline/260721-grpo-countdown-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_150/actor/.async_checkpoint_started_world_size_4_rank_2.jsonConfiguration62 B —
experiments/weak_to_strong/reasoning/countdown/baseline/260721-grpo-countdown-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_150/actor/.async_checkpoint_started_world_size_4_rank_3.jsonConfiguration62 B —
experiments/weak_to_strong/reasoning/countdown/baseline/260721-grpo-countdown-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_150/actor/.checkpoint_complete.jsonConfiguration51 B —
experiments/weak_to_strong/reasoning/countdown/baseline/260721-grpo-countdown-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_150/actor/.worker_sidecars_ready_world_size_4_rank_0.jsonConfiguration84 B —
experiments/weak_to_strong/reasoning/countdown/baseline/260721-grpo-countdown-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_150/actor/.worker_sidecars_ready_world_size_4_rank_1.jsonConfiguration84 B —
experiments/weak_to_strong/reasoning/countdown/baseline/260721-grpo-countdown-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_150/actor/.worker_sidecars_ready_world_size_4_rank_2.jsonConfiguration84 B —
experiments/weak_to_strong/reasoning/countdown/baseline/260721-grpo-countdown-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_150/actor/.worker_sidecars_ready_world_size_4_rank_3.jsonConfiguration84 B —
experiments/weak_to_strong/reasoning/countdown/baseline/260721-grpo-countdown-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_150/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/reasoning/countdown/baseline/260721-grpo-countdown-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_150/actor/huggingface/config.jsonConfiguration1.6 KB —
experiments/weak_to_strong/reasoning/countdown/baseline/260721-grpo-countdown-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_150/actor/huggingface/generation_config.jsonConfiguration139 B —
experiments/weak_to_strong/reasoning/countdown/baseline/260721-grpo-countdown-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/latest_checkpoint.jsonConfiguration361 B —
experiments/weak_to_strong/reasoning/countdown/distill_baseline/260730-sampledrkl-countdown-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/best_validation_checkpoint.jsonConfiguration222 B —
experiments/weak_to_strong/reasoning/countdown/distill_baseline/260730-sampledrkl-countdown-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_120/actor/.async_checkpoint_ready_world_size_2_rank_0.jsonConfiguration370 B —
experiments/weak_to_strong/reasoning/countdown/distill_baseline/260730-sampledrkl-countdown-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_120/actor/.async_checkpoint_ready_world_size_2_rank_1.jsonConfiguration183 B —
experiments/weak_to_strong/reasoning/countdown/distill_baseline/260730-sampledrkl-countdown-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_120/actor/.async_checkpoint_started_world_size_2_rank_0.jsonConfiguration62 B —
experiments/weak_to_strong/reasoning/countdown/distill_baseline/260730-sampledrkl-countdown-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_120/actor/.async_checkpoint_started_world_size_2_rank_1.jsonConfiguration62 B —
experiments/weak_to_strong/reasoning/countdown/distill_baseline/260730-sampledrkl-countdown-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_120/actor/.checkpoint_complete.jsonConfiguration51 B —
experiments/weak_to_strong/reasoning/countdown/distill_baseline/260730-sampledrkl-countdown-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_120/actor/.worker_sidecars_ready_world_size_2_rank_0.jsonConfiguration171 B —
experiments/weak_to_strong/reasoning/countdown/distill_baseline/260730-sampledrkl-countdown-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_120/actor/.worker_sidecars_ready_world_size_2_rank_1.jsonConfiguration171 B —
experiments/weak_to_strong/reasoning/countdown/distill_baseline/260730-sampledrkl-countdown-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_120/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/reasoning/countdown/distill_baseline/260730-sampledrkl-countdown-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_120/actor/huggingface/config.jsonConfiguration1.6 KB —
experiments/weak_to_strong/reasoning/countdown/distill_baseline/260730-sampledrkl-countdown-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_120/actor/huggingface/generation_config.jsonConfiguration139 B —
experiments/weak_to_strong/reasoning/countdown/distill_baseline/260730-sampledrkl-countdown-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_135/actor/.async_checkpoint_ready_world_size_2_rank_0.jsonConfiguration370 B —
experiments/weak_to_strong/reasoning/countdown/distill_baseline/260730-sampledrkl-countdown-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_135/actor/.async_checkpoint_ready_world_size_2_rank_1.jsonConfiguration183 B —
experiments/weak_to_strong/reasoning/countdown/distill_baseline/260730-sampledrkl-countdown-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_135/actor/.async_checkpoint_started_world_size_2_rank_0.jsonConfiguration62 B —
experiments/weak_to_strong/reasoning/countdown/distill_baseline/260730-sampledrkl-countdown-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_135/actor/.async_checkpoint_started_world_size_2_rank_1.jsonConfiguration62 B —
experiments/weak_to_strong/reasoning/countdown/distill_baseline/260730-sampledrkl-countdown-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_135/actor/.checkpoint_complete.jsonConfiguration51 B —
experiments/weak_to_strong/reasoning/countdown/distill_baseline/260730-sampledrkl-countdown-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_135/actor/.worker_sidecars_ready_world_size_2_rank_0.jsonConfiguration171 B —
experiments/weak_to_strong/reasoning/countdown/distill_baseline/260730-sampledrkl-countdown-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_135/actor/.worker_sidecars_ready_world_size_2_rank_1.jsonConfiguration171 B —
experiments/weak_to_strong/reasoning/countdown/distill_baseline/260730-sampledrkl-countdown-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_135/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/reasoning/countdown/distill_baseline/260730-sampledrkl-countdown-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_135/actor/huggingface/config.jsonConfiguration1.6 KB —
experiments/weak_to_strong/reasoning/countdown/distill_baseline/260730-sampledrkl-countdown-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_135/actor/huggingface/generation_config.jsonConfiguration139 B —
experiments/weak_to_strong/reasoning/countdown/distill_baseline/260730-sampledrkl-countdown-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_15/actor/.async_checkpoint_ready_world_size_2_rank_0.jsonConfiguration369 B —
experiments/weak_to_strong/reasoning/countdown/distill_baseline/260730-sampledrkl-countdown-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_15/actor/.async_checkpoint_ready_world_size_2_rank_1.jsonConfiguration182 B —
experiments/weak_to_strong/reasoning/countdown/distill_baseline/260730-sampledrkl-countdown-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_15/actor/.async_checkpoint_started_world_size_2_rank_0.jsonConfiguration61 B —
experiments/weak_to_strong/reasoning/countdown/distill_baseline/260730-sampledrkl-countdown-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_15/actor/.async_checkpoint_started_world_size_2_rank_1.jsonConfiguration61 B —
experiments/weak_to_strong/reasoning/countdown/distill_baseline/260730-sampledrkl-countdown-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_15/actor/.checkpoint_complete.jsonConfiguration50 B —
experiments/weak_to_strong/reasoning/countdown/distill_baseline/260730-sampledrkl-countdown-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_15/actor/.worker_sidecars_ready_world_size_2_rank_0.jsonConfiguration170 B —
experiments/weak_to_strong/reasoning/countdown/distill_baseline/260730-sampledrkl-countdown-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_15/actor/.worker_sidecars_ready_world_size_2_rank_1.jsonConfiguration170 B —
experiments/weak_to_strong/reasoning/countdown/distill_baseline/260730-sampledrkl-countdown-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_15/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/reasoning/countdown/distill_baseline/260730-sampledrkl-countdown-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_15/actor/huggingface/config.jsonConfiguration1.6 KB —
experiments/weak_to_strong/reasoning/countdown/distill_baseline/260730-sampledrkl-countdown-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_15/actor/huggingface/generation_config.jsonConfiguration139 B —
experiments/weak_to_strong/reasoning/countdown/distill_baseline/260730-sampledrkl-countdown-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_150/actor/.async_checkpoint_ready_world_size_2_rank_0.jsonConfiguration370 B —
experiments/weak_to_strong/reasoning/countdown/distill_baseline/260730-sampledrkl-countdown-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_150/actor/.async_checkpoint_ready_world_size_2_rank_1.jsonConfiguration183 B —
experiments/weak_to_strong/reasoning/countdown/distill_baseline/260730-sampledrkl-countdown-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_150/actor/.async_checkpoint_started_world_size_2_rank_0.jsonConfiguration62 B —
experiments/weak_to_strong/reasoning/countdown/distill_baseline/260730-sampledrkl-countdown-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_150/actor/.async_checkpoint_started_world_size_2_rank_1.jsonConfiguration62 B —
experiments/weak_to_strong/reasoning/countdown/distill_baseline/260730-sampledrkl-countdown-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_150/actor/.checkpoint_complete.jsonConfiguration51 B —
experiments/weak_to_strong/reasoning/countdown/distill_baseline/260730-sampledrkl-countdown-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_150/actor/.worker_sidecars_ready_world_size_2_rank_0.jsonConfiguration171 B —
experiments/weak_to_strong/reasoning/countdown/distill_baseline/260730-sampledrkl-countdown-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_150/actor/.worker_sidecars_ready_world_size_2_rank_1.jsonConfiguration171 B —
experiments/weak_to_strong/reasoning/countdown/distill_baseline/260730-sampledrkl-countdown-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_150/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/reasoning/countdown/distill_baseline/260730-sampledrkl-countdown-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_150/actor/huggingface/config.jsonConfiguration1.6 KB —
experiments/weak_to_strong/reasoning/countdown/distill_baseline/260730-sampledrkl-countdown-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_150/actor/huggingface/generation_config.jsonConfiguration139 B —
experiments/weak_to_strong/reasoning/countdown/distill_baseline/260730-sampledrkl-countdown-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_30/actor/.async_checkpoint_ready_world_size_2_rank_0.jsonConfiguration369 B —
experiments/weak_to_strong/reasoning/countdown/distill_baseline/260730-sampledrkl-countdown-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_30/actor/.async_checkpoint_ready_world_size_2_rank_1.jsonConfiguration182 B —
experiments/weak_to_strong/reasoning/countdown/distill_baseline/260730-sampledrkl-countdown-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_30/actor/.async_checkpoint_started_world_size_2_rank_0.jsonConfiguration61 B —
experiments/weak_to_strong/reasoning/countdown/distill_baseline/260730-sampledrkl-countdown-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_30/actor/.async_checkpoint_started_world_size_2_rank_1.jsonConfiguration61 B —
experiments/weak_to_strong/reasoning/countdown/distill_baseline/260730-sampledrkl-countdown-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_30/actor/.checkpoint_complete.jsonConfiguration50 B —
experiments/weak_to_strong/reasoning/countdown/distill_baseline/260730-sampledrkl-countdown-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_30/actor/.worker_sidecars_ready_world_size_2_rank_0.jsonConfiguration170 B —
experiments/weak_to_strong/reasoning/countdown/distill_baseline/260730-sampledrkl-countdown-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_30/actor/.worker_sidecars_ready_world_size_2_rank_1.jsonConfiguration170 B —
experiments/weak_to_strong/reasoning/countdown/distill_baseline/260730-sampledrkl-countdown-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_30/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/reasoning/countdown/distill_baseline/260730-sampledrkl-countdown-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_30/actor/huggingface/config.jsonConfiguration1.6 KB —
experiments/weak_to_strong/reasoning/countdown/distill_baseline/260730-sampledrkl-countdown-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_30/actor/huggingface/generation_config.jsonConfiguration139 B —
experiments/weak_to_strong/reasoning/countdown/distill_baseline/260730-sampledrkl-countdown-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_60/actor/.async_checkpoint_ready_world_size_2_rank_0.jsonConfiguration369 B —
experiments/weak_to_strong/reasoning/countdown/distill_baseline/260730-sampledrkl-countdown-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_60/actor/.async_checkpoint_ready_world_size_2_rank_1.jsonConfiguration182 B —
experiments/weak_to_strong/reasoning/countdown/distill_baseline/260730-sampledrkl-countdown-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_60/actor/.async_checkpoint_started_world_size_2_rank_0.jsonConfiguration61 B —
experiments/weak_to_strong/reasoning/countdown/distill_baseline/260730-sampledrkl-countdown-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_60/actor/.async_checkpoint_started_world_size_2_rank_1.jsonConfiguration61 B —
experiments/weak_to_strong/reasoning/countdown/distill_baseline/260730-sampledrkl-countdown-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_60/actor/.checkpoint_complete.jsonConfiguration50 B —
experiments/weak_to_strong/reasoning/countdown/distill_baseline/260730-sampledrkl-countdown-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_60/actor/.worker_sidecars_ready_world_size_2_rank_0.jsonConfiguration170 B —
experiments/weak_to_strong/reasoning/countdown/distill_baseline/260730-sampledrkl-countdown-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_60/actor/.worker_sidecars_ready_world_size_2_rank_1.jsonConfiguration170 B —
experiments/weak_to_strong/reasoning/countdown/distill_baseline/260730-sampledrkl-countdown-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_60/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/reasoning/countdown/distill_baseline/260730-sampledrkl-countdown-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_60/actor/huggingface/config.jsonConfiguration1.6 KB —
experiments/weak_to_strong/reasoning/countdown/distill_baseline/260730-sampledrkl-countdown-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_60/actor/huggingface/generation_config.jsonConfiguration139 B —
experiments/weak_to_strong/reasoning/countdown/distill_baseline/260730-sampledrkl-countdown-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_90/actor/.async_checkpoint_ready_world_size_2_rank_0.jsonConfiguration369 B —
experiments/weak_to_strong/reasoning/countdown/distill_baseline/260730-sampledrkl-countdown-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_90/actor/.async_checkpoint_ready_world_size_2_rank_1.jsonConfiguration182 B —
experiments/weak_to_strong/reasoning/countdown/distill_baseline/260730-sampledrkl-countdown-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_90/actor/.async_checkpoint_started_world_size_2_rank_0.jsonConfiguration61 B —
experiments/weak_to_strong/reasoning/countdown/distill_baseline/260730-sampledrkl-countdown-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_90/actor/.async_checkpoint_started_world_size_2_rank_1.jsonConfiguration61 B —
experiments/weak_to_strong/reasoning/countdown/distill_baseline/260730-sampledrkl-countdown-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_90/actor/.checkpoint_complete.jsonConfiguration50 B —
experiments/weak_to_strong/reasoning/countdown/distill_baseline/260730-sampledrkl-countdown-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_90/actor/.worker_sidecars_ready_world_size_2_rank_0.jsonConfiguration170 B —
experiments/weak_to_strong/reasoning/countdown/distill_baseline/260730-sampledrkl-countdown-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_90/actor/.worker_sidecars_ready_world_size_2_rank_1.jsonConfiguration170 B —
experiments/weak_to_strong/reasoning/countdown/distill_baseline/260730-sampledrkl-countdown-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_90/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/reasoning/countdown/distill_baseline/260730-sampledrkl-countdown-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_90/actor/huggingface/config.jsonConfiguration1.6 KB —
experiments/weak_to_strong/reasoning/countdown/distill_baseline/260730-sampledrkl-countdown-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/global_step_90/actor/huggingface/generation_config.jsonConfiguration139 B —
experiments/weak_to_strong/reasoning/countdown/distill_baseline/260730-sampledrkl-countdown-q3-8b-base-t4b-s105-tr8k-va8k-save30-best-latestopt-static10k-tistoken-is0520-clip0p2-0p28-b64-mb32-dp2/latest_checkpoint.jsonConfiguration448 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/best_validation_checkpoint.jsonConfiguration227 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_100/actor/.async_checkpoint_ready_world_size_4_rank_0.jsonConfiguration370 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_100/actor/.async_checkpoint_ready_world_size_4_rank_1.jsonConfiguration183 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_100/actor/.async_checkpoint_ready_world_size_4_rank_2.jsonConfiguration183 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_100/actor/.async_checkpoint_ready_world_size_4_rank_3.jsonConfiguration183 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_100/actor/.async_checkpoint_started_world_size_4_rank_0.jsonConfiguration62 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_100/actor/.async_checkpoint_started_world_size_4_rank_1.jsonConfiguration62 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_100/actor/.async_checkpoint_started_world_size_4_rank_2.jsonConfiguration62 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_100/actor/.async_checkpoint_started_world_size_4_rank_3.jsonConfiguration62 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_100/actor/.checkpoint_complete.jsonConfiguration51 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_100/actor/.worker_sidecars_ready_world_size_4_rank_0.jsonConfiguration84 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_100/actor/.worker_sidecars_ready_world_size_4_rank_1.jsonConfiguration84 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_100/actor/.worker_sidecars_ready_world_size_4_rank_2.jsonConfiguration84 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_100/actor/.worker_sidecars_ready_world_size_4_rank_3.jsonConfiguration84 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_100/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_100/actor/huggingface/config.jsonConfiguration1.6 KB —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_100/actor/huggingface/generation_config.jsonConfiguration139 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_105/actor/.async_checkpoint_ready_world_size_4_rank_0.jsonConfiguration370 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_105/actor/.async_checkpoint_ready_world_size_4_rank_1.jsonConfiguration183 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_105/actor/.async_checkpoint_ready_world_size_4_rank_2.jsonConfiguration183 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_105/actor/.async_checkpoint_ready_world_size_4_rank_3.jsonConfiguration183 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_105/actor/.async_checkpoint_started_world_size_4_rank_0.jsonConfiguration62 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_105/actor/.async_checkpoint_started_world_size_4_rank_1.jsonConfiguration62 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_105/actor/.async_checkpoint_started_world_size_4_rank_2.jsonConfiguration62 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_105/actor/.async_checkpoint_started_world_size_4_rank_3.jsonConfiguration62 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_105/actor/.checkpoint_complete.jsonConfiguration51 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_105/actor/.worker_sidecars_ready_world_size_4_rank_0.jsonConfiguration84 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_105/actor/.worker_sidecars_ready_world_size_4_rank_1.jsonConfiguration84 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_105/actor/.worker_sidecars_ready_world_size_4_rank_2.jsonConfiguration84 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_105/actor/.worker_sidecars_ready_world_size_4_rank_3.jsonConfiguration84 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_105/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_105/actor/huggingface/config.jsonConfiguration1.6 KB —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_105/actor/huggingface/generation_config.jsonConfiguration139 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_120/actor/.async_checkpoint_ready_world_size_4_rank_0.jsonConfiguration370 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_120/actor/.async_checkpoint_ready_world_size_4_rank_1.jsonConfiguration183 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_120/actor/.async_checkpoint_ready_world_size_4_rank_2.jsonConfiguration183 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_120/actor/.async_checkpoint_ready_world_size_4_rank_3.jsonConfiguration183 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_120/actor/.async_checkpoint_started_world_size_4_rank_0.jsonConfiguration62 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_120/actor/.async_checkpoint_started_world_size_4_rank_1.jsonConfiguration62 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_120/actor/.async_checkpoint_started_world_size_4_rank_2.jsonConfiguration62 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_120/actor/.async_checkpoint_started_world_size_4_rank_3.jsonConfiguration62 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_120/actor/.checkpoint_complete.jsonConfiguration51 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_120/actor/.worker_sidecars_ready_world_size_4_rank_0.jsonConfiguration84 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_120/actor/.worker_sidecars_ready_world_size_4_rank_1.jsonConfiguration84 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_120/actor/.worker_sidecars_ready_world_size_4_rank_2.jsonConfiguration84 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_120/actor/.worker_sidecars_ready_world_size_4_rank_3.jsonConfiguration84 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_120/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_120/actor/huggingface/config.jsonConfiguration1.6 KB —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_120/actor/huggingface/generation_config.jsonConfiguration139 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_135/actor/.async_checkpoint_ready_world_size_4_rank_0.jsonConfiguration370 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_135/actor/.async_checkpoint_ready_world_size_4_rank_1.jsonConfiguration183 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_135/actor/.async_checkpoint_ready_world_size_4_rank_2.jsonConfiguration183 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_135/actor/.async_checkpoint_ready_world_size_4_rank_3.jsonConfiguration183 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_135/actor/.async_checkpoint_started_world_size_4_rank_0.jsonConfiguration62 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_135/actor/.async_checkpoint_started_world_size_4_rank_1.jsonConfiguration62 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_135/actor/.async_checkpoint_started_world_size_4_rank_2.jsonConfiguration62 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_135/actor/.async_checkpoint_started_world_size_4_rank_3.jsonConfiguration62 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_135/actor/.checkpoint_complete.jsonConfiguration51 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_135/actor/.worker_sidecars_ready_world_size_4_rank_0.jsonConfiguration84 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_135/actor/.worker_sidecars_ready_world_size_4_rank_1.jsonConfiguration84 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_135/actor/.worker_sidecars_ready_world_size_4_rank_2.jsonConfiguration84 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_135/actor/.worker_sidecars_ready_world_size_4_rank_3.jsonConfiguration84 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_135/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_135/actor/huggingface/config.jsonConfiguration1.6 KB —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_135/actor/huggingface/generation_config.jsonConfiguration139 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_15/actor/.async_checkpoint_ready_world_size_4_rank_0.jsonConfiguration369 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_15/actor/.async_checkpoint_ready_world_size_4_rank_1.jsonConfiguration182 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_15/actor/.async_checkpoint_ready_world_size_4_rank_2.jsonConfiguration182 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_15/actor/.async_checkpoint_ready_world_size_4_rank_3.jsonConfiguration182 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_15/actor/.async_checkpoint_started_world_size_4_rank_0.jsonConfiguration61 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_15/actor/.async_checkpoint_started_world_size_4_rank_1.jsonConfiguration61 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_15/actor/.async_checkpoint_started_world_size_4_rank_2.jsonConfiguration61 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_15/actor/.async_checkpoint_started_world_size_4_rank_3.jsonConfiguration61 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_15/actor/.checkpoint_complete.jsonConfiguration50 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_15/actor/.worker_sidecars_ready_world_size_4_rank_0.jsonConfiguration83 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_15/actor/.worker_sidecars_ready_world_size_4_rank_1.jsonConfiguration83 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_15/actor/.worker_sidecars_ready_world_size_4_rank_2.jsonConfiguration83 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_15/actor/.worker_sidecars_ready_world_size_4_rank_3.jsonConfiguration83 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_15/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_15/actor/huggingface/config.jsonConfiguration1.6 KB —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_15/actor/huggingface/generation_config.jsonConfiguration139 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_150/actor/.async_checkpoint_ready_world_size_4_rank_0.jsonConfiguration370 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_150/actor/.async_checkpoint_ready_world_size_4_rank_1.jsonConfiguration183 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_150/actor/.async_checkpoint_ready_world_size_4_rank_2.jsonConfiguration183 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_150/actor/.async_checkpoint_ready_world_size_4_rank_3.jsonConfiguration183 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_150/actor/.async_checkpoint_started_world_size_4_rank_0.jsonConfiguration62 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_150/actor/.async_checkpoint_started_world_size_4_rank_1.jsonConfiguration62 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_150/actor/.async_checkpoint_started_world_size_4_rank_2.jsonConfiguration62 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_150/actor/.async_checkpoint_started_world_size_4_rank_3.jsonConfiguration62 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_150/actor/.checkpoint_complete.jsonConfiguration51 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_150/actor/.worker_sidecars_ready_world_size_4_rank_0.jsonConfiguration84 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_150/actor/.worker_sidecars_ready_world_size_4_rank_1.jsonConfiguration84 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_150/actor/.worker_sidecars_ready_world_size_4_rank_2.jsonConfiguration84 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_150/actor/.worker_sidecars_ready_world_size_4_rank_3.jsonConfiguration84 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_150/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_150/actor/huggingface/config.jsonConfiguration1.6 KB —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_150/actor/huggingface/generation_config.jsonConfiguration139 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_30/actor/.async_checkpoint_ready_world_size_4_rank_0.jsonConfiguration369 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_30/actor/.async_checkpoint_ready_world_size_4_rank_1.jsonConfiguration182 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_30/actor/.async_checkpoint_ready_world_size_4_rank_2.jsonConfiguration182 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_30/actor/.async_checkpoint_ready_world_size_4_rank_3.jsonConfiguration182 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_30/actor/.async_checkpoint_started_world_size_4_rank_0.jsonConfiguration61 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_30/actor/.async_checkpoint_started_world_size_4_rank_1.jsonConfiguration61 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_30/actor/.async_checkpoint_started_world_size_4_rank_2.jsonConfiguration61 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_30/actor/.async_checkpoint_started_world_size_4_rank_3.jsonConfiguration61 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_30/actor/.checkpoint_complete.jsonConfiguration50 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_30/actor/.worker_sidecars_ready_world_size_4_rank_0.jsonConfiguration83 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_30/actor/.worker_sidecars_ready_world_size_4_rank_1.jsonConfiguration83 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_30/actor/.worker_sidecars_ready_world_size_4_rank_2.jsonConfiguration83 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_30/actor/.worker_sidecars_ready_world_size_4_rank_3.jsonConfiguration83 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_30/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_30/actor/huggingface/config.jsonConfiguration1.6 KB —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_30/actor/huggingface/generation_config.jsonConfiguration139 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_45/actor/.async_checkpoint_ready_world_size_4_rank_0.jsonConfiguration369 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_45/actor/.async_checkpoint_ready_world_size_4_rank_1.jsonConfiguration182 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_45/actor/.async_checkpoint_ready_world_size_4_rank_2.jsonConfiguration182 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_45/actor/.async_checkpoint_ready_world_size_4_rank_3.jsonConfiguration182 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_45/actor/.async_checkpoint_started_world_size_4_rank_0.jsonConfiguration61 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_45/actor/.async_checkpoint_started_world_size_4_rank_1.jsonConfiguration61 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_45/actor/.async_checkpoint_started_world_size_4_rank_2.jsonConfiguration61 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_45/actor/.async_checkpoint_started_world_size_4_rank_3.jsonConfiguration61 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_45/actor/.checkpoint_complete.jsonConfiguration50 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_45/actor/.worker_sidecars_ready_world_size_4_rank_0.jsonConfiguration83 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_45/actor/.worker_sidecars_ready_world_size_4_rank_1.jsonConfiguration83 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_45/actor/.worker_sidecars_ready_world_size_4_rank_2.jsonConfiguration83 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_45/actor/.worker_sidecars_ready_world_size_4_rank_3.jsonConfiguration83 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_45/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_45/actor/huggingface/config.jsonConfiguration1.6 KB —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_45/actor/huggingface/generation_config.jsonConfiguration139 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_50/actor/.async_checkpoint_ready_world_size_4_rank_0.jsonConfiguration369 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_50/actor/.async_checkpoint_ready_world_size_4_rank_1.jsonConfiguration182 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_50/actor/.async_checkpoint_ready_world_size_4_rank_2.jsonConfiguration182 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_50/actor/.async_checkpoint_ready_world_size_4_rank_3.jsonConfiguration182 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_50/actor/.async_checkpoint_started_world_size_4_rank_0.jsonConfiguration61 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_50/actor/.async_checkpoint_started_world_size_4_rank_1.jsonConfiguration61 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_50/actor/.async_checkpoint_started_world_size_4_rank_2.jsonConfiguration61 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_50/actor/.async_checkpoint_started_world_size_4_rank_3.jsonConfiguration61 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_50/actor/.checkpoint_complete.jsonConfiguration50 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_50/actor/.worker_sidecars_ready_world_size_4_rank_0.jsonConfiguration83 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_50/actor/.worker_sidecars_ready_world_size_4_rank_1.jsonConfiguration83 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_50/actor/.worker_sidecars_ready_world_size_4_rank_2.jsonConfiguration83 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_50/actor/.worker_sidecars_ready_world_size_4_rank_3.jsonConfiguration83 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_50/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_50/actor/huggingface/config.jsonConfiguration1.6 KB —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_50/actor/huggingface/generation_config.jsonConfiguration139 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_60/actor/.async_checkpoint_ready_world_size_4_rank_0.jsonConfiguration369 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_60/actor/.async_checkpoint_ready_world_size_4_rank_1.jsonConfiguration182 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_60/actor/.async_checkpoint_ready_world_size_4_rank_2.jsonConfiguration182 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_60/actor/.async_checkpoint_ready_world_size_4_rank_3.jsonConfiguration182 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_60/actor/.async_checkpoint_started_world_size_4_rank_0.jsonConfiguration61 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_60/actor/.async_checkpoint_started_world_size_4_rank_1.jsonConfiguration61 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_60/actor/.async_checkpoint_started_world_size_4_rank_2.jsonConfiguration61 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_60/actor/.async_checkpoint_started_world_size_4_rank_3.jsonConfiguration61 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_60/actor/.checkpoint_complete.jsonConfiguration50 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_60/actor/.worker_sidecars_ready_world_size_4_rank_0.jsonConfiguration83 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_60/actor/.worker_sidecars_ready_world_size_4_rank_1.jsonConfiguration83 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_60/actor/.worker_sidecars_ready_world_size_4_rank_2.jsonConfiguration83 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_60/actor/.worker_sidecars_ready_world_size_4_rank_3.jsonConfiguration83 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_60/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_60/actor/huggingface/config.jsonConfiguration1.6 KB —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_60/actor/huggingface/generation_config.jsonConfiguration139 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_75/actor/.async_checkpoint_ready_world_size_4_rank_0.jsonConfiguration369 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_75/actor/.async_checkpoint_ready_world_size_4_rank_1.jsonConfiguration182 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_75/actor/.async_checkpoint_ready_world_size_4_rank_2.jsonConfiguration182 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_75/actor/.async_checkpoint_ready_world_size_4_rank_3.jsonConfiguration182 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_75/actor/.async_checkpoint_started_world_size_4_rank_0.jsonConfiguration61 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_75/actor/.async_checkpoint_started_world_size_4_rank_1.jsonConfiguration61 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_75/actor/.async_checkpoint_started_world_size_4_rank_2.jsonConfiguration61 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_75/actor/.async_checkpoint_started_world_size_4_rank_3.jsonConfiguration61 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_75/actor/.checkpoint_complete.jsonConfiguration50 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_75/actor/.worker_sidecars_ready_world_size_4_rank_0.jsonConfiguration83 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_75/actor/.worker_sidecars_ready_world_size_4_rank_1.jsonConfiguration83 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_75/actor/.worker_sidecars_ready_world_size_4_rank_2.jsonConfiguration83 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_75/actor/.worker_sidecars_ready_world_size_4_rank_3.jsonConfiguration83 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_75/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_75/actor/huggingface/config.jsonConfiguration1.6 KB —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_75/actor/huggingface/generation_config.jsonConfiguration139 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_90/actor/.async_checkpoint_ready_world_size_4_rank_0.jsonConfiguration369 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_90/actor/.async_checkpoint_ready_world_size_4_rank_1.jsonConfiguration182 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_90/actor/.async_checkpoint_ready_world_size_4_rank_2.jsonConfiguration182 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_90/actor/.async_checkpoint_ready_world_size_4_rank_3.jsonConfiguration182 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_90/actor/.async_checkpoint_started_world_size_4_rank_0.jsonConfiguration61 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_90/actor/.async_checkpoint_started_world_size_4_rank_1.jsonConfiguration61 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_90/actor/.async_checkpoint_started_world_size_4_rank_2.jsonConfiguration61 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_90/actor/.async_checkpoint_started_world_size_4_rank_3.jsonConfiguration61 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_90/actor/.checkpoint_complete.jsonConfiguration50 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_90/actor/.worker_sidecars_ready_world_size_4_rank_0.jsonConfiguration83 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_90/actor/.worker_sidecars_ready_world_size_4_rank_1.jsonConfiguration83 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_90/actor/.worker_sidecars_ready_world_size_4_rank_2.jsonConfiguration83 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_90/actor/.worker_sidecars_ready_world_size_4_rank_3.jsonConfiguration83 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_90/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_90/actor/huggingface/config.jsonConfiguration1.6 KB —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/global_step_90/actor/huggingface/generation_config.jsonConfiguration139 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260721-grpo-knights_knaves-q3-8b-base-s150-tr8k-va8k-save15-pin50-100-150-b64-mb32-dp4/latest_checkpoint.jsonConfiguration376 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260729-grpo-knights_knaves-q3-0p6b-instruct-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb64-dp2/best_validation_checkpoint.jsonConfiguration226 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260729-grpo-knights_knaves-q3-0p6b-instruct-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb64-dp2/global_step_105/actor/.async_checkpoint_ready_world_size_2_rank_0.jsonConfiguration370 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260729-grpo-knights_knaves-q3-0p6b-instruct-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb64-dp2/global_step_105/actor/.async_checkpoint_ready_world_size_2_rank_1.jsonConfiguration183 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260729-grpo-knights_knaves-q3-0p6b-instruct-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb64-dp2/global_step_105/actor/.async_checkpoint_started_world_size_2_rank_0.jsonConfiguration62 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260729-grpo-knights_knaves-q3-0p6b-instruct-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb64-dp2/global_step_105/actor/.async_checkpoint_started_world_size_2_rank_1.jsonConfiguration62 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260729-grpo-knights_knaves-q3-0p6b-instruct-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb64-dp2/global_step_105/actor/.checkpoint_complete.jsonConfiguration51 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260729-grpo-knights_knaves-q3-0p6b-instruct-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb64-dp2/global_step_105/actor/.worker_sidecars_ready_world_size_2_rank_0.jsonConfiguration84 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260729-grpo-knights_knaves-q3-0p6b-instruct-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb64-dp2/global_step_105/actor/.worker_sidecars_ready_world_size_2_rank_1.jsonConfiguration84 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260729-grpo-knights_knaves-q3-0p6b-instruct-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb64-dp2/global_step_105/actor/fsdp_config.jsonConfiguration46 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260729-grpo-knights_knaves-q3-0p6b-instruct-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb64-dp2/global_step_105/actor/huggingface/config.jsonConfiguration1.5 KB —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260729-grpo-knights_knaves-q3-0p6b-instruct-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb64-dp2/global_step_105/actor/huggingface/generation_config.jsonConfiguration214 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260729-grpo-knights_knaves-q3-0p6b-instruct-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb64-dp2/global_step_120/actor/.async_checkpoint_ready_world_size_2_rank_0.jsonConfiguration370 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260729-grpo-knights_knaves-q3-0p6b-instruct-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb64-dp2/global_step_120/actor/.async_checkpoint_ready_world_size_2_rank_1.jsonConfiguration183 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260729-grpo-knights_knaves-q3-0p6b-instruct-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb64-dp2/global_step_120/actor/.async_checkpoint_started_world_size_2_rank_0.jsonConfiguration62 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260729-grpo-knights_knaves-q3-0p6b-instruct-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb64-dp2/global_step_120/actor/.async_checkpoint_started_world_size_2_rank_1.jsonConfiguration62 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260729-grpo-knights_knaves-q3-0p6b-instruct-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb64-dp2/global_step_120/actor/.checkpoint_complete.jsonConfiguration51 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260729-grpo-knights_knaves-q3-0p6b-instruct-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb64-dp2/global_step_120/actor/.worker_sidecars_ready_world_size_2_rank_0.jsonConfiguration84 B —
experiments/weak_to_strong/reasoning/knights_knaves/baseline/260729-grpo-knights_knaves-q3-0p6b-instruct-s150-tr8k-va8k-clip0p2-0p28-save30-best-eval15-tistoken-b64-mb64-dp2/global_step_120/actor/.worker_sidecars_ready_world_size_2_rank_1.jsonConfiguration84 B —

License and Download

License
Not stated by the source
Access
Open weights, no gate
Download size
4.3 TB
Download from Youngrok Park

Released by Youngrok Park through its official repository on Hugging Face.

Memory Requirements

PrecisionWeights in memory
As published4.3 TB

Weights only, from the published parameter count; the key-value cache and runtime add to this.