Skip to page content
SAVRN
Search Plan a project

Open-weight model

Checkpoints

by Hoang P hoangp111/Checkpoints

Checkpoints is an open-weight model from Hoang P. Its published files total 616.5 GB.

Parameters—
Context—
Weights511.9 GB
License—
AccessOpen weights
Monthly Downloads—

Model Card

The publisher has not written a card for this model.

Identity and Version

Repository
hoangp111/Checkpoints
Publisher
Hoang P
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
ad902026e6f573a57fd94ee32d28e19fdd4b6535
First published
2026-09-26
Last updated
2026-10-17

Files and Weights

2,656 files, 616.5 GB in total. The weights are 214 files totalling 511.9 GB in pt, safetensors.

Weights214 files · 511.9 GB
Configuration124 files · 60.1 KB
Tokenizer76 files · 322.5 MB
Other2241 files · 104.2 GB
Repository1 file · 321.3 KB
Every file
FileTypeSizeSHA-256
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/checkpoints/global_step_421/actor/extra_state_world_size_4_rank_0.ptWeights15.1 KB cfc4f3cd2175
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/checkpoints/global_step_421/actor/extra_state_world_size_4_rank_1.ptWeights15.1 KB d827e14b3938
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/checkpoints/global_step_421/actor/extra_state_world_size_4_rank_2.ptWeights15.1 KB b7c14ca01370
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/checkpoints/global_step_421/actor/extra_state_world_size_4_rank_3.ptWeights15.1 KB 1b20e595cb27
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/checkpoints/global_step_421/actor/model_world_size_4_rank_0.ptWeights494.2 MB ddcdbb4389a1
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/checkpoints/global_step_421/actor/model_world_size_4_rank_1.ptWeights494.2 MB c7e6c1bb9915
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/checkpoints/global_step_421/actor/model_world_size_4_rank_2.ptWeights494.2 MB 03a34a422209
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/checkpoints/global_step_421/actor/model_world_size_4_rank_3.ptWeights494.2 MB 97bed61617b3
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/checkpoints/global_step_421/actor/optim_world_size_4_rank_0.ptWeights988.4 MB 9befe4682cc5
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/checkpoints/global_step_421/actor/optim_world_size_4_rank_1.ptWeights988.4 MB e3545e953787
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/checkpoints/global_step_421/actor/optim_world_size_4_rank_2.ptWeights988.4 MB 77ab4ca6c060
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/checkpoints/global_step_421/actor/optim_world_size_4_rank_3.ptWeights988.4 MB 51dca68235c4
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/checkpoints/global_step_421/data.ptWeights7.3 KB 67fc71c54b3e
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/checkpoints/global_step_220/actor/extra_state_world_size_4_rank_0.ptWeights15.1 KB 40087c0473f7
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/checkpoints/global_step_220/actor/extra_state_world_size_4_rank_1.ptWeights15.2 KB 64be58be27cd
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/checkpoints/global_step_220/actor/extra_state_world_size_4_rank_2.ptWeights15.2 KB 0cd307ac38da
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/checkpoints/global_step_220/actor/extra_state_world_size_4_rank_3.ptWeights15.1 KB bb4927cd7bad
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/checkpoints/global_step_220/actor/model_world_size_4_rank_0.ptWeights1.5 GB 3529141396a3
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/checkpoints/global_step_220/actor/model_world_size_4_rank_1.ptWeights1.5 GB c7314f0b31b2
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/checkpoints/global_step_220/actor/model_world_size_4_rank_2.ptWeights1.5 GB 39dab2388b30
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/checkpoints/global_step_220/actor/model_world_size_4_rank_3.ptWeights1.5 GB 0f80cc5ca42e
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/checkpoints/global_step_220/actor/optim_world_size_4_rank_0.ptWeights3.1 GB e0c2cbde8b8e
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/checkpoints/global_step_220/actor/optim_world_size_4_rank_1.ptWeights3.1 GB 5ca49d415ebf
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/checkpoints/global_step_220/actor/optim_world_size_4_rank_2.ptWeights3.1 GB d5dca052c1a0
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/checkpoints/global_step_220/actor/optim_world_size_4_rank_3.ptWeights3.1 GB 58ee851fb073
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/checkpoints/global_step_220/data.ptWeights7.3 KB 052f37a7c592
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/checkpoints/global_step_421/actor/extra_state_world_size_4_rank_0.ptWeights15.1 KB cac67f5891f6
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/checkpoints/global_step_421/actor/extra_state_world_size_4_rank_1.ptWeights15.2 KB ee204f6bb3bf
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/checkpoints/global_step_421/actor/extra_state_world_size_4_rank_2.ptWeights15.2 KB 8bb77edab852
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/checkpoints/global_step_421/actor/extra_state_world_size_4_rank_3.ptWeights15.1 KB bd27f1c0dab3
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/checkpoints/global_step_421/actor/model_world_size_4_rank_0.ptWeights1.5 GB 40c7cc970308
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/checkpoints/global_step_421/actor/model_world_size_4_rank_1.ptWeights1.5 GB e4f34d38cbf1
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/checkpoints/global_step_421/actor/model_world_size_4_rank_2.ptWeights1.5 GB 039401dbfcee
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/checkpoints/global_step_421/actor/model_world_size_4_rank_3.ptWeights1.5 GB 6682ff1e04d0
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/checkpoints/global_step_421/actor/optim_world_size_4_rank_0.ptWeights3.1 GB d2d7d76e5137
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/checkpoints/global_step_421/actor/optim_world_size_4_rank_1.ptWeights3.1 GB 6d9967f3bb2f
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/checkpoints/global_step_421/actor/optim_world_size_4_rank_2.ptWeights3.1 GB 9a53b41a4ac3
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/checkpoints/global_step_421/actor/optim_world_size_4_rank_3.ptWeights3.1 GB 3e8954386ea0
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/checkpoints/global_step_421/data.ptWeights7.3 KB 4dcea6e68190
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/checkpoints/global_step_421/actor/extra_state_world_size_4_rank_0.ptWeights15.1 KB 36faf63843fb
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/checkpoints/global_step_421/actor/extra_state_world_size_4_rank_1.ptWeights15.1 KB c19c0b466987
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/checkpoints/global_step_421/actor/extra_state_world_size_4_rank_2.ptWeights15.1 KB ec19215412f7
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/checkpoints/global_step_421/actor/extra_state_world_size_4_rank_3.ptWeights15.1 KB ba2b41b9e071
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/checkpoints/global_step_421/actor/model_world_size_4_rank_0.ptWeights3.1 GB 5deab36cf234
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/checkpoints/global_step_421/actor/model_world_size_4_rank_1.ptWeights3.1 GB 5ab64683b01b
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/checkpoints/global_step_421/actor/model_world_size_4_rank_2.ptWeights3.1 GB bf78fb7b5414
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/checkpoints/global_step_421/actor/model_world_size_4_rank_3.ptWeights3.1 GB 4790baf8a942
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/checkpoints/global_step_421/actor/optim_world_size_4_rank_0.ptWeights6.2 GB c7829bc07f68
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/checkpoints/global_step_421/actor/optim_world_size_4_rank_1.ptWeights6.2 GB 2e0aab811009
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/checkpoints/global_step_421/actor/optim_world_size_4_rank_2.ptWeights6.2 GB f991a61794c9
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/checkpoints/global_step_421/actor/optim_world_size_4_rank_3.ptWeights6.2 GB 9f67397c551d
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/checkpoints/global_step_421/data.ptWeights7.3 KB 119ac745d097
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/checkpoints/global_step_421/actor/extra_state_world_size_4_rank_0.ptWeights15.1 KB 79d409d7eda0
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/checkpoints/global_step_421/actor/extra_state_world_size_4_rank_1.ptWeights15.1 KB adb909ae3c46
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/checkpoints/global_step_421/actor/extra_state_world_size_4_rank_2.ptWeights15.1 KB 6feb6909d2de
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/checkpoints/global_step_421/actor/extra_state_world_size_4_rank_3.ptWeights15.1 KB f3d2627379c4
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/checkpoints/global_step_421/actor/model_world_size_4_rank_0.ptWeights7.6 GB 14b9ad6c15c4
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/checkpoints/global_step_421/actor/model_world_size_4_rank_1.ptWeights7.6 GB e443b32500da
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/checkpoints/global_step_421/actor/model_world_size_4_rank_2.ptWeights7.6 GB 7847c54fe672
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/checkpoints/global_step_421/actor/model_world_size_4_rank_3.ptWeights7.6 GB 1fdbf7139d25
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/checkpoints/global_step_421/actor/optim_world_size_4_rank_0.ptWeights15.2 GB 90e0bdf80e8f
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/checkpoints/global_step_421/actor/optim_world_size_4_rank_1.ptWeights15.2 GB 8cdef705d1be
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/checkpoints/global_step_421/actor/optim_world_size_4_rank_2.ptWeights15.2 GB d577b1a35cb7
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/checkpoints/global_step_421/actor/optim_world_size_4_rank_3.ptWeights15.2 GB 07e0a09a2819
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/checkpoints/global_step_421/data.ptWeights7.3 KB 655ed34bd8b1
models/GRPO_Guru/Qwen2.5-0.5B-low-lr5e-5/checkpoints/global_step_106/actor/extra_state_world_size_4_rank_0.ptWeights15.1 KB 17452720493a
models/GRPO_Guru/Qwen2.5-0.5B-low-lr5e-5/checkpoints/global_step_106/actor/extra_state_world_size_4_rank_1.ptWeights15.1 KB bbcd88d1ff04
models/GRPO_Guru/Qwen2.5-0.5B-low-lr5e-5/checkpoints/global_step_106/actor/extra_state_world_size_4_rank_2.ptWeights15.1 KB 60f5c5239962
models/GRPO_Guru/Qwen2.5-0.5B-low-lr5e-5/checkpoints/global_step_106/actor/extra_state_world_size_4_rank_3.ptWeights15.1 KB 4980dc6467a1
models/GRPO_Guru/Qwen2.5-0.5B-low-lr5e-5/checkpoints/global_step_106/actor/model_world_size_4_rank_0.ptWeights494.2 MB f47a2ae3e9a1
models/GRPO_Guru/Qwen2.5-0.5B-low-lr5e-5/checkpoints/global_step_106/actor/model_world_size_4_rank_1.ptWeights494.2 MB 96b209fb7673
models/GRPO_Guru/Qwen2.5-0.5B-low-lr5e-5/checkpoints/global_step_106/actor/model_world_size_4_rank_2.ptWeights494.2 MB fc0c72f1089f
models/GRPO_Guru/Qwen2.5-0.5B-low-lr5e-5/checkpoints/global_step_106/actor/model_world_size_4_rank_3.ptWeights494.2 MB ce84d67b95b5
models/GRPO_Guru/Qwen2.5-0.5B-low-lr5e-5/checkpoints/global_step_106/actor/optim_world_size_4_rank_0.ptWeights988.4 MB c752b11eadab
models/GRPO_Guru/Qwen2.5-0.5B-low-lr5e-5/checkpoints/global_step_106/actor/optim_world_size_4_rank_1.ptWeights988.4 MB f151061883fa
models/GRPO_Guru/Qwen2.5-0.5B-low-lr5e-5/checkpoints/global_step_106/actor/optim_world_size_4_rank_2.ptWeights988.4 MB dc75e29051b6
models/GRPO_Guru/Qwen2.5-0.5B-low-lr5e-5/checkpoints/global_step_106/actor/optim_world_size_4_rank_3.ptWeights988.4 MB 2a5d3997090a
models/GRPO_Guru/Qwen2.5-0.5B-low-lr5e-5/checkpoints/global_step_106/data.ptWeights7.3 KB b803728d19dd
models/GRPO_Guru/Qwen2.5-1.5B-low-lr5e-5/checkpoints/global_step_106/actor/extra_state_world_size_4_rank_0.ptWeights15.2 KB 0544f13430ba
models/GRPO_Guru/Qwen2.5-1.5B-low-lr5e-5/checkpoints/global_step_106/actor/extra_state_world_size_4_rank_1.ptWeights15.1 KB 9e5d9fff1a7f
models/GRPO_Guru/Qwen2.5-1.5B-low-lr5e-5/checkpoints/global_step_106/actor/extra_state_world_size_4_rank_2.ptWeights15.1 KB 82ef4cfe36f2
models/GRPO_Guru/Qwen2.5-1.5B-low-lr5e-5/checkpoints/global_step_106/actor/extra_state_world_size_4_rank_3.ptWeights15.1 KB 5bf31ba460f0
models/GRPO_Guru/Qwen2.5-1.5B-low-lr5e-5/checkpoints/global_step_106/actor/model_world_size_4_rank_0.ptWeights1.5 GB f009c36cf269
models/GRPO_Guru/Qwen2.5-1.5B-low-lr5e-5/checkpoints/global_step_106/actor/model_world_size_4_rank_1.ptWeights1.5 GB 066f7cadc54f
models/GRPO_Guru/Qwen2.5-1.5B-low-lr5e-5/checkpoints/global_step_106/actor/model_world_size_4_rank_2.ptWeights1.5 GB f6dd30647713
models/GRPO_Guru/Qwen2.5-1.5B-low-lr5e-5/checkpoints/global_step_106/actor/model_world_size_4_rank_3.ptWeights1.5 GB 039f0b17ec57
models/GRPO_Guru/Qwen2.5-1.5B-low-lr5e-5/checkpoints/global_step_106/actor/optim_world_size_4_rank_0.ptWeights3.1 GB c1baf641758c
models/GRPO_Guru/Qwen2.5-1.5B-low-lr5e-5/checkpoints/global_step_106/actor/optim_world_size_4_rank_1.ptWeights3.1 GB e0645b456cd8
models/GRPO_Guru/Qwen2.5-1.5B-low-lr5e-5/checkpoints/global_step_106/actor/optim_world_size_4_rank_2.ptWeights3.1 GB f5cc88aee15b
models/GRPO_Guru/Qwen2.5-1.5B-low-lr5e-5/checkpoints/global_step_106/actor/optim_world_size_4_rank_3.ptWeights3.1 GB 2dfc462fa202
models/GRPO_Guru/Qwen2.5-1.5B-low-lr5e-5/checkpoints/global_step_106/data.ptWeights7.3 KB 85bfc4cb43c0
models/GRPO_Guru/Qwen2.5-3B-low-lr4e-5/checkpoints/global_step_106/actor/extra_state_world_size_4_rank_0.ptWeights15.1 KB 36cadd114848
models/GRPO_Guru/Qwen2.5-3B-low-lr4e-5/checkpoints/global_step_106/actor/extra_state_world_size_4_rank_1.ptWeights15.1 KB 52f9312efe72
models/GRPO_Guru/Qwen2.5-3B-low-lr4e-5/checkpoints/global_step_106/actor/extra_state_world_size_4_rank_2.ptWeights15.1 KB ea28d12d1b20
models/GRPO_Guru/Qwen2.5-3B-low-lr4e-5/checkpoints/global_step_106/actor/extra_state_world_size_4_rank_3.ptWeights15.1 KB ed35a50dc44b
models/GRPO_Guru/Qwen2.5-3B-low-lr4e-5/checkpoints/global_step_106/actor/model_world_size_4_rank_0.ptWeights3.1 GB 1fe6dd6d8dcd
models/GRPO_Guru/Qwen2.5-3B-low-lr4e-5/checkpoints/global_step_106/actor/model_world_size_4_rank_1.ptWeights3.1 GB c2fa2d7fea39
models/GRPO_Guru/Qwen2.5-3B-low-lr4e-5/checkpoints/global_step_106/actor/model_world_size_4_rank_2.ptWeights3.1 GB d505691dd0bb
models/GRPO_Guru/Qwen2.5-3B-low-lr4e-5/checkpoints/global_step_106/actor/model_world_size_4_rank_3.ptWeights3.1 GB ae1a7c546ddc
models/GRPO_Guru/Qwen2.5-3B-low-lr4e-5/checkpoints/global_step_106/actor/optim_world_size_4_rank_0.ptWeights6.2 GB aef00caeeb39
models/GRPO_Guru/Qwen2.5-3B-low-lr4e-5/checkpoints/global_step_106/actor/optim_world_size_4_rank_1.ptWeights6.2 GB 1cbbc46273bf
models/GRPO_Guru/Qwen2.5-3B-low-lr4e-5/checkpoints/global_step_106/actor/optim_world_size_4_rank_2.ptWeights6.2 GB d449396a1a52
models/GRPO_Guru/Qwen2.5-3B-low-lr4e-5/checkpoints/global_step_106/actor/optim_world_size_4_rank_3.ptWeights6.2 GB e1b5664c863b
models/GRPO_Guru/Qwen2.5-3B-low-lr4e-5/checkpoints/global_step_106/data.ptWeights7.3 KB 673fdca428e6
models/GRPO_Guru/Qwen2.5-7B-low-lr4e-5/checkpoints/global_step_106/actor/extra_state_world_size_4_rank_0.ptWeights15.1 KB b649157055e5
models/GRPO_Guru/Qwen2.5-7B-low-lr4e-5/checkpoints/global_step_106/actor/extra_state_world_size_4_rank_1.ptWeights15.1 KB 76e667922796
models/GRPO_Guru/Qwen2.5-7B-low-lr4e-5/checkpoints/global_step_106/actor/extra_state_world_size_4_rank_2.ptWeights15.1 KB cd1a16c81aac
models/GRPO_Guru/Qwen2.5-7B-low-lr4e-5/checkpoints/global_step_106/actor/extra_state_world_size_4_rank_3.ptWeights15.1 KB ec466623cce0
models/GRPO_Guru/Qwen2.5-7B-low-lr4e-5/checkpoints/global_step_106/actor/model_world_size_4_rank_0.ptWeights7.6 GB 3fefd7f30591
models/GRPO_Guru/Qwen2.5-7B-low-lr4e-5/checkpoints/global_step_106/actor/model_world_size_4_rank_1.ptWeights7.6 GB 3c91de010dd9
models/GRPO_Guru/Qwen2.5-7B-low-lr4e-5/checkpoints/global_step_106/actor/model_world_size_4_rank_2.ptWeights7.6 GB c1c67c0cfdc5
models/GRPO_Guru/Qwen2.5-7B-low-lr4e-5/checkpoints/global_step_106/actor/model_world_size_4_rank_3.ptWeights7.6 GB db0a659ffa97
models/GRPO_Guru/Qwen2.5-7B-low-lr4e-5/checkpoints/global_step_106/actor/optim_world_size_4_rank_0.ptWeights15.2 GB d2b0cc4fda51
models/GRPO_Guru/Qwen2.5-7B-low-lr4e-5/checkpoints/global_step_106/actor/optim_world_size_4_rank_1.ptWeights15.2 GB ebbdcd89dab9
models/GRPO_Guru/Qwen2.5-7B-low-lr4e-5/checkpoints/global_step_106/actor/optim_world_size_4_rank_2.ptWeights15.2 GB 7c0be3b00f9b
models/GRPO_Guru/Qwen2.5-7B-low-lr4e-5/checkpoints/global_step_106/actor/optim_world_size_4_rank_3.ptWeights15.2 GB 0118395f81fb
models/GRPO_Guru/Qwen2.5-7B-low-lr4e-5/checkpoints/global_step_106/data.ptWeights7.3 KB 0ab4a02933bf
models/GRPO_Guru/Qwen3-0.6B-Base/checkpoints/global_step_848/actor/extra_state_world_size_4_rank_0.ptWeights15.1 KB f089c80d0b39
models/GRPO_Guru/Qwen3-0.6B-Base/checkpoints/global_step_848/actor/extra_state_world_size_4_rank_1.ptWeights15.1 KB 8d3d28407aab
models/GRPO_Guru/Qwen3-0.6B-Base/checkpoints/global_step_848/actor/extra_state_world_size_4_rank_2.ptWeights15.1 KB 59496eb83cde
models/GRPO_Guru/Qwen3-0.6B-Base/checkpoints/global_step_848/actor/extra_state_world_size_4_rank_3.ptWeights15.2 KB 34256301757a
models/GRPO_Guru/Qwen3-0.6B-Base/checkpoints/global_step_848/actor/model_world_size_4_rank_0.ptWeights596.2 MB 183fa8c1110a
models/GRPO_Guru/Qwen3-0.6B-Base/checkpoints/global_step_848/actor/model_world_size_4_rank_1.ptWeights596.2 MB 252f29bdb71e
models/GRPO_Guru/Qwen3-0.6B-Base/checkpoints/global_step_848/actor/model_world_size_4_rank_2.ptWeights596.2 MB 0092eb0de89a
models/GRPO_Guru/Qwen3-0.6B-Base/checkpoints/global_step_848/actor/model_world_size_4_rank_3.ptWeights596.2 MB 8349199ac93c
models/GRPO_Guru/Qwen3-0.6B-Base/checkpoints/global_step_848/actor/optim_world_size_4_rank_0.ptWeights1.2 GB a74769b307a1
models/GRPO_Guru/Qwen3-0.6B-Base/checkpoints/global_step_848/actor/optim_world_size_4_rank_1.ptWeights1.2 GB 821314894c22
models/GRPO_Guru/Qwen3-0.6B-Base/checkpoints/global_step_848/actor/optim_world_size_4_rank_2.ptWeights1.2 GB 07aa2243558e
models/GRPO_Guru/Qwen3-0.6B-Base/checkpoints/global_step_848/actor/optim_world_size_4_rank_3.ptWeights1.2 GB 363b40e13370
models/GRPO_Guru/Qwen3-0.6B-Base/checkpoints/global_step_848/data.ptWeights7.3 KB dc1f2a7ab861
models/GRPO_Guru/Qwen3-1.7B-Base/checkpoints/global_step_848/actor/extra_state_world_size_4_rank_0.ptWeights15.1 KB ec073a454731
models/GRPO_Guru/Qwen3-1.7B-Base/checkpoints/global_step_848/actor/extra_state_world_size_4_rank_1.ptWeights15.1 KB 6b3e5f07c57a
models/GRPO_Guru/Qwen3-1.7B-Base/checkpoints/global_step_848/actor/extra_state_world_size_4_rank_2.ptWeights15.1 KB 899549b6faf6
models/GRPO_Guru/Qwen3-1.7B-Base/checkpoints/global_step_848/actor/extra_state_world_size_4_rank_3.ptWeights15.1 KB edced8a486b1
models/GRPO_Guru/Qwen3-1.7B-Base/checkpoints/global_step_848/actor/model_world_size_4_rank_0.ptWeights1.7 GB 506f5b422e58
models/GRPO_Guru/Qwen3-1.7B-Base/checkpoints/global_step_848/actor/model_world_size_4_rank_1.ptWeights1.7 GB 298e8a30d7ed
models/GRPO_Guru/Qwen3-1.7B-Base/checkpoints/global_step_848/actor/model_world_size_4_rank_2.ptWeights1.7 GB 2fbbe6c71cc8
models/GRPO_Guru/Qwen3-1.7B-Base/checkpoints/global_step_848/actor/model_world_size_4_rank_3.ptWeights1.7 GB 13b1e467d32e
models/GRPO_Guru/Qwen3-1.7B-Base/checkpoints/global_step_848/actor/optim_world_size_4_rank_0.ptWeights3.4 GB a6beec23efc6
models/GRPO_Guru/Qwen3-1.7B-Base/checkpoints/global_step_848/actor/optim_world_size_4_rank_1.ptWeights3.4 GB 440eaa9ae0e4
models/GRPO_Guru/Qwen3-1.7B-Base/checkpoints/global_step_848/actor/optim_world_size_4_rank_2.ptWeights3.4 GB 592a8f83069c
models/GRPO_Guru/Qwen3-1.7B-Base/checkpoints/global_step_848/actor/optim_world_size_4_rank_3.ptWeights3.4 GB f00def1d2966
models/GRPO_Guru/Qwen3-1.7B-Base/checkpoints/global_step_848/data.ptWeights7.3 KB dc0a8f4c404b
models/GRPO_Guru/Qwen3-4B-Base/checkpoints/global_step_848/actor/extra_state_world_size_4_rank_0.ptWeights15.1 KB 7ad96f97483b
models/GRPO_Guru/Qwen3-4B-Base/checkpoints/global_step_848/actor/extra_state_world_size_4_rank_1.ptWeights15.3 KB 6535d148e723
models/GRPO_Guru/Qwen3-4B-Base/checkpoints/global_step_848/actor/extra_state_world_size_4_rank_2.ptWeights15.1 KB e9b7fe212956
models/GRPO_Guru/Qwen3-4B-Base/checkpoints/global_step_848/actor/extra_state_world_size_4_rank_3.ptWeights15.1 KB 1dc3f09444a9
models/GRPO_Guru/Qwen3-4B-Base/checkpoints/global_step_848/actor/model_world_size_4_rank_0.ptWeights4.0 GB ba912df5b7c9
models/GRPO_Guru/Qwen3-4B-Base/checkpoints/global_step_848/actor/model_world_size_4_rank_1.ptWeights4.0 GB 2dc36c3c895b
models/GRPO_Guru/Qwen3-4B-Base/checkpoints/global_step_848/actor/model_world_size_4_rank_2.ptWeights4.0 GB c966730f0c38
models/GRPO_Guru/Qwen3-4B-Base/checkpoints/global_step_848/actor/model_world_size_4_rank_3.ptWeights4.0 GB e3f33790efc6
models/GRPO_Guru/Qwen3-4B-Base/checkpoints/global_step_848/actor/optim_world_size_4_rank_0.ptWeights8.0 GB 3f91527298f0
models/GRPO_Guru/Qwen3-4B-Base/checkpoints/global_step_848/actor/optim_world_size_4_rank_1.ptWeights8.0 GB c029b71b23c3
models/GRPO_Guru/Qwen3-4B-Base/checkpoints/global_step_848/actor/optim_world_size_4_rank_2.ptWeights8.0 GB c9996a1bec97
models/GRPO_Guru/Qwen3-4B-Base/checkpoints/global_step_848/actor/optim_world_size_4_rank_3.ptWeights8.0 GB cd2111fa5cfe
models/GRPO_Guru/Qwen3-4B-Base/checkpoints/global_step_848/data.ptWeights7.3 KB adc24311726d
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-0.6B-Base/checkpoints/global_step_848/actor/extra_state_world_size_4_rank_0.ptWeights15.1 KB 58d4738fb5f8
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-0.6B-Base/checkpoints/global_step_848/actor/extra_state_world_size_4_rank_1.ptWeights15.1 KB f9ec20decc73
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-0.6B-Base/checkpoints/global_step_848/actor/extra_state_world_size_4_rank_2.ptWeights15.1 KB 0245b7374af5
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-0.6B-Base/checkpoints/global_step_848/actor/extra_state_world_size_4_rank_3.ptWeights15.1 KB b0ad21da0e0d
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-0.6B-Base/checkpoints/global_step_848/actor/model_world_size_4_rank_0.ptWeights596.2 MB 51ecad3294b6
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-0.6B-Base/checkpoints/global_step_848/actor/model_world_size_4_rank_1.ptWeights596.2 MB 4110faa4248d
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-0.6B-Base/checkpoints/global_step_848/actor/model_world_size_4_rank_2.ptWeights596.2 MB 5ffd9b12d8d5
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-0.6B-Base/checkpoints/global_step_848/actor/model_world_size_4_rank_3.ptWeights596.2 MB ab31aa628d66
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-0.6B-Base/checkpoints/global_step_848/actor/optim_world_size_4_rank_0.ptWeights1.2 GB 8541425a1a6b
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-0.6B-Base/checkpoints/global_step_848/actor/optim_world_size_4_rank_1.ptWeights1.2 GB 5bfbc22de525
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-0.6B-Base/checkpoints/global_step_848/actor/optim_world_size_4_rank_2.ptWeights1.2 GB 04bc3f215460
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-0.6B-Base/checkpoints/global_step_848/actor/optim_world_size_4_rank_3.ptWeights1.2 GB b7ae0e04de24
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-0.6B-Base/checkpoints/global_step_848/data.ptWeights7.3 KB abe551e3ebff
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-1.7B-Base/checkpoints/global_step_848/actor/extra_state_world_size_4_rank_0.ptWeights15.2 KB 1946de11867a
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-1.7B-Base/checkpoints/global_step_848/actor/extra_state_world_size_4_rank_1.ptWeights15.1 KB 12a4321e79f0
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-1.7B-Base/checkpoints/global_step_848/actor/extra_state_world_size_4_rank_2.ptWeights15.1 KB def1d5a7d9ef
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-1.7B-Base/checkpoints/global_step_848/actor/extra_state_world_size_4_rank_3.ptWeights15.1 KB d5dc09a729b7
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-1.7B-Base/checkpoints/global_step_848/actor/model_world_size_4_rank_0.ptWeights1.7 GB 2f56db523ad7
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-1.7B-Base/checkpoints/global_step_848/actor/model_world_size_4_rank_1.ptWeights1.7 GB e4000c53c3ec
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-1.7B-Base/checkpoints/global_step_848/actor/model_world_size_4_rank_2.ptWeights1.7 GB 248fb4d010ab
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-1.7B-Base/checkpoints/global_step_848/actor/model_world_size_4_rank_3.ptWeights1.7 GB 936e2b091399
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-1.7B-Base/checkpoints/global_step_848/actor/optim_world_size_4_rank_0.ptWeights3.4 GB d9caddb32cb0
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-1.7B-Base/checkpoints/global_step_848/actor/optim_world_size_4_rank_1.ptWeights3.4 GB 8519bf7dc439
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-1.7B-Base/checkpoints/global_step_848/actor/optim_world_size_4_rank_2.ptWeights3.4 GB d0dc59cfcd6c
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-1.7B-Base/checkpoints/global_step_848/actor/optim_world_size_4_rank_3.ptWeights3.4 GB 9dc07e754baa
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-1.7B-Base/checkpoints/global_step_848/data.ptWeights7.3 KB b6a0d679ec88
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-4B-Base/checkpoints/global_step_820/actor/extra_state_world_size_4_rank_0.ptWeights15.1 KB 9cb10462dd3a
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-4B-Base/checkpoints/global_step_820/actor/extra_state_world_size_4_rank_1.ptWeights15.2 KB 53598efb05ce
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-4B-Base/checkpoints/global_step_820/actor/extra_state_world_size_4_rank_2.ptWeights15.1 KB 524eb30816d8
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-4B-Base/checkpoints/global_step_820/actor/extra_state_world_size_4_rank_3.ptWeights15.1 KB f62878cefbaa
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-4B-Base/checkpoints/global_step_820/actor/model_world_size_4_rank_0.ptWeights4.0 GB 8ae9e0d8eab5
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-4B-Base/checkpoints/global_step_820/actor/model_world_size_4_rank_1.ptWeights4.0 GB 24c8dc5724cc
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-4B-Base/checkpoints/global_step_820/actor/model_world_size_4_rank_2.ptWeights4.0 GB 251b8301a452
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-4B-Base/checkpoints/global_step_820/actor/model_world_size_4_rank_3.ptWeights4.0 GB 57f768a72a9e
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-4B-Base/checkpoints/global_step_820/actor/optim_world_size_4_rank_0.ptWeights8.0 GB 2a6ffe8e049c
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-4B-Base/checkpoints/global_step_820/actor/optim_world_size_4_rank_1.ptWeights8.0 GB fc4c1c437694
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-4B-Base/checkpoints/global_step_820/actor/optim_world_size_4_rank_2.ptWeights8.0 GB c054caf89cce
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-4B-Base/checkpoints/global_step_820/actor/optim_world_size_4_rank_3.ptWeights8.0 GB 21158e789e81
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-4B-Base/checkpoints/global_step_820/data.ptWeights7.3 KB 1da2ace5f41b
models/PrefixGRPO-R1x2-R2x8-Lnull_Guru/Qwen2.5-0.5B-low-lr5e-5/checkpoints/global_step_424/actor/extra_state_world_size_4_rank_0.ptWeights15.1 KB 96c622d14aaf
models/PrefixGRPO-R1x2-R2x8-Lnull_Guru/Qwen2.5-0.5B-low-lr5e-5/checkpoints/global_step_424/actor/extra_state_world_size_4_rank_1.ptWeights15.1 KB 20eab48e1737
models/PrefixGRPO-R1x2-R2x8-Lnull_Guru/Qwen2.5-0.5B-low-lr5e-5/checkpoints/global_step_424/actor/extra_state_world_size_4_rank_2.ptWeights15.1 KB 65981d7e95c9
models/PrefixGRPO-R1x2-R2x8-Lnull_Guru/Qwen2.5-0.5B-low-lr5e-5/checkpoints/global_step_424/actor/extra_state_world_size_4_rank_3.ptWeights15.1 KB 4df3a3a2530f
models/PrefixGRPO-R1x2-R2x8-Lnull_Guru/Qwen2.5-0.5B-low-lr5e-5/checkpoints/global_step_424/actor/model_world_size_4_rank_0.ptWeights494.2 MB 0370c973c31f
models/PrefixGRPO-R1x2-R2x8-Lnull_Guru/Qwen2.5-0.5B-low-lr5e-5/checkpoints/global_step_424/actor/model_world_size_4_rank_1.ptWeights494.2 MB 2e4183673fc9
models/PrefixGRPO-R1x2-R2x8-Lnull_Guru/Qwen2.5-0.5B-low-lr5e-5/checkpoints/global_step_424/actor/model_world_size_4_rank_2.ptWeights494.2 MB f236b229d444
models/PrefixGRPO-R1x2-R2x8-Lnull_Guru/Qwen2.5-0.5B-low-lr5e-5/checkpoints/global_step_424/actor/model_world_size_4_rank_3.ptWeights494.2 MB a2966ff2b87f
models/PrefixGRPO-R1x2-R2x8-Lnull_Guru/Qwen2.5-0.5B-low-lr5e-5/checkpoints/global_step_424/actor/optim_world_size_4_rank_0.ptWeights988.4 MB af168e02d0d1
models/PrefixGRPO-R1x2-R2x8-Lnull_Guru/Qwen2.5-0.5B-low-lr5e-5/checkpoints/global_step_424/actor/optim_world_size_4_rank_1.ptWeights988.4 MB 61b76241b845
models/PrefixGRPO-R1x2-R2x8-Lnull_Guru/Qwen2.5-0.5B-low-lr5e-5/checkpoints/global_step_424/actor/optim_world_size_4_rank_2.ptWeights988.4 MB a49bd9947db4
models/PrefixGRPO-R1x2-R2x8-Lnull_Guru/Qwen2.5-0.5B-low-lr5e-5/checkpoints/global_step_424/actor/optim_world_size_4_rank_3.ptWeights988.4 MB d12570d57e82
models/PrefixGRPO-R1x2-R2x8-Lnull_Guru/Qwen2.5-0.5B-low-lr5e-5/checkpoints/global_step_424/data.ptWeights7.3 KB 6c15bf344ce9
models/SFT/Qwen2.5-0.5B-low-lr5e-5/model.safetensorsWeights988.1 MB 92f817abc260
models/SFT/Qwen2.5-0.5B-medium-lr5e-5/model.safetensorsWeights988.1 MB 7d5c38dd157d
models/SFT/Qwen2.5-1.5B-low-lr5e-5/model.safetensorsWeights3.1 GB 1185550ff5b0
models/SFT/Qwen2.5-1.5B-medium-lr5e-5/model.safetensorsWeights3.1 GB 29fef0543ca0
models/SFT/Qwen2.5-3B-low-lr4e-5/model.safetensorsWeights6.2 GB 0a421dd0e74a
models/SFT/Qwen2.5-7B-low-lr4e-5/model.safetensorsWeights15.2 GB baa7471cd460
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/checkpoints/global_step_421/actor/fsdp_config.jsonConfiguration46 B —
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/checkpoints/global_step_421/actor/huggingface/added_tokens.jsonConfiguration605 B —
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/checkpoints/global_step_421/actor/huggingface/config.jsonConfiguration1.3 KB —
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/checkpoints/global_step_421/actor/huggingface/generation_config.jsonConfiguration117 B —
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/checkpoints/global_step_421/actor/huggingface/special_tokens_map.jsonConfiguration616 B —
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/checkpoints/global_step_421/transfer_queue/metadata.jsonConfiguration77 B —
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/checkpoints/global_step_421/transfer_queue/simple_storage/storage_unit_info.jsonConfiguration256 B —
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/checkpoints/global_step_220/actor/fsdp_config.jsonConfiguration46 B —
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/checkpoints/global_step_220/actor/huggingface/added_tokens.jsonConfiguration605 B —
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/checkpoints/global_step_220/actor/huggingface/config.jsonConfiguration1.4 KB —
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/checkpoints/global_step_220/actor/huggingface/generation_config.jsonConfiguration117 B —
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/checkpoints/global_step_220/actor/huggingface/special_tokens_map.jsonConfiguration616 B —
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/checkpoints/global_step_220/transfer_queue/metadata.jsonConfiguration77 B —
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/checkpoints/global_step_220/transfer_queue/simple_storage/storage_unit_info.jsonConfiguration256 B —
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/checkpoints/global_step_421/actor/fsdp_config.jsonConfiguration46 B —
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/checkpoints/global_step_421/actor/huggingface/added_tokens.jsonConfiguration605 B —
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/checkpoints/global_step_421/actor/huggingface/config.jsonConfiguration1.4 KB —
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/checkpoints/global_step_421/actor/huggingface/generation_config.jsonConfiguration117 B —
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/checkpoints/global_step_421/actor/huggingface/special_tokens_map.jsonConfiguration616 B —
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/checkpoints/global_step_421/transfer_queue/metadata.jsonConfiguration77 B —
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/checkpoints/global_step_421/transfer_queue/simple_storage/storage_unit_info.jsonConfiguration256 B —
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/checkpoints/global_step_421/actor/fsdp_config.jsonConfiguration46 B —
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/checkpoints/global_step_421/actor/huggingface/added_tokens.jsonConfiguration605 B —
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/checkpoints/global_step_421/actor/huggingface/config.jsonConfiguration1.6 KB —
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/checkpoints/global_step_421/actor/huggingface/generation_config.jsonConfiguration117 B —
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/checkpoints/global_step_421/actor/huggingface/special_tokens_map.jsonConfiguration616 B —
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/checkpoints/global_step_421/transfer_queue/metadata.jsonConfiguration77 B —
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/checkpoints/global_step_421/transfer_queue/simple_storage/storage_unit_info.jsonConfiguration256 B —
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/checkpoints/global_step_421/actor/fsdp_config.jsonConfiguration46 B —
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/checkpoints/global_step_421/actor/huggingface/added_tokens.jsonConfiguration605 B —
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/checkpoints/global_step_421/actor/huggingface/config.jsonConfiguration1.4 KB —
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/checkpoints/global_step_421/actor/huggingface/generation_config.jsonConfiguration117 B —
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/checkpoints/global_step_421/actor/huggingface/special_tokens_map.jsonConfiguration616 B —
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/checkpoints/global_step_421/transfer_queue/metadata.jsonConfiguration77 B —
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/checkpoints/global_step_421/transfer_queue/simple_storage/storage_unit_info.jsonConfiguration256 B —
models/GRPO_Guru/Qwen2.5-0.5B-low-lr5e-5/checkpoints/global_step_106/actor/fsdp_config.jsonConfiguration46 B —
models/GRPO_Guru/Qwen2.5-0.5B-low-lr5e-5/checkpoints/global_step_106/actor/huggingface/added_tokens.jsonConfiguration605 B —
models/GRPO_Guru/Qwen2.5-0.5B-low-lr5e-5/checkpoints/global_step_106/actor/huggingface/config.jsonConfiguration1.3 KB —
models/GRPO_Guru/Qwen2.5-0.5B-low-lr5e-5/checkpoints/global_step_106/actor/huggingface/generation_config.jsonConfiguration117 B —
models/GRPO_Guru/Qwen2.5-0.5B-low-lr5e-5/checkpoints/global_step_106/actor/huggingface/special_tokens_map.jsonConfiguration616 B —
models/GRPO_Guru/Qwen2.5-0.5B-low-lr5e-5/checkpoints/global_step_106/transfer_queue/metadata.jsonConfiguration77 B —
models/GRPO_Guru/Qwen2.5-0.5B-low-lr5e-5/checkpoints/global_step_106/transfer_queue/simple_storage/storage_unit_info.jsonConfiguration256 B —
models/GRPO_Guru/Qwen2.5-1.5B-low-lr5e-5/checkpoints/global_step_106/actor/fsdp_config.jsonConfiguration46 B —
models/GRPO_Guru/Qwen2.5-1.5B-low-lr5e-5/checkpoints/global_step_106/actor/huggingface/added_tokens.jsonConfiguration605 B —
models/GRPO_Guru/Qwen2.5-1.5B-low-lr5e-5/checkpoints/global_step_106/actor/huggingface/config.jsonConfiguration1.4 KB —
models/GRPO_Guru/Qwen2.5-1.5B-low-lr5e-5/checkpoints/global_step_106/actor/huggingface/generation_config.jsonConfiguration117 B —
models/GRPO_Guru/Qwen2.5-1.5B-low-lr5e-5/checkpoints/global_step_106/actor/huggingface/special_tokens_map.jsonConfiguration616 B —
models/GRPO_Guru/Qwen2.5-1.5B-low-lr5e-5/checkpoints/global_step_106/transfer_queue/metadata.jsonConfiguration77 B —
models/GRPO_Guru/Qwen2.5-1.5B-low-lr5e-5/checkpoints/global_step_106/transfer_queue/simple_storage/storage_unit_info.jsonConfiguration256 B —
models/GRPO_Guru/Qwen2.5-3B-low-lr4e-5/checkpoints/global_step_106/actor/fsdp_config.jsonConfiguration46 B —
models/GRPO_Guru/Qwen2.5-3B-low-lr4e-5/checkpoints/global_step_106/actor/huggingface/added_tokens.jsonConfiguration605 B —
models/GRPO_Guru/Qwen2.5-3B-low-lr4e-5/checkpoints/global_step_106/actor/huggingface/config.jsonConfiguration1.6 KB —
models/GRPO_Guru/Qwen2.5-3B-low-lr4e-5/checkpoints/global_step_106/actor/huggingface/generation_config.jsonConfiguration117 B —
models/GRPO_Guru/Qwen2.5-3B-low-lr4e-5/checkpoints/global_step_106/actor/huggingface/special_tokens_map.jsonConfiguration616 B —
models/GRPO_Guru/Qwen2.5-3B-low-lr4e-5/checkpoints/global_step_106/transfer_queue/metadata.jsonConfiguration77 B —
models/GRPO_Guru/Qwen2.5-3B-low-lr4e-5/checkpoints/global_step_106/transfer_queue/simple_storage/storage_unit_info.jsonConfiguration256 B —
models/GRPO_Guru/Qwen2.5-7B-low-lr4e-5/checkpoints/global_step_106/actor/fsdp_config.jsonConfiguration46 B —
models/GRPO_Guru/Qwen2.5-7B-low-lr4e-5/checkpoints/global_step_106/actor/huggingface/added_tokens.jsonConfiguration605 B —
models/GRPO_Guru/Qwen2.5-7B-low-lr4e-5/checkpoints/global_step_106/actor/huggingface/config.jsonConfiguration1.4 KB —
models/GRPO_Guru/Qwen2.5-7B-low-lr4e-5/checkpoints/global_step_106/actor/huggingface/generation_config.jsonConfiguration117 B —
models/GRPO_Guru/Qwen2.5-7B-low-lr4e-5/checkpoints/global_step_106/actor/huggingface/special_tokens_map.jsonConfiguration616 B —
models/GRPO_Guru/Qwen2.5-7B-low-lr4e-5/checkpoints/global_step_106/transfer_queue/metadata.jsonConfiguration77 B —
models/GRPO_Guru/Qwen2.5-7B-low-lr4e-5/checkpoints/global_step_106/transfer_queue/simple_storage/storage_unit_info.jsonConfiguration256 B —
models/GRPO_Guru/Qwen3-0.6B-Base/checkpoints/global_step_848/actor/fsdp_config.jsonConfiguration46 B —
models/GRPO_Guru/Qwen3-0.6B-Base/checkpoints/global_step_848/actor/huggingface/added_tokens.jsonConfiguration707 B —
models/GRPO_Guru/Qwen3-0.6B-Base/checkpoints/global_step_848/actor/huggingface/config.jsonConfiguration1.4 KB —
models/GRPO_Guru/Qwen3-0.6B-Base/checkpoints/global_step_848/actor/huggingface/generation_config.jsonConfiguration117 B —
models/GRPO_Guru/Qwen3-0.6B-Base/checkpoints/global_step_848/actor/huggingface/special_tokens_map.jsonConfiguration616 B —
models/GRPO_Guru/Qwen3-0.6B-Base/checkpoints/global_step_848/transfer_queue/metadata.jsonConfiguration77 B —
models/GRPO_Guru/Qwen3-0.6B-Base/checkpoints/global_step_848/transfer_queue/simple_storage/storage_unit_info.jsonConfiguration256 B —
models/GRPO_Guru/Qwen3-1.7B-Base/checkpoints/global_step_848/actor/fsdp_config.jsonConfiguration46 B —
models/GRPO_Guru/Qwen3-1.7B-Base/checkpoints/global_step_848/actor/huggingface/added_tokens.jsonConfiguration707 B —
models/GRPO_Guru/Qwen3-1.7B-Base/checkpoints/global_step_848/actor/huggingface/config.jsonConfiguration1.4 KB —
models/GRPO_Guru/Qwen3-1.7B-Base/checkpoints/global_step_848/actor/huggingface/generation_config.jsonConfiguration117 B —
models/GRPO_Guru/Qwen3-1.7B-Base/checkpoints/global_step_848/actor/huggingface/special_tokens_map.jsonConfiguration616 B —
models/GRPO_Guru/Qwen3-1.7B-Base/checkpoints/global_step_848/transfer_queue/metadata.jsonConfiguration77 B —
models/GRPO_Guru/Qwen3-1.7B-Base/checkpoints/global_step_848/transfer_queue/simple_storage/storage_unit_info.jsonConfiguration256 B —
models/GRPO_Guru/Qwen3-4B-Base/checkpoints/global_step_848/actor/fsdp_config.jsonConfiguration46 B —
models/GRPO_Guru/Qwen3-4B-Base/checkpoints/global_step_848/actor/huggingface/added_tokens.jsonConfiguration707 B —
models/GRPO_Guru/Qwen3-4B-Base/checkpoints/global_step_848/actor/huggingface/config.jsonConfiguration1.5 KB —
models/GRPO_Guru/Qwen3-4B-Base/checkpoints/global_step_848/actor/huggingface/generation_config.jsonConfiguration117 B —
models/GRPO_Guru/Qwen3-4B-Base/checkpoints/global_step_848/actor/huggingface/special_tokens_map.jsonConfiguration616 B —
models/GRPO_Guru/Qwen3-4B-Base/checkpoints/global_step_848/transfer_queue/metadata.jsonConfiguration77 B —
models/GRPO_Guru/Qwen3-4B-Base/checkpoints/global_step_848/transfer_queue/simple_storage/storage_unit_info.jsonConfiguration256 B —
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-0.6B-Base/checkpoints/global_step_848/actor/fsdp_config.jsonConfiguration46 B —
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-0.6B-Base/checkpoints/global_step_848/actor/huggingface/added_tokens.jsonConfiguration707 B —
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-0.6B-Base/checkpoints/global_step_848/actor/huggingface/config.jsonConfiguration1.4 KB —
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-0.6B-Base/checkpoints/global_step_848/actor/huggingface/generation_config.jsonConfiguration117 B —
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-0.6B-Base/checkpoints/global_step_848/actor/huggingface/special_tokens_map.jsonConfiguration616 B —
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-0.6B-Base/checkpoints/global_step_848/transfer_queue/metadata.jsonConfiguration77 B —
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-0.6B-Base/checkpoints/global_step_848/transfer_queue/simple_storage/storage_unit_info.jsonConfiguration256 B —
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-1.7B-Base/checkpoints/global_step_848/actor/fsdp_config.jsonConfiguration46 B —
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-1.7B-Base/checkpoints/global_step_848/actor/huggingface/added_tokens.jsonConfiguration707 B —
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-1.7B-Base/checkpoints/global_step_848/actor/huggingface/config.jsonConfiguration1.4 KB —
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-1.7B-Base/checkpoints/global_step_848/actor/huggingface/generation_config.jsonConfiguration117 B —
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-1.7B-Base/checkpoints/global_step_848/actor/huggingface/special_tokens_map.jsonConfiguration616 B —
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-1.7B-Base/checkpoints/global_step_848/transfer_queue/metadata.jsonConfiguration77 B —
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-1.7B-Base/checkpoints/global_step_848/transfer_queue/simple_storage/storage_unit_info.jsonConfiguration256 B —
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-4B-Base/checkpoints/global_step_820/actor/fsdp_config.jsonConfiguration46 B —
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-4B-Base/checkpoints/global_step_820/actor/huggingface/added_tokens.jsonConfiguration707 B —
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-4B-Base/checkpoints/global_step_820/actor/huggingface/config.jsonConfiguration1.5 KB —
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-4B-Base/checkpoints/global_step_820/actor/huggingface/generation_config.jsonConfiguration117 B —
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-4B-Base/checkpoints/global_step_820/actor/huggingface/special_tokens_map.jsonConfiguration616 B —
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-4B-Base/checkpoints/global_step_820/transfer_queue/metadata.jsonConfiguration77 B —
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-4B-Base/checkpoints/global_step_820/transfer_queue/simple_storage/storage_unit_info.jsonConfiguration256 B —
models/PrefixGRPO-R1x2-R2x8-Lnull_Guru/Qwen2.5-0.5B-low-lr5e-5/checkpoints/global_step_424/actor/fsdp_config.jsonConfiguration46 B —
models/PrefixGRPO-R1x2-R2x8-Lnull_Guru/Qwen2.5-0.5B-low-lr5e-5/checkpoints/global_step_424/actor/huggingface/added_tokens.jsonConfiguration605 B —
models/PrefixGRPO-R1x2-R2x8-Lnull_Guru/Qwen2.5-0.5B-low-lr5e-5/checkpoints/global_step_424/actor/huggingface/config.jsonConfiguration1.3 KB —
models/PrefixGRPO-R1x2-R2x8-Lnull_Guru/Qwen2.5-0.5B-low-lr5e-5/checkpoints/global_step_424/actor/huggingface/generation_config.jsonConfiguration117 B —
models/PrefixGRPO-R1x2-R2x8-Lnull_Guru/Qwen2.5-0.5B-low-lr5e-5/checkpoints/global_step_424/actor/huggingface/special_tokens_map.jsonConfiguration616 B —
models/PrefixGRPO-R1x2-R2x8-Lnull_Guru/Qwen2.5-0.5B-low-lr5e-5/checkpoints/global_step_424/transfer_queue/metadata.jsonConfiguration77 B —
models/PrefixGRPO-R1x2-R2x8-Lnull_Guru/Qwen2.5-0.5B-low-lr5e-5/checkpoints/global_step_424/transfer_queue/simple_storage/storage_unit_info.jsonConfiguration256 B —
models/SFT/Qwen2.5-0.5B-low-lr5e-5/config.jsonConfiguration1.3 KB —
models/SFT/Qwen2.5-0.5B-low-lr5e-5/generation_config.jsonConfiguration139 B —
models/SFT/Qwen2.5-0.5B-medium-lr5e-5/config.jsonConfiguration1.3 KB —
models/SFT/Qwen2.5-0.5B-medium-lr5e-5/generation_config.jsonConfiguration139 B —
models/SFT/Qwen2.5-1.5B-low-lr5e-5/config.jsonConfiguration1.4 KB —
models/SFT/Qwen2.5-1.5B-low-lr5e-5/generation_config.jsonConfiguration139 B —
models/SFT/Qwen2.5-1.5B-medium-lr5e-5/config.jsonConfiguration1.4 KB —
models/SFT/Qwen2.5-1.5B-medium-lr5e-5/generation_config.jsonConfiguration139 B —
models/SFT/Qwen2.5-3B-low-lr4e-5/config.jsonConfiguration1.6 KB —
models/SFT/Qwen2.5-3B-low-lr4e-5/generation_config.jsonConfiguration139 B —
models/SFT/Qwen2.5-7B-low-lr4e-5/config.jsonConfiguration1.4 KB —
models/SFT/Qwen2.5-7B-low-lr4e-5/generation_config.jsonConfiguration139 B —
data/guru_verl/train/Qwen3-0.6B-Base_off_policy_data.jsonlOther939.7 MB 5dcddb1b5ddd
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/checkpoints/global_step_421/actor/huggingface/chat_template.jinjaOther2.4 KB —
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/checkpoints/global_step_421/transfer_queue/controller_state.pklOther6.3 MB e883e6c52e1b
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/checkpoints/global_step_421/transfer_queue/simple_storage/su_0_TQ_STORAGE_UNIT_e5e6fb25.pklOther171.3 MB 1f16b4b0790b
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/checkpoints/global_step_421/transfer_queue/simple_storage/su_1_TQ_STORAGE_UNIT_9c045851.pklOther169.9 MB 5babcccc28fe
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/checkpoints/global_step_421/transfer_queue/simple_storage/su_2_TQ_STORAGE_UNIT_0805b278.pklOther171.4 MB 6a111cd51da4
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/checkpoints/global_step_421/transfer_queue/simple_storage/su_3_TQ_STORAGE_UNIT_e05400c2.pklOther171.3 MB acdcac81462b
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/1.jsonlOther43.7 MB 20926ff24d2e
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/10.jsonlOther35.1 MB 94947480be1b
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/100.jsonlOther15.9 MB e0116f4fc30b
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/101.jsonlOther15.6 MB cbf3c4b5d7a4
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/102.jsonlOther15.9 MB 12fcdd41a0fa
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/103.jsonlOther15.9 MB 4f3f99297ebb
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/104.jsonlOther16.0 MB 4d2322124e2d
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/105.jsonlOther16.0 MB 91d347b95254
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/106.jsonlOther16.3 MB bfd33ab26332
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/107.jsonlOther16.1 MB 2be1bfff2c45
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/108.jsonlOther15.7 MB 1f9c9eeffbed
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/109.jsonlOther15.9 MB a283d1463f89
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/11.jsonlOther34.0 MB ce6498729d09
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/110.jsonlOther16.4 MB d1c225a5a80a
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/111.jsonlOther16.5 MB 1158e92c1452
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/112.jsonlOther16.7 MB 9a5bdc768186
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/113.jsonlOther16.0 MB 0f52a632d406
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/114.jsonlOther16.3 MB f5b8558fa348
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/115.jsonlOther16.2 MB 2d546f4adba8
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/116.jsonlOther16.5 MB ce4439adc3c4
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/117.jsonlOther16.4 MB fb0f2fd7b508
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/118.jsonlOther15.9 MB 01de7e5a2f5a
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/119.jsonlOther15.8 MB 60a6a771b9d3
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/12.jsonlOther31.3 MB acd0411b2d77
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/120.jsonlOther15.8 MB d153053871de
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/121.jsonlOther15.9 MB b23f23f403b6
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/122.jsonlOther15.5 MB f6fed8df9222
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/123.jsonlOther15.7 MB ae2776056890
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/124.jsonlOther15.3 MB de0a677ccbc0
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/125.jsonlOther15.4 MB 41714590a0da
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/126.jsonlOther15.6 MB e369046aa9e9
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/127.jsonlOther15.7 MB aec62193deaf
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/128.jsonlOther16.2 MB 8ca88fcfa0d2
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/129.jsonlOther15.5 MB 9636031df559
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/13.jsonlOther29.7 MB 2cc86a479315
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/130.jsonlOther15.9 MB 7341c85f64d7
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/131.jsonlOther16.1 MB 1ee2fa420dec
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/132.jsonlOther15.4 MB 05010b9f6fe1
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/133.jsonlOther15.6 MB 3306c9acb2bb
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/134.jsonlOther15.6 MB 4c2283dea2f9
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/135.jsonlOther15.5 MB 1e4ec636213e
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/136.jsonlOther15.4 MB 93fc2de23300
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/137.jsonlOther16.0 MB f855db8f56b6
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/138.jsonlOther15.7 MB db1535fe8751
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/139.jsonlOther15.5 MB 21602f0690d3
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/14.jsonlOther29.9 MB 85fa26f52e32
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/140.jsonlOther15.5 MB 8feb7b63f3bb
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/141.jsonlOther15.9 MB 496befaa048c
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/142.jsonlOther15.4 MB 402dc417141a
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/143.jsonlOther15.6 MB 7518d1c5023c
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/144.jsonlOther15.9 MB e88a59a5f6fd
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/145.jsonlOther15.8 MB f8c4c367351c
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/146.jsonlOther16.0 MB 451fe2fde6ed
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/147.jsonlOther16.0 MB 3fddf076e306
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/148.jsonlOther16.2 MB 181a33a2ce0b
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/149.jsonlOther16.2 MB c8c6f5baea9a
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/15.jsonlOther29.6 MB a729a37437d3
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/150.jsonlOther16.6 MB 3e846359ab27
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/151.jsonlOther16.5 MB b8117663d2fd
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/152.jsonlOther15.8 MB 6c946c0c8c52
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/153.jsonlOther16.3 MB edb3442714a7
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/154.jsonlOther15.7 MB 18755eb16bfd
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/155.jsonlOther16.2 MB f5f274f81b56
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/156.jsonlOther16.5 MB 822b420ac54c
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/157.jsonlOther16.2 MB 95b0623626cc
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/158.jsonlOther16.6 MB bb5bdf226202
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/159.jsonlOther15.6 MB 760b3062ae10
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/16.jsonlOther27.4 MB 5453913f0e98
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/160.jsonlOther15.7 MB c9b1924506fd
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/161.jsonlOther16.4 MB d26db3e67f45
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/162.jsonlOther16.3 MB b1a9423258b3
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/163.jsonlOther16.8 MB c9d340c9fdb4
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/164.jsonlOther16.1 MB c26faf8e0dfa
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/165.jsonlOther16.6 MB a78cb5943cab
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/166.jsonlOther16.2 MB 59cec4ec90e8
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/167.jsonlOther16.8 MB 67da08962964
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/168.jsonlOther16.4 MB ebdd711c1f80
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/169.jsonlOther16.5 MB 7552cbdb2765
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/17.jsonlOther27.2 MB c6ce3001e6e5
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/170.jsonlOther16.5 MB 7597201d6025
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/171.jsonlOther16.4 MB 58aa5d904905
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/172.jsonlOther16.4 MB 6aaffe84ab21
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/173.jsonlOther16.6 MB b134b0da3ec6
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/174.jsonlOther16.8 MB 1c4d7847ef7f
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/175.jsonlOther16.4 MB acb9ab92531b
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/176.jsonlOther16.5 MB 0b4c7bdc07a8
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/177.jsonlOther16.1 MB d2b5d8d62f87
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/178.jsonlOther17.0 MB 776f0214444d
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/179.jsonlOther17.0 MB 825dc8f36641
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/18.jsonlOther25.7 MB 233b6ac7be8c
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/180.jsonlOther16.7 MB 4cf8b3032458
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/181.jsonlOther17.6 MB ca3e4fbce2ee
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/182.jsonlOther16.9 MB d31a75c35c0b
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/183.jsonlOther16.9 MB a29640f12bca
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/184.jsonlOther17.2 MB cb5bb0605c7c
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/185.jsonlOther17.2 MB 0a8bb3963e48
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/186.jsonlOther17.3 MB 04a67736fb87
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/187.jsonlOther17.4 MB b327c4301cc7
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/188.jsonlOther17.2 MB de7c3c682a0d
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/189.jsonlOther17.4 MB 3bbb06fe8959
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/19.jsonlOther24.2 MB e44c833b21ac
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/190.jsonlOther16.9 MB b7118bf0e48a
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/191.jsonlOther17.5 MB b48ad28fa5d4
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/192.jsonlOther17.3 MB a80a10d5c209
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/193.jsonlOther17.6 MB cfad1dee36ca
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/194.jsonlOther17.4 MB 7f3e829b8739
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/195.jsonlOther17.9 MB d8d9336048d1
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/196.jsonlOther18.3 MB eb3d2943f5de
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/197.jsonlOther17.7 MB 1901c86f1042
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/198.jsonlOther17.8 MB 6eb0fa5987e6
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/199.jsonlOther17.9 MB 14fe22fb299b
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/2.jsonlOther44.8 MB 0ff3189f712c
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/20.jsonlOther22.8 MB 15c5ab27fe0e
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/200.jsonlOther18.5 MB 4cee80740430
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/201.jsonlOther18.1 MB 0824ce31b144
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/202.jsonlOther18.5 MB eb88e8ed77e4
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/203.jsonlOther18.4 MB 5c28e3570631
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/204.jsonlOther18.4 MB 9a0a862c5b6c
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/205.jsonlOther18.5 MB ba20183c2f5e
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/206.jsonlOther18.1 MB afd0c7578c12
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/207.jsonlOther19.1 MB f829a51b8276
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/208.jsonlOther18.9 MB 539f46cb1c54
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/209.jsonlOther18.8 MB d181569a6ac8
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/21.jsonlOther23.1 MB da9613426230
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/210.jsonlOther18.7 MB c42a16822963
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/211.jsonlOther18.6 MB 4325d8ce4c4b
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/212.jsonlOther17.9 MB 3f1f1aaf4acc
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/213.jsonlOther18.9 MB ed6d5f16a621
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/214.jsonlOther17.8 MB 0f2e6a15bb71
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/215.jsonlOther18.4 MB 12302c89b067
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/216.jsonlOther18.7 MB 272eacdf6ebf
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/217.jsonlOther18.6 MB 5a692e9cafca
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/218.jsonlOther18.4 MB 75864599ed2a
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/219.jsonlOther18.7 MB 05b21851f178
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/22.jsonlOther21.8 MB ef20d14501d2
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/220.jsonlOther18.9 MB d526f4a4c670
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/221.jsonlOther20.0 MB 07f3f62f9772
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/222.jsonlOther19.2 MB 4dfaa6d1043c
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/223.jsonlOther18.8 MB 526556805692
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/224.jsonlOther19.0 MB a9ea7894b1e2
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/225.jsonlOther19.3 MB d830c52a1ba7
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/226.jsonlOther18.9 MB b3c6da8b5902
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/227.jsonlOther19.8 MB b65a28fb70c1
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/228.jsonlOther18.5 MB 241630705da5
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/229.jsonlOther19.5 MB e883c0dc495c
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/23.jsonlOther20.9 MB 9034400a9a74
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/230.jsonlOther19.9 MB 8cc2bdffe5d0
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/231.jsonlOther19.7 MB af5f975029a8
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/232.jsonlOther19.4 MB 450a19c23af4
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/233.jsonlOther19.5 MB 93194eae6915
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/234.jsonlOther19.1 MB b78212bfcf9b
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/235.jsonlOther19.2 MB 50a02ea32043
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/236.jsonlOther19.1 MB 5e668e8676e1
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/237.jsonlOther19.3 MB d67188246fba
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/238.jsonlOther19.2 MB 78f82d76f5c2
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/239.jsonlOther19.1 MB 643b1312c6e5
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/24.jsonlOther20.2 MB 641fce9906c8
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/240.jsonlOther19.6 MB 2c67e59bb5f9
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/241.jsonlOther19.3 MB dc20d9cefca3
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/242.jsonlOther19.1 MB d8b514efedc7
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/243.jsonlOther20.3 MB 3d369f622cdf
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/244.jsonlOther19.3 MB 67b648d4d458
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/245.jsonlOther19.7 MB 921addc65643
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/246.jsonlOther19.9 MB 462a2a9f79c7
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/247.jsonlOther20.0 MB 6abc43c40f99
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/248.jsonlOther19.2 MB abd21d08fa62
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/249.jsonlOther20.0 MB 636e9737ac17
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/25.jsonlOther19.7 MB 1da02d88a0e6
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/250.jsonlOther19.7 MB 5338be666bec
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/251.jsonlOther19.5 MB cc88bbcda7d5
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/252.jsonlOther19.5 MB b5fb4787b154
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/253.jsonlOther19.8 MB ae7d792c783c
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/254.jsonlOther20.3 MB 83d2370dc0b6
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/255.jsonlOther20.4 MB a0360c6a1199
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/256.jsonlOther19.6 MB df97acfa3bde
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/257.jsonlOther19.8 MB 52938c7b2324
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/258.jsonlOther20.2 MB 511e9626e4f6
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/259.jsonlOther19.4 MB ea49c3d84c57
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/26.jsonlOther19.9 MB acddf3e01d28
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/260.jsonlOther20.4 MB 0cb65af9c142
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/261.jsonlOther20.1 MB 35973a750466
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/262.jsonlOther19.5 MB fa9d90bf3cce
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/263.jsonlOther20.5 MB cd1f8fe60b5b
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/264.jsonlOther20.1 MB 4b82fc2f8bd5
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/265.jsonlOther20.0 MB 8aedde12c07d
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/266.jsonlOther20.5 MB 484461ed0347
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/267.jsonlOther20.6 MB 31feae78a03a
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/268.jsonlOther20.7 MB 5c313e7577b7
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/269.jsonlOther19.6 MB 558dc8b2e2b7
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/27.jsonlOther19.3 MB 19c21f70f44d
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/270.jsonlOther20.9 MB dc05c548ef66
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/271.jsonlOther21.0 MB bf61dd88800d
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/272.jsonlOther20.6 MB ecea944e08e5
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/273.jsonlOther19.0 MB fc47356ac117
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/274.jsonlOther19.9 MB d4d517ee72d0
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/275.jsonlOther20.2 MB 380f55c2d9bc
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/276.jsonlOther20.6 MB c2b5da6f5395
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/277.jsonlOther19.6 MB f9492cabba89
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/278.jsonlOther21.1 MB 025bc92e7418
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/279.jsonlOther20.8 MB f84ed9d07fd7
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/28.jsonlOther18.2 MB 0b797a5f817b
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/280.jsonlOther19.8 MB 65d130d9d24f
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/281.jsonlOther19.4 MB 204b73f61432
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/282.jsonlOther20.2 MB 1213d79139b6
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/283.jsonlOther19.8 MB 1c533c3c4559
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/284.jsonlOther19.5 MB 72958e2b45b2
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/285.jsonlOther19.8 MB 89263c037530
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/286.jsonlOther20.5 MB f3ba6b042165
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/287.jsonlOther20.7 MB 81ae7b9f99ac
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/288.jsonlOther20.7 MB 6ef12ddc32cf
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/289.jsonlOther21.1 MB 462d173a6197
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/29.jsonlOther17.8 MB a535d9da6b3c
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/290.jsonlOther20.1 MB 9cb1b995fcf3
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/291.jsonlOther20.0 MB 0308586547f5
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/292.jsonlOther20.6 MB 0240cb717737
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/293.jsonlOther20.1 MB 6b14945fcce9
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/294.jsonlOther20.1 MB 396195c7266b
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/295.jsonlOther20.1 MB 75cfbda5de11
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/296.jsonlOther20.5 MB 922bcac68c12
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/297.jsonlOther19.6 MB 7108c6cf75a9
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/298.jsonlOther19.7 MB a0c6dc027698
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/299.jsonlOther20.4 MB 411e4830b568
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/3.jsonlOther44.5 MB 377f1409dd38
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/30.jsonlOther17.6 MB 1b1d0e9bd431
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/300.jsonlOther20.8 MB 50c42c6f27a3
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/301.jsonlOther20.0 MB 74123157add5
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/302.jsonlOther21.3 MB e9ab02bc2646
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/303.jsonlOther19.9 MB 4ffaa29f8254
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/304.jsonlOther20.7 MB 78001ef80c10
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/305.jsonlOther21.1 MB 47ca7ae32f7a
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/306.jsonlOther20.0 MB 4cf6438b013b
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/307.jsonlOther20.1 MB 7d5fbbe97466
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/308.jsonlOther21.0 MB bf394e6ab22a
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/309.jsonlOther20.5 MB 4f9901863509
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/31.jsonlOther17.5 MB 1f661e36fb46
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/310.jsonlOther20.0 MB 69f1ef50a0ce
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/311.jsonlOther20.7 MB da97033e05ab
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/312.jsonlOther20.6 MB 0b52315fbde1
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/313.jsonlOther20.1 MB 98804d554810
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/314.jsonlOther20.6 MB 4a32be5118ba
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/315.jsonlOther21.4 MB 2a6f41db7c55
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/316.jsonlOther20.7 MB d7968031d3bc
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/317.jsonlOther20.3 MB a088d4412926
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/318.jsonlOther20.8 MB 823284a264bf
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/319.jsonlOther20.5 MB 54d6c48ac3a6
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/32.jsonlOther17.1 MB 5114863b0d28
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/320.jsonlOther20.9 MB 4b8c323a7d0e
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/321.jsonlOther20.9 MB d060e22dffad
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/322.jsonlOther20.1 MB 141dd3db9f33
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/323.jsonlOther20.5 MB 04721ec14087
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/324.jsonlOther20.2 MB 98d03be2d32f
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/325.jsonlOther20.5 MB 0d8282d551ab
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/326.jsonlOther20.1 MB 4f8928abaaef
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/327.jsonlOther21.3 MB c0ed3a7aa6ac
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/328.jsonlOther20.9 MB b2a4f4312120
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/329.jsonlOther22.0 MB 153dde2dc6e3
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/33.jsonlOther17.3 MB 54449da6ce20
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/330.jsonlOther21.0 MB 0174041b3cf9
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/331.jsonlOther22.9 MB 1d1dbe024602
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/332.jsonlOther20.8 MB 87e25810615e
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/333.jsonlOther21.6 MB bfe4de93dfce
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/334.jsonlOther21.4 MB 7ceba223cba8
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/335.jsonlOther21.4 MB 2fdfc52e25d5
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/336.jsonlOther21.6 MB ce059a606872
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/337.jsonlOther21.1 MB db5a08d779aa
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/338.jsonlOther21.0 MB 5bbeab4aa89b
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/339.jsonlOther22.2 MB 199d789ebfa2
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/34.jsonlOther16.9 MB 5ce549a6d634
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/340.jsonlOther21.4 MB a6478d707045
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/341.jsonlOther21.7 MB e88079ec1b1f
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/342.jsonlOther20.9 MB 08aea19c6aec
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/343.jsonlOther21.4 MB 58711644e5e3
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/344.jsonlOther21.3 MB 604634fe2d40
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/345.jsonlOther20.8 MB 97c71a18be0e
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/346.jsonlOther20.7 MB e9bf7aab18ec
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/347.jsonlOther21.4 MB 3e859dd2cf27
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/348.jsonlOther20.9 MB 0f62c5926c3e
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/349.jsonlOther19.9 MB 1a294a2457fe
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/35.jsonlOther16.8 MB d6cb9f003cf9
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/350.jsonlOther21.1 MB 691e6aa62be8
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/351.jsonlOther20.2 MB 47591910c5f3
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/352.jsonlOther20.9 MB 993e06158813
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/353.jsonlOther20.6 MB ffe4cde4637a
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/354.jsonlOther20.5 MB 361b3e213860
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/355.jsonlOther20.9 MB f780e1953ccc
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/356.jsonlOther19.5 MB 08936d59050a
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/357.jsonlOther20.2 MB c45fa63fccfc
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/358.jsonlOther20.6 MB 33529c5341f7
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/359.jsonlOther19.9 MB 919b1d99f3bf
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/36.jsonlOther16.5 MB 546d52c53e29
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/360.jsonlOther20.6 MB 4393028aa266
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/361.jsonlOther19.5 MB 0352f56d5f69
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/362.jsonlOther20.0 MB f13a51ed8b15
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/363.jsonlOther19.6 MB fdc250db380d
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/364.jsonlOther19.7 MB aea4ede4f479
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/365.jsonlOther20.8 MB 92d65d9944eb
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/366.jsonlOther20.6 MB 81cc1c5c4666
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/367.jsonlOther20.5 MB e19a56e0f0b8
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/368.jsonlOther20.5 MB 2330a6b72578
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/369.jsonlOther21.5 MB 2bf80a364448
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/37.jsonlOther16.0 MB 616986f66e75
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/370.jsonlOther20.3 MB 77bffc07f6ce
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/371.jsonlOther19.8 MB 5fbcdbd3f8ee
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/372.jsonlOther20.1 MB 765b278f4377
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/373.jsonlOther19.2 MB 54dc7822369d
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/374.jsonlOther20.0 MB c0541ae2e61d
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/375.jsonlOther20.0 MB 63eb1ca33832
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/376.jsonlOther20.3 MB 8f7f1aef7a52
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/377.jsonlOther20.2 MB 4e8926fe1589
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/378.jsonlOther19.8 MB 6df4f0906cdb
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/379.jsonlOther20.4 MB 6444ac0af6d7
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/38.jsonlOther16.4 MB 38bb585e6e94
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/380.jsonlOther19.9 MB 18d34bcf4f52
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/381.jsonlOther19.2 MB f7c43b4b1985
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/382.jsonlOther20.0 MB 5346693a5b3a
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/383.jsonlOther19.7 MB 484b394ef301
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/384.jsonlOther19.9 MB 0b157b3f8029
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/385.jsonlOther19.8 MB 6f1b713b27ab
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/386.jsonlOther20.1 MB 55df1c77291d
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/387.jsonlOther19.7 MB d1362b0f1a7e
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/388.jsonlOther19.8 MB 2bb6895dd4c7
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/389.jsonlOther19.5 MB 985353f4a5aa
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/39.jsonlOther16.4 MB e95446bb6f1d
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/390.jsonlOther19.5 MB 680666006158
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/391.jsonlOther19.9 MB 65c655785766
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/392.jsonlOther20.6 MB a53f08ea4f9f
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/393.jsonlOther21.1 MB e0cc0c5d1318
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/394.jsonlOther20.6 MB 670b34c87c27
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/395.jsonlOther20.5 MB b89d23a26a96
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/396.jsonlOther20.3 MB f83d3517252e
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/397.jsonlOther20.2 MB dcc53dc801fe
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/398.jsonlOther20.0 MB 12d561c66851
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/399.jsonlOther19.6 MB 24f9b55175d0
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/4.jsonlOther43.2 MB de2239b6c83d
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/40.jsonlOther16.1 MB 986dd3cdbef0
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/400.jsonlOther19.9 MB 4eade85b8b9c
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/401.jsonlOther19.5 MB 19a9b5424ab8
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/402.jsonlOther19.5 MB e427a8756d1d
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/403.jsonlOther20.1 MB 104565c4ee6f
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/404.jsonlOther19.6 MB 831e0dc13175
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/405.jsonlOther19.3 MB 08754fe4b00a
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/406.jsonlOther19.1 MB 9cef20e99cdc
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/407.jsonlOther20.3 MB 43336caa6fcc
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/408.jsonlOther19.5 MB 3695acaf01e2
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/409.jsonlOther19.1 MB 15a5faf2d5a7
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/41.jsonlOther15.9 MB 69353372a3fa
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/410.jsonlOther18.9 MB 504108595b5e
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/411.jsonlOther19.4 MB b671121363ac
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/412.jsonlOther19.5 MB 27f6123786ce
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/413.jsonlOther18.8 MB 901594f34c6c
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/414.jsonlOther19.1 MB 6ece6515763e
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/415.jsonlOther19.1 MB 4d4d33a4e59e
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/416.jsonlOther19.1 MB 17d69fae0d1d
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/417.jsonlOther19.7 MB 7851d5c82709
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/418.jsonlOther19.1 MB 2fd99baf4e81
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/419.jsonlOther20.1 MB ca64cd1fa7fb
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/42.jsonlOther15.9 MB 3a8eaa0d53a7
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/420.jsonlOther19.3 MB 0bfb67bcd2e9
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/421.jsonlOther19.0 MB 6d3945762628
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/43.jsonlOther15.8 MB fa5276ee9063
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/44.jsonlOther15.6 MB 4106fbe14431
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/45.jsonlOther15.7 MB f96e2bbdc440
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/46.jsonlOther15.6 MB eebc09f7420d
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/47.jsonlOther15.5 MB adbe42dafe13
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/48.jsonlOther15.4 MB 389a3cb275d9
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/49.jsonlOther15.6 MB 3239aa9206fe
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/5.jsonlOther41.3 MB fdf5195a6fe7
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/50.jsonlOther15.6 MB 24ed9233cef1
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/51.jsonlOther14.8 MB 8de7451f742a
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/52.jsonlOther15.0 MB df195f75039f
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/53.jsonlOther15.0 MB bc5e41f45415
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/54.jsonlOther15.2 MB 9a6fcda7a574
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/55.jsonlOther14.5 MB c4a3b721f1c4
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/56.jsonlOther14.8 MB fddc4aff9527
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/57.jsonlOther14.6 MB f8a142b22994
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/58.jsonlOther15.0 MB a201e348487c
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/59.jsonlOther15.3 MB 63fc9cdde910
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/6.jsonlOther40.6 MB ce85a4713758
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/60.jsonlOther14.8 MB a3b2a0d24412
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/61.jsonlOther15.3 MB 67ff9deb7b45
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/62.jsonlOther15.2 MB c9294c650893
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/63.jsonlOther14.9 MB 15b498961972
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/64.jsonlOther15.3 MB 3c36cca00914
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/65.jsonlOther15.7 MB 29eb0997537c
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/66.jsonlOther15.3 MB ab48894a7d5e
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/67.jsonlOther15.3 MB 1385cedd6063
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/68.jsonlOther15.0 MB cd13159ccf01
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/69.jsonlOther15.1 MB 46012a6cf5fe
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/7.jsonlOther40.1 MB ab69ec2619a3
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/70.jsonlOther14.9 MB ffcbabb9911f
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/71.jsonlOther15.6 MB 2fad7dc9a7a0
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/72.jsonlOther15.3 MB bc4a51520ecb
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/73.jsonlOther15.5 MB b9dd3cf8b077
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/74.jsonlOther15.3 MB 103994f50802
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/75.jsonlOther15.5 MB b33ee663ca3a
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/76.jsonlOther15.5 MB 3af20ebf0efc
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/77.jsonlOther15.4 MB 84d62f6f1f41
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/78.jsonlOther15.3 MB 2f510baeb366
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/79.jsonlOther15.5 MB 98954657f9b7
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/8.jsonlOther37.1 MB 84f07d2a16e4
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/80.jsonlOther15.4 MB 0716ef60b9aa
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/81.jsonlOther15.0 MB 6e581c7cfa02
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/82.jsonlOther15.1 MB d181639ed6eb
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/83.jsonlOther15.0 MB 77340f1a1a5f
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/84.jsonlOther15.2 MB 8e2e990fa450
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/85.jsonlOther15.3 MB fe959a40493a
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/86.jsonlOther15.5 MB 5a3c731033d8
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/87.jsonlOther15.7 MB 841a93ac4fd3
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/88.jsonlOther16.0 MB 6bf291436c24
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/89.jsonlOther15.6 MB ce6c82e88d26
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/9.jsonlOther36.0 MB 02fbb7f3af90
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/90.jsonlOther15.3 MB a009155effb6
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/91.jsonlOther15.3 MB 8747e2f86ebc
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/92.jsonlOther15.6 MB 218a3d0d082c
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/93.jsonlOther16.0 MB 710cdbe9460f
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/94.jsonlOther16.0 MB 2fe71b5d9e24
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/95.jsonlOther15.4 MB 57a8dc8797f1
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/96.jsonlOther15.6 MB b0d1f22565e3
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/97.jsonlOther15.8 MB cc7b98056050
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/98.jsonlOther15.4 MB 734fb8ad9484
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/rollouts/99.jsonlOther15.4 MB 22e50205690e
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/validation/100.jsonlOther3.9 MB —
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/validation/120.jsonlOther3.9 MB —
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/validation/140.jsonlOther3.9 MB —
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/validation/160.jsonlOther4.0 MB —
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/validation/180.jsonlOther4.0 MB —
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/validation/20.jsonlOther6.7 MB —
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/validation/200.jsonlOther4.3 MB —
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/validation/220.jsonlOther4.3 MB —
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/validation/240.jsonlOther4.2 MB —
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/validation/260.jsonlOther4.1 MB —
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/validation/280.jsonlOther4.2 MB —
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/validation/300.jsonlOther4.4 MB —
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/validation/320.jsonlOther4.1 MB —
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/validation/340.jsonlOther4.2 MB —
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/validation/360.jsonlOther4.2 MB —
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/validation/380.jsonlOther4.1 MB —
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/validation/40.jsonlOther4.8 MB —
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/validation/400.jsonlOther4.1 MB —
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/validation/420.jsonlOther4.1 MB —
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/validation/421.jsonlOther4.1 MB —
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/validation/60.jsonlOther4.2 MB —
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/validation/80.jsonlOther3.9 MB —
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/checkpoints/global_step_220/actor/huggingface/chat_template.jinjaOther2.4 KB —
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/checkpoints/global_step_220/transfer_queue/controller_state.pklOther6.2 MB f8db38d772ce
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/checkpoints/global_step_220/transfer_queue/simple_storage/su_0_TQ_STORAGE_UNIT_e53104a9.pklOther266.9 MB 7a1b097748c1
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/checkpoints/global_step_220/transfer_queue/simple_storage/su_1_TQ_STORAGE_UNIT_cb1ce628.pklOther268.0 MB 13b2a312ad6f
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/checkpoints/global_step_220/transfer_queue/simple_storage/su_2_TQ_STORAGE_UNIT_2bd7f277.pklOther274.8 MB 9943aaf11541
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/checkpoints/global_step_220/transfer_queue/simple_storage/su_3_TQ_STORAGE_UNIT_c0b733e6.pklOther270.4 MB 7be1e80ca3f5
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/checkpoints/global_step_421/actor/huggingface/chat_template.jinjaOther2.4 KB —
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/checkpoints/global_step_421/transfer_queue/controller_state.pklOther9.5 MB ad39912da8f5
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/checkpoints/global_step_421/transfer_queue/simple_storage/su_0_TQ_STORAGE_UNIT_49fa5419.pklOther434.1 MB 03ddc37db0b1
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/checkpoints/global_step_421/transfer_queue/simple_storage/su_1_TQ_STORAGE_UNIT_96c1bb9d.pklOther432.7 MB 6a3741cd86e2
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/checkpoints/global_step_421/transfer_queue/simple_storage/su_2_TQ_STORAGE_UNIT_e722f001.pklOther435.7 MB da4d30c48e98
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/checkpoints/global_step_421/transfer_queue/simple_storage/su_3_TQ_STORAGE_UNIT_681877c0.pklOther434.2 MB 0aebdc66e8f1
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/1.jsonlOther29.3 MB 0bcb90082a87
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/10.jsonlOther28.0 MB f295eb3124c2
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/100.jsonlOther23.1 MB 32309ca935d9
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/101.jsonlOther22.8 MB 887c51f102e0
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/102.jsonlOther23.2 MB 24b0a5562de8
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/103.jsonlOther22.8 MB 95f1e1d53feb
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/104.jsonlOther23.9 MB 06e642579fa4
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/105.jsonlOther23.5 MB ac8365f243a2
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/106.jsonlOther23.2 MB 8f6d23a4efae
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/107.jsonlOther23.8 MB 586dc6904b5c
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/108.jsonlOther22.5 MB 44c38fcd46eb
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/109.jsonlOther23.7 MB cbfa2bb5b7e7
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/11.jsonlOther28.1 MB 57716dffb796
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/110.jsonlOther23.3 MB fe3cc9bdbba0
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/111.jsonlOther24.4 MB 7d4e2a5e51bd
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/112.jsonlOther25.2 MB 01d9a9b67447
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/113.jsonlOther24.5 MB ff33a9c8f140
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/114.jsonlOther25.2 MB 3f825384247e
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/115.jsonlOther25.6 MB b9fd7823c5da
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/116.jsonlOther25.1 MB 653438a66911
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/117.jsonlOther24.7 MB e627b69d8fe8
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/118.jsonlOther24.1 MB 57531c54bf64
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/119.jsonlOther24.1 MB 319143fa9601
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/12.jsonlOther27.5 MB 8ed3035e46da
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/120.jsonlOther23.3 MB 09a60e2c666f
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/121.jsonlOther24.1 MB e7f70a4ccbe8
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/122.jsonlOther23.5 MB 1d8000e55a0d
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/123.jsonlOther24.3 MB 78a83da12cf2
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/124.jsonlOther23.0 MB 8b65617ffce6
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/125.jsonlOther24.0 MB b0b9930eac51
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/126.jsonlOther23.7 MB 4250ef3c375b
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/127.jsonlOther24.5 MB 2f1206282eac
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/128.jsonlOther25.6 MB c3aad36c949d
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/129.jsonlOther23.2 MB 916b1c14af09
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/13.jsonlOther27.0 MB 2ecb282e3b8f
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/130.jsonlOther24.2 MB 49b57e90bbb6
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/131.jsonlOther25.5 MB 82e97b78c1db
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/132.jsonlOther23.6 MB 8898f95c67ed
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/133.jsonlOther23.9 MB f23f112ff6f2
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/134.jsonlOther25.0 MB 6dc7d45767f5
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/135.jsonlOther24.4 MB 185e6d090d47
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/136.jsonlOther24.6 MB 54a81a0e2378
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/137.jsonlOther25.9 MB 1e841c4cce7d
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/138.jsonlOther25.5 MB e7c5a56f8f98
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/139.jsonlOther25.7 MB 1565e5cb6a1a
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/14.jsonlOther27.1 MB 66a4e09d93c9
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/140.jsonlOther25.7 MB 73e96b93f940
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/141.jsonlOther25.4 MB 8f44f4851bf0
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/142.jsonlOther26.4 MB 127047745607
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/143.jsonlOther25.3 MB 5bb02e1b151c
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/144.jsonlOther26.0 MB 64b55a89ae54
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/145.jsonlOther26.5 MB 63ebbb09816a
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/146.jsonlOther25.8 MB 62224b7cdf6e
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/147.jsonlOther25.9 MB e8677f9d0e11
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/148.jsonlOther26.4 MB 17e680e5537c
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/149.jsonlOther25.1 MB 23603f9ad6a2
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/15.jsonlOther27.0 MB 9a140fdd6a38
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/150.jsonlOther26.7 MB ab7bf9a34867
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/151.jsonlOther26.6 MB 445fcaad5ca6
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/152.jsonlOther24.6 MB 2136ad258c8d
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/153.jsonlOther25.9 MB 68960b7dec0b
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/154.jsonlOther24.4 MB 3d290558e756
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/155.jsonlOther25.1 MB 2408ce79e6ea
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/156.jsonlOther26.7 MB 2b5346795c73
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/157.jsonlOther26.0 MB 60c3789775d1
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/158.jsonlOther27.0 MB f60b26cd3a95
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/159.jsonlOther25.1 MB b738480ef9f7
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/16.jsonlOther26.5 MB 997bd8d50ece
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/160.jsonlOther26.2 MB 61c1b7af2250
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/161.jsonlOther25.9 MB 2f4cf080009e
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/162.jsonlOther26.2 MB 14cb778dfbbc
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/163.jsonlOther26.7 MB 3f13f1c04f89
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/164.jsonlOther26.6 MB 753ec10e8854
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/165.jsonlOther26.7 MB 78dbfedcbdb8
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/166.jsonlOther26.3 MB 15a245964a4b
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/167.jsonlOther27.9 MB 5634f35ebe69
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/168.jsonlOther26.6 MB 674c08dfb5e9
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/169.jsonlOther27.2 MB 9374e68db871
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/17.jsonlOther26.3 MB 9e9fb39bc782
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/170.jsonlOther27.5 MB 5b2a7d68f629
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/171.jsonlOther28.7 MB 99810a787377
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/172.jsonlOther27.8 MB e8b27e250c92
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/173.jsonlOther27.7 MB 457625bec4c0
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/174.jsonlOther27.5 MB 7abe1ba5f18b
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/175.jsonlOther26.4 MB 18c7b6412a75
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/176.jsonlOther27.0 MB c927d3eea353
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/177.jsonlOther26.8 MB e5d6b9b7062f
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/178.jsonlOther27.8 MB 8bce8a2f7c60
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/179.jsonlOther27.6 MB 488efd8fb027
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/18.jsonlOther25.4 MB 925f99a08b04
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/180.jsonlOther26.6 MB 881c43176c78
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/181.jsonlOther27.2 MB cc21c6ed685a
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/182.jsonlOther27.3 MB 8eb3653811ed
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/183.jsonlOther27.6 MB 0076c90153bd
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/184.jsonlOther27.5 MB fc65d90e8d37
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/185.jsonlOther26.7 MB 87fc55bf2833
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/186.jsonlOther26.4 MB 32b5b9f5e466
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/187.jsonlOther27.5 MB 51cf04e9b462
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/188.jsonlOther27.4 MB cc631aea8361
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/189.jsonlOther27.5 MB 5ee91c210f1b
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/19.jsonlOther23.5 MB a3891f714992
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/190.jsonlOther26.3 MB 2e76bddea718
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/191.jsonlOther27.1 MB 288cc2338ce5
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/192.jsonlOther26.9 MB 4dd980ec9c00
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/193.jsonlOther26.8 MB 8652b80e30bf
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/194.jsonlOther26.5 MB 80cd04bc0bf0
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/195.jsonlOther28.3 MB 048de3078a42
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/196.jsonlOther27.7 MB b7fd438f1b25
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/197.jsonlOther26.3 MB 29ee9d303357
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/198.jsonlOther26.4 MB 9918163aad07
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/199.jsonlOther26.1 MB 9dbc76aacd58
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/2.jsonlOther31.5 MB 3a1443c54efa
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/20.jsonlOther24.4 MB a30ab7cdea9b
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/200.jsonlOther26.0 MB e74f432f5e87
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/201.jsonlOther26.4 MB b312e717c614
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/202.jsonlOther27.0 MB 790e02cb8c33
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/203.jsonlOther27.1 MB 8564d3b5002c
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/204.jsonlOther25.2 MB f73f295e23cc
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/205.jsonlOther26.8 MB 83dd7c827c6c
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/206.jsonlOther27.0 MB d703ce7818bd
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/207.jsonlOther27.6 MB 58403d3c8db7
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/208.jsonlOther27.8 MB be71813c0134
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/209.jsonlOther26.5 MB 1a4c07265e5b
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/21.jsonlOther25.2 MB b482ea65a7e0
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/210.jsonlOther27.3 MB eebc5a7ebfe8
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/211.jsonlOther27.0 MB a06b944eb076
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/212.jsonlOther27.2 MB e5d3fee77ae6
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/213.jsonlOther28.3 MB 2a2028cf2868
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/214.jsonlOther26.9 MB 317cc9d6b13b
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/215.jsonlOther28.4 MB b76fa4525784
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/216.jsonlOther28.4 MB 87502c55e04b
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/217.jsonlOther27.5 MB a4b0c6372b70
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/218.jsonlOther27.9 MB 6b9d89f81c5b
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/219.jsonlOther27.1 MB 8a4a26b21a8f
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/22.jsonlOther24.7 MB 56f8e6ed999f
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/220.jsonlOther28.2 MB 5e29c8e4e367
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/221.jsonlOther28.5 MB b895ed9bc81d
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/222.jsonlOther29.4 MB 8fa48e42d706
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/223.jsonlOther28.0 MB 2ed3430be6e0
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/224.jsonlOther28.6 MB 2bf09742e83b
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/225.jsonlOther28.0 MB 55377164ad3c
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/226.jsonlOther27.1 MB 759ba5ce8670
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/227.jsonlOther28.7 MB 70b410c75911
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/228.jsonlOther27.8 MB 9e372b245b18
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/229.jsonlOther28.7 MB 0b820eec1bfa
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/23.jsonlOther23.5 MB 256da940630d
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/230.jsonlOther28.2 MB c9ad6674fbee
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/231.jsonlOther27.8 MB 51766b85820e
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/232.jsonlOther28.9 MB 83a7329a2f21
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/233.jsonlOther28.3 MB 4009147e8fdc
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/234.jsonlOther26.9 MB d664be6b6ceb
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/235.jsonlOther27.7 MB 0b0b8e30aa22
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/236.jsonlOther27.7 MB a66adfd502e3
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/237.jsonlOther28.2 MB a32c196b1716
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/238.jsonlOther27.5 MB eb9725ec5b18
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/239.jsonlOther28.8 MB b6eb3aeb7e29
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/24.jsonlOther23.2 MB 632171b82a44
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/240.jsonlOther29.8 MB c36e45ae48ec
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/241.jsonlOther28.0 MB d130492a5dec
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/242.jsonlOther27.9 MB 7c10d72d2232
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/243.jsonlOther29.2 MB 08d0d474ef2b
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/244.jsonlOther29.4 MB d50dff254d1f
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/245.jsonlOther28.9 MB 756e90a218da
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/246.jsonlOther28.3 MB 6fa76ae346c9
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/247.jsonlOther29.5 MB ab7c4a2f2b98
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/248.jsonlOther27.8 MB a5940469c433
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/249.jsonlOther28.0 MB dfedf5461e4f
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/25.jsonlOther23.0 MB d9b1ba4313f9
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/250.jsonlOther29.1 MB eef0eb5ecb4d
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/251.jsonlOther28.4 MB 4dfb27e702fd
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/252.jsonlOther27.9 MB 76a7ce6d615f
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/253.jsonlOther28.2 MB eb2f8baa3aa5
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/254.jsonlOther28.0 MB fd3da81db867
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/255.jsonlOther28.6 MB ea55776eac0b
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/256.jsonlOther26.3 MB c8b9b4133b9d
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/257.jsonlOther27.3 MB b5a52b8bb9f1
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/258.jsonlOther28.7 MB 58330a09b7d6
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/259.jsonlOther28.2 MB c9d306a387de
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/26.jsonlOther23.6 MB 60cea5e0c827
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/260.jsonlOther29.0 MB 16d197650d12
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/261.jsonlOther28.9 MB 0c64ae742840
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/262.jsonlOther27.6 MB 493c135652ba
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/263.jsonlOther30.4 MB 61ecc00aad1e
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/264.jsonlOther30.3 MB 470e74e13047
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/265.jsonlOther29.0 MB 1fcbc57acf77
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/266.jsonlOther29.6 MB c7fd5535e4de
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/267.jsonlOther29.9 MB 610b02f755a7
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/268.jsonlOther29.5 MB 464413be264f
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/269.jsonlOther28.7 MB df6318d094eb
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/27.jsonlOther22.7 MB 0e954eeea72d
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/270.jsonlOther30.2 MB cc20e53aea13
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/271.jsonlOther28.6 MB fceb7dbd5cf4
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/272.jsonlOther29.7 MB c0e3657c0109
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/273.jsonlOther27.4 MB 03606a986b40
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/274.jsonlOther28.6 MB 4a93b8478b8f
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/275.jsonlOther29.4 MB 6975091ad14b
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/276.jsonlOther29.9 MB 31c174655d2c
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/277.jsonlOther28.9 MB 5359d6f3edd2
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/278.jsonlOther29.2 MB 7f62bb193987
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/279.jsonlOther28.9 MB 9394386dec4e
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/28.jsonlOther22.5 MB e8519923fcbe
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/280.jsonlOther29.8 MB 71b3b52e8503
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/281.jsonlOther28.2 MB 807ff4ad806a
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/282.jsonlOther28.8 MB 40f888ea9643
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/283.jsonlOther29.9 MB a7d530d32f39
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/284.jsonlOther27.8 MB 34a34d8f318c
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/285.jsonlOther28.8 MB e416a57ca09c
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/286.jsonlOther29.1 MB 2250cbb0b84f
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/287.jsonlOther28.4 MB 342886edbbf8
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/288.jsonlOther28.9 MB 494469bde881
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/289.jsonlOther30.2 MB d9c905e7be7e
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/29.jsonlOther22.6 MB 04d05634874c
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/290.jsonlOther28.5 MB 41082f3f67f5
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/291.jsonlOther28.4 MB 6b386362972b
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/292.jsonlOther30.3 MB a1c1286b84e5
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/293.jsonlOther29.0 MB 3d5e2aa81269
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/294.jsonlOther28.4 MB b97258af06dc
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/295.jsonlOther29.8 MB 3971ebb42f4f
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/296.jsonlOther29.3 MB a001247e3231
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/297.jsonlOther28.5 MB 2803e81893a9
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/298.jsonlOther29.4 MB 585025d98479
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/299.jsonlOther28.3 MB 54e566545cab
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/3.jsonlOther32.2 MB e3b1f2092d36
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/30.jsonlOther22.9 MB 2e54a29857be
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/300.jsonlOther29.3 MB 19af704ca7b2
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/301.jsonlOther27.6 MB be4d99e90af1
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/302.jsonlOther29.1 MB 3b34bfcc0302
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/303.jsonlOther28.1 MB 15fbbad34592
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/304.jsonlOther29.9 MB 20fe44a46df0
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/305.jsonlOther29.2 MB bc5932b19bdd
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/306.jsonlOther28.7 MB b7b0df0ebf77
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/307.jsonlOther29.2 MB 5837a8e5e11f
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/308.jsonlOther29.7 MB 9611fb582e5a
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/309.jsonlOther29.3 MB f979e1bdadb9
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/31.jsonlOther22.2 MB 70a5115d8e3c
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/310.jsonlOther29.2 MB 3f2d0cc7fba1
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/311.jsonlOther29.8 MB 3d096a2b0fe2
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/312.jsonlOther29.2 MB e0a48f0d7427
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/313.jsonlOther28.3 MB 1ca0a3989dad
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/314.jsonlOther29.7 MB dabda9f5857f
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/315.jsonlOther29.5 MB a32ef23f4be2
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/316.jsonlOther29.4 MB b77a934f12a7
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/317.jsonlOther29.5 MB 4817c116138d
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/318.jsonlOther29.3 MB 6abfa808f761
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/319.jsonlOther29.3 MB 6e9b428db0ec
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/32.jsonlOther22.0 MB f1666078e8f0
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/320.jsonlOther30.0 MB 75cb7e836f8c
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/321.jsonlOther30.3 MB 56b0011697e2
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/322.jsonlOther27.7 MB 072dfce5717e
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/323.jsonlOther29.4 MB 15c234fdbf4f
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/324.jsonlOther29.2 MB 05eb50873d94
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/325.jsonlOther29.9 MB dfefed0304b7
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/326.jsonlOther28.4 MB b08c7c5e668c
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/327.jsonlOther29.2 MB 82617cd8ca1f
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/328.jsonlOther29.9 MB 0d3e95e72822
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/329.jsonlOther30.9 MB a479a66b64cc
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/33.jsonlOther22.2 MB 2eff01d8b455
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/330.jsonlOther28.4 MB cd3fb5052564
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/331.jsonlOther31.2 MB 0e190edf449a
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/332.jsonlOther29.1 MB b2bfc5542753
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/333.jsonlOther29.5 MB 6abf856c3952
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/334.jsonlOther29.2 MB 3ec9cc24c04c
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/335.jsonlOther30.9 MB 319267385830
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/336.jsonlOther29.5 MB 4c65f97991a8
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/337.jsonlOther29.9 MB ab7a1be76627
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/338.jsonlOther30.4 MB 7404dd644852
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/339.jsonlOther30.5 MB f67f231863f9
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/34.jsonlOther21.5 MB 9905cfc930f6
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/340.jsonlOther30.3 MB 00d6f760fb11
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/341.jsonlOther29.8 MB c76aa415559a
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/342.jsonlOther29.2 MB 3b0ec79df34d
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/343.jsonlOther30.0 MB ed865885bfc4
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/344.jsonlOther29.2 MB 4c71000f8a50
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/345.jsonlOther29.5 MB 537f4fb77613
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/346.jsonlOther29.4 MB 96192cfd0598
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/347.jsonlOther29.1 MB 658362c88f06
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/348.jsonlOther28.9 MB 1aa12a0c280b
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/349.jsonlOther28.2 MB a8a9724b2f15
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/35.jsonlOther21.3 MB 3f14944940ff
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/350.jsonlOther29.1 MB 0395cd2731de
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/351.jsonlOther28.8 MB 2f7eb88e4362
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/352.jsonlOther29.1 MB 23bb948e696d
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/353.jsonlOther28.8 MB 059f9edb8ab2
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/354.jsonlOther28.6 MB ff253836be72
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/355.jsonlOther29.0 MB 62e7484fc4cf
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/356.jsonlOther27.7 MB f2a4fe04b9cf
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/357.jsonlOther28.5 MB 080c19886fd0
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/358.jsonlOther28.2 MB 4508e0a74cad
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/359.jsonlOther29.1 MB 287a8f0f6cbb
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/36.jsonlOther20.4 MB e4d3ae5f4a69
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/360.jsonlOther29.4 MB b3dab967256b
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/361.jsonlOther28.7 MB 1a4d6ecfcfa4
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/362.jsonlOther29.3 MB 68e09d3142a0
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/363.jsonlOther28.7 MB 7a76cafa8276
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/364.jsonlOther29.6 MB 1ea5c59a2241
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/365.jsonlOther29.6 MB 99dde05015da
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/366.jsonlOther29.3 MB 6ec62c4a8e93
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/367.jsonlOther29.5 MB d2553ebce52f
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/368.jsonlOther27.3 MB 64360ae1e6a9
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/369.jsonlOther30.3 MB 7947741c6979
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/37.jsonlOther20.8 MB 5323379b1fe7
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/370.jsonlOther29.5 MB f97418f4a4d3
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/371.jsonlOther29.9 MB 5602fcbb8f6d
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/372.jsonlOther29.1 MB 16096b6f918b
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/373.jsonlOther29.4 MB 75d4a5f0fa29
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/374.jsonlOther29.7 MB 492a3b326f11
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/375.jsonlOther29.1 MB ed3c330cf4f6
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/376.jsonlOther29.7 MB bba5c768000f
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/377.jsonlOther29.2 MB 6dead270dc4d
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/378.jsonlOther28.4 MB 6a2f93e790db
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/379.jsonlOther29.9 MB def6e6ff4066
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/38.jsonlOther21.3 MB 70a868baf38a
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/380.jsonlOther29.2 MB f0081fa3b8cb
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/381.jsonlOther28.3 MB 86f6ee15d391
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/382.jsonlOther29.0 MB aa7a1cbf3bfd
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/383.jsonlOther28.9 MB 70a35f507727
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/384.jsonlOther32.3 MB bbd741acafae
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/385.jsonlOther30.3 MB e646c1911060
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/386.jsonlOther30.7 MB 63c4881f792a
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/387.jsonlOther29.6 MB 4305487ec17c
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/388.jsonlOther29.6 MB d84bd548342e
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/389.jsonlOther28.6 MB f6960ba34cc3
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/39.jsonlOther20.7 MB 5537b677f4cf
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/390.jsonlOther28.3 MB a997f597bfac
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/391.jsonlOther29.2 MB b95cd3f5ba09
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/392.jsonlOther29.9 MB 8e5d59e6539d
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/393.jsonlOther29.1 MB 5aacc02361d3
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/394.jsonlOther30.2 MB a2a68c1fe738
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/395.jsonlOther29.6 MB 5f0974b1b054
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/396.jsonlOther29.9 MB ecfdbbb7bc8c
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/397.jsonlOther30.2 MB d52ea514640c
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/398.jsonlOther29.7 MB f41bde292dbf
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/399.jsonlOther30.4 MB f3f885b9452a
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/4.jsonlOther31.0 MB 7990e7142984
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/40.jsonlOther21.1 MB cfc814bdf833
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/400.jsonlOther30.5 MB 41c262debf7d
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/401.jsonlOther30.0 MB 0763805a196d
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/402.jsonlOther29.7 MB c9a7c21b5134
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/403.jsonlOther30.0 MB fd84cdea7a2c
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/404.jsonlOther30.3 MB 7e63b84b2a4a
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/405.jsonlOther28.9 MB bf4bd4711942
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/406.jsonlOther29.1 MB 68aa628e6dd0
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/407.jsonlOther31.0 MB 4d63dfa364b8
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/408.jsonlOther29.6 MB ab74c41655ea
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/409.jsonlOther28.5 MB af88a78b94f6
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/41.jsonlOther20.6 MB ebf810a7ea24
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/410.jsonlOther28.7 MB b5493f583593
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/411.jsonlOther28.8 MB a3bb075d72f4
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/412.jsonlOther28.7 MB eafead66526e
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/413.jsonlOther27.8 MB cbd29819da75
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/414.jsonlOther28.2 MB c87e846cc668
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/415.jsonlOther28.2 MB 04ea16162b83
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/416.jsonlOther28.3 MB 44f44c57d7a9
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/417.jsonlOther29.3 MB ff5e397e19ec
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/418.jsonlOther27.5 MB e3b6826bfc43
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/419.jsonlOther28.8 MB df25b983fbab
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/42.jsonlOther21.5 MB bf347eec5a13
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/420.jsonlOther28.9 MB 11171857a03c
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/421.jsonlOther28.4 MB cab4e8ba123c
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/43.jsonlOther20.3 MB 857bdcc71c07
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/44.jsonlOther20.6 MB 96fcf6fdfd90
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/45.jsonlOther20.7 MB 80334330f0c7
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/46.jsonlOther20.6 MB 06bf2ef78eae
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/47.jsonlOther21.0 MB 7809274cf521
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/48.jsonlOther20.5 MB 5456987f135d
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/49.jsonlOther20.9 MB 2c3d34ca0163
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/5.jsonlOther31.2 MB 8f0588dab979
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/50.jsonlOther21.5 MB 8dccdfa59019
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/51.jsonlOther20.6 MB b36ca784d600
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/52.jsonlOther21.1 MB 34d8946e5ccc
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/53.jsonlOther20.6 MB f925a0c06e25
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/54.jsonlOther21.4 MB 64a0ae5755e7
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/55.jsonlOther19.7 MB 20adb0ed8ec0
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/56.jsonlOther20.6 MB 2110349934fc
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/57.jsonlOther20.9 MB 97398f679a92
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/58.jsonlOther21.5 MB 26c234733692
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/59.jsonlOther21.1 MB 4f87e9810977
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/6.jsonlOther29.9 MB 13c71282b289
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/60.jsonlOther20.9 MB 99e120578e8f
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/61.jsonlOther21.1 MB d71ca9e99c1d
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/62.jsonlOther21.5 MB 793b4b67cc8b
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/63.jsonlOther20.6 MB 4fa39bdca6b2
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/64.jsonlOther21.5 MB 4bbcc08c2877
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/65.jsonlOther21.9 MB 5a5d8f9646fc
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/66.jsonlOther20.5 MB 9fd1bdee39aa
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/67.jsonlOther21.1 MB 992a8dcbad00
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/68.jsonlOther20.8 MB b46c2dced3b5
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/69.jsonlOther21.4 MB add6c0505201
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/7.jsonlOther29.8 MB 3017da733d96
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/70.jsonlOther20.6 MB 63c7d8559de4
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/71.jsonlOther21.9 MB e51e8dbee76b
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/72.jsonlOther21.3 MB af4e1eb64f67
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/73.jsonlOther21.1 MB 990eee265dc6
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/74.jsonlOther21.8 MB e6afcebafcd7
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/75.jsonlOther21.0 MB 2967ea7ba5a9
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/76.jsonlOther21.6 MB d508c7be6deb
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/77.jsonlOther21.6 MB 0ea64cc8876a
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/78.jsonlOther22.0 MB 219004afd182
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/79.jsonlOther21.2 MB 93cb6889a9c5
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/8.jsonlOther28.1 MB 13987ef33017
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/80.jsonlOther21.6 MB 5a1350fbaafe
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/81.jsonlOther21.5 MB ec13106e30b0
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/82.jsonlOther21.1 MB 2e0b5881eb99
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/83.jsonlOther20.6 MB eb3abdab28fa
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/84.jsonlOther21.4 MB 71d6314940e0
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/85.jsonlOther21.3 MB 9b72fd4592c9
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/86.jsonlOther22.1 MB d7ef6a8ba573
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/87.jsonlOther21.9 MB 64d85853dd9b
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/88.jsonlOther23.1 MB d0878747aefb
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/89.jsonlOther21.8 MB 7f67e7750683
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/9.jsonlOther28.4 MB 97957aa117b3
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/90.jsonlOther21.4 MB e7182c029733
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/91.jsonlOther21.8 MB 3843f9f7909f
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/92.jsonlOther21.9 MB ad85cfe90d3e
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/93.jsonlOther23.2 MB 0238a0f777bc
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/94.jsonlOther23.0 MB c7b4b18c7fcf
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/95.jsonlOther21.6 MB 83dbbc779134
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/96.jsonlOther21.8 MB 3e5e618ce874
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/97.jsonlOther22.9 MB c508c08393b1
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/98.jsonlOther21.7 MB a6f45546d018
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/rollouts/99.jsonlOther22.3 MB f638ca5af3e9
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/validation/100.jsonlOther5.8 MB —
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/validation/120.jsonlOther5.8 MB —
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/validation/140.jsonlOther6.2 MB —
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/validation/160.jsonlOther6.3 MB —
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/validation/180.jsonlOther6.3 MB —
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/validation/20.jsonlOther7.0 MB —
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/validation/200.jsonlOther6.2 MB —
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/validation/220.jsonlOther6.4 MB —
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/validation/240.jsonlOther6.6 MB —
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/validation/260.jsonlOther6.7 MB —
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/validation/280.jsonlOther6.5 MB —
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/validation/300.jsonlOther6.6 MB —
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/validation/320.jsonlOther6.7 MB —
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/validation/340.jsonlOther6.6 MB —
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/validation/360.jsonlOther6.4 MB —
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/validation/380.jsonlOther6.6 MB —
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/validation/40.jsonlOther5.7 MB —
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/validation/400.jsonlOther6.5 MB —
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/validation/420.jsonlOther6.3 MB —
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/validation/421.jsonlOther6.3 MB —
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/validation/60.jsonlOther5.5 MB —
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/validation/80.jsonlOther5.5 MB —
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/checkpoints/global_step_421/actor/huggingface/chat_template.jinjaOther2.4 KB —
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/checkpoints/global_step_421/transfer_queue/controller_state.pklOther6.3 MB fb0f6400f55b
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/checkpoints/global_step_421/transfer_queue/simple_storage/su_0_TQ_STORAGE_UNIT_7249731c.pklOther280.0 MB 9e7d67730215
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/checkpoints/global_step_421/transfer_queue/simple_storage/su_1_TQ_STORAGE_UNIT_0862fdd5.pklOther282.5 MB 36dded92d4f8
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/checkpoints/global_step_421/transfer_queue/simple_storage/su_2_TQ_STORAGE_UNIT_e877813c.pklOther281.1 MB b84b0e7b5db2
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/checkpoints/global_step_421/transfer_queue/simple_storage/su_3_TQ_STORAGE_UNIT_7c230002.pklOther280.2 MB 378dbd3b02f3
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/1.jsonlOther27.5 MB bfe31c688922
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/10.jsonlOther27.3 MB 4da13002b73f
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/100.jsonlOther25.7 MB c9941a5c343d
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/101.jsonlOther25.6 MB 63d01da71dcd
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/102.jsonlOther26.7 MB aee37ac748f0
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/103.jsonlOther25.3 MB 63ce7bddeeaa
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/104.jsonlOther26.7 MB cf5d1f008b32
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/105.jsonlOther25.9 MB 7b9ff7bde1dc
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/106.jsonlOther25.6 MB a013bf2ca120
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/107.jsonlOther26.7 MB 651530936898
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/108.jsonlOther24.9 MB 4bc72013b67c
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/109.jsonlOther25.3 MB b57ba488a262
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/11.jsonlOther28.3 MB 362c973a28eb
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/110.jsonlOther24.9 MB b8f7c3bb7cb3
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/111.jsonlOther26.2 MB 173e03ff89de
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/112.jsonlOther27.0 MB d4a84aa361fe
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/113.jsonlOther25.3 MB 214906df441c
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/114.jsonlOther26.2 MB a4b2bc737fd0
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/115.jsonlOther27.8 MB cbca0a0a2b0d
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/116.jsonlOther27.1 MB 8aa9a5c87528
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/117.jsonlOther26.6 MB 8e04e75ede74
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/118.jsonlOther26.3 MB 57f0605d0277
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/119.jsonlOther26.1 MB 7da80aa7c6d5
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/12.jsonlOther27.5 MB cb10e6de3b81
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/120.jsonlOther25.1 MB 3e4dad5c2d64
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/121.jsonlOther25.0 MB fe13f5408848
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/122.jsonlOther25.5 MB 6014bc567613
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/123.jsonlOther26.0 MB ea3b17b4cf7d
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/124.jsonlOther24.4 MB e9016b123f88
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/125.jsonlOther25.9 MB 33562a4e066d
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/126.jsonlOther26.0 MB 3a0202281274
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/127.jsonlOther26.2 MB 30c5366f3618
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/128.jsonlOther27.6 MB 35ccdfe779f8
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/129.jsonlOther24.6 MB 1061fab8acdb
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/13.jsonlOther27.0 MB a487bb3996fb
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/130.jsonlOther25.6 MB cf4b0ee79185
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/131.jsonlOther27.2 MB 19e7b2948c91
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/132.jsonlOther25.3 MB eab88327f303
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/133.jsonlOther25.4 MB 92838f2ce6df
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/134.jsonlOther26.8 MB 3790d23f2bdb
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/135.jsonlOther26.1 MB 252d064571e9
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/136.jsonlOther25.5 MB d5db330c4a78
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/137.jsonlOther26.3 MB cb94b8dd8027
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/138.jsonlOther26.9 MB 05305acf3429
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/139.jsonlOther27.7 MB f019c6e3e216
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/14.jsonlOther27.3 MB 34b3c96a37bb
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/140.jsonlOther27.0 MB 13065ef9d481
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/141.jsonlOther26.6 MB ccf05334388c
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/142.jsonlOther27.0 MB 365c589113fa
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/143.jsonlOther26.2 MB 12f517335dd6
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/144.jsonlOther27.5 MB 649b8f7278f8
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/145.jsonlOther28.1 MB a243a1097604
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/146.jsonlOther26.3 MB 32764332a6b0
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/147.jsonlOther26.7 MB 5a5edd1f11c3
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/148.jsonlOther27.1 MB 42c69afeb949
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/149.jsonlOther25.7 MB b33cb0913e19
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/15.jsonlOther27.6 MB 95b28cbcf39a
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/150.jsonlOther27.9 MB 60ff14a7e823
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/151.jsonlOther27.3 MB 045aed462776
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/152.jsonlOther25.1 MB 13aecb67e4a4
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/153.jsonlOther26.9 MB 031dadc75890
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/154.jsonlOther25.4 MB 5ae3d201ccf7
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/155.jsonlOther25.2 MB 104864d77c4e
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/156.jsonlOther27.2 MB 3f852c41f8b7
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/157.jsonlOther27.5 MB 55f285eecd45
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/158.jsonlOther27.7 MB 7de66bd8a36b
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/159.jsonlOther25.9 MB c638f24aa52e
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/16.jsonlOther26.1 MB 2c6487182d88
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/160.jsonlOther26.8 MB 1310dfe75b27
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/161.jsonlOther25.9 MB 76f3b81b8470
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/162.jsonlOther26.3 MB c1c38352a629
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/163.jsonlOther26.8 MB 88cb8b3eef74
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/164.jsonlOther26.3 MB 100d16be9828
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/165.jsonlOther26.6 MB b1eb54394e40
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/166.jsonlOther25.7 MB 6f6c56a4729e
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/167.jsonlOther27.0 MB 4a39f706c4e3
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/168.jsonlOther26.6 MB 4d5112ddee77
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/169.jsonlOther27.7 MB bf15d21c9c69
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/17.jsonlOther26.7 MB e469c44bcbab
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/170.jsonlOther26.6 MB 518424a5393e
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/171.jsonlOther28.8 MB 6001b8074fee
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/172.jsonlOther28.2 MB b1697c6e517c
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/173.jsonlOther27.5 MB d239904e8713
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/174.jsonlOther27.1 MB 4310ff66c49b
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/175.jsonlOther26.8 MB 901921c81cc3
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/176.jsonlOther27.4 MB df4ba8d00131
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/177.jsonlOther27.0 MB 300f72ceed13
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/178.jsonlOther28.3 MB c6f25a68cef0
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/179.jsonlOther28.2 MB faa057908981
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/18.jsonlOther25.8 MB fee73c7c7da3
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/180.jsonlOther26.8 MB d59608ce35f0
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/181.jsonlOther28.1 MB 76a3acc6d622
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/182.jsonlOther27.8 MB 0898ae51af15
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/183.jsonlOther29.1 MB 158f36a3d19a
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/184.jsonlOther28.5 MB 5853d8ad8d26
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/185.jsonlOther28.4 MB bcc4fe551cb3
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/186.jsonlOther28.1 MB 5632a7bf2416
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/187.jsonlOther29.6 MB d61cb7b5b07e
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/188.jsonlOther29.2 MB 261ce054f08b
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/189.jsonlOther29.7 MB 491e492139c2
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/19.jsonlOther23.7 MB 5b00d2cd8252
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/190.jsonlOther28.0 MB ec092222c670
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/191.jsonlOther29.4 MB 126a1fe2ca34
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/192.jsonlOther28.9 MB 78c00155c0ed
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/193.jsonlOther29.4 MB 43bc8dfce4a4
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/194.jsonlOther28.1 MB ec1cdb6d64fa
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/195.jsonlOther30.8 MB 0a8c1f5f5064
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/196.jsonlOther29.8 MB 909f7ebda5f9
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/197.jsonlOther28.9 MB 64ae943149f6
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/198.jsonlOther28.0 MB 89f371b7dac0
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/199.jsonlOther27.8 MB 08aaa2c5724b
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/2.jsonlOther30.8 MB b1c9d41fcd59
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/20.jsonlOther25.7 MB 9d7d53b605f8
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/200.jsonlOther27.7 MB 86cf001e6be0
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/201.jsonlOther27.8 MB e698a4e76f75
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/202.jsonlOther28.0 MB d48336546b00
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/203.jsonlOther28.6 MB 53f4af624ab3
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/204.jsonlOther26.1 MB fc29628f392a
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/205.jsonlOther27.9 MB 42a312f422e3
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/206.jsonlOther28.2 MB b28b7e31113b
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/207.jsonlOther29.0 MB 991b441e2e11
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/208.jsonlOther29.6 MB a097dcec68e9
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/209.jsonlOther27.8 MB d5c3ac0e1146
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/21.jsonlOther25.4 MB 981273947dc7
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/210.jsonlOther29.0 MB 2bf10e2f182b
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/211.jsonlOther28.1 MB cc18427aaf50
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/212.jsonlOther28.6 MB ccf39eff1c56
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/213.jsonlOther29.7 MB fd551e893f2a
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/214.jsonlOther28.7 MB ce4e569aed6a
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/215.jsonlOther30.2 MB 46299749f144
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/216.jsonlOther29.5 MB 955b5d86d1e9
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/217.jsonlOther28.6 MB 66a824dd12b9
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/218.jsonlOther28.7 MB ca985a63ac99
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/219.jsonlOther27.9 MB 4a0050bea78c
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/22.jsonlOther25.5 MB dd97907dcb32
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/220.jsonlOther29.7 MB f9e83db340c0
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/221.jsonlOther29.8 MB 3d30b4f0d7ec
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/222.jsonlOther31.2 MB 29743d421300
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/223.jsonlOther29.4 MB a05144df26d9
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/224.jsonlOther30.9 MB b120e83bfd60
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/225.jsonlOther29.3 MB 2edd522170eb
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/226.jsonlOther29.1 MB bd00f4f9770c
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/227.jsonlOther31.3 MB d45bc4ef9a5a
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/228.jsonlOther30.0 MB 68ab23f2026e
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/229.jsonlOther31.0 MB d2105bd0e272
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/23.jsonlOther24.4 MB 286246515a91
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/230.jsonlOther30.8 MB 94e7ec01f3ad
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/231.jsonlOther30.2 MB 7793627bfab0
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/232.jsonlOther30.6 MB c17e2bac0d08
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/233.jsonlOther30.7 MB 7c66f08fd743
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/234.jsonlOther28.1 MB 8de7bb2e4d87
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/235.jsonlOther28.1 MB c4d0e06a3ccb
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/236.jsonlOther29.2 MB 649cb41b2fd8
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/237.jsonlOther30.9 MB 3613ad9c945f
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/238.jsonlOther29.4 MB 7c3f0d2f0786
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/239.jsonlOther31.0 MB 6e7c6c1d03d4
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/24.jsonlOther24.8 MB 30b0445c695f
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/240.jsonlOther32.1 MB 568678bf66f2
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/241.jsonlOther29.3 MB 72c70c646caf
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/242.jsonlOther28.7 MB 90aeaaa42312
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/243.jsonlOther29.6 MB c3ae647e8901
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/244.jsonlOther29.5 MB 0dafe96c1709
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/245.jsonlOther30.1 MB 4c66be03a600
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/246.jsonlOther28.8 MB ec76860362d7
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/247.jsonlOther30.3 MB bcc4f2c83fa1
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/248.jsonlOther29.2 MB 28604e45561f
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/249.jsonlOther29.4 MB 8697330c76e7
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/25.jsonlOther24.7 MB 9472e2513453
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/250.jsonlOther30.2 MB 39a1e53c2fc9
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/251.jsonlOther28.8 MB 5c88d3a7f85b
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/252.jsonlOther29.9 MB ea765da9bb84
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/253.jsonlOther29.9 MB 3602b8656ff3
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/254.jsonlOther28.6 MB 69376d5a7b73
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/255.jsonlOther29.1 MB 1c757240029b
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/256.jsonlOther27.2 MB d5753fe82d82
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/257.jsonlOther28.6 MB cba60619948c
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/258.jsonlOther29.4 MB 3415dd56cc36
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/259.jsonlOther29.2 MB 464f08ee14aa
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/26.jsonlOther25.6 MB 8a7399f90616
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/260.jsonlOther30.2 MB 6dae10304ae2
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/261.jsonlOther30.3 MB 7bbf0dfc2c99
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/262.jsonlOther28.6 MB ede1f7b42465
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/263.jsonlOther31.6 MB 65716d3763f4
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/264.jsonlOther31.9 MB aa84c48ee04b
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/265.jsonlOther30.6 MB accb4575b3bd
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/266.jsonlOther29.8 MB 98f1eaacf23d
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/267.jsonlOther31.2 MB 728f383a9f30
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/268.jsonlOther32.5 MB 234b087e90bc
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/269.jsonlOther30.9 MB 1a59534a7e90
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/27.jsonlOther24.4 MB 1e72abff5198
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/270.jsonlOther32.3 MB 1fe9fed71c80
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/271.jsonlOther30.9 MB 87daf14519b6
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/272.jsonlOther32.5 MB 76ce0a3dae7b
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/273.jsonlOther29.5 MB 5da4cb33b103
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/274.jsonlOther30.6 MB aaf30324440d
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/275.jsonlOther30.7 MB ad4fd5e8ed52
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/276.jsonlOther32.8 MB 80d2b30db190
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/277.jsonlOther32.8 MB 607d77525b9f
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/278.jsonlOther31.6 MB 9263a36f67de
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/279.jsonlOther31.8 MB 51cb8c5f396f
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/28.jsonlOther24.7 MB 9e83053e0762
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/280.jsonlOther33.0 MB 438a5a5fe4ad
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/281.jsonlOther31.6 MB 8d0197aafc7f
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/282.jsonlOther31.2 MB e4554a42d29b
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/283.jsonlOther31.5 MB 4cafa5a5ed07
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/284.jsonlOther30.2 MB d6a4ad1c8c49
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/285.jsonlOther29.7 MB 624cca25d2fe
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/286.jsonlOther32.2 MB 26ba79a0abbf
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/287.jsonlOther30.6 MB c1186e00696a
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/288.jsonlOther30.3 MB 00dd25150b8f
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/289.jsonlOther32.1 MB 09ffc6bcd1a9
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/29.jsonlOther24.4 MB fa6cbc2533e3
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/290.jsonlOther31.0 MB f3d216277da1
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/291.jsonlOther30.6 MB c286959a873a
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/292.jsonlOther32.9 MB 382921f05f63
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/293.jsonlOther32.3 MB 97e45c53b960
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/294.jsonlOther30.8 MB 0e240b913fd1
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/295.jsonlOther32.6 MB 7631480ea87f
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/296.jsonlOther32.8 MB e88dad70eef9
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/297.jsonlOther30.3 MB cb4a518c78fb
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/298.jsonlOther31.1 MB 875a3b6f1ad1
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/299.jsonlOther30.6 MB bc19d41ceeba
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/3.jsonlOther29.8 MB 8edf0b6fe50e
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/30.jsonlOther25.0 MB d66d62a9816c
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/300.jsonlOther31.0 MB 5b24c63ecbcb
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/301.jsonlOther28.7 MB 3b98ee899ef3
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/302.jsonlOther31.0 MB 66e47c2441a7
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/303.jsonlOther30.1 MB 57f2cb43bd58
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/304.jsonlOther32.1 MB 92a71c211653
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/305.jsonlOther30.8 MB 3afdcbf56d11
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/306.jsonlOther30.5 MB e3af3e42af27
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/307.jsonlOther31.7 MB d6db4ba087f4
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/308.jsonlOther31.3 MB eba3401c8164
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/309.jsonlOther30.6 MB 4f6486f67093
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/31.jsonlOther24.5 MB 132ea13d1386
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/310.jsonlOther30.7 MB ff868a5c2d04
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/311.jsonlOther30.9 MB 04cf531756c3
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/312.jsonlOther30.5 MB a30f94ec292e
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/313.jsonlOther28.6 MB 6ae131bb3fec
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/314.jsonlOther30.1 MB e4c41b998b83
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/315.jsonlOther29.0 MB 8a26456ded77
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/316.jsonlOther29.6 MB efe332f52ca5
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/317.jsonlOther28.8 MB b2b70cbaf5a7
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/318.jsonlOther28.1 MB 1585ee960a02
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/319.jsonlOther28.3 MB 35634dc01b09
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/32.jsonlOther24.0 MB 50c8cf65353d
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/320.jsonlOther29.0 MB cf0586333b4a
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/321.jsonlOther29.4 MB 5611c1f2575b
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/322.jsonlOther27.7 MB 10126ca8256e
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/323.jsonlOther30.5 MB a24b0bb14647
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/324.jsonlOther30.4 MB 2a96fd29b0e3
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/325.jsonlOther30.8 MB 9c6a7240aedd
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/326.jsonlOther28.5 MB 87a442e260b7
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/327.jsonlOther28.8 MB e085a6b4d84d
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/328.jsonlOther30.1 MB 0363d6f5d565
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/329.jsonlOther30.3 MB 5dcf7b3fca40
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/33.jsonlOther24.3 MB b7720ed32b71
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/330.jsonlOther29.1 MB cee770f21acd
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/331.jsonlOther31.2 MB e168520149e0
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/332.jsonlOther28.5 MB b0827cc03466
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/333.jsonlOther29.4 MB dcdf832625b4
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/334.jsonlOther27.7 MB 8c2ca0dffc1b
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/335.jsonlOther30.4 MB 5e76338d0ae3
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/336.jsonlOther28.4 MB 2afab0fdbc6d
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/337.jsonlOther28.7 MB 2979dcfa1601
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/338.jsonlOther30.0 MB e455b8736c47
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/339.jsonlOther29.4 MB 8f00ac2738db
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/34.jsonlOther23.0 MB 964346822bd3
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/340.jsonlOther29.0 MB d9a1e4fefeb0
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/341.jsonlOther29.1 MB 89f1b2f16736
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/342.jsonlOther28.2 MB ab23ec8d615b
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/343.jsonlOther29.4 MB 6129ae864970
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/344.jsonlOther28.6 MB 2a1831e02358
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/345.jsonlOther30.2 MB a9fbdcd9192d
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/346.jsonlOther31.0 MB 9886c0673f0a
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/347.jsonlOther30.2 MB 5f4f344470e8
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/348.jsonlOther29.7 MB f02a95771063
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/349.jsonlOther29.8 MB 498157b99f41
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/35.jsonlOther23.2 MB 27e1c6729820
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/350.jsonlOther29.5 MB d322ef0e63ae
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/351.jsonlOther30.4 MB 650154569e61
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/352.jsonlOther30.1 MB 1667b2bcc60b
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/353.jsonlOther31.0 MB 01ba42b1a4a4
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/354.jsonlOther29.6 MB b3d6d9457389
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/355.jsonlOther30.5 MB 1ae16a626d9b
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/356.jsonlOther28.1 MB 8461834ef3f3
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/357.jsonlOther29.9 MB 3369da1477d2
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/358.jsonlOther29.2 MB 4c9d0ecdf0ee
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/359.jsonlOther29.8 MB ec6c6f04e57b
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/36.jsonlOther22.3 MB 0f42fd2252bb
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/360.jsonlOther30.1 MB 035f4ea46e1e
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/361.jsonlOther30.8 MB 22d382241a1b
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/362.jsonlOther30.2 MB 504d499204d8
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/363.jsonlOther29.9 MB 2ab156a6b6b3
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/364.jsonlOther30.1 MB b8e373c82708
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/365.jsonlOther30.1 MB 0e95587062a0
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/366.jsonlOther29.9 MB 0aafbc5b746e
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/367.jsonlOther29.5 MB 0c1a6e53850a
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/368.jsonlOther27.1 MB 68049aac41ab
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/369.jsonlOther30.7 MB bac50716837d
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/37.jsonlOther23.1 MB e6ea50570cea
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/370.jsonlOther30.0 MB f90374f84336
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/371.jsonlOther30.2 MB c65bd9b94ff7
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/372.jsonlOther29.3 MB de747b6d6185
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/373.jsonlOther29.1 MB 229f0d7085ab
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/374.jsonlOther28.8 MB 074aaec4a648
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/375.jsonlOther28.2 MB 78125f0cb75d
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/376.jsonlOther29.1 MB 47c99dc067f0
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/377.jsonlOther28.9 MB 0019caaa976f
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/378.jsonlOther28.5 MB 029cb7962963
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/379.jsonlOther29.7 MB 3ac372386621
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/38.jsonlOther23.6 MB 46701547ceb0
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/380.jsonlOther29.1 MB 32f40a0cd7b3
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/381.jsonlOther28.1 MB 77b06f019a0d
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/382.jsonlOther29.2 MB 3ebb5f600f4e
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/383.jsonlOther27.9 MB 2c2557ab5868
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/384.jsonlOther32.3 MB 3d492959ad6a
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/385.jsonlOther28.4 MB 71665aab1d27
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/386.jsonlOther29.4 MB c5fb8c1c0217
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/387.jsonlOther29.0 MB ea7aae5312b2
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/388.jsonlOther29.1 MB c6bc2c1b86aa
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/389.jsonlOther28.9 MB 4fe4aee2fdb4
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/39.jsonlOther23.1 MB 49a39cbf7b08
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/390.jsonlOther27.8 MB 52efdf0942a3
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/391.jsonlOther29.4 MB 9025285427a7
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/392.jsonlOther30.0 MB 0062a4a2c4fe
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/393.jsonlOther28.8 MB 1bea5be18895
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/394.jsonlOther29.5 MB 833660c37563
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/395.jsonlOther28.8 MB 1165ff2107d4
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/396.jsonlOther27.7 MB 7dfe6d7e57a9
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/397.jsonlOther27.9 MB 7f38598117ff
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/398.jsonlOther27.7 MB 2c3128f992cd
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/399.jsonlOther28.5 MB 6bf5b9be1a55
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/4.jsonlOther29.5 MB 9e043f19ee82
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/40.jsonlOther23.3 MB 71aa5ea1d2df
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/400.jsonlOther28.5 MB db5e73a48e7e
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/401.jsonlOther27.3 MB ad5ab1581a33
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/402.jsonlOther28.6 MB 9fb42f45d0a9
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/403.jsonlOther29.0 MB 3fe70670c78a
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/404.jsonlOther28.9 MB da40924ec739
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/405.jsonlOther27.4 MB ed7d7271436e
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/406.jsonlOther27.2 MB 2e505f8a4fe1
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/407.jsonlOther29.1 MB b6c5112b68a5
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/408.jsonlOther27.0 MB 3cd30bc493b8
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/409.jsonlOther26.6 MB 3b0c438aaf73
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/41.jsonlOther22.9 MB 6c88a2c38ec8
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/410.jsonlOther27.5 MB ce840e100418
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/411.jsonlOther28.2 MB 24ce26513500
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/412.jsonlOther27.2 MB 7fe742d73208
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/413.jsonlOther27.1 MB 77c6596c9117
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/414.jsonlOther28.3 MB 716f1852a979
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/415.jsonlOther28.2 MB 675073b7f552
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/416.jsonlOther28.9 MB 11205f5d0d02
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/417.jsonlOther29.1 MB 048383dd93bb
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/418.jsonlOther28.5 MB ab149787d533
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/419.jsonlOther29.6 MB 7d1944bb86bb
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/42.jsonlOther24.5 MB f520d0b76323
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/420.jsonlOther30.0 MB 822d9f91807d
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/421.jsonlOther28.9 MB e318e0415e2a
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/43.jsonlOther23.9 MB e970ed5064e6
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/44.jsonlOther23.5 MB b7d5d9ea0ca0
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/45.jsonlOther23.2 MB 5954c4793ecb
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/46.jsonlOther23.9 MB 8825648af104
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/47.jsonlOther23.7 MB 215caa9ae5bb
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/48.jsonlOther22.9 MB 8a5d25044974
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/49.jsonlOther23.4 MB efe38959e9cb
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/5.jsonlOther30.2 MB 9bd616b23511
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/50.jsonlOther23.3 MB b7e559a0ca82
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/51.jsonlOther23.2 MB a414bd88389b
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/52.jsonlOther23.1 MB bcf2afd02b75
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/53.jsonlOther23.2 MB e360d86831b4
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/54.jsonlOther24.0 MB ffbb6ceb1e08
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/55.jsonlOther21.7 MB f3fef8beb2e3
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/56.jsonlOther22.9 MB db61dec7c711
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/57.jsonlOther23.7 MB 833f30aa1180
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/58.jsonlOther24.4 MB d3d7a894436e
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/59.jsonlOther24.0 MB 5dcba0b5158a
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/6.jsonlOther28.3 MB 9a49f54d06c3
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/60.jsonlOther23.8 MB d4605d039b11
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/61.jsonlOther23.2 MB 627bd677d0fb
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/62.jsonlOther24.8 MB 045754f36dbe
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/63.jsonlOther23.0 MB 7cf03ce596d2
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/64.jsonlOther24.5 MB f5379fe5d226
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/65.jsonlOther24.7 MB 09a71e07494f
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/66.jsonlOther23.3 MB 7d7828d28456
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/67.jsonlOther23.7 MB 66cb646b4ce1
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/68.jsonlOther22.7 MB b3b27df8447d
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/69.jsonlOther23.8 MB 1da9afddf8f7
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/7.jsonlOther29.4 MB 1e75a27baf50
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/70.jsonlOther23.6 MB 401a54998c7c
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/71.jsonlOther24.7 MB 32c7d84c3bb4
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/72.jsonlOther24.2 MB 55aaccd94ec7
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/73.jsonlOther24.2 MB c88692c63d62
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/74.jsonlOther24.6 MB a9ceead6061e
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/75.jsonlOther24.1 MB d0d1f53e5b02
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/76.jsonlOther24.3 MB 4f2e6f5cabca
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/77.jsonlOther24.6 MB a892cbdec928
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/78.jsonlOther24.5 MB 01bf3e405a7e
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/79.jsonlOther24.5 MB 010f810da93e
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/8.jsonlOther27.1 MB 3ab3d0a636a7
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/80.jsonlOther25.2 MB b5b864946ad0
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/81.jsonlOther25.4 MB 48db8c7d7cea
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/82.jsonlOther24.8 MB 9c61fa016f43
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/83.jsonlOther24.1 MB 38ff3d5e6ab5
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/84.jsonlOther24.6 MB c9b2b0f91bde
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/85.jsonlOther24.7 MB 6e202ce2c6eb
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/86.jsonlOther25.8 MB 70c4951b5f07
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/87.jsonlOther25.9 MB d84f13f59d82
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/88.jsonlOther26.3 MB 456954f60984
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/89.jsonlOther24.8 MB bac6f9117e58
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/9.jsonlOther28.5 MB be5d0d851e28
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/90.jsonlOther23.6 MB 403531df5ad0
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/91.jsonlOther24.4 MB 135396d64264
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/92.jsonlOther24.4 MB 708ba94bb23c
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/93.jsonlOther25.6 MB f7f146cc321d
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/94.jsonlOther25.2 MB 3a29efc27ad4
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/95.jsonlOther24.9 MB 2fc2412ce139
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/96.jsonlOther24.4 MB e3fc5adcdad2
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/97.jsonlOther26.1 MB ed1d8b1cb3cc
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/98.jsonlOther24.6 MB 48a9be9165bb
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/rollouts/99.jsonlOther25.4 MB dde7c64ac1b3
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/validation/100.jsonlOther5.8 MB —
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/validation/120.jsonlOther6.0 MB —
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/validation/140.jsonlOther6.1 MB —
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/validation/160.jsonlOther6.0 MB —
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/validation/180.jsonlOther6.2 MB —
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/validation/20.jsonlOther6.1 MB —
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/validation/200.jsonlOther6.2 MB —
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/validation/220.jsonlOther6.3 MB —
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/validation/240.jsonlOther6.3 MB —
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/validation/260.jsonlOther6.5 MB —
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/validation/280.jsonlOther6.6 MB —
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/validation/300.jsonlOther6.4 MB —
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/validation/320.jsonlOther6.2 MB —
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/validation/340.jsonlOther6.4 MB —
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/validation/360.jsonlOther6.4 MB —
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/validation/380.jsonlOther6.3 MB —
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/validation/40.jsonlOther5.6 MB —
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/validation/400.jsonlOther6.1 MB —
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/validation/420.jsonlOther6.3 MB —
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/validation/421.jsonlOther6.3 MB —
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/validation/60.jsonlOther5.6 MB —
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/validation/80.jsonlOther5.8 MB —
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/checkpoints/global_step_421/actor/huggingface/chat_template.jinjaOther2.4 KB —
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/checkpoints/global_step_421/transfer_queue/controller_state.pklOther9.5 MB 32d60d0aaba5
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/checkpoints/global_step_421/transfer_queue/simple_storage/su_0_TQ_STORAGE_UNIT_c16b44a8.pklOther450.0 MB 9c2a51f88404
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/checkpoints/global_step_421/transfer_queue/simple_storage/su_1_TQ_STORAGE_UNIT_62164708.pklOther455.7 MB c5f9120377bb
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/checkpoints/global_step_421/transfer_queue/simple_storage/su_2_TQ_STORAGE_UNIT_ce2b2438.pklOther444.1 MB b2b463ae7e78
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/checkpoints/global_step_421/transfer_queue/simple_storage/su_3_TQ_STORAGE_UNIT_cea4c426.pklOther449.4 MB 38ef5f0406f0
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/1.jsonlOther21.7 MB 5e48e62a9f22
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/10.jsonlOther23.7 MB 3483501027c6
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/100.jsonlOther25.4 MB 00ffb99d30d9
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/101.jsonlOther26.1 MB c0d5bfd9a3be
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/102.jsonlOther27.6 MB b6bfc23aabc0
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/103.jsonlOther24.8 MB e6260ec22ad3
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/104.jsonlOther26.6 MB b117faa1c4f5
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/105.jsonlOther26.5 MB aa19f8c02f86
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/106.jsonlOther25.7 MB c49adcc540cf
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/107.jsonlOther26.1 MB e5e33d97bc1d
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/108.jsonlOther24.5 MB d23dae14daff
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/109.jsonlOther25.5 MB cc9ab1994111
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/11.jsonlOther24.1 MB de89e0559efd
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/110.jsonlOther24.5 MB 153533bcaade
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/111.jsonlOther25.6 MB a933ed6465b8
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/112.jsonlOther26.5 MB ecad07dff55f
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/113.jsonlOther24.8 MB ad631f7ccebf
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/114.jsonlOther25.8 MB dfa3711d58ca
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/115.jsonlOther26.8 MB a2e484fe2603
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/116.jsonlOther27.0 MB 191a90066d1a
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/117.jsonlOther26.1 MB 853bdef3be70
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/118.jsonlOther25.5 MB 97f24195c318
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/119.jsonlOther25.5 MB 6fa8c8d72480
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/12.jsonlOther24.5 MB b9df34f3e240
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/120.jsonlOther24.5 MB 4f4065064719
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/121.jsonlOther24.7 MB 51023a532944
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/122.jsonlOther25.6 MB 72d5078a71f6
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/123.jsonlOther25.8 MB 9a9e61cd85d1
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/124.jsonlOther24.5 MB b89d84fa19df
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/125.jsonlOther25.8 MB 707fe8486c15
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/126.jsonlOther25.9 MB ca93ad9df391
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/127.jsonlOther25.7 MB bfc76c49cfe6
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/128.jsonlOther27.5 MB c6c91bbf426f
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/129.jsonlOther24.9 MB cef655e3f11c
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/13.jsonlOther23.6 MB f55a360d8e16
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/130.jsonlOther25.4 MB 0e07231969a3
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/131.jsonlOther26.9 MB df8990abd9a4
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/132.jsonlOther26.2 MB 862bebe25056
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/133.jsonlOther25.5 MB 2f6e5a3c7bc6
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/134.jsonlOther26.4 MB 92fc29f2f8d5
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/135.jsonlOther25.7 MB 2d0b32bbf7cd
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/136.jsonlOther25.1 MB b55a84105054
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/137.jsonlOther27.2 MB ca113a058f79
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/138.jsonlOther27.0 MB b71525c065c0
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/139.jsonlOther27.6 MB fbcab4dfc2be
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/14.jsonlOther24.4 MB 98bfd718e33b
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/140.jsonlOther26.6 MB 9d0b4266a0a5
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/141.jsonlOther26.6 MB f19d27c9e433
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/142.jsonlOther26.6 MB 7eb72ad81589
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/143.jsonlOther26.6 MB c76ec901509f
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/144.jsonlOther26.6 MB 12662e36f6ac
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/145.jsonlOther27.9 MB ccf30c138145
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/146.jsonlOther25.9 MB 212893594d67
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/147.jsonlOther27.3 MB f62605d71253
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/148.jsonlOther26.5 MB cc7fad801b78
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/149.jsonlOther25.7 MB c9c30a7cef04
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/15.jsonlOther24.9 MB fe2643092acd
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/150.jsonlOther28.7 MB 043f5c999fc8
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/151.jsonlOther27.2 MB 928fe56d55c9
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/152.jsonlOther26.3 MB 1edbc0db1081
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/153.jsonlOther26.5 MB 062ed2d821f6
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/154.jsonlOther25.4 MB 1e0916ec88d8
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/155.jsonlOther25.1 MB 2186c04b3902
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/156.jsonlOther26.9 MB af25365f73ae
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/157.jsonlOther27.0 MB be537656d325
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/158.jsonlOther27.7 MB 89961d51fc15
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/159.jsonlOther26.4 MB 9dee027bf846
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/16.jsonlOther23.0 MB 8efbef173a09
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/160.jsonlOther27.3 MB d2e7057bc97d
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/161.jsonlOther25.9 MB cb014e0a89a6
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/162.jsonlOther26.5 MB 35b683f3abd6
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/163.jsonlOther26.7 MB 7c99933c235d
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/164.jsonlOther26.6 MB 7544af13c0eb
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/165.jsonlOther26.5 MB 01192902d743
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/166.jsonlOther25.5 MB bdfebeb70d37
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/167.jsonlOther27.0 MB 994ea133c4fd
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/168.jsonlOther26.3 MB fdc4066998c3
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/169.jsonlOther27.0 MB 786f8445cfd2
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/17.jsonlOther24.1 MB d731351fbc35
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/170.jsonlOther26.1 MB 21764e783752
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/171.jsonlOther28.6 MB 62133da686ce
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/172.jsonlOther27.1 MB f7bedc03f942
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/173.jsonlOther26.8 MB 796cf5655f5f
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/174.jsonlOther27.3 MB 050220afd1a0
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/175.jsonlOther26.1 MB 20247237c60b
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/176.jsonlOther26.6 MB 11921b69179c
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/177.jsonlOther27.2 MB ee1f8dc64e2d
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/178.jsonlOther27.5 MB 00b378ed86d2
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/179.jsonlOther26.5 MB 0d5e138b8f10
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/18.jsonlOther23.7 MB 4970af074927
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/180.jsonlOther26.1 MB 100c5f3b0b59
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/181.jsonlOther26.7 MB 00b358abab71
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/182.jsonlOther27.0 MB c010a99a434c
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/183.jsonlOther27.4 MB e11138cd5e6f
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/184.jsonlOther26.4 MB e575c4895998
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/185.jsonlOther27.0 MB 5b5889dbf7d1
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/186.jsonlOther26.7 MB bd62e1efd754
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/187.jsonlOther26.9 MB f4d4b9e172f7
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/188.jsonlOther27.3 MB 44606d2a4bf9
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/189.jsonlOther27.8 MB 172b260f283b
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/19.jsonlOther22.0 MB 0d4cb109e94c
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/190.jsonlOther26.5 MB e1754db56b36
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/191.jsonlOther27.7 MB 8fa997b14070
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/192.jsonlOther27.6 MB bff90a9d537e
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/193.jsonlOther27.4 MB add5a0a5ca26
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/194.jsonlOther26.5 MB acc5cacc732b
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/195.jsonlOther28.6 MB 8b2543a0161d
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/196.jsonlOther27.4 MB cccce6c46ecf
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/197.jsonlOther27.2 MB 479dfb3a772b
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/198.jsonlOther26.6 MB 72714c0c059b
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/199.jsonlOther26.4 MB 671cf58f043b
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/2.jsonlOther25.2 MB 50f6f6feadb4
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/20.jsonlOther24.3 MB ffa20a02c552
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/200.jsonlOther26.7 MB a59529f3d5f4
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/201.jsonlOther27.7 MB 2bb901feec71
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/202.jsonlOther27.6 MB 5aa9f3437cb7
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/203.jsonlOther28.4 MB cd785a0cb69e
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/204.jsonlOther25.3 MB 80e7c00b7099
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/205.jsonlOther26.7 MB 8360509a0980
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/206.jsonlOther26.8 MB 6c822bdd878d
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/207.jsonlOther27.5 MB ebbcae621ba5
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/208.jsonlOther27.9 MB 86ff6dd37555
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/209.jsonlOther26.2 MB 9b2c9519a6fa
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/21.jsonlOther24.9 MB 7f8f21540574
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/210.jsonlOther28.3 MB afd0111befed
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/211.jsonlOther27.6 MB a3c638b35721
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/212.jsonlOther27.4 MB e5863193e15e
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/213.jsonlOther29.2 MB 32745c5b6279
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/214.jsonlOther28.4 MB df834dda260f
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/215.jsonlOther28.2 MB 354fc44b776d
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/216.jsonlOther27.9 MB b31af400140b
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/217.jsonlOther27.2 MB 9a7d8057f675
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/218.jsonlOther28.1 MB 566fdaef55c9
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/219.jsonlOther26.6 MB 75f674ac138e
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/22.jsonlOther25.0 MB 57170288937e
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/220.jsonlOther28.6 MB 000ef7419eff
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/221.jsonlOther28.5 MB 7d122178e763
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/222.jsonlOther30.0 MB 20abe441939b
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/223.jsonlOther28.2 MB d8c6b54317af
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/224.jsonlOther28.4 MB 44ec6408c03a
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/225.jsonlOther26.8 MB 611c68e57db5
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/226.jsonlOther26.8 MB 05f228aa6151
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/227.jsonlOther28.3 MB ef05ef9005a2
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/228.jsonlOther27.4 MB 4459f310ee5b
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/229.jsonlOther27.9 MB 998a67a50976
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/23.jsonlOther23.6 MB e064797a9a5b
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/230.jsonlOther28.3 MB afbb6d6a3ef6
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/231.jsonlOther27.7 MB a23a6a92598a
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/232.jsonlOther27.3 MB afb33f04a51d
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/233.jsonlOther27.9 MB 06d6780c4917
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/234.jsonlOther25.6 MB 66ec90963901
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/235.jsonlOther25.1 MB f96a1921742f
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/236.jsonlOther26.6 MB a40aeeacceef
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/237.jsonlOther27.9 MB 80861e0e64c5
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/238.jsonlOther26.9 MB c2d488144d89
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/239.jsonlOther28.3 MB ab87faa16e29
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/24.jsonlOther24.8 MB cbfce2dc0eee
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/240.jsonlOther28.7 MB 3fcae59871d6
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/241.jsonlOther26.8 MB 30305b289526
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/242.jsonlOther27.0 MB 6eabefa2e257
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/243.jsonlOther28.2 MB faba16d25a40
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/244.jsonlOther28.3 MB 76fa68904b1c
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/245.jsonlOther28.6 MB f0a1860ff4f6
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/246.jsonlOther27.2 MB f7e863781aa2
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/247.jsonlOther28.6 MB 353a2a4e1d6d
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/248.jsonlOther27.8 MB 8964dbc3daec
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/249.jsonlOther27.6 MB 833a5372f87c
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/25.jsonlOther24.3 MB 891afb825dc7
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/250.jsonlOther28.1 MB d188776e6dcf
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/251.jsonlOther27.5 MB 16e1a79715d7
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/252.jsonlOther28.0 MB ec6d6a3d61f6
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/253.jsonlOther28.1 MB d94ffd87ee3c
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/254.jsonlOther27.0 MB 4ae6b0e41d21
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/255.jsonlOther27.1 MB 71aa0c4a0502
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/256.jsonlOther25.5 MB 05424b87a559
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/257.jsonlOther26.5 MB e1cf075d5437
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/258.jsonlOther28.4 MB 3b10b93fef55
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/259.jsonlOther28.4 MB ce145907497d
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/26.jsonlOther25.0 MB 0a009155b172
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/260.jsonlOther28.4 MB 7d9e1d435ddd
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/261.jsonlOther28.5 MB 26f5fb8e76b1
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/262.jsonlOther27.0 MB e9772636b7d6
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/263.jsonlOther28.9 MB 581bf6859100
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/264.jsonlOther28.9 MB ab1ed0f5c32e
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/265.jsonlOther28.1 MB dced4b7d48b2
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/266.jsonlOther28.1 MB 60b2e9e30101
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/267.jsonlOther28.3 MB ce2647c8e063
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/268.jsonlOther29.4 MB feb1fff51011
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/269.jsonlOther27.9 MB 486d626aa8ef
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/27.jsonlOther24.1 MB 568fa2e6e971
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/270.jsonlOther28.3 MB f1cddc14ac2c
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/271.jsonlOther28.1 MB 10314e7e259c
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/272.jsonlOther29.2 MB 85f98453152d
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/273.jsonlOther26.4 MB 9be054dea6d1
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/274.jsonlOther26.9 MB a2ffb1d00919
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/275.jsonlOther28.3 MB a33cd73c5314
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/276.jsonlOther28.7 MB c32da14beffc
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/277.jsonlOther28.0 MB 54068887a1b7
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/278.jsonlOther27.2 MB 2b2c947f9664
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/279.jsonlOther27.3 MB 6e6feb436666
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/28.jsonlOther23.8 MB 9e2a15521394
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/280.jsonlOther28.2 MB efc53ef75535
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/281.jsonlOther27.6 MB b9f12f51b038
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/282.jsonlOther27.8 MB d5ac80146cfb
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/283.jsonlOther28.2 MB 30e72dfd3459
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/284.jsonlOther27.4 MB 4095042d7714
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/285.jsonlOther25.6 MB 960ce5aacd9c
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/286.jsonlOther28.1 MB 134bd3853785
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/287.jsonlOther27.6 MB c789d4046817
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/288.jsonlOther26.7 MB ba41c1b1fe6c
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/289.jsonlOther27.5 MB 94117a6a4570
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/29.jsonlOther23.0 MB 90ba36cdb46e
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/290.jsonlOther25.9 MB 5b790b494bab
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/291.jsonlOther26.7 MB f28c47096caf
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/292.jsonlOther27.9 MB 9d8c5b367400
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/293.jsonlOther27.7 MB 8628622aee14
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/294.jsonlOther26.7 MB 5099baec4ebe
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/295.jsonlOther27.3 MB 240632c66bb5
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/296.jsonlOther27.4 MB d2efd598a67d
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/297.jsonlOther27.1 MB c6c0449bfd7c
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/298.jsonlOther28.1 MB 74a140d6c030
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/299.jsonlOther27.5 MB 893e57a7c0db
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/3.jsonlOther23.7 MB 8c8e42827352
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/30.jsonlOther24.5 MB e150a1ac9b23
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/300.jsonlOther27.1 MB 61b906628099
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/301.jsonlOther25.5 MB a7c121264f8f
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/302.jsonlOther27.7 MB d67339dc2988
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/303.jsonlOther27.3 MB 6f0fe6a7408f
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/304.jsonlOther28.7 MB db381fffcf5a
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/305.jsonlOther27.7 MB 37b62b40b395
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/306.jsonlOther26.6 MB 1fe40531ce16
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/307.jsonlOther27.7 MB 79729d2ca3b6
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/308.jsonlOther27.8 MB 9748b4a29aa3
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/309.jsonlOther27.7 MB 30a28d20bff7
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/31.jsonlOther23.6 MB 1da6d592ea4c
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/310.jsonlOther27.3 MB 227f64277a0e
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/311.jsonlOther27.3 MB af88b0ec89d7
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/312.jsonlOther27.7 MB e22c1405e0f0
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/313.jsonlOther26.4 MB 4a4881f740b2
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/314.jsonlOther27.4 MB 116527199386
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/315.jsonlOther27.2 MB 37dccb46285d
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/316.jsonlOther26.8 MB 2ec5a79ad282
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/317.jsonlOther26.5 MB 6a21eb908f21
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/318.jsonlOther26.4 MB fa0dbb91301c
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/319.jsonlOther26.2 MB 9d1958b58f8a
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/32.jsonlOther23.7 MB 586b0dfb448f
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/320.jsonlOther27.0 MB c3d479467b3f
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/321.jsonlOther27.4 MB 9b310d5a7bb6
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/322.jsonlOther26.2 MB 4b51ddc9d96a
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/323.jsonlOther27.9 MB 9c777b757ce7
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/324.jsonlOther28.0 MB 122fdd19913e
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/325.jsonlOther28.8 MB 8f0f71bae164
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/326.jsonlOther26.6 MB 4b88e26ac73d
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/327.jsonlOther26.6 MB ca3599d66e5a
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/328.jsonlOther27.7 MB fdeaff7eb2fe
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/329.jsonlOther28.0 MB b903ff072f6d
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/33.jsonlOther24.5 MB 2fe09ceb4ee1
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/330.jsonlOther26.5 MB e69ac1f7ae76
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/331.jsonlOther28.2 MB 7e38e64984b3
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/332.jsonlOther26.5 MB 5e91162cc91d
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/333.jsonlOther26.5 MB 4bdeb01a7388
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/334.jsonlOther25.9 MB e13e6fb25b68
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/335.jsonlOther28.0 MB 7c43bdc1f594
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/336.jsonlOther26.8 MB 2a3f9c1197ed
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/337.jsonlOther26.2 MB 0a413215695d
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/338.jsonlOther28.0 MB 534dcbaaf994
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/339.jsonlOther26.7 MB aa9acc7caa91
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/34.jsonlOther23.8 MB f776de9ec829
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/340.jsonlOther26.5 MB 5045098b5af4
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/341.jsonlOther26.4 MB f1f7cf89bfa9
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/342.jsonlOther26.0 MB 6f30a228b7d5
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/343.jsonlOther26.8 MB 5d7e7d2362bd
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/344.jsonlOther26.8 MB b4a1d64bf1e8
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/345.jsonlOther27.3 MB 4948f88609c5
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/346.jsonlOther27.1 MB 42ad44c9e2b9
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/347.jsonlOther27.5 MB 824556bd43df
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/348.jsonlOther26.4 MB 24f68d2b2100
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/349.jsonlOther26.8 MB 1038f37e9c5d
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/35.jsonlOther23.2 MB 458bf7b59f80
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/350.jsonlOther26.4 MB c8ba7b4ff75c
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/351.jsonlOther27.5 MB de78e7e7deb8
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/352.jsonlOther27.1 MB 964634ce3dfc
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/353.jsonlOther28.1 MB 8df3f9222ff0
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/354.jsonlOther26.2 MB 9d28fbd5ab8a
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/355.jsonlOther27.7 MB 2a2a5cc5d4ba
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/356.jsonlOther26.4 MB 23e2d05c6cda
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/357.jsonlOther27.4 MB fa073f44d746
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/358.jsonlOther26.5 MB be0d506c8aed
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/359.jsonlOther27.0 MB 4d009b5b58b1
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/36.jsonlOther22.9 MB a403b88b844d
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/360.jsonlOther27.7 MB 7cbb81825b81
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/361.jsonlOther28.0 MB 39fca23deb3a
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/362.jsonlOther28.5 MB 585fdd394a35
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/363.jsonlOther28.2 MB 2a7d1cf38332
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/364.jsonlOther28.6 MB e129f675ed74
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/365.jsonlOther28.4 MB b139e1ab8e31
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/366.jsonlOther28.6 MB d83446ee3fe0
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/367.jsonlOther27.1 MB fd5c06272dbb
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/368.jsonlOther26.3 MB fa888fab288f
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/369.jsonlOther30.2 MB 1a8a7397eb09
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/37.jsonlOther23.4 MB 4bfe916a4d71
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/370.jsonlOther30.3 MB 22309b60e16d
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/371.jsonlOther29.3 MB 31dcaf69690f
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/372.jsonlOther29.1 MB 1928ec37d46f
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/373.jsonlOther28.6 MB cb5aca67a27a
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/374.jsonlOther28.1 MB d878c5eb1cb2
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/375.jsonlOther28.0 MB 0ea616febf43
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/376.jsonlOther28.9 MB c643aa939881
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/377.jsonlOther29.0 MB 6ba492ec8209
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/378.jsonlOther29.0 MB b66bfb13a877
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/379.jsonlOther29.8 MB dd85d35233f1
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/38.jsonlOther23.8 MB c3f8690477a2
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/380.jsonlOther30.0 MB 45c0000cf6ab
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/381.jsonlOther29.3 MB 4b355f3f92cf
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/382.jsonlOther30.4 MB 8425be8a4051
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/383.jsonlOther28.8 MB 09e307177367
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/384.jsonlOther32.0 MB e93535fea866
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/385.jsonlOther30.3 MB 7bcb42ca2536
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/386.jsonlOther29.6 MB 0551abc57646
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/387.jsonlOther28.7 MB e89aa418b752
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/388.jsonlOther28.2 MB 439a6ec829c9
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/389.jsonlOther28.3 MB e947066c2c44
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/39.jsonlOther24.0 MB 8ea4b310807a
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/390.jsonlOther27.5 MB 8727f50984d3
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/391.jsonlOther30.2 MB 3adf74e722c4
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/392.jsonlOther30.5 MB 2c241a189a3a
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/393.jsonlOther28.8 MB 009eee16db1b
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/394.jsonlOther29.7 MB 6e4ff3c70abb
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/395.jsonlOther30.3 MB 54cd6853be06
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/396.jsonlOther28.2 MB dd1e384cb63e
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/397.jsonlOther29.2 MB b983fd42a195
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/398.jsonlOther28.8 MB 1269c9a4f115
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/399.jsonlOther29.2 MB 32965ab08486
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/4.jsonlOther24.4 MB 5b9236e1bdd3
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/40.jsonlOther24.0 MB 8b39c72d275f
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/400.jsonlOther29.2 MB 2b6ff4fdfc64
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/401.jsonlOther29.1 MB c8fe423f6358
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/402.jsonlOther30.0 MB cef2b909f5ac
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/403.jsonlOther30.4 MB 63dc118cdb50
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/404.jsonlOther30.0 MB 6251569f21ec
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/405.jsonlOther29.4 MB cc7e06f79035
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/406.jsonlOther29.0 MB 2ce792c4891b
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/407.jsonlOther30.8 MB 3f4b1a686489
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/408.jsonlOther29.3 MB dbfef7a5ae14
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/409.jsonlOther27.8 MB 4e9ac4770280
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/41.jsonlOther23.2 MB 75887ce81686
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/410.jsonlOther29.4 MB 0eaf6ee6ce93
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/411.jsonlOther29.3 MB 106393d8a46d
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/412.jsonlOther28.5 MB 9648734492a5
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/413.jsonlOther28.7 MB 1c1c6b8c7949
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/414.jsonlOther29.7 MB 2653ba98409d
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/415.jsonlOther29.5 MB b05ed584e35f
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/416.jsonlOther31.3 MB 8fa90b5a3078
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/417.jsonlOther30.6 MB 3ba859d9ed50
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/418.jsonlOther29.1 MB 6656a0c15503
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/419.jsonlOther30.9 MB efaa70baa587
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/42.jsonlOther24.0 MB ff2bd176d105
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/420.jsonlOther31.4 MB 7a186d8a1a44
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/421.jsonlOther29.4 MB 2ae358cc9ef3
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/43.jsonlOther23.8 MB 839085789293
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/44.jsonlOther23.0 MB a90197cddd42
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/45.jsonlOther22.8 MB 284c8c4e1872
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/46.jsonlOther24.3 MB 0129ffea535b
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/47.jsonlOther23.7 MB 3f3fef26eec6
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/48.jsonlOther23.6 MB 4c20f115939b
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/49.jsonlOther24.3 MB c27bac64cb9a
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/5.jsonlOther24.2 MB b8fef93d9dbf
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/50.jsonlOther24.3 MB 6f2781305345
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/51.jsonlOther24.1 MB d215ec70abdc
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/52.jsonlOther23.3 MB a7332463f9a3
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/53.jsonlOther23.5 MB d443f441d053
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/54.jsonlOther24.7 MB 567bceda9879
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/55.jsonlOther21.8 MB 985bd3223e56
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/56.jsonlOther22.9 MB 6b7227a495d6
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/57.jsonlOther23.7 MB 3bf7aed8abf0
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/58.jsonlOther24.3 MB bae79516558a
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/59.jsonlOther23.2 MB 5dc9388b7462
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/6.jsonlOther23.7 MB 4f88ab98eea5
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/60.jsonlOther23.3 MB aea022da9d05
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/61.jsonlOther22.4 MB 0c5cbeb2e446
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/62.jsonlOther24.2 MB 58ea17fabd4f
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/63.jsonlOther22.7 MB e895c3692275
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/64.jsonlOther24.4 MB 07c314bc0ede
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/65.jsonlOther24.9 MB 184c34074fd6
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/66.jsonlOther23.7 MB e05e40937faf
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/67.jsonlOther23.8 MB 7e898f95c558
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/68.jsonlOther23.2 MB 0ec0d8dfbe7a
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/69.jsonlOther24.3 MB 2cbc2c422a37
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/7.jsonlOther24.1 MB b27c3e003828
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/70.jsonlOther24.0 MB 3dbb936d2b24
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/71.jsonlOther25.0 MB a7a843e7a42b
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/72.jsonlOther23.7 MB 84c5cdcca909
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/73.jsonlOther24.6 MB 552fc6f3135f
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/74.jsonlOther25.1 MB f8d284c623f1
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/75.jsonlOther24.0 MB a4bc5a6ecd6e
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/76.jsonlOther24.5 MB 413299b4e564
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/77.jsonlOther25.2 MB b6c4bfbf8eb3
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/78.jsonlOther23.9 MB 0bb8ec8493d0
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/79.jsonlOther23.9 MB cab21ae01f88
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/8.jsonlOther22.7 MB 8d79750fff27
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/80.jsonlOther24.7 MB f60f3421fe43
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/81.jsonlOther24.4 MB 0dcbfbef35fd
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/82.jsonlOther24.7 MB c31c7675724d
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/83.jsonlOther23.8 MB bb411b213ab5
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/84.jsonlOther23.4 MB 3a5d3a7687c3
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/85.jsonlOther23.8 MB f74aafc4b58d
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/86.jsonlOther24.9 MB 2fc5acc4de11
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/87.jsonlOther25.7 MB c55204e6a5fb
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/88.jsonlOther26.3 MB 83db466459dc
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/89.jsonlOther25.0 MB d7bf6d2d61d5
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/9.jsonlOther23.9 MB fe90f2582302
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/90.jsonlOther24.3 MB b219e6464e5f
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/91.jsonlOther24.4 MB bda0c4194f5b
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/92.jsonlOther24.7 MB 2f5e30c6a94d
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/93.jsonlOther26.2 MB 100b9f16538c
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/94.jsonlOther25.9 MB ca1838a42b17
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/95.jsonlOther25.8 MB 5642fbad4bfa
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/96.jsonlOther25.3 MB 2c10500c91d9
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/97.jsonlOther25.6 MB 8ce434eef9b4
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/98.jsonlOther24.8 MB d1a914469190
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/rollouts/99.jsonlOther26.1 MB 5c270d0da603
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/validation/100.jsonlOther6.1 MB —
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/validation/120.jsonlOther5.8 MB —
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/validation/140.jsonlOther6.0 MB —
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/validation/160.jsonlOther6.1 MB —
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/validation/180.jsonlOther5.9 MB —
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/validation/20.jsonlOther6.0 MB —
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/validation/200.jsonlOther6.1 MB —
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/validation/220.jsonlOther6.1 MB —
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/validation/240.jsonlOther6.2 MB —
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/validation/260.jsonlOther6.3 MB —
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/validation/280.jsonlOther6.1 MB —
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/validation/300.jsonlOther6.1 MB —
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/validation/320.jsonlOther6.1 MB —
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/validation/340.jsonlOther5.9 MB —
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/validation/360.jsonlOther6.1 MB —
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/validation/380.jsonlOther6.6 MB —
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/validation/40.jsonlOther5.6 MB —
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/validation/400.jsonlOther6.3 MB —
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/validation/420.jsonlOther6.5 MB —
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/validation/421.jsonlOther6.5 MB —
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/validation/60.jsonlOther5.6 MB —
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/validation/80.jsonlOther6.0 MB —
models/GRPO_Guru/Qwen2.5-0.5B-low-lr5e-5/checkpoints/global_step_106/actor/huggingface/chat_template.jinjaOther2.4 KB —
models/GRPO_Guru/Qwen2.5-0.5B-low-lr5e-5/checkpoints/global_step_106/transfer_queue/controller_state.pklOther13.2 MB d6de40acd8a7
models/GRPO_Guru/Qwen2.5-0.5B-low-lr5e-5/checkpoints/global_step_106/transfer_queue/simple_storage/su_0_TQ_STORAGE_UNIT_e2bc9b20.pklOther196.6 MB ebdad6b9cf8f
models/GRPO_Guru/Qwen2.5-0.5B-low-lr5e-5/checkpoints/global_step_106/transfer_queue/simple_storage/su_1_TQ_STORAGE_UNIT_ef62ad17.pklOther194.2 MB 36eca44fee78
models/GRPO_Guru/Qwen2.5-0.5B-low-lr5e-5/checkpoints/global_step_106/transfer_queue/simple_storage/su_2_TQ_STORAGE_UNIT_3f367bef.pklOther193.3 MB bfbe8552016e
models/GRPO_Guru/Qwen2.5-0.5B-low-lr5e-5/checkpoints/global_step_106/transfer_queue/simple_storage/su_3_TQ_STORAGE_UNIT_4ca57002.pklOther191.4 MB fc9887fe4527
models/GRPO_Guru/Qwen2.5-0.5B-low-lr5e-5/validation/10.jsonlOther136.1 MB d8535c7a2aa3
models/GRPO_Guru/Qwen2.5-0.5B-low-lr5e-5/validation/100.jsonlOther68.5 MB f07296cf9108
models/GRPO_Guru/Qwen2.5-0.5B-low-lr5e-5/validation/105.jsonlOther65.8 MB 0abef2180221
models/GRPO_Guru/Qwen2.5-0.5B-low-lr5e-5/validation/106.jsonlOther66.2 MB eb49f7ff94a4
models/GRPO_Guru/Qwen2.5-0.5B-low-lr5e-5/validation/15.jsonlOther124.6 MB 9b3263892557
models/GRPO_Guru/Qwen2.5-0.5B-low-lr5e-5/validation/20.jsonlOther114.0 MB ec46cd066c33
models/GRPO_Guru/Qwen2.5-0.5B-low-lr5e-5/validation/25.jsonlOther104.0 MB 0e06cdd3880c
models/GRPO_Guru/Qwen2.5-0.5B-low-lr5e-5/validation/30.jsonlOther95.9 MB eaa262b7f02e
models/GRPO_Guru/Qwen2.5-0.5B-low-lr5e-5/validation/35.jsonlOther90.6 MB 351e9a45c894
models/GRPO_Guru/Qwen2.5-0.5B-low-lr5e-5/validation/40.jsonlOther89.3 MB deffc8db4a01
models/GRPO_Guru/Qwen2.5-0.5B-low-lr5e-5/validation/45.jsonlOther84.9 MB 2f10c334cc65
models/GRPO_Guru/Qwen2.5-0.5B-low-lr5e-5/validation/5.jsonlOther143.8 MB 5ae8f608f587
models/GRPO_Guru/Qwen2.5-0.5B-low-lr5e-5/validation/50.jsonlOther76.8 MB 6263a9ff6588
models/GRPO_Guru/Qwen2.5-0.5B-low-lr5e-5/validation/55.jsonlOther77.4 MB 78f0150b45d7
models/GRPO_Guru/Qwen2.5-0.5B-low-lr5e-5/validation/60.jsonlOther79.7 MB df43ccdae09e
models/GRPO_Guru/Qwen2.5-0.5B-low-lr5e-5/validation/65.jsonlOther72.5 MB 1671825d7f5f
models/GRPO_Guru/Qwen2.5-0.5B-low-lr5e-5/validation/70.jsonlOther71.9 MB 7461c942828b
models/GRPO_Guru/Qwen2.5-0.5B-low-lr5e-5/validation/75.jsonlOther71.2 MB 7e88c8ab0698
models/GRPO_Guru/Qwen2.5-0.5B-low-lr5e-5/validation/80.jsonlOther72.0 MB 03fd5503e532
models/GRPO_Guru/Qwen2.5-0.5B-low-lr5e-5/validation/85.jsonlOther68.9 MB 726e628f66a7
models/GRPO_Guru/Qwen2.5-0.5B-low-lr5e-5/validation/90.jsonlOther65.8 MB 56813c22015d
models/GRPO_Guru/Qwen2.5-0.5B-low-lr5e-5/validation/95.jsonlOther66.3 MB f59d712cb729
models/GRPO_Guru/Qwen2.5-1.5B-low-lr5e-5/checkpoints/global_step_106/actor/huggingface/chat_template.jinjaOther2.4 KB —
models/GRPO_Guru/Qwen2.5-1.5B-low-lr5e-5/checkpoints/global_step_106/transfer_queue/controller_state.pklOther20.7 MB 9b8a5c85b34e
models/GRPO_Guru/Qwen2.5-1.5B-low-lr5e-5/checkpoints/global_step_106/transfer_queue/simple_storage/su_0_TQ_STORAGE_UNIT_e95818ee.pklOther774.0 MB 5bd233f93e47
models/GRPO_Guru/Qwen2.5-1.5B-low-lr5e-5/checkpoints/global_step_106/transfer_queue/simple_storage/su_1_TQ_STORAGE_UNIT_7cec3d16.pklOther765.6 MB e4975f4960ec
models/GRPO_Guru/Qwen2.5-1.5B-low-lr5e-5/checkpoints/global_step_106/transfer_queue/simple_storage/su_2_TQ_STORAGE_UNIT_e83f65d8.pklOther762.4 MB 6f9981157545
models/GRPO_Guru/Qwen2.5-1.5B-low-lr5e-5/checkpoints/global_step_106/transfer_queue/simple_storage/su_3_TQ_STORAGE_UNIT_92c6dd43.pklOther775.8 MB 667607627d9c
models/GRPO_Guru/Qwen2.5-1.5B-low-lr5e-5/validation/10.jsonlOther124.7 MB 2e25d69066c6
models/GRPO_Guru/Qwen2.5-1.5B-low-lr5e-5/validation/100.jsonlOther88.5 MB 99708ddb22ae
models/GRPO_Guru/Qwen2.5-1.5B-low-lr5e-5/validation/105.jsonlOther88.8 MB 9d01255d821d
models/GRPO_Guru/Qwen2.5-1.5B-low-lr5e-5/validation/106.jsonlOther88.4 MB 4aeefab023b2
models/GRPO_Guru/Qwen2.5-1.5B-low-lr5e-5/validation/15.jsonlOther119.2 MB 88750d9c7a84
models/GRPO_Guru/Qwen2.5-1.5B-low-lr5e-5/validation/20.jsonlOther113.0 MB a040ac463072
models/GRPO_Guru/Qwen2.5-1.5B-low-lr5e-5/validation/25.jsonlOther106.8 MB b051db29dfd4
models/GRPO_Guru/Qwen2.5-1.5B-low-lr5e-5/validation/30.jsonlOther104.1 MB 6a4ba2f9ff6f
models/GRPO_Guru/Qwen2.5-1.5B-low-lr5e-5/validation/35.jsonlOther98.1 MB 1c38f28e2d88
models/GRPO_Guru/Qwen2.5-1.5B-low-lr5e-5/validation/40.jsonlOther94.5 MB 045d207af768
models/GRPO_Guru/Qwen2.5-1.5B-low-lr5e-5/validation/45.jsonlOther92.2 MB 5d9d76ba97cb
models/GRPO_Guru/Qwen2.5-1.5B-low-lr5e-5/validation/5.jsonlOther130.1 MB 124af51264e4
models/GRPO_Guru/Qwen2.5-1.5B-low-lr5e-5/validation/50.jsonlOther92.9 MB 61168f5b0f85
models/GRPO_Guru/Qwen2.5-1.5B-low-lr5e-5/validation/55.jsonlOther88.6 MB 1a8237d830e3
models/GRPO_Guru/Qwen2.5-1.5B-low-lr5e-5/validation/60.jsonlOther84.6 MB cbbf4e5fb70c
models/GRPO_Guru/Qwen2.5-1.5B-low-lr5e-5/validation/65.jsonlOther84.1 MB 356306b0cd13
models/GRPO_Guru/Qwen2.5-1.5B-low-lr5e-5/validation/70.jsonlOther85.0 MB f228ab26c5fc
models/GRPO_Guru/Qwen2.5-1.5B-low-lr5e-5/validation/75.jsonlOther87.7 MB 4cf69d89983e
models/GRPO_Guru/Qwen2.5-1.5B-low-lr5e-5/validation/80.jsonlOther87.1 MB 76badb5ce12e
models/GRPO_Guru/Qwen2.5-1.5B-low-lr5e-5/validation/85.jsonlOther85.5 MB 1f8018833020
models/GRPO_Guru/Qwen2.5-1.5B-low-lr5e-5/validation/90.jsonlOther85.5 MB e48898b149fe
models/GRPO_Guru/Qwen2.5-1.5B-low-lr5e-5/validation/95.jsonlOther86.4 MB 0202d70ed4cc
models/GRPO_Guru/Qwen2.5-3B-low-lr4e-5/checkpoints/global_step_106/actor/huggingface/chat_template.jinjaOther2.4 KB —
models/GRPO_Guru/Qwen2.5-3B-low-lr4e-5/checkpoints/global_step_106/transfer_queue/controller_state.pklOther20.8 MB 28b95c3efebb
models/GRPO_Guru/Qwen2.5-3B-low-lr4e-5/checkpoints/global_step_106/transfer_queue/simple_storage/su_0_TQ_STORAGE_UNIT_bb7c84c5.pklOther1.2 GB 822aef6c7e97
models/GRPO_Guru/Qwen2.5-3B-low-lr4e-5/checkpoints/global_step_106/transfer_queue/simple_storage/su_1_TQ_STORAGE_UNIT_898c988b.pklOther1.3 GB 49f473cfc538
models/GRPO_Guru/Qwen2.5-3B-low-lr4e-5/checkpoints/global_step_106/transfer_queue/simple_storage/su_2_TQ_STORAGE_UNIT_863dee13.pklOther1.2 GB 0170921c3ec9
models/GRPO_Guru/Qwen2.5-3B-low-lr4e-5/checkpoints/global_step_106/transfer_queue/simple_storage/su_3_TQ_STORAGE_UNIT_570948b1.pklOther1.2 GB af8030ec0250
models/GRPO_Guru/Qwen2.5-3B-low-lr4e-5/validation/10.jsonlOther103.1 MB 810b1bd8377c
models/GRPO_Guru/Qwen2.5-3B-low-lr4e-5/validation/100.jsonlOther88.0 MB 60f9a1c700e3
models/GRPO_Guru/Qwen2.5-3B-low-lr4e-5/validation/105.jsonlOther89.1 MB f714b7447219
models/GRPO_Guru/Qwen2.5-3B-low-lr4e-5/validation/106.jsonlOther89.0 MB bc659da6f38a
models/GRPO_Guru/Qwen2.5-3B-low-lr4e-5/validation/15.jsonlOther98.1 MB f8fdbfed38e7
models/GRPO_Guru/Qwen2.5-3B-low-lr4e-5/validation/20.jsonlOther92.6 MB 0e21d90d5ac3
models/GRPO_Guru/Qwen2.5-3B-low-lr4e-5/validation/25.jsonlOther89.8 MB 230fa4db56ce
models/GRPO_Guru/Qwen2.5-3B-low-lr4e-5/validation/30.jsonlOther86.6 MB 223b9ec74e25
models/GRPO_Guru/Qwen2.5-3B-low-lr4e-5/validation/35.jsonlOther85.2 MB 14b71cca916c
models/GRPO_Guru/Qwen2.5-3B-low-lr4e-5/validation/40.jsonlOther83.0 MB d31261e83be6
models/GRPO_Guru/Qwen2.5-3B-low-lr4e-5/validation/45.jsonlOther82.7 MB b2bf362906e4
models/GRPO_Guru/Qwen2.5-3B-low-lr4e-5/validation/5.jsonlOther109.4 MB ba9fbb8f404f
models/GRPO_Guru/Qwen2.5-3B-low-lr4e-5/validation/50.jsonlOther81.2 MB c8c3c3d3b8ff
models/GRPO_Guru/Qwen2.5-3B-low-lr4e-5/validation/55.jsonlOther81.9 MB 8491ae52fe06
models/GRPO_Guru/Qwen2.5-3B-low-lr4e-5/validation/60.jsonlOther82.2 MB 54880cba1a41
models/GRPO_Guru/Qwen2.5-3B-low-lr4e-5/validation/65.jsonlOther83.5 MB 94d496a4dbf8
models/GRPO_Guru/Qwen2.5-3B-low-lr4e-5/validation/70.jsonlOther83.5 MB ba5b9d68672f
models/GRPO_Guru/Qwen2.5-3B-low-lr4e-5/validation/75.jsonlOther83.9 MB d6c8bb0aaca9
models/GRPO_Guru/Qwen2.5-3B-low-lr4e-5/validation/80.jsonlOther84.1 MB 29da9f3e7966
models/GRPO_Guru/Qwen2.5-3B-low-lr4e-5/validation/85.jsonlOther85.9 MB 15f0d17b8ace
models/GRPO_Guru/Qwen2.5-3B-low-lr4e-5/validation/90.jsonlOther86.6 MB e58c0ac9cb2f
models/GRPO_Guru/Qwen2.5-3B-low-lr4e-5/validation/95.jsonlOther87.8 MB 1970b99796bc
models/GRPO_Guru/Qwen2.5-7B-low-lr4e-5/checkpoints/global_step_106/actor/huggingface/chat_template.jinjaOther2.4 KB —
models/GRPO_Guru/Qwen2.5-7B-low-lr4e-5/checkpoints/global_step_106/transfer_queue/controller_state.pklOther20.8 MB cd34f1fd716c
models/GRPO_Guru/Qwen2.5-7B-low-lr4e-5/checkpoints/global_step_106/transfer_queue/simple_storage/su_0_TQ_STORAGE_UNIT_9ac18fc2.pklOther1.6 GB e5ce3d7db43f
models/GRPO_Guru/Qwen2.5-7B-low-lr4e-5/checkpoints/global_step_106/transfer_queue/simple_storage/su_1_TQ_STORAGE_UNIT_ac916d6b.pklOther1.6 GB 4ff5e5a362a2
models/GRPO_Guru/Qwen2.5-7B-low-lr4e-5/checkpoints/global_step_106/transfer_queue/simple_storage/su_2_TQ_STORAGE_UNIT_792ffd5b.pklOther1.5 GB e75784a91094
models/GRPO_Guru/Qwen2.5-7B-low-lr4e-5/checkpoints/global_step_106/transfer_queue/simple_storage/su_3_TQ_STORAGE_UNIT_74f29dc8.pklOther1.6 GB 268da5081d77
models/GRPO_Guru/Qwen2.5-7B-low-lr4e-5/validation/10.jsonlOther92.0 MB ad1d8e54c095
models/GRPO_Guru/Qwen2.5-7B-low-lr4e-5/validation/100.jsonlOther93.8 MB 56b9a6409372
models/GRPO_Guru/Qwen2.5-7B-low-lr4e-5/validation/105.jsonlOther94.6 MB b63f23823b68
models/GRPO_Guru/Qwen2.5-7B-low-lr4e-5/validation/106.jsonlOther94.8 MB 80dd9a43112b
models/GRPO_Guru/Qwen2.5-7B-low-lr4e-5/validation/15.jsonlOther90.6 MB 7871f65805c0
models/GRPO_Guru/Qwen2.5-7B-low-lr4e-5/validation/20.jsonlOther87.4 MB 0a456c3043b6
models/GRPO_Guru/Qwen2.5-7B-low-lr4e-5/validation/25.jsonlOther86.9 MB 241b7bbe29dc
models/GRPO_Guru/Qwen2.5-7B-low-lr4e-5/validation/30.jsonlOther86.4 MB 124bf6b8233e
models/GRPO_Guru/Qwen2.5-7B-low-lr4e-5/validation/35.jsonlOther87.7 MB 400e941e6d9f
models/GRPO_Guru/Qwen2.5-7B-low-lr4e-5/validation/40.jsonlOther88.8 MB 2abb65447be3
models/GRPO_Guru/Qwen2.5-7B-low-lr4e-5/validation/45.jsonlOther88.3 MB 236279d35fe2
models/GRPO_Guru/Qwen2.5-7B-low-lr4e-5/validation/5.jsonlOther94.8 MB 98bc21be62b7
models/GRPO_Guru/Qwen2.5-7B-low-lr4e-5/validation/50.jsonlOther89.8 MB a28673cec67a
models/GRPO_Guru/Qwen2.5-7B-low-lr4e-5/validation/55.jsonlOther91.0 MB 5e2203a01e0c
models/GRPO_Guru/Qwen2.5-7B-low-lr4e-5/validation/60.jsonlOther90.1 MB b787765a1415
models/GRPO_Guru/Qwen2.5-7B-low-lr4e-5/validation/65.jsonlOther90.0 MB 7183d87aaf92
models/GRPO_Guru/Qwen2.5-7B-low-lr4e-5/validation/70.jsonlOther92.2 MB 171f21b777eb
models/GRPO_Guru/Qwen2.5-7B-low-lr4e-5/validation/75.jsonlOther91.7 MB 79c3c6139145
models/GRPO_Guru/Qwen2.5-7B-low-lr4e-5/validation/80.jsonlOther91.1 MB 4537b1a58179
models/GRPO_Guru/Qwen2.5-7B-low-lr4e-5/validation/85.jsonlOther92.2 MB b027cf7c82d1
models/GRPO_Guru/Qwen2.5-7B-low-lr4e-5/validation/90.jsonlOther93.3 MB ad71027822e4
models/GRPO_Guru/Qwen2.5-7B-low-lr4e-5/validation/95.jsonlOther93.6 MB 8103918424ad
models/GRPO_Guru/Qwen3-0.6B-Base/checkpoints/global_step_848/actor/huggingface/chat_template.jinjaOther4.1 KB —
models/GRPO_Guru/Qwen3-0.6B-Base/checkpoints/global_step_848/transfer_queue/controller_state.pklOther4.0 MB d5f64914d175
models/GRPO_Guru/Qwen3-0.6B-Base/checkpoints/global_step_848/transfer_queue/simple_storage/su_0_TQ_STORAGE_UNIT_bf44a7ea.pklOther135.7 MB ac892051fb22
models/GRPO_Guru/Qwen3-0.6B-Base/checkpoints/global_step_848/transfer_queue/simple_storage/su_1_TQ_STORAGE_UNIT_5c806c41.pklOther135.5 MB ebb96880b759
models/GRPO_Guru/Qwen3-0.6B-Base/checkpoints/global_step_848/transfer_queue/simple_storage/su_2_TQ_STORAGE_UNIT_5cad3862.pklOther133.3 MB 5359a2dee3f0
models/GRPO_Guru/Qwen3-0.6B-Base/checkpoints/global_step_848/transfer_queue/simple_storage/su_3_TQ_STORAGE_UNIT_c56bec39.pklOther134.8 MB ceeb3f5b6a07
models/GRPO_Guru/Qwen3-0.6B-Base/validation/100.jsonlOther76.6 MB 6fd481348ba8
models/GRPO_Guru/Qwen3-0.6B-Base/validation/120.jsonlOther77.1 MB 20d30a991667
models/GRPO_Guru/Qwen3-0.6B-Base/validation/140.jsonlOther74.3 MB 407db17dab50
models/GRPO_Guru/Qwen3-0.6B-Base/validation/160.jsonlOther75.4 MB 96825ac4c780
models/GRPO_Guru/Qwen3-0.6B-Base/validation/180.jsonlOther75.0 MB 93812021685a
models/GRPO_Guru/Qwen3-0.6B-Base/validation/20.jsonlOther115.0 MB 67547c28cdde
models/GRPO_Guru/Qwen3-0.6B-Base/validation/200.jsonlOther73.4 MB bc1549aa7143
models/GRPO_Guru/Qwen3-0.6B-Base/validation/220.jsonlOther71.8 MB 2161eaa92d3a
models/GRPO_Guru/Qwen3-0.6B-Base/validation/240.jsonlOther71.0 MB fa563dadb731
models/GRPO_Guru/Qwen3-0.6B-Base/validation/260.jsonlOther70.2 MB 07bc049f9df5
models/GRPO_Guru/Qwen3-0.6B-Base/validation/280.jsonlOther69.1 MB f2720643f005
models/GRPO_Guru/Qwen3-0.6B-Base/validation/300.jsonlOther69.4 MB 8800447f4ef3
models/GRPO_Guru/Qwen3-0.6B-Base/validation/320.jsonlOther72.7 MB de663c218dfb
models/GRPO_Guru/Qwen3-0.6B-Base/validation/340.jsonlOther71.2 MB c39124ffed4c
models/GRPO_Guru/Qwen3-0.6B-Base/validation/360.jsonlOther72.0 MB e402f06b38fe
models/GRPO_Guru/Qwen3-0.6B-Base/validation/380.jsonlOther73.1 MB 8b8438c2fb87
models/GRPO_Guru/Qwen3-0.6B-Base/validation/40.jsonlOther87.7 MB c93bfa400178
models/GRPO_Guru/Qwen3-0.6B-Base/validation/400.jsonlOther81.3 MB f9a4c870a526
models/GRPO_Guru/Qwen3-0.6B-Base/validation/420.jsonlOther89.0 MB 50dd3e57692d
models/GRPO_Guru/Qwen3-0.6B-Base/validation/440.jsonlOther94.5 MB abdfafec5dc3
models/GRPO_Guru/Qwen3-0.6B-Base/validation/460.jsonlOther88.7 MB 9dfb0d12ccbd
models/GRPO_Guru/Qwen3-0.6B-Base/validation/480.jsonlOther89.3 MB 043dfd963e85
models/GRPO_Guru/Qwen3-0.6B-Base/validation/500.jsonlOther86.6 MB 2122a506fd77
models/GRPO_Guru/Qwen3-0.6B-Base/validation/520.jsonlOther82.9 MB be4b0b5d2659
models/GRPO_Guru/Qwen3-0.6B-Base/validation/540.jsonlOther86.4 MB 79fcb6ae6aef
models/GRPO_Guru/Qwen3-0.6B-Base/validation/560.jsonlOther82.7 MB 7ceffdd7a93d
models/GRPO_Guru/Qwen3-0.6B-Base/validation/580.jsonlOther84.5 MB 21e3f05e20ce
models/GRPO_Guru/Qwen3-0.6B-Base/validation/60.jsonlOther81.5 MB ae1c0dac3fa9
models/GRPO_Guru/Qwen3-0.6B-Base/validation/600.jsonlOther84.8 MB 7b7ae3e5a4d6
models/GRPO_Guru/Qwen3-0.6B-Base/validation/620.jsonlOther89.6 MB d4827658162f
models/GRPO_Guru/Qwen3-0.6B-Base/validation/640.jsonlOther89.2 MB 2c9e63902046
models/GRPO_Guru/Qwen3-0.6B-Base/validation/660.jsonlOther86.1 MB 78755a644bec
models/GRPO_Guru/Qwen3-0.6B-Base/validation/680.jsonlOther90.7 MB 44621827fa92
models/GRPO_Guru/Qwen3-0.6B-Base/validation/700.jsonlOther89.4 MB 36c09e45b95e
models/GRPO_Guru/Qwen3-0.6B-Base/validation/720.jsonlOther86.0 MB 435fd53f98f0
models/GRPO_Guru/Qwen3-0.6B-Base/validation/740.jsonlOther85.3 MB 0e970ca49d93
models/GRPO_Guru/Qwen3-0.6B-Base/validation/760.jsonlOther86.1 MB 8b5ae6eeed60
models/GRPO_Guru/Qwen3-0.6B-Base/validation/780.jsonlOther85.3 MB 6d9e2eba553a
models/GRPO_Guru/Qwen3-0.6B-Base/validation/80.jsonlOther77.9 MB 35ab449ac0b6
models/GRPO_Guru/Qwen3-0.6B-Base/validation/800.jsonlOther87.5 MB c76f79bac15e
models/GRPO_Guru/Qwen3-0.6B-Base/validation/820.jsonlOther94.8 MB 127d2d181ff0
models/GRPO_Guru/Qwen3-0.6B-Base/validation/840.jsonlOther94.6 MB 845c7590ee3d
models/GRPO_Guru/Qwen3-0.6B-Base/validation/848.jsonlOther92.5 MB d946f04be6b1
models/GRPO_Guru/Qwen3-1.7B-Base/checkpoints/global_step_848/actor/huggingface/chat_template.jinjaOther4.1 KB —
models/GRPO_Guru/Qwen3-1.7B-Base/checkpoints/global_step_848/transfer_queue/controller_state.pklOther4.0 MB 4bb0d8edc843
models/GRPO_Guru/Qwen3-1.7B-Base/checkpoints/global_step_848/transfer_queue/simple_storage/su_0_TQ_STORAGE_UNIT_6f26f652.pklOther129.1 MB e53edf8633ff
models/GRPO_Guru/Qwen3-1.7B-Base/checkpoints/global_step_848/transfer_queue/simple_storage/su_1_TQ_STORAGE_UNIT_1d3fd70d.pklOther130.7 MB d718e7d2b36a
models/GRPO_Guru/Qwen3-1.7B-Base/checkpoints/global_step_848/transfer_queue/simple_storage/su_2_TQ_STORAGE_UNIT_7e4f7f42.pklOther133.3 MB dddfce2ef587
models/GRPO_Guru/Qwen3-1.7B-Base/checkpoints/global_step_848/transfer_queue/simple_storage/su_3_TQ_STORAGE_UNIT_9d8be51c.pklOther128.2 MB 1baf210ee260
models/GRPO_Guru/Qwen3-1.7B-Base/validation/100.jsonlOther69.2 MB c43af43d6631
models/GRPO_Guru/Qwen3-1.7B-Base/validation/120.jsonlOther68.5 MB c323a626f6fb
models/GRPO_Guru/Qwen3-1.7B-Base/validation/140.jsonlOther67.9 MB cf86f0539ee2
models/GRPO_Guru/Qwen3-1.7B-Base/validation/160.jsonlOther66.9 MB 2d85e876f2d6
models/GRPO_Guru/Qwen3-1.7B-Base/validation/180.jsonlOther66.7 MB 98b6f0b0f94a
models/GRPO_Guru/Qwen3-1.7B-Base/validation/20.jsonlOther75.1 MB 1c084e66bb46
models/GRPO_Guru/Qwen3-1.7B-Base/validation/200.jsonlOther66.7 MB 0b0c80367ffc
models/GRPO_Guru/Qwen3-1.7B-Base/validation/220.jsonlOther67.0 MB b99afe326777
models/GRPO_Guru/Qwen3-1.7B-Base/validation/240.jsonlOther66.5 MB 91b5e22a3523
models/GRPO_Guru/Qwen3-1.7B-Base/validation/260.jsonlOther66.4 MB 66e37aea2f01
models/GRPO_Guru/Qwen3-1.7B-Base/validation/280.jsonlOther69.5 MB bc8da7e43d85
models/GRPO_Guru/Qwen3-1.7B-Base/validation/300.jsonlOther73.8 MB 8a38876e16eb
models/GRPO_Guru/Qwen3-1.7B-Base/validation/320.jsonlOther77.2 MB 06698ddf0401
models/GRPO_Guru/Qwen3-1.7B-Base/validation/340.jsonlOther80.4 MB 4eb73361e515
models/GRPO_Guru/Qwen3-1.7B-Base/validation/360.jsonlOther82.2 MB 2def32a63013
models/GRPO_Guru/Qwen3-1.7B-Base/validation/380.jsonlOther88.7 MB de7804605fda
models/GRPO_Guru/Qwen3-1.7B-Base/validation/40.jsonlOther72.9 MB d5c4453a399f
models/GRPO_Guru/Qwen3-1.7B-Base/validation/400.jsonlOther94.2 MB 76f60aea6d62
models/GRPO_Guru/Qwen3-1.7B-Base/validation/420.jsonlOther94.2 MB 7468e9961c48
models/GRPO_Guru/Qwen3-1.7B-Base/validation/440.jsonlOther93.4 MB 14f20271096f
models/GRPO_Guru/Qwen3-1.7B-Base/validation/460.jsonlOther91.2 MB 8106fb48bfeb
models/GRPO_Guru/Qwen3-1.7B-Base/validation/480.jsonlOther93.2 MB 113b76a8989e
models/GRPO_Guru/Qwen3-1.7B-Base/validation/500.jsonlOther97.2 MB d6782fedad3e
models/GRPO_Guru/Qwen3-1.7B-Base/validation/520.jsonlOther101.5 MB 60a787e17a30
models/GRPO_Guru/Qwen3-1.7B-Base/validation/540.jsonlOther102.2 MB 4b26ca0bf4fd
models/GRPO_Guru/Qwen3-1.7B-Base/validation/560.jsonlOther103.3 MB 37f8351efe02
models/GRPO_Guru/Qwen3-1.7B-Base/validation/580.jsonlOther107.7 MB 6a1ed042f5ef
models/GRPO_Guru/Qwen3-1.7B-Base/validation/60.jsonlOther71.8 MB 0f91a3da5d84
models/GRPO_Guru/Qwen3-1.7B-Base/validation/600.jsonlOther109.2 MB 719eaeaf1c52
models/GRPO_Guru/Qwen3-1.7B-Base/validation/620.jsonlOther113.3 MB b0de9c613ea2
models/GRPO_Guru/Qwen3-1.7B-Base/validation/640.jsonlOther114.5 MB 6ab982dfa305
models/GRPO_Guru/Qwen3-1.7B-Base/validation/660.jsonlOther112.7 MB b0e9bd1b00d3
models/GRPO_Guru/Qwen3-1.7B-Base/validation/680.jsonlOther111.2 MB 4cbb11928f56
models/GRPO_Guru/Qwen3-1.7B-Base/validation/700.jsonlOther111.6 MB fe7405b0b74f
models/GRPO_Guru/Qwen3-1.7B-Base/validation/720.jsonlOther117.1 MB 9378cc68d3e4
models/GRPO_Guru/Qwen3-1.7B-Base/validation/740.jsonlOther116.7 MB 0cb08dcdaec1
models/GRPO_Guru/Qwen3-1.7B-Base/validation/760.jsonlOther112.3 MB 295880576761
models/GRPO_Guru/Qwen3-1.7B-Base/validation/780.jsonlOther106.6 MB c40262b10a8f
models/GRPO_Guru/Qwen3-1.7B-Base/validation/80.jsonlOther70.1 MB 2dd729d1ade1
models/GRPO_Guru/Qwen3-1.7B-Base/validation/800.jsonlOther106.2 MB 0435798ec70d
models/GRPO_Guru/Qwen3-1.7B-Base/validation/820.jsonlOther109.9 MB c3f2052c9097
models/GRPO_Guru/Qwen3-1.7B-Base/validation/840.jsonlOther107.5 MB 364dc664fa4e
models/GRPO_Guru/Qwen3-1.7B-Base/validation/848.jsonlOther104.9 MB cc7d2b9136eb
models/GRPO_Guru/Qwen3-4B-Base/checkpoints/global_step_848/actor/huggingface/chat_template.jinjaOther4.1 KB —
models/GRPO_Guru/Qwen3-4B-Base/checkpoints/global_step_848/transfer_queue/controller_state.pklOther3.1 MB 25483fe03eec
models/GRPO_Guru/Qwen3-4B-Base/checkpoints/global_step_848/transfer_queue/simple_storage/su_0_TQ_STORAGE_UNIT_91794d73.pklOther175.5 MB 414712b88da1
models/GRPO_Guru/Qwen3-4B-Base/checkpoints/global_step_848/transfer_queue/simple_storage/su_1_TQ_STORAGE_UNIT_d7634add.pklOther175.0 MB 3e2f362ecce7
models/GRPO_Guru/Qwen3-4B-Base/checkpoints/global_step_848/transfer_queue/simple_storage/su_2_TQ_STORAGE_UNIT_3754b939.pklOther173.1 MB f06b24a7aac8
models/GRPO_Guru/Qwen3-4B-Base/checkpoints/global_step_848/transfer_queue/simple_storage/su_3_TQ_STORAGE_UNIT_1b242cc7.pklOther174.6 MB f9725c96118b
models/GRPO_Guru/Qwen3-4B-Base/validation/100.jsonlOther144.1 MB 568ccaa4ea39
models/GRPO_Guru/Qwen3-4B-Base/validation/120.jsonlOther144.9 MB 47916e8c1132
models/GRPO_Guru/Qwen3-4B-Base/validation/140.jsonlOther143.0 MB 840da872f2c2
models/GRPO_Guru/Qwen3-4B-Base/validation/160.jsonlOther140.1 MB fc8524192fa1
models/GRPO_Guru/Qwen3-4B-Base/validation/180.jsonlOther137.3 MB e8e9060c27cc
models/GRPO_Guru/Qwen3-4B-Base/validation/20.jsonlOther66.4 MB f268c8118ae3
models/GRPO_Guru/Qwen3-4B-Base/validation/200.jsonlOther135.2 MB d76caa9340a6
models/GRPO_Guru/Qwen3-4B-Base/validation/220.jsonlOther134.2 MB 7d32effbbea8
models/GRPO_Guru/Qwen3-4B-Base/validation/240.jsonlOther136.5 MB e1ecfd34a02a
models/GRPO_Guru/Qwen3-4B-Base/validation/260.jsonlOther133.5 MB 17547c9e0a94
models/GRPO_Guru/Qwen3-4B-Base/validation/280.jsonlOther133.5 MB ec4c18614fe4
models/GRPO_Guru/Qwen3-4B-Base/validation/300.jsonlOther134.1 MB 2a3440167a55
models/GRPO_Guru/Qwen3-4B-Base/validation/320.jsonlOther133.5 MB 7653e9d5510f
models/GRPO_Guru/Qwen3-4B-Base/validation/340.jsonlOther134.2 MB 466e22e32a83
models/GRPO_Guru/Qwen3-4B-Base/validation/360.jsonlOther134.6 MB c2542b9d0b07
models/GRPO_Guru/Qwen3-4B-Base/validation/380.jsonlOther132.3 MB 686397c12be9
models/GRPO_Guru/Qwen3-4B-Base/validation/40.jsonlOther64.9 MB 822898ea9495
models/GRPO_Guru/Qwen3-4B-Base/validation/400.jsonlOther134.8 MB d2fb8883e9ad
models/GRPO_Guru/Qwen3-4B-Base/validation/420.jsonlOther136.9 MB df4dd0611789
models/GRPO_Guru/Qwen3-4B-Base/validation/440.jsonlOther137.1 MB 6f3f9d8bcbf5
models/GRPO_Guru/Qwen3-4B-Base/validation/460.jsonlOther138.8 MB 89284b8555f7
models/GRPO_Guru/Qwen3-4B-Base/validation/480.jsonlOther141.4 MB e0b5c1dc83ce
models/GRPO_Guru/Qwen3-4B-Base/validation/500.jsonlOther139.4 MB 50bc1fc5be58
models/GRPO_Guru/Qwen3-4B-Base/validation/520.jsonlOther139.8 MB 6591d52e76de
models/GRPO_Guru/Qwen3-4B-Base/validation/540.jsonlOther139.5 MB dce284868cae
models/GRPO_Guru/Qwen3-4B-Base/validation/560.jsonlOther142.2 MB 2f817204d49a
models/GRPO_Guru/Qwen3-4B-Base/validation/580.jsonlOther142.2 MB b491a5e662b5
models/GRPO_Guru/Qwen3-4B-Base/validation/60.jsonlOther66.2 MB d15b9814e8eb
models/GRPO_Guru/Qwen3-4B-Base/validation/600.jsonlOther141.5 MB ea1eba8f2e20
models/GRPO_Guru/Qwen3-4B-Base/validation/620.jsonlOther144.4 MB f9f8daf34715
models/GRPO_Guru/Qwen3-4B-Base/validation/640.jsonlOther142.7 MB 8d98648b90a6
models/GRPO_Guru/Qwen3-4B-Base/validation/660.jsonlOther145.4 MB 20d85e75a66d
models/GRPO_Guru/Qwen3-4B-Base/validation/680.jsonlOther145.8 MB 972cf3bfb75f
models/GRPO_Guru/Qwen3-4B-Base/validation/700.jsonlOther148.4 MB a7c1412d1e24
models/GRPO_Guru/Qwen3-4B-Base/validation/720.jsonlOther144.7 MB 3961822be211
models/GRPO_Guru/Qwen3-4B-Base/validation/740.jsonlOther146.0 MB 43da02f4738f
models/GRPO_Guru/Qwen3-4B-Base/validation/760.jsonlOther146.0 MB d8bd93ce6a19
models/GRPO_Guru/Qwen3-4B-Base/validation/780.jsonlOther146.5 MB 16dd0fa1dc28
models/GRPO_Guru/Qwen3-4B-Base/validation/80.jsonlOther103.2 MB 25ef15d06ac7
models/GRPO_Guru/Qwen3-4B-Base/validation/800.jsonlOther142.8 MB e675f8b2c3c5
models/GRPO_Guru/Qwen3-4B-Base/validation/820.jsonlOther146.2 MB e35ffe6e7c53
models/GRPO_Guru/Qwen3-4B-Base/validation/840.jsonlOther149.7 MB 5e2f773c8af9
models/GRPO_Guru/Qwen3-4B-Base/validation/848.jsonlOther149.3 MB a61247f6901f
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-0.6B-Base/checkpoints/global_step_848/actor/huggingface/chat_template.jinjaOther4.1 KB —
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-0.6B-Base/checkpoints/global_step_848/transfer_queue/controller_state.pklOther3.2 MB 19e27673065a
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-0.6B-Base/checkpoints/global_step_848/transfer_queue/simple_storage/su_0_TQ_STORAGE_UNIT_b7d7960b.pklOther96.7 MB a643e00e6484
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-0.6B-Base/checkpoints/global_step_848/transfer_queue/simple_storage/su_1_TQ_STORAGE_UNIT_24a8610d.pklOther94.2 MB 904f6263fe34
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-0.6B-Base/checkpoints/global_step_848/transfer_queue/simple_storage/su_2_TQ_STORAGE_UNIT_34aef140.pklOther94.7 MB 5280dacb29a9
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-0.6B-Base/checkpoints/global_step_848/transfer_queue/simple_storage/su_3_TQ_STORAGE_UNIT_d64978c9.pklOther95.3 MB 33ba85f58253
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-0.6B-Base/validation/100.jsonlOther101.8 MB a5d35f6fe67b
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-0.6B-Base/validation/120.jsonlOther94.8 MB f5e26c0ed820
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-0.6B-Base/validation/140.jsonlOther90.6 MB 26fb0caecaef
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-0.6B-Base/validation/160.jsonlOther87.1 MB 36384d6c9a94
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-0.6B-Base/validation/180.jsonlOther80.5 MB decf134e0af1
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-0.6B-Base/validation/20.jsonlOther146.2 MB 964f26727742
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-0.6B-Base/validation/200.jsonlOther76.6 MB 26d2e18f46ca
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-0.6B-Base/validation/220.jsonlOther78.6 MB 70b866cda570
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-0.6B-Base/validation/240.jsonlOther79.7 MB 699d3a1644c7
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-0.6B-Base/validation/260.jsonlOther78.3 MB 5301c01c50ff
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-0.6B-Base/validation/280.jsonlOther75.8 MB b75373aaca4c
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-0.6B-Base/validation/300.jsonlOther72.7 MB 45f7a2aa94fb
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-0.6B-Base/validation/320.jsonlOther75.0 MB db1813dc899a
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-0.6B-Base/validation/340.jsonlOther75.7 MB e369e57e1f47
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-0.6B-Base/validation/360.jsonlOther78.8 MB 9e4ff250a043
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-0.6B-Base/validation/380.jsonlOther80.6 MB 48594afeabd1
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-0.6B-Base/validation/40.jsonlOther136.5 MB ac546b95dc92
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-0.6B-Base/validation/400.jsonlOther81.6 MB cb137ab3c1bc
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-0.6B-Base/validation/420.jsonlOther86.0 MB fed1b5741f29
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-0.6B-Base/validation/440.jsonlOther89.5 MB 7b3159f0cafc
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-0.6B-Base/validation/460.jsonlOther102.6 MB 1c9afdd85ec9
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-0.6B-Base/validation/480.jsonlOther105.6 MB 9872cea4a1db
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-0.6B-Base/validation/500.jsonlOther103.6 MB e1aacce6bc94
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-0.6B-Base/validation/520.jsonlOther97.8 MB 2e38ed1b8eae
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-0.6B-Base/validation/540.jsonlOther103.2 MB 6b0fd98cf30a
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-0.6B-Base/validation/560.jsonlOther98.5 MB 07acdf13cf63
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-0.6B-Base/validation/580.jsonlOther98.5 MB 6d206820721f
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-0.6B-Base/validation/60.jsonlOther123.9 MB 84149770ac80
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-0.6B-Base/validation/600.jsonlOther97.3 MB af40f9e0c160
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-0.6B-Base/validation/620.jsonlOther88.6 MB a9c19f4e15f1
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-0.6B-Base/validation/640.jsonlOther89.4 MB 38b934ed4b7f
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-0.6B-Base/validation/660.jsonlOther101.5 MB 9f6d97522f79
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-0.6B-Base/validation/680.jsonlOther101.0 MB 69bd73bffeba
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-0.6B-Base/validation/700.jsonlOther103.3 MB 26cb6946cf12
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-0.6B-Base/validation/720.jsonlOther102.0 MB cf9f8230bbbc
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-0.6B-Base/validation/740.jsonlOther99.5 MB 2a38b1c2ac5a
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-0.6B-Base/validation/760.jsonlOther100.5 MB 409b517ae507
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-0.6B-Base/validation/780.jsonlOther94.2 MB abe07e875f73
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-0.6B-Base/validation/80.jsonlOther112.9 MB 6fdca71708f5
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-0.6B-Base/validation/800.jsonlOther96.1 MB c3cb7ca62a39
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-0.6B-Base/validation/820.jsonlOther94.4 MB d9e21fb656a2
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-0.6B-Base/validation/840.jsonlOther95.5 MB 3c7491a270fc
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-0.6B-Base/validation/848.jsonlOther93.9 MB 0b232beed189
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-1.7B-Base/checkpoints/global_step_848/actor/huggingface/chat_template.jinjaOther4.1 KB —
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-1.7B-Base/checkpoints/global_step_848/transfer_queue/controller_state.pklOther3.2 MB d18f528a6094
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-1.7B-Base/checkpoints/global_step_848/transfer_queue/simple_storage/su_0_TQ_STORAGE_UNIT_61363cef.pklOther59.3 MB e7489e94ebba
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-1.7B-Base/checkpoints/global_step_848/transfer_queue/simple_storage/su_1_TQ_STORAGE_UNIT_648014c7.pklOther59.0 MB fcea064e9155
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-1.7B-Base/checkpoints/global_step_848/transfer_queue/simple_storage/su_2_TQ_STORAGE_UNIT_5289aca2.pklOther59.5 MB 54d81045b0ce
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-1.7B-Base/checkpoints/global_step_848/transfer_queue/simple_storage/su_3_TQ_STORAGE_UNIT_2eba4a46.pklOther58.9 MB 9ef476ad1f4f
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-1.7B-Base/validation/100.jsonlOther71.1 MB 44014ee6b2e0
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-1.7B-Base/validation/120.jsonlOther70.0 MB a51c218487d8
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-1.7B-Base/validation/140.jsonlOther68.5 MB 1486048d40e7
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-1.7B-Base/validation/160.jsonlOther68.2 MB b8c6cb131efe
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-1.7B-Base/validation/180.jsonlOther67.0 MB 32f902397980
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-1.7B-Base/validation/20.jsonlOther75.8 MB e150756f7058
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-1.7B-Base/validation/200.jsonlOther65.1 MB 8c7fd2d5120c
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-1.7B-Base/validation/220.jsonlOther64.4 MB ba091e7c50c5
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-1.7B-Base/validation/240.jsonlOther63.9 MB 7f50726a6334
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-1.7B-Base/validation/260.jsonlOther63.7 MB 9ff60272b55c
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-1.7B-Base/validation/280.jsonlOther64.2 MB c3295c1a6675
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-1.7B-Base/validation/300.jsonlOther62.6 MB 126bfff2a3fb
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-1.7B-Base/validation/320.jsonlOther62.6 MB 22f07fa0f322
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-1.7B-Base/validation/340.jsonlOther62.4 MB f39a41c89fce
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-1.7B-Base/validation/360.jsonlOther60.6 MB f47edfd34000
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-1.7B-Base/validation/380.jsonlOther60.4 MB dc180c0af20c
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-1.7B-Base/validation/40.jsonlOther74.9 MB bd1dcb5126a7
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-1.7B-Base/validation/400.jsonlOther61.2 MB c9cf60c90f50
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-1.7B-Base/validation/420.jsonlOther60.9 MB f41d9897a2c7
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-1.7B-Base/validation/440.jsonlOther60.5 MB ce9c23bd6b0a
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-1.7B-Base/validation/460.jsonlOther61.1 MB 2a0ec6111c1f
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-1.7B-Base/validation/480.jsonlOther61.4 MB 7b8d2951ddf7
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-1.7B-Base/validation/500.jsonlOther62.6 MB 64fe572a80f6
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-1.7B-Base/validation/520.jsonlOther62.7 MB efcd14696f5d
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-1.7B-Base/validation/540.jsonlOther60.8 MB c4a9ace0fe45
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-1.7B-Base/validation/560.jsonlOther58.5 MB 4ad082811a89
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-1.7B-Base/validation/580.jsonlOther58.6 MB cc2c4e15adb2
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-1.7B-Base/validation/60.jsonlOther74.4 MB 6ad5f5a04418
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-1.7B-Base/validation/600.jsonlOther58.7 MB 2bb6327fa5ee
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-1.7B-Base/validation/620.jsonlOther59.5 MB 8df9d06ccf82
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-1.7B-Base/validation/640.jsonlOther61.3 MB 69d00959b37e
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-1.7B-Base/validation/660.jsonlOther60.1 MB e7045116df0c
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-1.7B-Base/validation/680.jsonlOther61.7 MB f57606bec8ad
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-1.7B-Base/validation/700.jsonlOther62.6 MB b1eb152b70ed
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-1.7B-Base/validation/720.jsonlOther64.4 MB b021ba8678ce
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-1.7B-Base/validation/740.jsonlOther66.0 MB f471703edc66
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-1.7B-Base/validation/760.jsonlOther65.4 MB 6d3e92aee605
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-1.7B-Base/validation/780.jsonlOther65.9 MB 7c6abcb2cd1f
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-1.7B-Base/validation/80.jsonlOther72.9 MB f0e1cdae3a91
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-1.7B-Base/validation/800.jsonlOther68.4 MB 014a7ebf62c5
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-1.7B-Base/validation/820.jsonlOther69.3 MB 7fe3c95279c5
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-1.7B-Base/validation/840.jsonlOther64.8 MB ee96f07caf74
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-1.7B-Base/validation/848.jsonlOther63.0 MB 75ce7415c10f
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-4B-Base/checkpoints/global_step_820/actor/huggingface/chat_template.jinjaOther4.1 KB —
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-4B-Base/checkpoints/global_step_820/transfer_queue/controller_state.pklOther3.2 MB 039b1e62f1af
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-4B-Base/checkpoints/global_step_820/transfer_queue/simple_storage/su_0_TQ_STORAGE_UNIT_31e9e011.pklOther196.1 MB 9139707b4809
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-4B-Base/checkpoints/global_step_820/transfer_queue/simple_storage/su_1_TQ_STORAGE_UNIT_d0f1a9db.pklOther195.0 MB 0828afc9d530
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-4B-Base/checkpoints/global_step_820/transfer_queue/simple_storage/su_2_TQ_STORAGE_UNIT_2ba6f9f1.pklOther194.4 MB 5353e43f8c94
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-4B-Base/checkpoints/global_step_820/transfer_queue/simple_storage/su_3_TQ_STORAGE_UNIT_30792de3.pklOther195.0 MB 6dcb793eb089
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-4B-Base/validation/100.jsonlOther68.2 MB d5ba34d0f77c
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-4B-Base/validation/120.jsonlOther68.3 MB e21ac972f18d
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-4B-Base/validation/140.jsonlOther72.1 MB 20611df129c6
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-4B-Base/validation/160.jsonlOther80.3 MB d0473167f69d
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-4B-Base/validation/180.jsonlOther87.7 MB bb6749c6bbc5
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-4B-Base/validation/20.jsonlOther69.0 MB aad688ec6c78
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-4B-Base/validation/200.jsonlOther96.7 MB 7be7d2dd6a1b
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-4B-Base/validation/220.jsonlOther106.1 MB 1894fdf05815
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-4B-Base/validation/240.jsonlOther117.1 MB aac569381d0b
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-4B-Base/validation/260.jsonlOther120.2 MB 989203c3b1ef
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-4B-Base/validation/280.jsonlOther127.8 MB 511faefd2ca3
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-4B-Base/validation/300.jsonlOther129.5 MB 7d9aa369a536
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-4B-Base/validation/320.jsonlOther125.6 MB 25635bdccbd9
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-4B-Base/validation/340.jsonlOther129.0 MB bb78ed4ad1a2
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-4B-Base/validation/360.jsonlOther137.4 MB 83db9a84f98b
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-4B-Base/validation/380.jsonlOther139.0 MB 8bda1d1232c2
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-4B-Base/validation/40.jsonlOther68.1 MB 79ac55127f1b
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-4B-Base/validation/400.jsonlOther136.3 MB f4c59d971a7a
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-4B-Base/validation/420.jsonlOther142.9 MB 3e8cfc2d79a0
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-4B-Base/validation/440.jsonlOther149.8 MB 118de268ebc3
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-4B-Base/validation/460.jsonlOther149.4 MB e3b32c9412f7
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-4B-Base/validation/480.jsonlOther146.0 MB e3cbb38e6d97
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-4B-Base/validation/500.jsonlOther150.1 MB 0dbe472570cf
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-4B-Base/validation/520.jsonlOther151.9 MB 982ccc7b97c0
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-4B-Base/validation/540.jsonlOther163.1 MB e698e42da534
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-4B-Base/validation/560.jsonlOther160.5 MB 74f3521d28ad
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-4B-Base/validation/580.jsonlOther151.2 MB 9ef6028cf260
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-4B-Base/validation/60.jsonlOther67.0 MB 2d235c4f0ca0
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-4B-Base/validation/600.jsonlOther160.0 MB 246ca080494e
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-4B-Base/validation/620.jsonlOther166.6 MB 256079a85f93
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-4B-Base/validation/640.jsonlOther159.5 MB c860aa285119
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-4B-Base/validation/660.jsonlOther153.8 MB 17f44eecadf4
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-4B-Base/validation/680.jsonlOther164.5 MB 2ee43477c9ae
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-4B-Base/validation/700.jsonlOther153.6 MB 684846b19a5b
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-4B-Base/validation/720.jsonlOther153.6 MB e9b6e6c14347
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-4B-Base/validation/740.jsonlOther146.8 MB 7ff715172a72
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-4B-Base/validation/760.jsonlOther141.9 MB c5914b0234c4
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-4B-Base/validation/780.jsonlOther142.3 MB 55b954bc5e04
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-4B-Base/validation/80.jsonlOther67.9 MB 84892c818b44
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-4B-Base/validation/800.jsonlOther148.1 MB 6e5706b3263e
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-4B-Base/validation/820.jsonlOther145.0 MB 45f08ebc6517
models/PrefixGRPO-R1x2-R2x8-Lnull_Guru/Qwen2.5-0.5B-low-lr5e-5/checkpoints/global_step_424/actor/huggingface/chat_template.jinjaOther2.4 KB —
models/PrefixGRPO-R1x2-R2x8-Lnull_Guru/Qwen2.5-0.5B-low-lr5e-5/checkpoints/global_step_424/transfer_queue/controller_state.pklOther3.2 MB 4e20c37a35db
models/PrefixGRPO-R1x2-R2x8-Lnull_Guru/Qwen2.5-0.5B-low-lr5e-5/checkpoints/global_step_424/transfer_queue/simple_storage/su_0_TQ_STORAGE_UNIT_908a860d.pklOther90.6 MB a40a70eef0ea
models/PrefixGRPO-R1x2-R2x8-Lnull_Guru/Qwen2.5-0.5B-low-lr5e-5/checkpoints/global_step_424/transfer_queue/simple_storage/su_1_TQ_STORAGE_UNIT_4844d4ff.pklOther90.2 MB df64d4d06821
models/PrefixGRPO-R1x2-R2x8-Lnull_Guru/Qwen2.5-0.5B-low-lr5e-5/checkpoints/global_step_424/transfer_queue/simple_storage/su_2_TQ_STORAGE_UNIT_d83481a3.pklOther91.5 MB 0a241573e53f
models/PrefixGRPO-R1x2-R2x8-Lnull_Guru/Qwen2.5-0.5B-low-lr5e-5/checkpoints/global_step_424/transfer_queue/simple_storage/su_3_TQ_STORAGE_UNIT_d346cbff.pklOther91.0 MB f44b5eb852e2
models/PrefixGRPO-R1x2-R2x8-Lnull_Guru/Qwen2.5-0.5B-low-lr5e-5/validation/100.jsonlOther117.5 MB 9fe31105e4d3
models/PrefixGRPO-R1x2-R2x8-Lnull_Guru/Qwen2.5-0.5B-low-lr5e-5/validation/120.jsonlOther108.1 MB baaed88a2f85
models/PrefixGRPO-R1x2-R2x8-Lnull_Guru/Qwen2.5-0.5B-low-lr5e-5/validation/140.jsonlOther102.7 MB 6636e6e73cbc
models/PrefixGRPO-R1x2-R2x8-Lnull_Guru/Qwen2.5-0.5B-low-lr5e-5/validation/160.jsonlOther93.4 MB 58d234ede477
models/PrefixGRPO-R1x2-R2x8-Lnull_Guru/Qwen2.5-0.5B-low-lr5e-5/validation/180.jsonlOther92.4 MB 3bf46f9f25e3
models/PrefixGRPO-R1x2-R2x8-Lnull_Guru/Qwen2.5-0.5B-low-lr5e-5/validation/20.jsonlOther145.7 MB e96cf6543510
models/PrefixGRPO-R1x2-R2x8-Lnull_Guru/Qwen2.5-0.5B-low-lr5e-5/validation/200.jsonlOther87.9 MB 05c4ac501785
models/PrefixGRPO-R1x2-R2x8-Lnull_Guru/Qwen2.5-0.5B-low-lr5e-5/validation/220.jsonlOther89.0 MB a58dcd9df029
models/PrefixGRPO-R1x2-R2x8-Lnull_Guru/Qwen2.5-0.5B-low-lr5e-5/validation/240.jsonlOther87.2 MB c7a8c6e2d707
models/PrefixGRPO-R1x2-R2x8-Lnull_Guru/Qwen2.5-0.5B-low-lr5e-5/validation/260.jsonlOther82.1 MB 85496768f6b8
models/PrefixGRPO-R1x2-R2x8-Lnull_Guru/Qwen2.5-0.5B-low-lr5e-5/validation/280.jsonlOther81.4 MB f2b3f0ffdebe
models/PrefixGRPO-R1x2-R2x8-Lnull_Guru/Qwen2.5-0.5B-low-lr5e-5/validation/300.jsonlOther84.0 MB e2024fd22c56
models/PrefixGRPO-R1x2-R2x8-Lnull_Guru/Qwen2.5-0.5B-low-lr5e-5/validation/320.jsonlOther83.5 MB 6e3fd1492131
models/PrefixGRPO-R1x2-R2x8-Lnull_Guru/Qwen2.5-0.5B-low-lr5e-5/validation/340.jsonlOther82.2 MB b6d820c0f0bd
models/PrefixGRPO-R1x2-R2x8-Lnull_Guru/Qwen2.5-0.5B-low-lr5e-5/validation/360.jsonlOther80.0 MB efbd5b40ca13
models/PrefixGRPO-R1x2-R2x8-Lnull_Guru/Qwen2.5-0.5B-low-lr5e-5/validation/380.jsonlOther81.6 MB 79f43b6f2c92
models/PrefixGRPO-R1x2-R2x8-Lnull_Guru/Qwen2.5-0.5B-low-lr5e-5/validation/40.jsonlOther139.7 MB 2b05ac76dcb3
models/PrefixGRPO-R1x2-R2x8-Lnull_Guru/Qwen2.5-0.5B-low-lr5e-5/validation/400.jsonlOther86.8 MB 7353d241a369
models/PrefixGRPO-R1x2-R2x8-Lnull_Guru/Qwen2.5-0.5B-low-lr5e-5/validation/420.jsonlOther86.0 MB ef7105260616
models/PrefixGRPO-R1x2-R2x8-Lnull_Guru/Qwen2.5-0.5B-low-lr5e-5/validation/424.jsonlOther83.6 MB ac99ce69100d
models/PrefixGRPO-R1x2-R2x8-Lnull_Guru/Qwen2.5-0.5B-low-lr5e-5/validation/60.jsonlOther135.7 MB 70902223d74d
models/PrefixGRPO-R1x2-R2x8-Lnull_Guru/Qwen2.5-0.5B-low-lr5e-5/validation/80.jsonlOther126.4 MB bf791f02b2d3
models/SFT/Qwen2.5-0.5B-low-lr5e-5/chat_template.jinjaOther2.4 KB —
models/SFT/Qwen2.5-0.5B-medium-lr5e-5/chat_template.jinjaOther2.4 KB —
models/SFT/Qwen2.5-1.5B-low-lr5e-5/chat_template.jinjaOther2.4 KB —
models/SFT/Qwen2.5-1.5B-medium-lr5e-5/chat_template.jinjaOther2.4 KB —
models/SFT/Qwen2.5-3B-low-lr4e-5/chat_template.jinjaOther2.4 KB —
models/SFT/Qwen2.5-7B-low-lr4e-5/chat_template.jinjaOther2.4 KB —
.gitattributesRepository321.3 KB —
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/checkpoints/global_step_421/actor/huggingface/merges.txtTokenizer1.7 MB —
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/checkpoints/global_step_421/actor/huggingface/tokenizer.jsonTokenizer11.4 MB 3fd169731d2c
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/checkpoints/global_step_421/actor/huggingface/tokenizer_config.jsonTokenizer4.7 KB —
models/GRPO_BigMath/Qwen2.5-0.5B-low-lr5e-5/checkpoints/global_step_421/actor/huggingface/vocab.jsonTokenizer2.8 MB —
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/checkpoints/global_step_220/actor/huggingface/merges.txtTokenizer1.7 MB —
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/checkpoints/global_step_220/actor/huggingface/tokenizer.jsonTokenizer11.4 MB 3fd169731d2c
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/checkpoints/global_step_220/actor/huggingface/tokenizer_config.jsonTokenizer4.7 KB —
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/checkpoints/global_step_220/actor/huggingface/vocab.jsonTokenizer2.8 MB —
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/checkpoints/global_step_421/actor/huggingface/merges.txtTokenizer1.7 MB —
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/checkpoints/global_step_421/actor/huggingface/tokenizer.jsonTokenizer11.4 MB 3fd169731d2c
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/checkpoints/global_step_421/actor/huggingface/tokenizer_config.jsonTokenizer4.7 KB —
models/GRPO_BigMath/Qwen2.5-1.5B-low-lr5e-5/checkpoints/global_step_421/actor/huggingface/vocab.jsonTokenizer2.8 MB —
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/checkpoints/global_step_421/actor/huggingface/merges.txtTokenizer1.7 MB —
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/checkpoints/global_step_421/actor/huggingface/tokenizer.jsonTokenizer11.4 MB 3fd169731d2c
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/checkpoints/global_step_421/actor/huggingface/tokenizer_config.jsonTokenizer4.7 KB —
models/GRPO_BigMath/Qwen2.5-3B-low-lr4e-5/checkpoints/global_step_421/actor/huggingface/vocab.jsonTokenizer2.8 MB —
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/checkpoints/global_step_421/actor/huggingface/merges.txtTokenizer1.7 MB —
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/checkpoints/global_step_421/actor/huggingface/tokenizer.jsonTokenizer11.4 MB 3fd169731d2c
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/checkpoints/global_step_421/actor/huggingface/tokenizer_config.jsonTokenizer4.7 KB —
models/GRPO_BigMath/Qwen2.5-7B-low-lr4e-5/checkpoints/global_step_421/actor/huggingface/vocab.jsonTokenizer2.8 MB —
models/GRPO_Guru/Qwen2.5-0.5B-low-lr5e-5/checkpoints/global_step_106/actor/huggingface/merges.txtTokenizer1.7 MB —
models/GRPO_Guru/Qwen2.5-0.5B-low-lr5e-5/checkpoints/global_step_106/actor/huggingface/tokenizer.jsonTokenizer11.4 MB 3fd169731d2c
models/GRPO_Guru/Qwen2.5-0.5B-low-lr5e-5/checkpoints/global_step_106/actor/huggingface/tokenizer_config.jsonTokenizer4.7 KB —
models/GRPO_Guru/Qwen2.5-0.5B-low-lr5e-5/checkpoints/global_step_106/actor/huggingface/vocab.jsonTokenizer2.8 MB —
models/GRPO_Guru/Qwen2.5-1.5B-low-lr5e-5/checkpoints/global_step_106/actor/huggingface/merges.txtTokenizer1.7 MB —
models/GRPO_Guru/Qwen2.5-1.5B-low-lr5e-5/checkpoints/global_step_106/actor/huggingface/tokenizer.jsonTokenizer11.4 MB 3fd169731d2c
models/GRPO_Guru/Qwen2.5-1.5B-low-lr5e-5/checkpoints/global_step_106/actor/huggingface/tokenizer_config.jsonTokenizer4.7 KB —
models/GRPO_Guru/Qwen2.5-1.5B-low-lr5e-5/checkpoints/global_step_106/actor/huggingface/vocab.jsonTokenizer2.8 MB —
models/GRPO_Guru/Qwen2.5-3B-low-lr4e-5/checkpoints/global_step_106/actor/huggingface/merges.txtTokenizer1.7 MB —
models/GRPO_Guru/Qwen2.5-3B-low-lr4e-5/checkpoints/global_step_106/actor/huggingface/tokenizer.jsonTokenizer11.4 MB 3fd169731d2c
models/GRPO_Guru/Qwen2.5-3B-low-lr4e-5/checkpoints/global_step_106/actor/huggingface/tokenizer_config.jsonTokenizer4.7 KB —
models/GRPO_Guru/Qwen2.5-3B-low-lr4e-5/checkpoints/global_step_106/actor/huggingface/vocab.jsonTokenizer2.8 MB —
models/GRPO_Guru/Qwen2.5-7B-low-lr4e-5/checkpoints/global_step_106/actor/huggingface/merges.txtTokenizer1.7 MB —
models/GRPO_Guru/Qwen2.5-7B-low-lr4e-5/checkpoints/global_step_106/actor/huggingface/tokenizer.jsonTokenizer11.4 MB 3fd169731d2c
models/GRPO_Guru/Qwen2.5-7B-low-lr4e-5/checkpoints/global_step_106/actor/huggingface/tokenizer_config.jsonTokenizer4.7 KB —
models/GRPO_Guru/Qwen2.5-7B-low-lr4e-5/checkpoints/global_step_106/actor/huggingface/vocab.jsonTokenizer2.8 MB —
models/GRPO_Guru/Qwen3-0.6B-Base/checkpoints/global_step_848/actor/huggingface/merges.txtTokenizer1.7 MB —
models/GRPO_Guru/Qwen3-0.6B-Base/checkpoints/global_step_848/actor/huggingface/tokenizer.jsonTokenizer11.4 MB aeb13307a71a
models/GRPO_Guru/Qwen3-0.6B-Base/checkpoints/global_step_848/actor/huggingface/tokenizer_config.jsonTokenizer5.4 KB —
models/GRPO_Guru/Qwen3-0.6B-Base/checkpoints/global_step_848/actor/huggingface/vocab.jsonTokenizer2.8 MB —
models/GRPO_Guru/Qwen3-1.7B-Base/checkpoints/global_step_848/actor/huggingface/merges.txtTokenizer1.7 MB —
models/GRPO_Guru/Qwen3-1.7B-Base/checkpoints/global_step_848/actor/huggingface/tokenizer.jsonTokenizer11.4 MB aeb13307a71a
models/GRPO_Guru/Qwen3-1.7B-Base/checkpoints/global_step_848/actor/huggingface/tokenizer_config.jsonTokenizer5.4 KB —
models/GRPO_Guru/Qwen3-1.7B-Base/checkpoints/global_step_848/actor/huggingface/vocab.jsonTokenizer2.8 MB —
models/GRPO_Guru/Qwen3-4B-Base/checkpoints/global_step_848/actor/huggingface/merges.txtTokenizer1.7 MB —
models/GRPO_Guru/Qwen3-4B-Base/checkpoints/global_step_848/actor/huggingface/tokenizer.jsonTokenizer11.4 MB aeb13307a71a
models/GRPO_Guru/Qwen3-4B-Base/checkpoints/global_step_848/actor/huggingface/tokenizer_config.jsonTokenizer5.4 KB —
models/GRPO_Guru/Qwen3-4B-Base/checkpoints/global_step_848/actor/huggingface/vocab.jsonTokenizer2.8 MB —
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-0.6B-Base/checkpoints/global_step_848/actor/huggingface/merges.txtTokenizer1.7 MB —
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-0.6B-Base/checkpoints/global_step_848/actor/huggingface/tokenizer.jsonTokenizer11.4 MB aeb13307a71a
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-0.6B-Base/checkpoints/global_step_848/actor/huggingface/tokenizer_config.jsonTokenizer5.4 KB —
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-0.6B-Base/checkpoints/global_step_848/actor/huggingface/vocab.jsonTokenizer2.8 MB —
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-1.7B-Base/checkpoints/global_step_848/actor/huggingface/merges.txtTokenizer1.7 MB —
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-1.7B-Base/checkpoints/global_step_848/actor/huggingface/tokenizer.jsonTokenizer11.4 MB aeb13307a71a
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-1.7B-Base/checkpoints/global_step_848/actor/huggingface/tokenizer_config.jsonTokenizer5.4 KB —
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-1.7B-Base/checkpoints/global_step_848/actor/huggingface/vocab.jsonTokenizer2.8 MB —
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-4B-Base/checkpoints/global_step_820/actor/huggingface/merges.txtTokenizer1.7 MB —
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-4B-Base/checkpoints/global_step_820/actor/huggingface/tokenizer.jsonTokenizer11.4 MB aeb13307a71a
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-4B-Base/checkpoints/global_step_820/actor/huggingface/tokenizer_config.jsonTokenizer5.4 KB —
models/PrefixGRPO-R1x2-R2x8-L50_Guru/Qwen3-4B-Base/checkpoints/global_step_820/actor/huggingface/vocab.jsonTokenizer2.8 MB —
models/PrefixGRPO-R1x2-R2x8-Lnull_Guru/Qwen2.5-0.5B-low-lr5e-5/checkpoints/global_step_424/actor/huggingface/merges.txtTokenizer1.7 MB —
models/PrefixGRPO-R1x2-R2x8-Lnull_Guru/Qwen2.5-0.5B-low-lr5e-5/checkpoints/global_step_424/actor/huggingface/tokenizer.jsonTokenizer11.4 MB 3fd169731d2c
models/PrefixGRPO-R1x2-R2x8-Lnull_Guru/Qwen2.5-0.5B-low-lr5e-5/checkpoints/global_step_424/actor/huggingface/tokenizer_config.jsonTokenizer4.7 KB —
models/PrefixGRPO-R1x2-R2x8-Lnull_Guru/Qwen2.5-0.5B-low-lr5e-5/checkpoints/global_step_424/actor/huggingface/vocab.jsonTokenizer2.8 MB —
models/SFT/Qwen2.5-0.5B-low-lr5e-5/tokenizer.jsonTokenizer11.4 MB 3fd169731d2c
models/SFT/Qwen2.5-0.5B-low-lr5e-5/tokenizer_config.jsonTokenizer696 B —
models/SFT/Qwen2.5-0.5B-medium-lr5e-5/tokenizer.jsonTokenizer11.4 MB 3fd169731d2c
models/SFT/Qwen2.5-0.5B-medium-lr5e-5/tokenizer_config.jsonTokenizer696 B —
models/SFT/Qwen2.5-1.5B-low-lr5e-5/tokenizer.jsonTokenizer11.4 MB 3fd169731d2c
models/SFT/Qwen2.5-1.5B-low-lr5e-5/tokenizer_config.jsonTokenizer696 B —
models/SFT/Qwen2.5-1.5B-medium-lr5e-5/tokenizer.jsonTokenizer11.4 MB 3fd169731d2c
models/SFT/Qwen2.5-1.5B-medium-lr5e-5/tokenizer_config.jsonTokenizer696 B —
models/SFT/Qwen2.5-3B-low-lr4e-5/tokenizer.jsonTokenizer11.4 MB 3fd169731d2c
models/SFT/Qwen2.5-3B-low-lr4e-5/tokenizer_config.jsonTokenizer696 B —
models/SFT/Qwen2.5-7B-low-lr4e-5/tokenizer.jsonTokenizer11.4 MB 3fd169731d2c
models/SFT/Qwen2.5-7B-low-lr4e-5/tokenizer_config.jsonTokenizer696 B —

License and Download

License
Not stated by the source
Access
Open weights, no gate
Download size
511.9 GB
Download from Hoang P

Released by Hoang P through its official repository on Hugging Face.

Memory Requirements

PrecisionWeights in memory
As published511.9 GB

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