Skip to page content
SAVRN
Search Plan a project

Open-weight model

opd-checkpoints

by LINGHUA ZHANG icemoon28/opd-checkpoints

opd-checkpoints is an open-weight model from LINGHUA ZHANG. Its published files total 1.0 TB.

Parameters—
Context—
Weights977.1 GB
License—
AccessOpen weights
Monthly Downloads—

Model Card

The publisher has not written a card for this model.

Identity and Version

Repository
icemoon28/opd-checkpoints
Publisher
LINGHUA ZHANG
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
04db6077c24147493d09aeea2f4023be858e4a8f
First published
2026-08-27
Last updated
2026-10-06

Files and Weights

1,213 files, 1.0 TB in total. The weights are 275 files totalling 977.1 GB in pt, safetensors.

Weights275 files · 977.1 GB
Configuration408 files · 685.3 KB
Tokenizer388 files · 1.5 GB
Documentation1 file · 1.5 KB
Other140 files · 44.0 GB
Repository1 file · 14.7 KB
Every file
FileTypeSizeSHA-256
checkpoints/baselines/math_code/tip_topk32_rho50_8gpu_6s2t_b516/global_step_60/model.safetensorsWeights4.1 GB f3a0e14642ae
checkpoints/baselines/math_code/topk32_uniform_8gpu_6s2t_b516/global_step_60/model.safetensorsWeights4.1 GB 811474711f31
checkpoints/global_step_60/model.safetensorsWeights4.1 GB c28badeb854d
checkpoints/math/q1p7b-4g-math-fullvocab-toploss-topp05-fixed4-b256-colocated-s60/global_step_60/model.safetensorsWeights4.1 GB 72b4a7bf29cd
checkpoints/math/q1p7b-math-a-ns-expanded-v2-i1w1k29-5gpu-b256/global_step_55/model.safetensorsWeights4.1 GB c921bf8d3291
checkpoints/math/q1p7b-math-a-ns-expanded-v2-i1w1k29-5gpu-b256/global_step_60/model.safetensorsWeights4.1 GB cd9c8401f103
checkpoints/math/q1p7b-math-a-ns-v3-u-i1w1k25-8gpu_6a2t_b258/global_step_60/model.safetensorsWeights4.1 GB dc5e3e4867ef
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-split-i1w1k21pt-b255/global_step_55/model.safetensorsWeights4.1 GB 483b65407a3a
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-split-i1w1k21pt-b255/global_step_60/model.safetensorsWeights4.1 GB 941691322b25
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-split-i1w1k21pt-b255/global_step_65/model.safetensorsWeights4.1 GB 14fa8c92a2c8
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-split-i1w1k21pt-b255/global_step_70/model.safetensorsWeights4.1 GB 17049ae98681
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-split-topp0p05-i1w1-4gpu-3a1t-b255-r20260911/global_step_55/model.safetensorsWeights4.1 GB 969e46459de5
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-split-topp0p05-i1w1-4gpu-3a1t-b255-r20260911/global_step_60/model.safetensorsWeights4.1 GB f112e660d904
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-split-topp0p05-i1w1-4gpu-3a1t-b255-r20260911/global_step_65/model.safetensorsWeights4.1 GB 04e432f49e00
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p01-i1w1-5gpu-3a2t-b258-resume15/global_step_55/model.safetensorsWeights4.1 GB c06e68a241f4
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p01-i1w1-5gpu-3a2t-b258-resume15/global_step_60/model.safetensorsWeights4.1 GB 693ea3768711
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p01-i1w1-5gpu-3a2t-b258-resume15/global_step_65/model.safetensorsWeights4.1 GB b326fa0686eb
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p01-i1w1-5gpu-3a2t-b258-resume15/global_step_70/model.safetensorsWeights4.1 GB 3f2b0805af2f
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p02-i1w1-8gpu-6a2t-b258/global_step_60/model.safetensorsWeights4.1 GB 528eecb70376
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p05-i1w1-5gpu-b256/global_step_55/model.safetensorsWeights4.1 GB a109683f14cf
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p05-i1w1-5gpu-b256/global_step_60/model.safetensorsWeights4.1 GB 744f2bf39b53
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p05-i1w1-5gpu-b256/global_step_65/model.safetensorsWeights4.1 GB d79b905b34d3
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p075-i1w1-5gpu-4a1t-b256/global_step_55/model.safetensorsWeights4.1 GB e255ed70f57c
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p075-i1w1-5gpu-4a1t-b256/global_step_60/model.safetensorsWeights4.1 GB 73d6da4397b0
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p1-i1w1-5gpu-3a2t-b258/global_step_55/model.safetensorsWeights4.1 GB 6db11514d9d8
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p1-i1w1-5gpu-3a2t-b258/global_step_60/model.safetensorsWeights4.1 GB 2043c82b95c5
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p1-i1w1-5gpu-3a2t-b258/global_step_65/model.safetensorsWeights4.1 GB 0ecbcb776640
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p1-i1w1-5gpu-3a2t-b258/global_step_70/model.safetensorsWeights4.1 GB 7355dfab3491
checkpoints/math/q1p7b-math-top32kl-taxonomy-topp05-qsel-w4-5g4a1t-b256/global_step_55/model.safetensorsWeights4.1 GB ebb1ad0e7404
checkpoints/math/q1p7b-math-top32kl-taxonomy-topp05-qsel-w4-5g4a1t-b256/global_step_60/model.safetensorsWeights4.1 GB 7cdb3a180893
checkpoints/math/q1p7b-math-top32kl-taxonomy-topp05-qsel-w4-5g4a1t-b256/global_step_65/model.safetensorsWeights4.1 GB 4c7f8cd9e163
checkpoints/math/q1p7b-math-top32kl-taxonomy-topp05-qsel-w4-5g4a1t-b256/global_step_70/model.safetensorsWeights4.1 GB 295aaa6ac87f
checkpoints/math/q1p7b-math-top32kl-taxonomy-topp05-randsel-w4-4g3a1t-b255/global_step_55/model.safetensorsWeights4.1 GB fe7f2fd182cf
checkpoints/math/q1p7b-math-top32kl-taxonomy-topp05-randsel-w4-4g3a1t-b255/global_step_60/model.safetensorsWeights4.1 GB 3d94011c5277
checkpoints/math/q1p7b-math-top32kl-topp05-lossratio-5g4a1t-b256/global_step_55/model.safetensorsWeights4.1 GB 34da31b15e69
checkpoints/math/q1p7b-math-top32kl-topp05-lossratio-5g4a1t-b256/global_step_60/model.safetensorsWeights4.1 GB 79aeaac9c91d
checkpoints/math/q1p7b-math-top32kl-topp05-lossratio-5g4a1t-b256/global_step_65/model.safetensorsWeights4.1 GB 4c95daa71060
checkpoints/math/q1p7b-math-top32kl-topp05-lossratio-5g4a1t-b256/global_step_70/model.safetensorsWeights4.1 GB e2403d926e39
checkpoints/math/q1p7b-math-top32kl-topp05-lossratio-a1p75-8g6a2t-b258/global_step_60/model.safetensorsWeights4.1 GB 296815cc3f0c
checkpoints/math/q1p7b-math-top32kl-v3-topp075-w4-8g6a2t-b258/global_step_60/model.safetensorsWeights4.1 GB b6ec245266db
checkpoints/math/q1p7b-math-top32kl-v3-topp1-w4-5g4a1t-b256/global_step_55/model.safetensorsWeights4.1 GB 7af9fba3ebf4
checkpoints/math/q1p7b-math-top32kl-v3-topp1-w4-5g4a1t-b256/global_step_60/model.safetensorsWeights4.1 GB 0f3d4c4335f6
checkpoints/math/q1p7b-taxonomy-q-topp05-fixed4-5g4a1t-b256-r20260908/global_step_55/model.safetensorsWeights4.1 GB c6473861bfcf
checkpoints/math/q1p7b-taxonomy-q-topp05-fixed4-5g4a1t-b256-r20260908/global_step_60/model.safetensorsWeights4.1 GB 12fd5b9fc86e
checkpoints/math/q1p7b-taxonomy-q-topp05-fixed4-5g4a1t-b256-r20260908/global_step_65/model.safetensorsWeights4.1 GB e4b272ac0cc7
checkpoints/math/q1p7b-taxonomy-q-topp05-fixed4-5g4a1t-b256-r20260908/global_step_70/model.safetensorsWeights4.1 GB edc17af50e27
checkpoints/math/q1p7b-taxonomy-toploss-topp05-fixed2-4g3a1t-b255/global_step_55/model.safetensorsWeights4.1 GB 00e5ba000882
checkpoints/math/q1p7b-taxonomy-toploss-topp05-fixed2-4g3a1t-b255/global_step_60/model.safetensorsWeights4.1 GB 11f338129151
checkpoints/math/q1p7b-taxonomy-toploss-topp05-fixed2-4g3a1t-b255/global_step_65/model.safetensorsWeights4.1 GB 5fd16f8fb93d
checkpoints/math/q1p7b-taxonomy-toploss-topp05-fixed2-4g3a1t-b255/global_step_70/model.safetensorsWeights4.1 GB 687809bb73bb
checkpoints/math/q1p7b-taxonomy-toploss-topp05-fixed6-4g3a1t-b255-r20260909/global_step_55/model.safetensorsWeights4.1 GB abdfe762fe0a
checkpoints/math/q1p7b-taxonomy-toploss-topp05-fixed6-4g3a1t-b255-r20260909/global_step_60/model.safetensorsWeights4.1 GB a2c2fc1bbdbc
checkpoints/math/q1p7b-taxonomy-toploss-topp05-fixed6-4g3a1t-b255-r20260909/global_step_65/model.safetensorsWeights4.1 GB bc9b7cf84594
checkpoints/math/q1p7b-taxonomy-toploss-topp05-fixed6-4g3a1t-b255-r20260909/global_step_70/model.safetensorsWeights4.1 GB ecbb2b2ba05f
checkpoints/math/q1p7b-v3-topp05-lossratio-i1w1-5g4a1t-b256-r20260907/global_step_55/model.safetensorsWeights4.1 GB 153a1bfb33cb
checkpoints/math/q1p7b-v3-topp05-lossratio-i1w1-5g4a1t-b256-r20260907/global_step_60/model.safetensorsWeights4.1 GB dcf158ada622
checkpoints/math/q1p7b-v3-topp05-lossratio-i1w1-5g4a1t-b256-r20260907/global_step_65/model.safetensorsWeights4.1 GB 14b864fa2810
checkpoints/math/qwen1p7b-30b-math-eopd-4gpu-b255/global_step_50/actor/extra_state_world_size_3_rank_0.ptWeights15.2 KB a9b42a16859c
checkpoints/math/qwen1p7b-30b-math-eopd-4gpu-b255/global_step_50/actor/extra_state_world_size_3_rank_1.ptWeights15.2 KB 9c1522589354
checkpoints/math/qwen1p7b-30b-math-eopd-4gpu-b255/global_step_50/actor/extra_state_world_size_3_rank_2.ptWeights15.2 KB db021d9800c7
checkpoints/math/qwen1p7b-30b-math-eopd-4gpu-b255/global_step_50/actor/huggingface/model.safetensorsWeights4.1 GB 5942439a7821
checkpoints/math/qwen1p7b-30b-math-eopd-4gpu-b255/global_step_50/actor/model_world_size_3_rank_0.ptWeights4.1 GB ac5160815f21
checkpoints/math/qwen1p7b-30b-math-eopd-4gpu-b255/global_step_50/actor/model_world_size_3_rank_1.ptWeights4.1 GB aadffb7e0a5a
checkpoints/math/qwen1p7b-30b-math-eopd-4gpu-b255/global_step_50/actor/model_world_size_3_rank_2.ptWeights4.1 GB bb02607c9060
checkpoints/math/qwen1p7b-30b-math-eopd-4gpu-b255/global_step_50/actor/optim_world_size_3_rank_0.ptWeights6.9 GB 649700acf5a6
checkpoints/math/qwen1p7b-30b-math-eopd-4gpu-b255/global_step_50/actor/optim_world_size_3_rank_1.ptWeights6.9 GB 520deaafe51a
checkpoints/math/qwen1p7b-30b-math-eopd-4gpu-b255/global_step_50/actor/optim_world_size_3_rank_2.ptWeights6.9 GB 0ef2821b8f9f
checkpoints/math/qwen1p7b-30b-math-eopd-4gpu-b255/global_step_50/data.ptWeights7.6 KB 839c288c5967
checkpoints/math/qwen1p7b-30b-math-eopd-4gpu-b255/global_step_55/actor/extra_state_world_size_3_rank_0.ptWeights15.2 KB b7ac173c0898
checkpoints/math/qwen1p7b-30b-math-eopd-4gpu-b255/global_step_55/actor/extra_state_world_size_3_rank_1.ptWeights15.2 KB 6fe2338e3326
checkpoints/math/qwen1p7b-30b-math-eopd-4gpu-b255/global_step_55/actor/extra_state_world_size_3_rank_2.ptWeights15.2 KB 78a95ea90b3c
checkpoints/math/qwen1p7b-30b-math-eopd-4gpu-b255/global_step_55/actor/huggingface/model.safetensorsWeights4.1 GB 7cb2487a7179
checkpoints/math/qwen1p7b-30b-math-eopd-4gpu-b255/global_step_55/actor/model_world_size_3_rank_0.ptWeights4.1 GB 6f0dd03c87ff
checkpoints/math/qwen1p7b-30b-math-eopd-4gpu-b255/global_step_55/actor/model_world_size_3_rank_1.ptWeights4.1 GB c4147264c745
checkpoints/math/qwen1p7b-30b-math-eopd-4gpu-b255/global_step_55/actor/model_world_size_3_rank_2.ptWeights4.1 GB 1c5e33aa8833
checkpoints/math/qwen1p7b-30b-math-eopd-4gpu-b255/global_step_55/actor/optim_world_size_3_rank_0.ptWeights6.9 GB 033e74e4f7f7
checkpoints/math/qwen1p7b-30b-math-eopd-4gpu-b255/global_step_55/actor/optim_world_size_3_rank_1.ptWeights6.9 GB e0e22e9d7ab8
checkpoints/math/qwen1p7b-30b-math-eopd-4gpu-b255/global_step_55/actor/optim_world_size_3_rank_2.ptWeights6.9 GB 3f7329fc6ff2
checkpoints/math/qwen1p7b-30b-math-eopd-4gpu-b255/global_step_55/data.ptWeights7.6 KB 50d547d16738
checkpoints/math/qwen1p7b-30b-math-eopd-4gpu-b255/global_step_60/actor/extra_state_world_size_3_rank_0.ptWeights15.1 KB 4a8aeb072fba
checkpoints/math/qwen1p7b-30b-math-eopd-4gpu-b255/global_step_60/actor/extra_state_world_size_3_rank_1.ptWeights15.1 KB a5ce1b1074ec
checkpoints/math/qwen1p7b-30b-math-eopd-4gpu-b255/global_step_60/actor/extra_state_world_size_3_rank_2.ptWeights15.1 KB a9a893e0bfa0
checkpoints/math/qwen1p7b-30b-math-eopd-4gpu-b255/global_step_60/actor/huggingface/model.safetensorsWeights4.1 GB 09d76c915d83
checkpoints/math/qwen1p7b-30b-math-eopd-4gpu-b255/global_step_60/actor/model_world_size_3_rank_0.ptWeights4.1 GB a37675ab1f0d
checkpoints/math/qwen1p7b-30b-math-eopd-4gpu-b255/global_step_60/actor/model_world_size_3_rank_1.ptWeights4.1 GB 1d451ac1b4f0
checkpoints/math/qwen1p7b-30b-math-eopd-4gpu-b255/global_step_60/actor/model_world_size_3_rank_2.ptWeights4.1 GB 607ce4c5d0b4
checkpoints/math/qwen1p7b-30b-math-eopd-4gpu-b255/global_step_60/actor/optim_world_size_3_rank_0.ptWeights6.9 GB d08b980a7ff1
checkpoints/math/qwen1p7b-30b-math-eopd-4gpu-b255/global_step_60/actor/optim_world_size_3_rank_1.ptWeights6.9 GB af5c83102c08
checkpoints/math/qwen1p7b-30b-math-eopd-4gpu-b255/global_step_60/actor/optim_world_size_3_rank_2.ptWeights6.9 GB a74f11fef6b2
checkpoints/math/qwen1p7b-30b-math-eopd-4gpu-b255/global_step_60/data.ptWeights7.6 KB ff1c56179aac
checkpoints/math/qwen1p7b-30b-math-eopd-4gpu-b255/global_step_65/actor/extra_state_world_size_3_rank_0.ptWeights15.2 KB dd50eff42cad
checkpoints/math/qwen1p7b-30b-math-eopd-4gpu-b255/global_step_65/actor/extra_state_world_size_3_rank_1.ptWeights15.2 KB 5919afd00760
checkpoints/math/qwen1p7b-30b-math-eopd-4gpu-b255/global_step_65/actor/extra_state_world_size_3_rank_2.ptWeights15.2 KB ddfa02c39de8
checkpoints/math/qwen1p7b-30b-math-eopd-4gpu-b255/global_step_65/actor/huggingface/model.safetensorsWeights4.1 GB 46e9abda3737
checkpoints/math/qwen1p7b-30b-math-eopd-4gpu-b255/global_step_65/actor/model_world_size_3_rank_0.ptWeights4.1 GB bce508929822
checkpoints/math/qwen1p7b-30b-math-eopd-4gpu-b255/global_step_65/actor/model_world_size_3_rank_1.ptWeights4.1 GB 348fad566de9
checkpoints/math/qwen1p7b-30b-math-eopd-4gpu-b255/global_step_65/actor/model_world_size_3_rank_2.ptWeights4.1 GB f26868a0b80f
checkpoints/math/qwen1p7b-30b-math-eopd-4gpu-b255/global_step_65/actor/optim_world_size_3_rank_0.ptWeights6.9 GB 54b3e18058b9
checkpoints/math/qwen1p7b-30b-math-eopd-4gpu-b255/global_step_65/actor/optim_world_size_3_rank_1.ptWeights6.9 GB cdf8c85468ba
checkpoints/math/qwen1p7b-30b-math-eopd-4gpu-b255/global_step_65/actor/optim_world_size_3_rank_2.ptWeights6.9 GB 8d8e1fff6b07
checkpoints/math/qwen1p7b-30b-math-eopd-4gpu-b255/global_step_65/data.ptWeights7.6 KB a57fc5ae1c76
checkpoints/math/qwen1p7b-30b-math-exopd-lambda1p25-4gpu-b255/global_step_55/actor/extra_state_world_size_3_rank_0.ptWeights15.2 KB b7ac173c0898
checkpoints/math/qwen1p7b-30b-math-exopd-lambda1p25-4gpu-b255/global_step_55/actor/extra_state_world_size_3_rank_1.ptWeights15.2 KB 6fe2338e3326
checkpoints/math/qwen1p7b-30b-math-exopd-lambda1p25-4gpu-b255/global_step_55/actor/extra_state_world_size_3_rank_2.ptWeights15.2 KB 78a95ea90b3c
checkpoints/math/qwen1p7b-30b-math-exopd-lambda1p25-4gpu-b255/global_step_55/actor/huggingface/model.safetensorsWeights4.1 GB 163a4f457785
checkpoints/math/qwen1p7b-30b-math-exopd-lambda1p25-4gpu-b255/global_step_55/actor/model_world_size_3_rank_0.ptWeights4.1 GB 605d3c430e70
checkpoints/math/qwen1p7b-30b-math-exopd-lambda1p25-4gpu-b255/global_step_55/actor/model_world_size_3_rank_1.ptWeights4.1 GB 437328312718
checkpoints/math/qwen1p7b-30b-math-exopd-lambda1p25-4gpu-b255/global_step_55/actor/model_world_size_3_rank_2.ptWeights4.1 GB 34b6a280d81e
checkpoints/math/qwen1p7b-30b-math-exopd-lambda1p25-4gpu-b255/global_step_55/actor/optim_world_size_3_rank_0.ptWeights6.9 GB dfda30a14223
checkpoints/math/qwen1p7b-30b-math-exopd-lambda1p25-4gpu-b255/global_step_55/actor/optim_world_size_3_rank_1.ptWeights6.9 GB d71bcbf0a2ad
checkpoints/math/qwen1p7b-30b-math-exopd-lambda1p25-4gpu-b255/global_step_55/actor/optim_world_size_3_rank_2.ptWeights6.9 GB 109bf19d0101
checkpoints/math/qwen1p7b-30b-math-exopd-lambda1p25-4gpu-b255/global_step_55/data.ptWeights7.6 KB 50d547d16738
checkpoints/math/qwen1p7b-30b-math-exopd-lambda1p25-4gpu-b255/global_step_60/actor/extra_state_world_size_3_rank_0.ptWeights15.1 KB 4a8aeb072fba
checkpoints/math/qwen1p7b-30b-math-exopd-lambda1p25-4gpu-b255/global_step_60/actor/extra_state_world_size_3_rank_1.ptWeights15.1 KB a5ce1b1074ec
checkpoints/math/qwen1p7b-30b-math-exopd-lambda1p25-4gpu-b255/global_step_60/actor/extra_state_world_size_3_rank_2.ptWeights15.1 KB a9a893e0bfa0
checkpoints/math/qwen1p7b-30b-math-exopd-lambda1p25-4gpu-b255/global_step_60/actor/huggingface/model.safetensorsWeights4.1 GB 1f8cf3726bbb
checkpoints/math/qwen1p7b-30b-math-exopd-lambda1p25-4gpu-b255/global_step_60/actor/model_world_size_3_rank_0.ptWeights4.1 GB eb2f1e17d77e
checkpoints/math/qwen1p7b-30b-math-exopd-lambda1p25-4gpu-b255/global_step_60/actor/model_world_size_3_rank_1.ptWeights4.1 GB fe0098fa3b36
checkpoints/math/qwen1p7b-30b-math-exopd-lambda1p25-4gpu-b255/global_step_60/actor/model_world_size_3_rank_2.ptWeights4.1 GB 9a8e898e5454
checkpoints/math/qwen1p7b-30b-math-exopd-lambda1p25-4gpu-b255/global_step_60/actor/optim_world_size_3_rank_0.ptWeights6.9 GB 9bc62b7e9a92
checkpoints/math/qwen1p7b-30b-math-exopd-lambda1p25-4gpu-b255/global_step_60/actor/optim_world_size_3_rank_1.ptWeights6.9 GB a048e4d9605d
checkpoints/math/qwen1p7b-30b-math-exopd-lambda1p25-4gpu-b255/global_step_60/actor/optim_world_size_3_rank_2.ptWeights6.9 GB f9482e316957
checkpoints/math/qwen1p7b-30b-math-exopd-lambda1p25-4gpu-b255/global_step_60/data.ptWeights7.6 KB ff1c56179aac
checkpoints/math/qwen1p7b-30b-math-exopd-lambda1p25-4gpu-b255/global_step_65/actor/extra_state_world_size_3_rank_0.ptWeights15.2 KB dd50eff42cad
checkpoints/math/qwen1p7b-30b-math-exopd-lambda1p25-4gpu-b255/global_step_65/actor/extra_state_world_size_3_rank_1.ptWeights15.2 KB 5919afd00760
checkpoints/math/qwen1p7b-30b-math-exopd-lambda1p25-4gpu-b255/global_step_65/actor/extra_state_world_size_3_rank_2.ptWeights15.2 KB ddfa02c39de8
checkpoints/math/qwen1p7b-30b-math-exopd-lambda1p25-4gpu-b255/global_step_65/actor/huggingface/model.safetensorsWeights4.1 GB 235429287e30
checkpoints/math/qwen1p7b-30b-math-exopd-lambda1p25-4gpu-b255/global_step_65/actor/model_world_size_3_rank_0.ptWeights4.1 GB 27e4be695542
checkpoints/math/qwen1p7b-30b-math-exopd-lambda1p25-4gpu-b255/global_step_65/actor/model_world_size_3_rank_1.ptWeights4.1 GB fa0e455c65f4
checkpoints/math/qwen1p7b-30b-math-exopd-lambda1p25-4gpu-b255/global_step_65/actor/model_world_size_3_rank_2.ptWeights4.1 GB 02b86fde64a7
checkpoints/math/qwen1p7b-30b-math-exopd-lambda1p25-4gpu-b255/global_step_65/actor/optim_world_size_3_rank_0.ptWeights6.9 GB aefe5f8a5688
checkpoints/math/qwen1p7b-30b-math-exopd-lambda1p25-4gpu-b255/global_step_65/actor/optim_world_size_3_rank_1.ptWeights6.9 GB c528d4fff0a1
checkpoints/math/qwen1p7b-30b-math-exopd-lambda1p25-4gpu-b255/global_step_65/actor/optim_world_size_3_rank_2.ptWeights6.9 GB 19d36b7e4d2e
checkpoints/math/qwen1p7b-30b-math-exopd-lambda1p25-4gpu-b255/global_step_65/data.ptWeights7.6 KB a57fc5ae1c76
checkpoints/math/qwen1p7b-30b-math-exopd-lambda1p25-4gpu-b255/global_step_70/actor/extra_state_world_size_3_rank_0.ptWeights15.1 KB 6beaf7367b83
checkpoints/math/qwen1p7b-30b-math-exopd-lambda1p25-4gpu-b255/global_step_70/actor/extra_state_world_size_3_rank_1.ptWeights15.1 KB 8bca7e6b4e4f
checkpoints/math/qwen1p7b-30b-math-exopd-lambda1p25-4gpu-b255/global_step_70/actor/extra_state_world_size_3_rank_2.ptWeights15.1 KB 2fb185709d7f
checkpoints/math/qwen1p7b-30b-math-exopd-lambda1p25-4gpu-b255/global_step_70/actor/huggingface/model.safetensorsWeights4.1 GB 3c25cb18e421
checkpoints/math/qwen1p7b-30b-math-exopd-lambda1p25-4gpu-b255/global_step_70/actor/model_world_size_3_rank_0.ptWeights4.1 GB 54e897de256d
checkpoints/math/qwen1p7b-30b-math-exopd-lambda1p25-4gpu-b255/global_step_70/actor/model_world_size_3_rank_1.ptWeights4.1 GB f185cc299128
checkpoints/math/qwen1p7b-30b-math-exopd-lambda1p25-4gpu-b255/global_step_70/actor/model_world_size_3_rank_2.ptWeights4.1 GB 7b4ec1f37503
checkpoints/math/qwen1p7b-30b-math-exopd-lambda1p25-4gpu-b255/global_step_70/actor/optim_world_size_3_rank_0.ptWeights6.9 GB 40964371983e
checkpoints/math/qwen1p7b-30b-math-exopd-lambda1p25-4gpu-b255/global_step_70/actor/optim_world_size_3_rank_1.ptWeights6.9 GB c7379f5f71b2
checkpoints/math/qwen1p7b-30b-math-exopd-lambda1p25-4gpu-b255/global_step_70/actor/optim_world_size_3_rank_2.ptWeights6.9 GB bdf9bb9a5359
checkpoints/math/qwen1p7b-30b-math-exopd-lambda1p25-4gpu-b255/global_step_70/data.ptWeights7.6 KB a84267c6716f
checkpoints/math/qwen1p7b-30b-math-fire-opd-4gpu-b255/global_step_55/actor/extra_state_world_size_3_rank_0.ptWeights15.2 KB b7ac173c0898
checkpoints/math/qwen1p7b-30b-math-fire-opd-4gpu-b255/global_step_55/actor/extra_state_world_size_3_rank_1.ptWeights15.2 KB 6fe2338e3326
checkpoints/math/qwen1p7b-30b-math-fire-opd-4gpu-b255/global_step_55/actor/extra_state_world_size_3_rank_2.ptWeights15.2 KB 78a95ea90b3c
checkpoints/math/qwen1p7b-30b-math-fire-opd-4gpu-b255/global_step_55/actor/huggingface/model.safetensorsWeights4.1 GB 5ee4875beb9d
checkpoints/math/qwen1p7b-30b-math-fire-opd-4gpu-b255/global_step_55/actor/model_world_size_3_rank_0.ptWeights4.1 GB 0368fff24a82
checkpoints/math/qwen1p7b-30b-math-fire-opd-4gpu-b255/global_step_55/actor/model_world_size_3_rank_1.ptWeights4.1 GB 028f8c658925
checkpoints/math/qwen1p7b-30b-math-fire-opd-4gpu-b255/global_step_55/actor/model_world_size_3_rank_2.ptWeights4.1 GB be43951ea3ac
checkpoints/math/qwen1p7b-30b-math-fire-opd-4gpu-b255/global_step_55/actor/optim_world_size_3_rank_0.ptWeights6.9 GB bced6ef09c28
checkpoints/math/qwen1p7b-30b-math-fire-opd-4gpu-b255/global_step_55/actor/optim_world_size_3_rank_1.ptWeights6.9 GB 5f7c597751ca
checkpoints/math/qwen1p7b-30b-math-fire-opd-4gpu-b255/global_step_55/actor/optim_world_size_3_rank_2.ptWeights6.9 GB a76d66657c7a
checkpoints/math/qwen1p7b-30b-math-fire-opd-4gpu-b255/global_step_55/data.ptWeights7.6 KB 50d547d16738
checkpoints/math/qwen1p7b-30b-math-fire-opd-4gpu-b255/global_step_60/actor/extra_state_world_size_3_rank_0.ptWeights15.1 KB 4a8aeb072fba
checkpoints/math/qwen1p7b-30b-math-fire-opd-4gpu-b255/global_step_60/actor/extra_state_world_size_3_rank_1.ptWeights15.1 KB a5ce1b1074ec
checkpoints/math/qwen1p7b-30b-math-fire-opd-4gpu-b255/global_step_60/actor/extra_state_world_size_3_rank_2.ptWeights15.1 KB a9a893e0bfa0
checkpoints/math/qwen1p7b-30b-math-fire-opd-4gpu-b255/global_step_60/actor/huggingface/model.safetensorsWeights4.1 GB c31711fc0c12
checkpoints/math/qwen1p7b-30b-math-fire-opd-4gpu-b255/global_step_60/actor/model_world_size_3_rank_0.ptWeights4.1 GB 2b17815552fd
checkpoints/math/qwen1p7b-30b-math-fire-opd-4gpu-b255/global_step_60/actor/model_world_size_3_rank_1.ptWeights4.1 GB f603b91e6e3d
checkpoints/math/qwen1p7b-30b-math-fire-opd-4gpu-b255/global_step_60/actor/model_world_size_3_rank_2.ptWeights4.1 GB 9e72c1560a4a
checkpoints/math/qwen1p7b-30b-math-fire-opd-4gpu-b255/global_step_60/actor/optim_world_size_3_rank_0.ptWeights6.9 GB 871f2709b22a
checkpoints/math/qwen1p7b-30b-math-fire-opd-4gpu-b255/global_step_60/actor/optim_world_size_3_rank_1.ptWeights6.9 GB a0e23c05ea8e
checkpoints/math/qwen1p7b-30b-math-fire-opd-4gpu-b255/global_step_60/actor/optim_world_size_3_rank_2.ptWeights6.9 GB e64ac3d2c284
checkpoints/math/qwen1p7b-30b-math-fire-opd-4gpu-b255/global_step_60/data.ptWeights7.6 KB ff1c56179aac
checkpoints/math/qwen1p7b-30b-math-fire-opd-4gpu-b255/global_step_65/actor/extra_state_world_size_3_rank_0.ptWeights15.2 KB dd50eff42cad
checkpoints/math/qwen1p7b-30b-math-fire-opd-4gpu-b255/global_step_65/actor/extra_state_world_size_3_rank_1.ptWeights15.2 KB 5919afd00760
checkpoints/math/qwen1p7b-30b-math-fire-opd-4gpu-b255/global_step_65/actor/extra_state_world_size_3_rank_2.ptWeights15.2 KB ddfa02c39de8
checkpoints/math/qwen1p7b-30b-math-fire-opd-4gpu-b255/global_step_65/actor/huggingface/model.safetensorsWeights4.1 GB 65f0c120520e
checkpoints/math/qwen1p7b-30b-math-fire-opd-4gpu-b255/global_step_65/actor/model_world_size_3_rank_0.ptWeights4.1 GB 8bf02c8775c9
checkpoints/math/qwen1p7b-30b-math-fire-opd-4gpu-b255/global_step_65/actor/model_world_size_3_rank_1.ptWeights4.1 GB 9bfb742c290c
checkpoints/math/qwen1p7b-30b-math-fire-opd-4gpu-b255/global_step_65/actor/model_world_size_3_rank_2.ptWeights4.1 GB 6d84eb49e834
checkpoints/math/qwen1p7b-30b-math-fire-opd-4gpu-b255/global_step_65/actor/optim_world_size_3_rank_0.ptWeights6.9 GB cd2e522bf98e
checkpoints/math/qwen1p7b-30b-math-fire-opd-4gpu-b255/global_step_65/actor/optim_world_size_3_rank_1.ptWeights6.9 GB 7e6c3e142fca
checkpoints/math/qwen1p7b-30b-math-fire-opd-4gpu-b255/global_step_65/actor/optim_world_size_3_rank_2.ptWeights6.9 GB 675f83120c87
checkpoints/math/qwen1p7b-30b-math-fire-opd-4gpu-b255/global_step_65/data.ptWeights7.6 KB a57fc5ae1c76
checkpoints/math/qwen1p7b-30b-math-fire-opd-4gpu-b255/global_step_70/actor/extra_state_world_size_3_rank_0.ptWeights15.1 KB 6beaf7367b83
checkpoints/math/qwen1p7b-30b-math-fire-opd-4gpu-b255/global_step_70/actor/extra_state_world_size_3_rank_1.ptWeights15.1 KB 8bca7e6b4e4f
checkpoints/math/qwen1p7b-30b-math-fire-opd-4gpu-b255/global_step_70/actor/extra_state_world_size_3_rank_2.ptWeights15.1 KB 2fb185709d7f
checkpoints/math/qwen1p7b-30b-math-fire-opd-4gpu-b255/global_step_70/actor/huggingface/model.safetensorsWeights4.1 GB 0f933e3961e6
checkpoints/math/qwen1p7b-30b-math-fire-opd-4gpu-b255/global_step_70/actor/model_world_size_3_rank_0.ptWeights4.1 GB 62160eec954e
checkpoints/math/qwen1p7b-30b-math-fire-opd-4gpu-b255/global_step_70/actor/model_world_size_3_rank_1.ptWeights4.1 GB 68c06b5e345b
checkpoints/math/qwen1p7b-30b-math-fire-opd-4gpu-b255/global_step_70/actor/model_world_size_3_rank_2.ptWeights4.1 GB a3622581d957
checkpoints/math/qwen1p7b-30b-math-fire-opd-4gpu-b255/global_step_70/actor/optim_world_size_3_rank_0.ptWeights6.9 GB 915cac912c72
checkpoints/math/qwen1p7b-30b-math-fire-opd-4gpu-b255/global_step_70/actor/optim_world_size_3_rank_1.ptWeights6.9 GB 1144552bfd47
checkpoints/math/qwen1p7b-30b-math-fire-opd-4gpu-b255/global_step_70/actor/optim_world_size_3_rank_2.ptWeights6.9 GB 444a0152c191
checkpoints/math/qwen1p7b-30b-math-fire-opd-4gpu-b255/global_step_70/data.ptWeights7.6 KB a84267c6716f
checkpoints/math/qwen1p7b-30b-math-opd-4gpu-b255/global_step_50/actor/extra_state_world_size_3_rank_0.ptWeights15.2 KB a9b42a16859c
checkpoints/math/qwen1p7b-30b-math-opd-4gpu-b255/global_step_50/actor/extra_state_world_size_3_rank_1.ptWeights15.2 KB 9c1522589354
checkpoints/math/qwen1p7b-30b-math-opd-4gpu-b255/global_step_50/actor/extra_state_world_size_3_rank_2.ptWeights15.2 KB db021d9800c7
checkpoints/math/qwen1p7b-30b-math-opd-4gpu-b255/global_step_50/actor/model_world_size_3_rank_0.ptWeights4.1 GB 7322fd47a5ec
checkpoints/math/qwen1p7b-30b-math-opd-4gpu-b255/global_step_50/actor/model_world_size_3_rank_1.ptWeights4.1 GB 894a4dd5a4ca
checkpoints/math/qwen1p7b-30b-math-opd-4gpu-b255/global_step_50/actor/model_world_size_3_rank_2.ptWeights4.1 GB 9380b05dd9fe
checkpoints/math/qwen1p7b-30b-math-opd-4gpu-b255/global_step_50/actor/optim_world_size_3_rank_0.ptWeights6.9 GB a8317c7edeed
checkpoints/math/qwen1p7b-30b-math-opd-4gpu-b255/global_step_50/actor/optim_world_size_3_rank_1.ptWeights6.9 GB ac436b481f6d
checkpoints/math/qwen1p7b-30b-math-opd-4gpu-b255/global_step_50/actor/optim_world_size_3_rank_2.ptWeights6.9 GB 779c736aa043
checkpoints/math/qwen1p7b-30b-math-opd-4gpu-b255/global_step_50/data.ptWeights7.6 KB 839c288c5967
checkpoints/math/qwen1p7b-30b-math-opd-4gpu-b255/global_step_55/actor/extra_state_world_size_3_rank_0.ptWeights15.2 KB b7ac173c0898
checkpoints/math/qwen1p7b-30b-math-opd-4gpu-b255/global_step_55/actor/extra_state_world_size_3_rank_1.ptWeights15.2 KB 6fe2338e3326
checkpoints/math/qwen1p7b-30b-math-opd-4gpu-b255/global_step_55/actor/extra_state_world_size_3_rank_2.ptWeights15.2 KB 78a95ea90b3c
checkpoints/math/qwen1p7b-30b-math-opd-4gpu-b255/global_step_55/actor/model_world_size_3_rank_0.ptWeights4.1 GB 7cf1a312510a
checkpoints/math/qwen1p7b-30b-math-opd-4gpu-b255/global_step_55/actor/model_world_size_3_rank_1.ptWeights4.1 GB 1e9844a4b9e7
checkpoints/math/qwen1p7b-30b-math-opd-4gpu-b255/global_step_55/actor/model_world_size_3_rank_2.ptWeights4.1 GB 70f9c6643813
checkpoints/math/qwen1p7b-30b-math-opd-4gpu-b255/global_step_55/actor/optim_world_size_3_rank_0.ptWeights6.9 GB 65da7a575b82
checkpoints/math/qwen1p7b-30b-math-opd-4gpu-b255/global_step_55/actor/optim_world_size_3_rank_1.ptWeights6.9 GB 4ef40aa681e4
checkpoints/math/qwen1p7b-30b-math-opd-4gpu-b255/global_step_55/actor/optim_world_size_3_rank_2.ptWeights6.9 GB a6df0ee71c2a
checkpoints/math/qwen1p7b-30b-math-opd-4gpu-b255/global_step_55/data.ptWeights7.6 KB 50d547d16738
checkpoints/math/qwen1p7b-30b-math-tip-topk32-rho50-4gpu-b255/global_step_55/actor/extra_state_world_size_3_rank_0.ptWeights15.2 KB b7ac173c0898
checkpoints/math/qwen1p7b-30b-math-tip-topk32-rho50-4gpu-b255/global_step_55/actor/extra_state_world_size_3_rank_1.ptWeights15.2 KB 6fe2338e3326
checkpoints/math/qwen1p7b-30b-math-tip-topk32-rho50-4gpu-b255/global_step_55/actor/extra_state_world_size_3_rank_2.ptWeights15.2 KB 78a95ea90b3c
checkpoints/math/qwen1p7b-30b-math-tip-topk32-rho50-4gpu-b255/global_step_55/actor/huggingface/model.safetensorsWeights4.1 GB b4d53e8559c0
checkpoints/math/qwen1p7b-30b-math-tip-topk32-rho50-4gpu-b255/global_step_55/actor/model_world_size_3_rank_0.ptWeights4.1 GB 9b0b252fd0e8
checkpoints/math/qwen1p7b-30b-math-tip-topk32-rho50-4gpu-b255/global_step_55/actor/model_world_size_3_rank_1.ptWeights4.1 GB b00844b86dc7
checkpoints/math/qwen1p7b-30b-math-tip-topk32-rho50-4gpu-b255/global_step_55/actor/model_world_size_3_rank_2.ptWeights4.1 GB 35c5e8d2f48c
checkpoints/math/qwen1p7b-30b-math-tip-topk32-rho50-4gpu-b255/global_step_55/actor/optim_world_size_3_rank_0.ptWeights6.9 GB 370995924840
checkpoints/math/qwen1p7b-30b-math-tip-topk32-rho50-4gpu-b255/global_step_55/actor/optim_world_size_3_rank_1.ptWeights6.9 GB 2811e945752d
checkpoints/math/qwen1p7b-30b-math-tip-topk32-rho50-4gpu-b255/global_step_55/actor/optim_world_size_3_rank_2.ptWeights6.9 GB c13b1993a4b2
checkpoints/math/qwen1p7b-30b-math-tip-topk32-rho50-4gpu-b255/global_step_55/data.ptWeights7.6 KB 50d547d16738
checkpoints/math/qwen1p7b-30b-math-tip-topk32-rho50-4gpu-b255/global_step_60/actor/extra_state_world_size_3_rank_0.ptWeights15.1 KB 4a8aeb072fba
checkpoints/math/qwen1p7b-30b-math-tip-topk32-rho50-4gpu-b255/global_step_60/actor/extra_state_world_size_3_rank_1.ptWeights15.1 KB a5ce1b1074ec
checkpoints/math/qwen1p7b-30b-math-tip-topk32-rho50-4gpu-b255/global_step_60/actor/extra_state_world_size_3_rank_2.ptWeights15.1 KB a9a893e0bfa0
checkpoints/math/qwen1p7b-30b-math-tip-topk32-rho50-4gpu-b255/global_step_60/actor/huggingface/model.safetensorsWeights4.1 GB a51b97216773
checkpoints/math/qwen1p7b-30b-math-tip-topk32-rho50-4gpu-b255/global_step_60/actor/model_world_size_3_rank_0.ptWeights4.1 GB 448aedac71a2
checkpoints/math/qwen1p7b-30b-math-tip-topk32-rho50-4gpu-b255/global_step_60/actor/model_world_size_3_rank_1.ptWeights4.1 GB 4e94c1fa9ecb
checkpoints/math/qwen1p7b-30b-math-tip-topk32-rho50-4gpu-b255/global_step_60/actor/model_world_size_3_rank_2.ptWeights4.1 GB 230812c6531f
checkpoints/math/qwen1p7b-30b-math-tip-topk32-rho50-4gpu-b255/global_step_60/actor/optim_world_size_3_rank_0.ptWeights6.9 GB 89434d56da69
checkpoints/math/qwen1p7b-30b-math-tip-topk32-rho50-4gpu-b255/global_step_60/actor/optim_world_size_3_rank_1.ptWeights6.9 GB f942c300ebdc
checkpoints/math/qwen1p7b-30b-math-tip-topk32-rho50-4gpu-b255/global_step_60/actor/optim_world_size_3_rank_2.ptWeights6.9 GB 66df3af2a321
checkpoints/math/qwen1p7b-30b-math-tip-topk32-rho50-4gpu-b255/global_step_60/data.ptWeights7.6 KB ff1c56179aac
checkpoints/math/qwen1p7b-30b-math-tip-topk32-rho50-4gpu-b255/global_step_65/actor/extra_state_world_size_3_rank_0.ptWeights15.2 KB dd50eff42cad
checkpoints/math/qwen1p7b-30b-math-tip-topk32-rho50-4gpu-b255/global_step_65/actor/extra_state_world_size_3_rank_1.ptWeights15.2 KB 5919afd00760
checkpoints/math/qwen1p7b-30b-math-tip-topk32-rho50-4gpu-b255/global_step_65/actor/extra_state_world_size_3_rank_2.ptWeights15.2 KB ddfa02c39de8
checkpoints/math/qwen1p7b-30b-math-tip-topk32-rho50-4gpu-b255/global_step_65/actor/huggingface/model.safetensorsWeights4.1 GB 308974bfdb80
checkpoints/math/qwen1p7b-30b-math-tip-topk32-rho50-4gpu-b255/global_step_65/actor/model_world_size_3_rank_0.ptWeights4.1 GB 55efbabbce81
checkpoints/math/qwen1p7b-30b-math-tip-topk32-rho50-4gpu-b255/global_step_65/actor/model_world_size_3_rank_1.ptWeights4.1 GB 86f1e2e18b65
checkpoints/math/qwen1p7b-30b-math-tip-topk32-rho50-4gpu-b255/global_step_65/actor/model_world_size_3_rank_2.ptWeights4.1 GB 4f8b49a9b3d3
checkpoints/math/qwen1p7b-30b-math-tip-topk32-rho50-4gpu-b255/global_step_65/actor/optim_world_size_3_rank_0.ptWeights6.9 GB 1f7a8b2e954c
checkpoints/math/qwen1p7b-30b-math-tip-topk32-rho50-4gpu-b255/global_step_65/actor/optim_world_size_3_rank_1.ptWeights6.9 GB 17c6eee67150
checkpoints/math/qwen1p7b-30b-math-tip-topk32-rho50-4gpu-b255/global_step_65/actor/optim_world_size_3_rank_2.ptWeights6.9 GB f69d38f851b2
checkpoints/math/qwen1p7b-30b-math-tip-topk32-rho50-4gpu-b255/global_step_65/data.ptWeights7.6 KB a57fc5ae1c76
checkpoints/math/qwen1p7b-30b-math-tip-topk32-rho50-4gpu-b255/global_step_70/actor/extra_state_world_size_3_rank_0.ptWeights15.1 KB 6beaf7367b83
checkpoints/math/qwen1p7b-30b-math-tip-topk32-rho50-4gpu-b255/global_step_70/actor/extra_state_world_size_3_rank_1.ptWeights15.1 KB 8bca7e6b4e4f
checkpoints/math/qwen1p7b-30b-math-tip-topk32-rho50-4gpu-b255/global_step_70/actor/extra_state_world_size_3_rank_2.ptWeights15.1 KB 2fb185709d7f
checkpoints/math/qwen1p7b-30b-math-tip-topk32-rho50-4gpu-b255/global_step_70/actor/huggingface/model.safetensorsWeights4.1 GB c42541ac0a38
checkpoints/math/qwen1p7b-30b-math-tip-topk32-rho50-4gpu-b255/global_step_70/actor/model_world_size_3_rank_0.ptWeights4.1 GB aace2cc503dc
checkpoints/math/qwen1p7b-30b-math-tip-topk32-rho50-4gpu-b255/global_step_70/actor/model_world_size_3_rank_1.ptWeights4.1 GB 8a35a298b4be
checkpoints/math/qwen1p7b-30b-math-tip-topk32-rho50-4gpu-b255/global_step_70/actor/model_world_size_3_rank_2.ptWeights4.1 GB b505358969de
checkpoints/math/qwen1p7b-30b-math-tip-topk32-rho50-4gpu-b255/global_step_70/actor/optim_world_size_3_rank_0.ptWeights6.9 GB c6b1b87d5e88
checkpoints/math/qwen1p7b-30b-math-tip-topk32-rho50-4gpu-b255/global_step_70/actor/optim_world_size_3_rank_1.ptWeights6.9 GB b759efa2af4c
checkpoints/math/qwen1p7b-30b-math-tip-topk32-rho50-4gpu-b255/global_step_70/actor/optim_world_size_3_rank_2.ptWeights6.9 GB f53b31cdacfd
checkpoints/math/qwen1p7b-30b-math-tip-topk32-rho50-4gpu-b255/global_step_70/data.ptWeights7.6 KB a84267c6716f
checkpoints/mopd/q1p7b-4g-mcs-m05c01s01-stconf-cfkl-srkl-f4-b528-coloc-s60/global_step_60/model.safetensorsWeights4.1 GB 97123e44ef39
checkpoints/mopd/q1p7b-4g-mcs-mtl05-ctl01-sltc01-f4-b528-coloc-s60/global_step_60/model.safetensorsWeights4.1 GB 09dd1c67952e
checkpoints/mopd/q1p7b-4g-mcs-mtl05-ctl01cs-stl01-f4-b528-coloc-s60/global_step_60/model.safetensorsWeights4.1 GB 35165e418c00
checkpoints/mopd/q1p7b-8g-mcs-m05c01s01-stloss-cfkl-srkl-f4-b528-s60/global_step_60/model.safetensorsWeights4.1 GB bf6fc0fa2be1
checkpoints/mopd/q1p7b-8g-mcs-mtl05-ctl01cs-sltc01-f4-b528-s60/global_step_60/model.safetensorsWeights4.1 GB 6bfaf2e2a71d
checkpoints/mopd/q1p7b-8g-mcs-mtl05-ctl02-sltc02-f4-b528-s60/global_step_60/model.safetensorsWeights4.1 GB be2ff3713a05
checkpoints/mopd/q1p7b-8g-mcs-p05-toploss-cfkl-srkl-f4-b528-s60/global_step_60/model.safetensorsWeights4.1 GB 1885f9d8898b
checkpoints/mopd/q1p7b-8g-mcs-taxonomy-toploss-topp05-fixed4-b528-s60/global_step_60/model.safetensorsWeights4.1 GB ae0b85b7fecd
checkpoints/mopd/q1p7b3s1t-mc-tl-m05c01-cstruct-disc33-f4-b528-s60/global_step_60/model.safetensorsWeights4.1 GB 32754ca8f4bf
checkpoints/mopd/q1p7b3s1t-mc-v6-cs-current-m05c01-f4-b528-s60/global_step_60/model.safetensorsWeights4.1 GB 3d9aa1cbc453
checkpoints/mopd/q1p7b4g-mc-tl-m05c01-cstruct-8g6s2t-b528-s60/global_step_60/model.safetensorsWeights4.1 GB 9b19d2346fe2
checkpoints/mopd/q1p7b4g-mc-tl-m05c01-f4-b528-s60/global_step_60/model.safetensorsWeights4.1 GB 76baf79b1b1e
checkpoints/mopd/q1p7b4g-mc-tl-m05c02-cstruct-8g6s2t-b528-s60/global_step_60/model.safetensorsWeights4.1 GB cae7b0c32419
checkpoints/mopd/q1p7b4g-mc-tl-m05c02-cstruct-f4-b528-s60/global_step_60/model.safetensorsWeights4.1 GB de4aaba33f86
checkpoints/mopd/q1p7b4g-mc-tl-m05c05-8g6s2t-b528-s60/global_step_60/model.safetensorsWeights4.1 GB 26f041ba83cd
checkpoints/mopd/q1p7b4g-mc-tl-m05c05-cstruct-8g6s2t-b528-s60/global_step_60/model.safetensorsWeights4.1 GB d619f365d535
checkpoints/mopd/q1p7b4g-mc-v4-r3-cs-next-m05c01-f4-b528-s60/global_step_60/model.safetensorsWeights4.1 GB e40b837ae459
checkpoints/mopd/q1p7b8g-mc-legacy-cstruct-current-m05c01-f4-b528-s60-retry1/global_step_60/model.safetensorsWeights4.1 GB 52c3b56e7034
checkpoints/mopd/q1p7b8g-mc-v5-r3-cs-next-m05c01-f4-b528-s60/global_step_60/model.safetensorsWeights4.1 GB 9badfc10cc46
checkpoints/mopd/q1p7b8g-mc-v7-cs-current-m05c01-f4-6s2t-b528-s60/global_step_60/model.safetensorsWeights4.1 GB 9c221788da33
checkpoints/mopd/q1p7b8g-mc-v8-cs-current-m05c01-f4-6s2t-b528-s60/global_step_60/model.safetensorsWeights4.1 GB 3b1df3f28882
checkpoints/mopd/qwen1p7b-30b-eopd-native-8gpu-b528-teacher50-final/global_step_60/model.safetensorsWeights4.1 GB 7b49aa21abb2
audits/mopd/q1p7b-8g-mcs-taxonomy-toploss-topp05-fixed4-b528-s60/manifest.jsonConfiguration351.3 KB —
audits/mopd/q1p7b4g-mc-tl-m05c01-cstruct-8g6s2t-b528-s60/selection-step1-60/resolved_config.yamlConfiguration58.8 KB —
checkpoints/baselines/math_code/tip_topk32_rho50_8gpu_6s2t_b516/global_step_60/added_tokens.jsonConfiguration707 B —
checkpoints/baselines/math_code/tip_topk32_rho50_8gpu_6s2t_b516/global_step_60/config.jsonConfiguration773 B —
checkpoints/baselines/math_code/tip_topk32_rho50_8gpu_6s2t_b516/global_step_60/generation_config.jsonConfiguration214 B —
checkpoints/baselines/math_code/tip_topk32_rho50_8gpu_6s2t_b516/global_step_60/special_tokens_map.jsonConfiguration613 B —
checkpoints/baselines/math_code/topk32_uniform_8gpu_6s2t_b516/global_step_60/added_tokens.jsonConfiguration707 B —
checkpoints/baselines/math_code/topk32_uniform_8gpu_6s2t_b516/global_step_60/config.jsonConfiguration773 B —
checkpoints/baselines/math_code/topk32_uniform_8gpu_6s2t_b516/global_step_60/generation_config.jsonConfiguration214 B —
checkpoints/baselines/math_code/topk32_uniform_8gpu_6s2t_b516/global_step_60/special_tokens_map.jsonConfiguration613 B —
checkpoints/global_step_60/added_tokens.jsonConfiguration707 B —
checkpoints/global_step_60/config.jsonConfiguration1.4 KB —
checkpoints/global_step_60/generation_config.jsonConfiguration214 B —
checkpoints/global_step_60/special_tokens_map.jsonConfiguration613 B —
checkpoints/math/q1p7b-4g-math-fullvocab-toploss-topp05-fixed4-b256-colocated-s60/global_step_60/added_tokens.jsonConfiguration707 B —
checkpoints/math/q1p7b-4g-math-fullvocab-toploss-topp05-fixed4-b256-colocated-s60/global_step_60/config.jsonConfiguration1.4 KB —
checkpoints/math/q1p7b-4g-math-fullvocab-toploss-topp05-fixed4-b256-colocated-s60/global_step_60/generation_config.jsonConfiguration214 B —
checkpoints/math/q1p7b-4g-math-fullvocab-toploss-topp05-fixed4-b256-colocated-s60/global_step_60/special_tokens_map.jsonConfiguration613 B —
checkpoints/math/q1p7b-math-a-ns-expanded-v2-i1w1k29-5gpu-b256/global_step_55/added_tokens.jsonConfiguration707 B —
checkpoints/math/q1p7b-math-a-ns-expanded-v2-i1w1k29-5gpu-b256/global_step_55/config.jsonConfiguration1.4 KB —
checkpoints/math/q1p7b-math-a-ns-expanded-v2-i1w1k29-5gpu-b256/global_step_55/generation_config.jsonConfiguration214 B —
checkpoints/math/q1p7b-math-a-ns-expanded-v2-i1w1k29-5gpu-b256/global_step_55/special_tokens_map.jsonConfiguration613 B —
checkpoints/math/q1p7b-math-a-ns-expanded-v2-i1w1k29-5gpu-b256/global_step_60/added_tokens.jsonConfiguration707 B —
checkpoints/math/q1p7b-math-a-ns-expanded-v2-i1w1k29-5gpu-b256/global_step_60/config.jsonConfiguration1.4 KB —
checkpoints/math/q1p7b-math-a-ns-expanded-v2-i1w1k29-5gpu-b256/global_step_60/generation_config.jsonConfiguration214 B —
checkpoints/math/q1p7b-math-a-ns-expanded-v2-i1w1k29-5gpu-b256/global_step_60/special_tokens_map.jsonConfiguration613 B —
checkpoints/math/q1p7b-math-a-ns-v3-u-i1w1k25-8gpu_6a2t_b258/global_step_60/added_tokens.jsonConfiguration707 B —
checkpoints/math/q1p7b-math-a-ns-v3-u-i1w1k25-8gpu_6a2t_b258/global_step_60/config.jsonConfiguration773 B —
checkpoints/math/q1p7b-math-a-ns-v3-u-i1w1k25-8gpu_6a2t_b258/global_step_60/generation_config.jsonConfiguration214 B —
checkpoints/math/q1p7b-math-a-ns-v3-u-i1w1k25-8gpu_6a2t_b258/global_step_60/special_tokens_map.jsonConfiguration613 B —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-split-i1w1k21pt-b255/global_step_55/added_tokens.jsonConfiguration707 B —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-split-i1w1k21pt-b255/global_step_55/config.jsonConfiguration1.4 KB —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-split-i1w1k21pt-b255/global_step_55/generation_config.jsonConfiguration214 B —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-split-i1w1k21pt-b255/global_step_55/special_tokens_map.jsonConfiguration613 B —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-split-i1w1k21pt-b255/global_step_60/added_tokens.jsonConfiguration707 B —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-split-i1w1k21pt-b255/global_step_60/config.jsonConfiguration1.4 KB —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-split-i1w1k21pt-b255/global_step_60/generation_config.jsonConfiguration214 B —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-split-i1w1k21pt-b255/global_step_60/special_tokens_map.jsonConfiguration613 B —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-split-i1w1k21pt-b255/global_step_65/added_tokens.jsonConfiguration707 B —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-split-i1w1k21pt-b255/global_step_65/config.jsonConfiguration1.4 KB —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-split-i1w1k21pt-b255/global_step_65/generation_config.jsonConfiguration214 B —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-split-i1w1k21pt-b255/global_step_65/special_tokens_map.jsonConfiguration613 B —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-split-i1w1k21pt-b255/global_step_70/added_tokens.jsonConfiguration707 B —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-split-i1w1k21pt-b255/global_step_70/config.jsonConfiguration1.4 KB —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-split-i1w1k21pt-b255/global_step_70/generation_config.jsonConfiguration214 B —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-split-i1w1k21pt-b255/global_step_70/special_tokens_map.jsonConfiguration613 B —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-split-topp0p05-i1w1-4gpu-3a1t-b255-r20260911/global_step_55/added_tokens.jsonConfiguration707 B —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-split-topp0p05-i1w1-4gpu-3a1t-b255-r20260911/global_step_55/config.jsonConfiguration1.4 KB —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-split-topp0p05-i1w1-4gpu-3a1t-b255-r20260911/global_step_55/generation_config.jsonConfiguration214 B —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-split-topp0p05-i1w1-4gpu-3a1t-b255-r20260911/global_step_55/special_tokens_map.jsonConfiguration613 B —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-split-topp0p05-i1w1-4gpu-3a1t-b255-r20260911/global_step_60/added_tokens.jsonConfiguration707 B —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-split-topp0p05-i1w1-4gpu-3a1t-b255-r20260911/global_step_60/config.jsonConfiguration1.4 KB —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-split-topp0p05-i1w1-4gpu-3a1t-b255-r20260911/global_step_60/generation_config.jsonConfiguration214 B —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-split-topp0p05-i1w1-4gpu-3a1t-b255-r20260911/global_step_60/special_tokens_map.jsonConfiguration613 B —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-split-topp0p05-i1w1-4gpu-3a1t-b255-r20260911/global_step_65/added_tokens.jsonConfiguration707 B —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-split-topp0p05-i1w1-4gpu-3a1t-b255-r20260911/global_step_65/config.jsonConfiguration1.4 KB —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-split-topp0p05-i1w1-4gpu-3a1t-b255-r20260911/global_step_65/generation_config.jsonConfiguration214 B —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-split-topp0p05-i1w1-4gpu-3a1t-b255-r20260911/global_step_65/special_tokens_map.jsonConfiguration613 B —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p01-i1w1-5gpu-3a2t-b258-resume15/global_step_55/added_tokens.jsonConfiguration707 B —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p01-i1w1-5gpu-3a2t-b258-resume15/global_step_55/config.jsonConfiguration1.4 KB —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p01-i1w1-5gpu-3a2t-b258-resume15/global_step_55/generation_config.jsonConfiguration214 B —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p01-i1w1-5gpu-3a2t-b258-resume15/global_step_55/special_tokens_map.jsonConfiguration613 B —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p01-i1w1-5gpu-3a2t-b258-resume15/global_step_60/added_tokens.jsonConfiguration707 B —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p01-i1w1-5gpu-3a2t-b258-resume15/global_step_60/config.jsonConfiguration1.4 KB —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p01-i1w1-5gpu-3a2t-b258-resume15/global_step_60/generation_config.jsonConfiguration214 B —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p01-i1w1-5gpu-3a2t-b258-resume15/global_step_60/special_tokens_map.jsonConfiguration613 B —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p01-i1w1-5gpu-3a2t-b258-resume15/global_step_65/added_tokens.jsonConfiguration707 B —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p01-i1w1-5gpu-3a2t-b258-resume15/global_step_65/config.jsonConfiguration1.4 KB —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p01-i1w1-5gpu-3a2t-b258-resume15/global_step_65/generation_config.jsonConfiguration214 B —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p01-i1w1-5gpu-3a2t-b258-resume15/global_step_65/special_tokens_map.jsonConfiguration613 B —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p01-i1w1-5gpu-3a2t-b258-resume15/global_step_70/added_tokens.jsonConfiguration707 B —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p01-i1w1-5gpu-3a2t-b258-resume15/global_step_70/config.jsonConfiguration1.4 KB —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p01-i1w1-5gpu-3a2t-b258-resume15/global_step_70/generation_config.jsonConfiguration214 B —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p01-i1w1-5gpu-3a2t-b258-resume15/global_step_70/special_tokens_map.jsonConfiguration613 B —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p02-i1w1-8gpu-6a2t-b258/global_step_60/added_tokens.jsonConfiguration707 B —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p02-i1w1-8gpu-6a2t-b258/global_step_60/config.jsonConfiguration773 B —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p02-i1w1-8gpu-6a2t-b258/global_step_60/generation_config.jsonConfiguration214 B —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p02-i1w1-8gpu-6a2t-b258/global_step_60/special_tokens_map.jsonConfiguration613 B —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p05-i1w1-5gpu-b256/global_step_55/added_tokens.jsonConfiguration707 B —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p05-i1w1-5gpu-b256/global_step_55/config.jsonConfiguration1.4 KB —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p05-i1w1-5gpu-b256/global_step_55/generation_config.jsonConfiguration214 B —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p05-i1w1-5gpu-b256/global_step_55/special_tokens_map.jsonConfiguration613 B —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p05-i1w1-5gpu-b256/global_step_60/added_tokens.jsonConfiguration707 B —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p05-i1w1-5gpu-b256/global_step_60/config.jsonConfiguration1.4 KB —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p05-i1w1-5gpu-b256/global_step_60/generation_config.jsonConfiguration214 B —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p05-i1w1-5gpu-b256/global_step_60/special_tokens_map.jsonConfiguration613 B —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p05-i1w1-5gpu-b256/global_step_65/added_tokens.jsonConfiguration707 B —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p05-i1w1-5gpu-b256/global_step_65/config.jsonConfiguration1.4 KB —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p05-i1w1-5gpu-b256/global_step_65/generation_config.jsonConfiguration214 B —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p05-i1w1-5gpu-b256/global_step_65/special_tokens_map.jsonConfiguration613 B —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p075-i1w1-5gpu-4a1t-b256/global_step_55/added_tokens.jsonConfiguration707 B —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p075-i1w1-5gpu-4a1t-b256/global_step_55/config.jsonConfiguration1.4 KB —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p075-i1w1-5gpu-4a1t-b256/global_step_55/generation_config.jsonConfiguration214 B —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p075-i1w1-5gpu-4a1t-b256/global_step_55/special_tokens_map.jsonConfiguration613 B —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p075-i1w1-5gpu-4a1t-b256/global_step_60/added_tokens.jsonConfiguration707 B —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p075-i1w1-5gpu-4a1t-b256/global_step_60/config.jsonConfiguration1.4 KB —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p075-i1w1-5gpu-4a1t-b256/global_step_60/generation_config.jsonConfiguration214 B —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p075-i1w1-5gpu-4a1t-b256/global_step_60/special_tokens_map.jsonConfiguration613 B —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p1-i1w1-5gpu-3a2t-b258/global_step_55/added_tokens.jsonConfiguration707 B —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p1-i1w1-5gpu-3a2t-b258/global_step_55/config.jsonConfiguration1.4 KB —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p1-i1w1-5gpu-3a2t-b258/global_step_55/generation_config.jsonConfiguration214 B —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p1-i1w1-5gpu-3a2t-b258/global_step_55/special_tokens_map.jsonConfiguration613 B —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p1-i1w1-5gpu-3a2t-b258/global_step_60/added_tokens.jsonConfiguration707 B —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p1-i1w1-5gpu-3a2t-b258/global_step_60/config.jsonConfiguration1.4 KB —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p1-i1w1-5gpu-3a2t-b258/global_step_60/generation_config.jsonConfiguration214 B —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p1-i1w1-5gpu-3a2t-b258/global_step_60/special_tokens_map.jsonConfiguration613 B —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p1-i1w1-5gpu-3a2t-b258/global_step_65/added_tokens.jsonConfiguration707 B —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p1-i1w1-5gpu-3a2t-b258/global_step_65/config.jsonConfiguration1.4 KB —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p1-i1w1-5gpu-3a2t-b258/global_step_65/generation_config.jsonConfiguration214 B —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p1-i1w1-5gpu-3a2t-b258/global_step_65/special_tokens_map.jsonConfiguration613 B —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p1-i1w1-5gpu-3a2t-b258/global_step_70/added_tokens.jsonConfiguration707 B —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p1-i1w1-5gpu-3a2t-b258/global_step_70/config.jsonConfiguration1.4 KB —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p1-i1w1-5gpu-3a2t-b258/global_step_70/generation_config.jsonConfiguration214 B —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p1-i1w1-5gpu-3a2t-b258/global_step_70/special_tokens_map.jsonConfiguration613 B —
checkpoints/math/q1p7b-math-top32kl-taxonomy-topp05-qsel-w4-5g4a1t-b256/global_step_55/added_tokens.jsonConfiguration707 B —
checkpoints/math/q1p7b-math-top32kl-taxonomy-topp05-qsel-w4-5g4a1t-b256/global_step_55/config.jsonConfiguration1.4 KB —
checkpoints/math/q1p7b-math-top32kl-taxonomy-topp05-qsel-w4-5g4a1t-b256/global_step_55/generation_config.jsonConfiguration214 B —
checkpoints/math/q1p7b-math-top32kl-taxonomy-topp05-qsel-w4-5g4a1t-b256/global_step_55/special_tokens_map.jsonConfiguration613 B —
checkpoints/math/q1p7b-math-top32kl-taxonomy-topp05-qsel-w4-5g4a1t-b256/global_step_60/added_tokens.jsonConfiguration707 B —
checkpoints/math/q1p7b-math-top32kl-taxonomy-topp05-qsel-w4-5g4a1t-b256/global_step_60/config.jsonConfiguration1.4 KB —
checkpoints/math/q1p7b-math-top32kl-taxonomy-topp05-qsel-w4-5g4a1t-b256/global_step_60/generation_config.jsonConfiguration214 B —
checkpoints/math/q1p7b-math-top32kl-taxonomy-topp05-qsel-w4-5g4a1t-b256/global_step_60/special_tokens_map.jsonConfiguration613 B —
checkpoints/math/q1p7b-math-top32kl-taxonomy-topp05-qsel-w4-5g4a1t-b256/global_step_65/added_tokens.jsonConfiguration707 B —
checkpoints/math/q1p7b-math-top32kl-taxonomy-topp05-qsel-w4-5g4a1t-b256/global_step_65/config.jsonConfiguration1.4 KB —
checkpoints/math/q1p7b-math-top32kl-taxonomy-topp05-qsel-w4-5g4a1t-b256/global_step_65/generation_config.jsonConfiguration214 B —
checkpoints/math/q1p7b-math-top32kl-taxonomy-topp05-qsel-w4-5g4a1t-b256/global_step_65/special_tokens_map.jsonConfiguration613 B —
checkpoints/math/q1p7b-math-top32kl-taxonomy-topp05-qsel-w4-5g4a1t-b256/global_step_70/added_tokens.jsonConfiguration707 B —
checkpoints/math/q1p7b-math-top32kl-taxonomy-topp05-qsel-w4-5g4a1t-b256/global_step_70/config.jsonConfiguration1.4 KB —
checkpoints/math/q1p7b-math-top32kl-taxonomy-topp05-qsel-w4-5g4a1t-b256/global_step_70/generation_config.jsonConfiguration214 B —
checkpoints/math/q1p7b-math-top32kl-taxonomy-topp05-qsel-w4-5g4a1t-b256/global_step_70/special_tokens_map.jsonConfiguration613 B —
checkpoints/math/q1p7b-math-top32kl-taxonomy-topp05-randsel-w4-4g3a1t-b255/global_step_55/added_tokens.jsonConfiguration707 B —
checkpoints/math/q1p7b-math-top32kl-taxonomy-topp05-randsel-w4-4g3a1t-b255/global_step_55/config.jsonConfiguration1.4 KB —
checkpoints/math/q1p7b-math-top32kl-taxonomy-topp05-randsel-w4-4g3a1t-b255/global_step_55/generation_config.jsonConfiguration214 B —
checkpoints/math/q1p7b-math-top32kl-taxonomy-topp05-randsel-w4-4g3a1t-b255/global_step_55/special_tokens_map.jsonConfiguration613 B —
checkpoints/math/q1p7b-math-top32kl-taxonomy-topp05-randsel-w4-4g3a1t-b255/global_step_60/added_tokens.jsonConfiguration707 B —
checkpoints/math/q1p7b-math-top32kl-taxonomy-topp05-randsel-w4-4g3a1t-b255/global_step_60/config.jsonConfiguration1.4 KB —
checkpoints/math/q1p7b-math-top32kl-taxonomy-topp05-randsel-w4-4g3a1t-b255/global_step_60/generation_config.jsonConfiguration214 B —
checkpoints/math/q1p7b-math-top32kl-taxonomy-topp05-randsel-w4-4g3a1t-b255/global_step_60/special_tokens_map.jsonConfiguration613 B —
checkpoints/math/q1p7b-math-top32kl-topp05-lossratio-5g4a1t-b256/global_step_55/added_tokens.jsonConfiguration707 B —
checkpoints/math/q1p7b-math-top32kl-topp05-lossratio-5g4a1t-b256/global_step_55/config.jsonConfiguration1.4 KB —
checkpoints/math/q1p7b-math-top32kl-topp05-lossratio-5g4a1t-b256/global_step_55/generation_config.jsonConfiguration214 B —
checkpoints/math/q1p7b-math-top32kl-topp05-lossratio-5g4a1t-b256/global_step_55/special_tokens_map.jsonConfiguration613 B —
checkpoints/math/q1p7b-math-top32kl-topp05-lossratio-5g4a1t-b256/global_step_60/added_tokens.jsonConfiguration707 B —
checkpoints/math/q1p7b-math-top32kl-topp05-lossratio-5g4a1t-b256/global_step_60/config.jsonConfiguration1.4 KB —
checkpoints/math/q1p7b-math-top32kl-topp05-lossratio-5g4a1t-b256/global_step_60/generation_config.jsonConfiguration214 B —
checkpoints/math/q1p7b-math-top32kl-topp05-lossratio-5g4a1t-b256/global_step_60/special_tokens_map.jsonConfiguration613 B —
checkpoints/math/q1p7b-math-top32kl-topp05-lossratio-5g4a1t-b256/global_step_65/added_tokens.jsonConfiguration707 B —
checkpoints/math/q1p7b-math-top32kl-topp05-lossratio-5g4a1t-b256/global_step_65/config.jsonConfiguration1.4 KB —
checkpoints/math/q1p7b-math-top32kl-topp05-lossratio-5g4a1t-b256/global_step_65/generation_config.jsonConfiguration214 B —
checkpoints/math/q1p7b-math-top32kl-topp05-lossratio-5g4a1t-b256/global_step_65/special_tokens_map.jsonConfiguration613 B —
checkpoints/math/q1p7b-math-top32kl-topp05-lossratio-5g4a1t-b256/global_step_70/added_tokens.jsonConfiguration707 B —
checkpoints/math/q1p7b-math-top32kl-topp05-lossratio-5g4a1t-b256/global_step_70/config.jsonConfiguration1.4 KB —
checkpoints/math/q1p7b-math-top32kl-topp05-lossratio-5g4a1t-b256/global_step_70/generation_config.jsonConfiguration214 B —
checkpoints/math/q1p7b-math-top32kl-topp05-lossratio-5g4a1t-b256/global_step_70/special_tokens_map.jsonConfiguration613 B —
checkpoints/math/q1p7b-math-top32kl-topp05-lossratio-a1p75-8g6a2t-b258/global_step_60/added_tokens.jsonConfiguration707 B —
checkpoints/math/q1p7b-math-top32kl-topp05-lossratio-a1p75-8g6a2t-b258/global_step_60/config.jsonConfiguration773 B —
checkpoints/math/q1p7b-math-top32kl-topp05-lossratio-a1p75-8g6a2t-b258/global_step_60/generation_config.jsonConfiguration214 B —
checkpoints/math/q1p7b-math-top32kl-topp05-lossratio-a1p75-8g6a2t-b258/global_step_60/special_tokens_map.jsonConfiguration613 B —
checkpoints/math/q1p7b-math-top32kl-v3-topp075-w4-8g6a2t-b258/global_step_60/added_tokens.jsonConfiguration707 B —
checkpoints/math/q1p7b-math-top32kl-v3-topp075-w4-8g6a2t-b258/global_step_60/config.jsonConfiguration773 B —
checkpoints/math/q1p7b-math-top32kl-v3-topp075-w4-8g6a2t-b258/global_step_60/generation_config.jsonConfiguration214 B —
checkpoints/math/q1p7b-math-top32kl-v3-topp075-w4-8g6a2t-b258/global_step_60/special_tokens_map.jsonConfiguration613 B —
checkpoints/math/q1p7b-math-top32kl-v3-topp1-w4-5g4a1t-b256/global_step_55/added_tokens.jsonConfiguration707 B —
checkpoints/math/q1p7b-math-top32kl-v3-topp1-w4-5g4a1t-b256/global_step_55/config.jsonConfiguration1.4 KB —
checkpoints/math/q1p7b-math-top32kl-v3-topp1-w4-5g4a1t-b256/global_step_55/generation_config.jsonConfiguration214 B —
checkpoints/math/q1p7b-math-top32kl-v3-topp1-w4-5g4a1t-b256/global_step_55/special_tokens_map.jsonConfiguration613 B —
checkpoints/math/q1p7b-math-top32kl-v3-topp1-w4-5g4a1t-b256/global_step_60/added_tokens.jsonConfiguration707 B —
checkpoints/math/q1p7b-math-top32kl-v3-topp1-w4-5g4a1t-b256/global_step_60/config.jsonConfiguration1.4 KB —
checkpoints/math/q1p7b-math-top32kl-v3-topp1-w4-5g4a1t-b256/global_step_60/generation_config.jsonConfiguration214 B —
checkpoints/math/q1p7b-math-top32kl-v3-topp1-w4-5g4a1t-b256/global_step_60/special_tokens_map.jsonConfiguration613 B —
checkpoints/math/q1p7b-taxonomy-q-topp05-fixed4-5g4a1t-b256-r20260908/global_step_55/added_tokens.jsonConfiguration707 B —
checkpoints/math/q1p7b-taxonomy-q-topp05-fixed4-5g4a1t-b256-r20260908/global_step_55/config.jsonConfiguration1.4 KB —
checkpoints/math/q1p7b-taxonomy-q-topp05-fixed4-5g4a1t-b256-r20260908/global_step_55/generation_config.jsonConfiguration214 B —
checkpoints/math/q1p7b-taxonomy-q-topp05-fixed4-5g4a1t-b256-r20260908/global_step_55/special_tokens_map.jsonConfiguration613 B —
checkpoints/math/q1p7b-taxonomy-q-topp05-fixed4-5g4a1t-b256-r20260908/global_step_60/added_tokens.jsonConfiguration707 B —
checkpoints/math/q1p7b-taxonomy-q-topp05-fixed4-5g4a1t-b256-r20260908/global_step_60/config.jsonConfiguration1.4 KB —
checkpoints/math/q1p7b-taxonomy-q-topp05-fixed4-5g4a1t-b256-r20260908/global_step_60/generation_config.jsonConfiguration214 B —
checkpoints/math/q1p7b-taxonomy-q-topp05-fixed4-5g4a1t-b256-r20260908/global_step_60/special_tokens_map.jsonConfiguration613 B —
checkpoints/math/q1p7b-taxonomy-q-topp05-fixed4-5g4a1t-b256-r20260908/global_step_65/added_tokens.jsonConfiguration707 B —
checkpoints/math/q1p7b-taxonomy-q-topp05-fixed4-5g4a1t-b256-r20260908/global_step_65/config.jsonConfiguration1.4 KB —
checkpoints/math/q1p7b-taxonomy-q-topp05-fixed4-5g4a1t-b256-r20260908/global_step_65/generation_config.jsonConfiguration214 B —
checkpoints/math/q1p7b-taxonomy-q-topp05-fixed4-5g4a1t-b256-r20260908/global_step_65/special_tokens_map.jsonConfiguration613 B —
checkpoints/math/q1p7b-taxonomy-q-topp05-fixed4-5g4a1t-b256-r20260908/global_step_70/added_tokens.jsonConfiguration707 B —
checkpoints/math/q1p7b-taxonomy-q-topp05-fixed4-5g4a1t-b256-r20260908/global_step_70/config.jsonConfiguration1.4 KB —
checkpoints/math/q1p7b-taxonomy-q-topp05-fixed4-5g4a1t-b256-r20260908/global_step_70/generation_config.jsonConfiguration214 B —
checkpoints/math/q1p7b-taxonomy-q-topp05-fixed4-5g4a1t-b256-r20260908/global_step_70/special_tokens_map.jsonConfiguration613 B —
checkpoints/math/q1p7b-taxonomy-toploss-topp05-fixed2-4g3a1t-b255/global_step_55/added_tokens.jsonConfiguration707 B —
checkpoints/math/q1p7b-taxonomy-toploss-topp05-fixed2-4g3a1t-b255/global_step_55/config.jsonConfiguration1.4 KB —
checkpoints/math/q1p7b-taxonomy-toploss-topp05-fixed2-4g3a1t-b255/global_step_55/generation_config.jsonConfiguration214 B —
checkpoints/math/q1p7b-taxonomy-toploss-topp05-fixed2-4g3a1t-b255/global_step_55/special_tokens_map.jsonConfiguration613 B —
checkpoints/math/q1p7b-taxonomy-toploss-topp05-fixed2-4g3a1t-b255/global_step_60/added_tokens.jsonConfiguration707 B —
checkpoints/math/q1p7b-taxonomy-toploss-topp05-fixed2-4g3a1t-b255/global_step_60/config.jsonConfiguration1.4 KB —
checkpoints/math/q1p7b-taxonomy-toploss-topp05-fixed2-4g3a1t-b255/global_step_60/generation_config.jsonConfiguration214 B —
checkpoints/math/q1p7b-taxonomy-toploss-topp05-fixed2-4g3a1t-b255/global_step_60/special_tokens_map.jsonConfiguration613 B —
checkpoints/math/q1p7b-taxonomy-toploss-topp05-fixed2-4g3a1t-b255/global_step_65/added_tokens.jsonConfiguration707 B —
checkpoints/math/q1p7b-taxonomy-toploss-topp05-fixed2-4g3a1t-b255/global_step_65/config.jsonConfiguration1.4 KB —
checkpoints/math/q1p7b-taxonomy-toploss-topp05-fixed2-4g3a1t-b255/global_step_65/generation_config.jsonConfiguration214 B —
checkpoints/math/q1p7b-taxonomy-toploss-topp05-fixed2-4g3a1t-b255/global_step_65/special_tokens_map.jsonConfiguration613 B —
checkpoints/math/q1p7b-taxonomy-toploss-topp05-fixed2-4g3a1t-b255/global_step_70/added_tokens.jsonConfiguration707 B —
checkpoints/math/q1p7b-taxonomy-toploss-topp05-fixed2-4g3a1t-b255/global_step_70/config.jsonConfiguration1.4 KB —
checkpoints/math/q1p7b-taxonomy-toploss-topp05-fixed2-4g3a1t-b255/global_step_70/generation_config.jsonConfiguration214 B —
checkpoints/math/q1p7b-taxonomy-toploss-topp05-fixed2-4g3a1t-b255/global_step_70/special_tokens_map.jsonConfiguration613 B —
checkpoints/math/q1p7b-taxonomy-toploss-topp05-fixed6-4g3a1t-b255-r20260909/global_step_55/added_tokens.jsonConfiguration707 B —
checkpoints/math/q1p7b-taxonomy-toploss-topp05-fixed6-4g3a1t-b255-r20260909/global_step_55/config.jsonConfiguration1.4 KB —
checkpoints/math/q1p7b-taxonomy-toploss-topp05-fixed6-4g3a1t-b255-r20260909/global_step_55/generation_config.jsonConfiguration214 B —
checkpoints/math/q1p7b-taxonomy-toploss-topp05-fixed6-4g3a1t-b255-r20260909/global_step_55/special_tokens_map.jsonConfiguration613 B —
checkpoints/math/q1p7b-taxonomy-toploss-topp05-fixed6-4g3a1t-b255-r20260909/global_step_60/added_tokens.jsonConfiguration707 B —
checkpoints/math/q1p7b-taxonomy-toploss-topp05-fixed6-4g3a1t-b255-r20260909/global_step_60/config.jsonConfiguration1.4 KB —
checkpoints/math/q1p7b-taxonomy-toploss-topp05-fixed6-4g3a1t-b255-r20260909/global_step_60/generation_config.jsonConfiguration214 B —
checkpoints/math/q1p7b-taxonomy-toploss-topp05-fixed6-4g3a1t-b255-r20260909/global_step_60/special_tokens_map.jsonConfiguration613 B —
checkpoints/math/q1p7b-taxonomy-toploss-topp05-fixed6-4g3a1t-b255-r20260909/global_step_65/added_tokens.jsonConfiguration707 B —
checkpoints/math/q1p7b-taxonomy-toploss-topp05-fixed6-4g3a1t-b255-r20260909/global_step_65/config.jsonConfiguration1.4 KB —
checkpoints/math/q1p7b-taxonomy-toploss-topp05-fixed6-4g3a1t-b255-r20260909/global_step_65/generation_config.jsonConfiguration214 B —
checkpoints/math/q1p7b-taxonomy-toploss-topp05-fixed6-4g3a1t-b255-r20260909/global_step_65/special_tokens_map.jsonConfiguration613 B —
checkpoints/math/q1p7b-taxonomy-toploss-topp05-fixed6-4g3a1t-b255-r20260909/global_step_70/added_tokens.jsonConfiguration707 B —
checkpoints/math/q1p7b-taxonomy-toploss-topp05-fixed6-4g3a1t-b255-r20260909/global_step_70/config.jsonConfiguration1.4 KB —
checkpoints/math/q1p7b-taxonomy-toploss-topp05-fixed6-4g3a1t-b255-r20260909/global_step_70/generation_config.jsonConfiguration214 B —
checkpoints/math/q1p7b-taxonomy-toploss-topp05-fixed6-4g3a1t-b255-r20260909/global_step_70/special_tokens_map.jsonConfiguration613 B —
checkpoints/math/q1p7b-v3-topp05-lossratio-i1w1-5g4a1t-b256-r20260907/global_step_55/added_tokens.jsonConfiguration707 B —
checkpoints/math/q1p7b-v3-topp05-lossratio-i1w1-5g4a1t-b256-r20260907/global_step_55/config.jsonConfiguration1.4 KB —
checkpoints/math/q1p7b-v3-topp05-lossratio-i1w1-5g4a1t-b256-r20260907/global_step_55/generation_config.jsonConfiguration214 B —
checkpoints/math/q1p7b-v3-topp05-lossratio-i1w1-5g4a1t-b256-r20260907/global_step_55/special_tokens_map.jsonConfiguration613 B —
checkpoints/math/q1p7b-v3-topp05-lossratio-i1w1-5g4a1t-b256-r20260907/global_step_60/added_tokens.jsonConfiguration707 B —
checkpoints/math/q1p7b-v3-topp05-lossratio-i1w1-5g4a1t-b256-r20260907/global_step_60/config.jsonConfiguration1.4 KB —
checkpoints/math/q1p7b-v3-topp05-lossratio-i1w1-5g4a1t-b256-r20260907/global_step_60/generation_config.jsonConfiguration214 B —
checkpoints/math/q1p7b-v3-topp05-lossratio-i1w1-5g4a1t-b256-r20260907/global_step_60/special_tokens_map.jsonConfiguration613 B —
checkpoints/math/q1p7b-v3-topp05-lossratio-i1w1-5g4a1t-b256-r20260907/global_step_65/added_tokens.jsonConfiguration707 B —
checkpoints/math/q1p7b-v3-topp05-lossratio-i1w1-5g4a1t-b256-r20260907/global_step_65/config.jsonConfiguration1.4 KB —
checkpoints/math/q1p7b-v3-topp05-lossratio-i1w1-5g4a1t-b256-r20260907/global_step_65/generation_config.jsonConfiguration214 B —
checkpoints/math/q1p7b-v3-topp05-lossratio-i1w1-5g4a1t-b256-r20260907/global_step_65/special_tokens_map.jsonConfiguration613 B —
checkpoints/math/qwen1p7b-30b-math-eopd-4gpu-b255/global_step_50/actor/fsdp_config.jsonConfiguration152 B —
checkpoints/math/qwen1p7b-30b-math-eopd-4gpu-b255/global_step_50/actor/huggingface/added_tokens.jsonConfiguration707 B —
checkpoints/math/qwen1p7b-30b-math-eopd-4gpu-b255/global_step_50/actor/huggingface/config.jsonConfiguration1.4 KB —
checkpoints/math/qwen1p7b-30b-math-eopd-4gpu-b255/global_step_50/actor/huggingface/generation_config.jsonConfiguration214 B —
checkpoints/math/qwen1p7b-30b-math-eopd-4gpu-b255/global_step_50/actor/huggingface/special_tokens_map.jsonConfiguration613 B —
checkpoints/math/qwen1p7b-30b-math-eopd-4gpu-b255/global_step_55/actor/fsdp_config.jsonConfiguration152 B —
checkpoints/math/qwen1p7b-30b-math-eopd-4gpu-b255/global_step_55/actor/huggingface/added_tokens.jsonConfiguration707 B —
checkpoints/math/qwen1p7b-30b-math-eopd-4gpu-b255/global_step_55/actor/huggingface/config.jsonConfiguration1.4 KB —
checkpoints/math/qwen1p7b-30b-math-eopd-4gpu-b255/global_step_55/actor/huggingface/generation_config.jsonConfiguration214 B —
checkpoints/math/qwen1p7b-30b-math-eopd-4gpu-b255/global_step_55/actor/huggingface/special_tokens_map.jsonConfiguration613 B —
checkpoints/math/qwen1p7b-30b-math-eopd-4gpu-b255/global_step_60/actor/fsdp_config.jsonConfiguration152 B —
checkpoints/math/qwen1p7b-30b-math-eopd-4gpu-b255/global_step_60/actor/huggingface/added_tokens.jsonConfiguration707 B —
checkpoints/math/qwen1p7b-30b-math-eopd-4gpu-b255/global_step_60/actor/huggingface/config.jsonConfiguration1.4 KB —
checkpoints/math/qwen1p7b-30b-math-eopd-4gpu-b255/global_step_60/actor/huggingface/generation_config.jsonConfiguration214 B —
checkpoints/math/qwen1p7b-30b-math-eopd-4gpu-b255/global_step_60/actor/huggingface/special_tokens_map.jsonConfiguration613 B —
checkpoints/math/qwen1p7b-30b-math-eopd-4gpu-b255/global_step_65/actor/fsdp_config.jsonConfiguration152 B —
checkpoints/math/qwen1p7b-30b-math-eopd-4gpu-b255/global_step_65/actor/huggingface/added_tokens.jsonConfiguration707 B —
checkpoints/math/qwen1p7b-30b-math-eopd-4gpu-b255/global_step_65/actor/huggingface/config.jsonConfiguration1.4 KB —
checkpoints/math/qwen1p7b-30b-math-eopd-4gpu-b255/global_step_65/actor/huggingface/generation_config.jsonConfiguration214 B —
checkpoints/math/qwen1p7b-30b-math-eopd-4gpu-b255/global_step_65/actor/huggingface/special_tokens_map.jsonConfiguration613 B —
checkpoints/math/qwen1p7b-30b-math-exopd-lambda1p25-4gpu-b255/global_step_55/actor/fsdp_config.jsonConfiguration152 B —
checkpoints/math/qwen1p7b-30b-math-exopd-lambda1p25-4gpu-b255/global_step_55/actor/huggingface/added_tokens.jsonConfiguration707 B —
checkpoints/math/qwen1p7b-30b-math-exopd-lambda1p25-4gpu-b255/global_step_55/actor/huggingface/config.jsonConfiguration1.4 KB —
checkpoints/math/qwen1p7b-30b-math-exopd-lambda1p25-4gpu-b255/global_step_55/actor/huggingface/generation_config.jsonConfiguration214 B —
checkpoints/math/qwen1p7b-30b-math-exopd-lambda1p25-4gpu-b255/global_step_55/actor/huggingface/special_tokens_map.jsonConfiguration613 B —
checkpoints/math/qwen1p7b-30b-math-exopd-lambda1p25-4gpu-b255/global_step_60/actor/fsdp_config.jsonConfiguration152 B —
checkpoints/math/qwen1p7b-30b-math-exopd-lambda1p25-4gpu-b255/global_step_60/actor/huggingface/added_tokens.jsonConfiguration707 B —
checkpoints/math/qwen1p7b-30b-math-exopd-lambda1p25-4gpu-b255/global_step_60/actor/huggingface/config.jsonConfiguration1.4 KB —
checkpoints/math/qwen1p7b-30b-math-exopd-lambda1p25-4gpu-b255/global_step_60/actor/huggingface/generation_config.jsonConfiguration214 B —
checkpoints/math/qwen1p7b-30b-math-exopd-lambda1p25-4gpu-b255/global_step_60/actor/huggingface/special_tokens_map.jsonConfiguration613 B —
checkpoints/math/qwen1p7b-30b-math-exopd-lambda1p25-4gpu-b255/global_step_65/actor/fsdp_config.jsonConfiguration152 B —
checkpoints/math/qwen1p7b-30b-math-exopd-lambda1p25-4gpu-b255/global_step_65/actor/huggingface/added_tokens.jsonConfiguration707 B —
checkpoints/math/qwen1p7b-30b-math-exopd-lambda1p25-4gpu-b255/global_step_65/actor/huggingface/config.jsonConfiguration1.4 KB —
checkpoints/math/qwen1p7b-30b-math-exopd-lambda1p25-4gpu-b255/global_step_65/actor/huggingface/generation_config.jsonConfiguration214 B —
checkpoints/math/qwen1p7b-30b-math-exopd-lambda1p25-4gpu-b255/global_step_65/actor/huggingface/special_tokens_map.jsonConfiguration613 B —
checkpoints/math/qwen1p7b-30b-math-exopd-lambda1p25-4gpu-b255/global_step_70/actor/fsdp_config.jsonConfiguration152 B —
checkpoints/math/qwen1p7b-30b-math-exopd-lambda1p25-4gpu-b255/global_step_70/actor/huggingface/added_tokens.jsonConfiguration707 B —
checkpoints/math/qwen1p7b-30b-math-exopd-lambda1p25-4gpu-b255/global_step_70/actor/huggingface/config.jsonConfiguration1.4 KB —
checkpoints/math/qwen1p7b-30b-math-exopd-lambda1p25-4gpu-b255/global_step_70/actor/huggingface/generation_config.jsonConfiguration214 B —
checkpoints/math/qwen1p7b-30b-math-exopd-lambda1p25-4gpu-b255/global_step_70/actor/huggingface/special_tokens_map.jsonConfiguration613 B —
checkpoints/math/qwen1p7b-30b-math-fire-opd-4gpu-b255/global_step_55/actor/fsdp_config.jsonConfiguration152 B —
checkpoints/math/qwen1p7b-30b-math-fire-opd-4gpu-b255/global_step_55/actor/huggingface/added_tokens.jsonConfiguration707 B —
checkpoints/math/qwen1p7b-30b-math-fire-opd-4gpu-b255/global_step_55/actor/huggingface/config.jsonConfiguration1.4 KB —
checkpoints/math/qwen1p7b-30b-math-fire-opd-4gpu-b255/global_step_55/actor/huggingface/generation_config.jsonConfiguration214 B —
checkpoints/math/qwen1p7b-30b-math-fire-opd-4gpu-b255/global_step_55/actor/huggingface/special_tokens_map.jsonConfiguration613 B —
checkpoints/math/qwen1p7b-30b-math-fire-opd-4gpu-b255/global_step_60/actor/fsdp_config.jsonConfiguration152 B —
checkpoints/math/qwen1p7b-30b-math-fire-opd-4gpu-b255/global_step_60/actor/huggingface/added_tokens.jsonConfiguration707 B —
checkpoints/math/qwen1p7b-30b-math-fire-opd-4gpu-b255/global_step_60/actor/huggingface/config.jsonConfiguration1.4 KB —
checkpoints/math/qwen1p7b-30b-math-fire-opd-4gpu-b255/global_step_60/actor/huggingface/generation_config.jsonConfiguration214 B —
checkpoints/math/qwen1p7b-30b-math-fire-opd-4gpu-b255/global_step_60/actor/huggingface/special_tokens_map.jsonConfiguration613 B —
checkpoints/math/qwen1p7b-30b-math-fire-opd-4gpu-b255/global_step_65/actor/fsdp_config.jsonConfiguration152 B —
checkpoints/math/qwen1p7b-30b-math-fire-opd-4gpu-b255/global_step_65/actor/huggingface/added_tokens.jsonConfiguration707 B —
checkpoints/math/qwen1p7b-30b-math-fire-opd-4gpu-b255/global_step_65/actor/huggingface/config.jsonConfiguration1.4 KB —
checkpoints/math/qwen1p7b-30b-math-fire-opd-4gpu-b255/global_step_65/actor/huggingface/generation_config.jsonConfiguration214 B —
checkpoints/math/qwen1p7b-30b-math-fire-opd-4gpu-b255/global_step_65/actor/huggingface/special_tokens_map.jsonConfiguration613 B —
checkpoints/math/qwen1p7b-30b-math-fire-opd-4gpu-b255/global_step_70/actor/fsdp_config.jsonConfiguration152 B —
checkpoints/math/qwen1p7b-30b-math-fire-opd-4gpu-b255/global_step_70/actor/huggingface/added_tokens.jsonConfiguration707 B —
checkpoints/math/qwen1p7b-30b-math-fire-opd-4gpu-b255/global_step_70/actor/huggingface/config.jsonConfiguration1.4 KB —
checkpoints/math/qwen1p7b-30b-math-fire-opd-4gpu-b255/global_step_70/actor/huggingface/generation_config.jsonConfiguration214 B —
checkpoints/math/qwen1p7b-30b-math-fire-opd-4gpu-b255/global_step_70/actor/huggingface/special_tokens_map.jsonConfiguration613 B —
checkpoints/math/qwen1p7b-30b-math-opd-4gpu-b255/global_step_50/actor/fsdp_config.jsonConfiguration152 B —
checkpoints/math/qwen1p7b-30b-math-opd-4gpu-b255/global_step_50/actor/huggingface/added_tokens.jsonConfiguration707 B —
checkpoints/math/qwen1p7b-30b-math-opd-4gpu-b255/global_step_50/actor/huggingface/config.jsonConfiguration1.4 KB —
checkpoints/math/qwen1p7b-30b-math-opd-4gpu-b255/global_step_50/actor/huggingface/generation_config.jsonConfiguration214 B —
checkpoints/math/qwen1p7b-30b-math-opd-4gpu-b255/global_step_50/actor/huggingface/special_tokens_map.jsonConfiguration613 B —
checkpoints/math/qwen1p7b-30b-math-opd-4gpu-b255/global_step_55/actor/fsdp_config.jsonConfiguration152 B —
checkpoints/math/qwen1p7b-30b-math-opd-4gpu-b255/global_step_55/actor/huggingface/added_tokens.jsonConfiguration707 B —
checkpoints/math/qwen1p7b-30b-math-opd-4gpu-b255/global_step_55/actor/huggingface/config.jsonConfiguration1.4 KB —
checkpoints/math/qwen1p7b-30b-math-opd-4gpu-b255/global_step_55/actor/huggingface/generation_config.jsonConfiguration214 B —
checkpoints/math/qwen1p7b-30b-math-opd-4gpu-b255/global_step_55/actor/huggingface/special_tokens_map.jsonConfiguration613 B —
checkpoints/math/qwen1p7b-30b-math-tip-topk32-rho50-4gpu-b255/global_step_55/actor/fsdp_config.jsonConfiguration152 B —
checkpoints/math/qwen1p7b-30b-math-tip-topk32-rho50-4gpu-b255/global_step_55/actor/huggingface/added_tokens.jsonConfiguration707 B —
checkpoints/math/qwen1p7b-30b-math-tip-topk32-rho50-4gpu-b255/global_step_55/actor/huggingface/config.jsonConfiguration1.4 KB —
checkpoints/math/qwen1p7b-30b-math-tip-topk32-rho50-4gpu-b255/global_step_55/actor/huggingface/generation_config.jsonConfiguration214 B —
checkpoints/math/qwen1p7b-30b-math-tip-topk32-rho50-4gpu-b255/global_step_55/actor/huggingface/special_tokens_map.jsonConfiguration613 B —
checkpoints/math/qwen1p7b-30b-math-tip-topk32-rho50-4gpu-b255/global_step_60/actor/fsdp_config.jsonConfiguration152 B —
checkpoints/math/qwen1p7b-30b-math-tip-topk32-rho50-4gpu-b255/global_step_60/actor/huggingface/added_tokens.jsonConfiguration707 B —
checkpoints/math/qwen1p7b-30b-math-tip-topk32-rho50-4gpu-b255/global_step_60/actor/huggingface/config.jsonConfiguration1.4 KB —
checkpoints/math/qwen1p7b-30b-math-tip-topk32-rho50-4gpu-b255/global_step_60/actor/huggingface/generation_config.jsonConfiguration214 B —
checkpoints/math/qwen1p7b-30b-math-tip-topk32-rho50-4gpu-b255/global_step_60/actor/huggingface/special_tokens_map.jsonConfiguration613 B —
checkpoints/math/qwen1p7b-30b-math-tip-topk32-rho50-4gpu-b255/global_step_65/actor/fsdp_config.jsonConfiguration152 B —
checkpoints/math/qwen1p7b-30b-math-tip-topk32-rho50-4gpu-b255/global_step_65/actor/huggingface/added_tokens.jsonConfiguration707 B —
checkpoints/math/qwen1p7b-30b-math-tip-topk32-rho50-4gpu-b255/global_step_65/actor/huggingface/config.jsonConfiguration1.4 KB —
checkpoints/math/qwen1p7b-30b-math-tip-topk32-rho50-4gpu-b255/global_step_65/actor/huggingface/generation_config.jsonConfiguration214 B —
checkpoints/math/qwen1p7b-30b-math-tip-topk32-rho50-4gpu-b255/global_step_65/actor/huggingface/special_tokens_map.jsonConfiguration613 B —
checkpoints/math/qwen1p7b-30b-math-tip-topk32-rho50-4gpu-b255/global_step_70/actor/fsdp_config.jsonConfiguration152 B —
checkpoints/math/qwen1p7b-30b-math-tip-topk32-rho50-4gpu-b255/global_step_70/actor/huggingface/added_tokens.jsonConfiguration707 B —
checkpoints/math/qwen1p7b-30b-math-tip-topk32-rho50-4gpu-b255/global_step_70/actor/huggingface/config.jsonConfiguration1.4 KB —
checkpoints/math/qwen1p7b-30b-math-tip-topk32-rho50-4gpu-b255/global_step_70/actor/huggingface/generation_config.jsonConfiguration214 B —
checkpoints/math/qwen1p7b-30b-math-tip-topk32-rho50-4gpu-b255/global_step_70/actor/huggingface/special_tokens_map.jsonConfiguration613 B —
checkpoints/mopd/q1p7b-4g-mcs-m05c01s01-stconf-cfkl-srkl-f4-b528-coloc-s60/global_step_60/added_tokens.jsonConfiguration707 B —
checkpoints/mopd/q1p7b-4g-mcs-m05c01s01-stconf-cfkl-srkl-f4-b528-coloc-s60/global_step_60/config.jsonConfiguration1.4 KB —
checkpoints/mopd/q1p7b-4g-mcs-m05c01s01-stconf-cfkl-srkl-f4-b528-coloc-s60/global_step_60/generation_config.jsonConfiguration214 B —
checkpoints/mopd/q1p7b-4g-mcs-m05c01s01-stconf-cfkl-srkl-f4-b528-coloc-s60/global_step_60/special_tokens_map.jsonConfiguration613 B —
checkpoints/mopd/q1p7b-4g-mcs-mtl05-ctl01-sltc01-f4-b528-coloc-s60/global_step_60/added_tokens.jsonConfiguration707 B —
checkpoints/mopd/q1p7b-4g-mcs-mtl05-ctl01-sltc01-f4-b528-coloc-s60/global_step_60/config.jsonConfiguration1.4 KB —
checkpoints/mopd/q1p7b-4g-mcs-mtl05-ctl01-sltc01-f4-b528-coloc-s60/global_step_60/generation_config.jsonConfiguration214 B —
checkpoints/mopd/q1p7b-4g-mcs-mtl05-ctl01-sltc01-f4-b528-coloc-s60/global_step_60/special_tokens_map.jsonConfiguration613 B —
checkpoints/mopd/q1p7b-4g-mcs-mtl05-ctl01cs-stl01-f4-b528-coloc-s60/global_step_60/added_tokens.jsonConfiguration707 B —
checkpoints/mopd/q1p7b-4g-mcs-mtl05-ctl01cs-stl01-f4-b528-coloc-s60/global_step_60/config.jsonConfiguration1.4 KB —
checkpoints/mopd/q1p7b-4g-mcs-mtl05-ctl01cs-stl01-f4-b528-coloc-s60/global_step_60/generation_config.jsonConfiguration214 B —
checkpoints/mopd/q1p7b-4g-mcs-mtl05-ctl01cs-stl01-f4-b528-coloc-s60/global_step_60/special_tokens_map.jsonConfiguration613 B —
checkpoints/mopd/q1p7b-8g-mcs-m05c01s01-stloss-cfkl-srkl-f4-b528-s60/global_step_60/added_tokens.jsonConfiguration707 B —
checkpoints/mopd/q1p7b-8g-mcs-m05c01s01-stloss-cfkl-srkl-f4-b528-s60/global_step_60/config.jsonConfiguration773 B —
checkpoints/mopd/q1p7b-8g-mcs-m05c01s01-stloss-cfkl-srkl-f4-b528-s60/global_step_60/generation_config.jsonConfiguration214 B —
checkpoints/mopd/q1p7b-8g-mcs-m05c01s01-stloss-cfkl-srkl-f4-b528-s60/global_step_60/special_tokens_map.jsonConfiguration613 B —
checkpoints/mopd/q1p7b-8g-mcs-mtl05-ctl01cs-sltc01-f4-b528-s60/global_step_60/added_tokens.jsonConfiguration707 B —
checkpoints/mopd/q1p7b-8g-mcs-mtl05-ctl01cs-sltc01-f4-b528-s60/global_step_60/config.jsonConfiguration773 B —
checkpoints/mopd/q1p7b-8g-mcs-mtl05-ctl01cs-sltc01-f4-b528-s60/global_step_60/generation_config.jsonConfiguration214 B —
checkpoints/mopd/q1p7b-8g-mcs-mtl05-ctl01cs-sltc01-f4-b528-s60/global_step_60/special_tokens_map.jsonConfiguration613 B —
checkpoints/mopd/q1p7b-8g-mcs-mtl05-ctl02-sltc02-f4-b528-s60/global_step_60/added_tokens.jsonConfiguration707 B —
checkpoints/mopd/q1p7b-8g-mcs-mtl05-ctl02-sltc02-f4-b528-s60/global_step_60/config.jsonConfiguration773 B —
checkpoints/mopd/q1p7b-8g-mcs-mtl05-ctl02-sltc02-f4-b528-s60/global_step_60/generation_config.jsonConfiguration214 B —
checkpoints/mopd/q1p7b-8g-mcs-mtl05-ctl02-sltc02-f4-b528-s60/global_step_60/special_tokens_map.jsonConfiguration613 B —
checkpoints/mopd/q1p7b-8g-mcs-p05-toploss-cfkl-srkl-f4-b528-s60/global_step_60/added_tokens.jsonConfiguration707 B —
checkpoints/mopd/q1p7b-8g-mcs-p05-toploss-cfkl-srkl-f4-b528-s60/global_step_60/config.jsonConfiguration773 B —
checkpoints/mopd/q1p7b-8g-mcs-p05-toploss-cfkl-srkl-f4-b528-s60/global_step_60/generation_config.jsonConfiguration214 B —
checkpoints/mopd/q1p7b-8g-mcs-p05-toploss-cfkl-srkl-f4-b528-s60/global_step_60/special_tokens_map.jsonConfiguration613 B —
checkpoints/mopd/q1p7b-8g-mcs-taxonomy-toploss-topp05-fixed4-b528-s60/global_step_60/added_tokens.jsonConfiguration707 B —
checkpoints/mopd/q1p7b-8g-mcs-taxonomy-toploss-topp05-fixed4-b528-s60/global_step_60/config.jsonConfiguration773 B —
checkpoints/mopd/q1p7b-8g-mcs-taxonomy-toploss-topp05-fixed4-b528-s60/global_step_60/generation_config.jsonConfiguration214 B —
checkpoints/mopd/q1p7b-8g-mcs-taxonomy-toploss-topp05-fixed4-b528-s60/global_step_60/special_tokens_map.jsonConfiguration613 B —
checkpoints/mopd/q1p7b3s1t-mc-tl-m05c01-cstruct-disc33-f4-b528-s60/global_step_60/added_tokens.jsonConfiguration707 B —
checkpoints/mopd/q1p7b3s1t-mc-tl-m05c01-cstruct-disc33-f4-b528-s60/global_step_60/config.jsonConfiguration1.4 KB —
checkpoints/mopd/q1p7b3s1t-mc-tl-m05c01-cstruct-disc33-f4-b528-s60/global_step_60/generation_config.jsonConfiguration214 B —
checkpoints/mopd/q1p7b3s1t-mc-tl-m05c01-cstruct-disc33-f4-b528-s60/global_step_60/special_tokens_map.jsonConfiguration613 B —
checkpoints/mopd/q1p7b3s1t-mc-v6-cs-current-m05c01-f4-b528-s60/global_step_60/added_tokens.jsonConfiguration707 B —
checkpoints/mopd/q1p7b3s1t-mc-v6-cs-current-m05c01-f4-b528-s60/global_step_60/config.jsonConfiguration1.4 KB —
checkpoints/mopd/q1p7b3s1t-mc-v6-cs-current-m05c01-f4-b528-s60/global_step_60/generation_config.jsonConfiguration214 B —
checkpoints/mopd/q1p7b3s1t-mc-v6-cs-current-m05c01-f4-b528-s60/global_step_60/special_tokens_map.jsonConfiguration613 B —
checkpoints/mopd/q1p7b4g-mc-tl-m05c01-cstruct-8g6s2t-b528-s60/global_step_60/added_tokens.jsonConfiguration707 B —
checkpoints/mopd/q1p7b4g-mc-tl-m05c01-cstruct-8g6s2t-b528-s60/global_step_60/config.jsonConfiguration773 B —
checkpoints/mopd/q1p7b4g-mc-tl-m05c01-cstruct-8g6s2t-b528-s60/global_step_60/generation_config.jsonConfiguration214 B —
checkpoints/mopd/q1p7b4g-mc-tl-m05c01-cstruct-8g6s2t-b528-s60/global_step_60/special_tokens_map.jsonConfiguration613 B —
checkpoints/mopd/q1p7b4g-mc-tl-m05c01-f4-b528-s60/global_step_60/added_tokens.jsonConfiguration707 B —
checkpoints/mopd/q1p7b4g-mc-tl-m05c01-f4-b528-s60/global_step_60/config.jsonConfiguration1.4 KB —
checkpoints/mopd/q1p7b4g-mc-tl-m05c01-f4-b528-s60/global_step_60/generation_config.jsonConfiguration214 B —
checkpoints/mopd/q1p7b4g-mc-tl-m05c01-f4-b528-s60/global_step_60/special_tokens_map.jsonConfiguration613 B —
checkpoints/mopd/q1p7b4g-mc-tl-m05c02-cstruct-8g6s2t-b528-s60/global_step_60/added_tokens.jsonConfiguration707 B —
checkpoints/mopd/q1p7b4g-mc-tl-m05c02-cstruct-8g6s2t-b528-s60/global_step_60/config.jsonConfiguration773 B —
checkpoints/mopd/q1p7b4g-mc-tl-m05c02-cstruct-8g6s2t-b528-s60/global_step_60/generation_config.jsonConfiguration214 B —
checkpoints/mopd/q1p7b4g-mc-tl-m05c02-cstruct-8g6s2t-b528-s60/global_step_60/special_tokens_map.jsonConfiguration613 B —
checkpoints/mopd/q1p7b4g-mc-tl-m05c02-cstruct-f4-b528-s60/global_step_60/added_tokens.jsonConfiguration707 B —
checkpoints/mopd/q1p7b4g-mc-tl-m05c02-cstruct-f4-b528-s60/global_step_60/config.jsonConfiguration1.4 KB —
checkpoints/mopd/q1p7b4g-mc-tl-m05c02-cstruct-f4-b528-s60/global_step_60/generation_config.jsonConfiguration214 B —
checkpoints/mopd/q1p7b4g-mc-tl-m05c02-cstruct-f4-b528-s60/global_step_60/special_tokens_map.jsonConfiguration613 B —
checkpoints/mopd/q1p7b4g-mc-tl-m05c05-8g6s2t-b528-s60/global_step_60/added_tokens.jsonConfiguration707 B —
checkpoints/mopd/q1p7b4g-mc-tl-m05c05-8g6s2t-b528-s60/global_step_60/config.jsonConfiguration773 B —
checkpoints/mopd/q1p7b4g-mc-tl-m05c05-8g6s2t-b528-s60/global_step_60/generation_config.jsonConfiguration214 B —
checkpoints/mopd/q1p7b4g-mc-tl-m05c05-8g6s2t-b528-s60/global_step_60/special_tokens_map.jsonConfiguration613 B —
checkpoints/mopd/q1p7b4g-mc-tl-m05c05-cstruct-8g6s2t-b528-s60/global_step_60/added_tokens.jsonConfiguration707 B —
checkpoints/mopd/q1p7b4g-mc-tl-m05c05-cstruct-8g6s2t-b528-s60/global_step_60/config.jsonConfiguration773 B —
checkpoints/mopd/q1p7b4g-mc-tl-m05c05-cstruct-8g6s2t-b528-s60/global_step_60/generation_config.jsonConfiguration214 B —
checkpoints/mopd/q1p7b4g-mc-tl-m05c05-cstruct-8g6s2t-b528-s60/global_step_60/special_tokens_map.jsonConfiguration613 B —
checkpoints/mopd/q1p7b4g-mc-v4-r3-cs-next-m05c01-f4-b528-s60/global_step_60/added_tokens.jsonConfiguration707 B —
checkpoints/mopd/q1p7b4g-mc-v4-r3-cs-next-m05c01-f4-b528-s60/global_step_60/config.jsonConfiguration1.4 KB —
checkpoints/mopd/q1p7b4g-mc-v4-r3-cs-next-m05c01-f4-b528-s60/global_step_60/generation_config.jsonConfiguration214 B —
checkpoints/mopd/q1p7b4g-mc-v4-r3-cs-next-m05c01-f4-b528-s60/global_step_60/special_tokens_map.jsonConfiguration613 B —
checkpoints/mopd/q1p7b8g-mc-legacy-cstruct-current-m05c01-f4-b528-s60-retry1/global_step_60/added_tokens.jsonConfiguration707 B —
checkpoints/mopd/q1p7b8g-mc-legacy-cstruct-current-m05c01-f4-b528-s60-retry1/global_step_60/config.jsonConfiguration773 B —
checkpoints/mopd/q1p7b8g-mc-legacy-cstruct-current-m05c01-f4-b528-s60-retry1/global_step_60/generation_config.jsonConfiguration214 B —
checkpoints/mopd/q1p7b8g-mc-legacy-cstruct-current-m05c01-f4-b528-s60-retry1/global_step_60/special_tokens_map.jsonConfiguration613 B —
checkpoints/mopd/q1p7b8g-mc-v5-r3-cs-next-m05c01-f4-b528-s60/global_step_60/added_tokens.jsonConfiguration707 B —
checkpoints/mopd/q1p7b8g-mc-v5-r3-cs-next-m05c01-f4-b528-s60/global_step_60/config.jsonConfiguration773 B —
checkpoints/mopd/q1p7b8g-mc-v5-r3-cs-next-m05c01-f4-b528-s60/global_step_60/generation_config.jsonConfiguration214 B —
checkpoints/mopd/q1p7b8g-mc-v5-r3-cs-next-m05c01-f4-b528-s60/global_step_60/special_tokens_map.jsonConfiguration613 B —
checkpoints/mopd/q1p7b8g-mc-v7-cs-current-m05c01-f4-6s2t-b528-s60/global_step_60/added_tokens.jsonConfiguration707 B —
checkpoints/mopd/q1p7b8g-mc-v7-cs-current-m05c01-f4-6s2t-b528-s60/global_step_60/config.jsonConfiguration773 B —
checkpoints/mopd/q1p7b8g-mc-v7-cs-current-m05c01-f4-6s2t-b528-s60/global_step_60/generation_config.jsonConfiguration214 B —
checkpoints/mopd/q1p7b8g-mc-v7-cs-current-m05c01-f4-6s2t-b528-s60/global_step_60/special_tokens_map.jsonConfiguration613 B —
checkpoints/mopd/q1p7b8g-mc-v8-cs-current-m05c01-f4-6s2t-b528-s60/global_step_60/added_tokens.jsonConfiguration707 B —
checkpoints/mopd/q1p7b8g-mc-v8-cs-current-m05c01-f4-6s2t-b528-s60/global_step_60/config.jsonConfiguration773 B —
checkpoints/mopd/q1p7b8g-mc-v8-cs-current-m05c01-f4-6s2t-b528-s60/global_step_60/generation_config.jsonConfiguration214 B —
checkpoints/mopd/q1p7b8g-mc-v8-cs-current-m05c01-f4-6s2t-b528-s60/global_step_60/special_tokens_map.jsonConfiguration613 B —
checkpoints/mopd/qwen1p7b-30b-eopd-native-8gpu-b528-teacher50-final/global_step_60/added_tokens.jsonConfiguration707 B —
checkpoints/mopd/qwen1p7b-30b-eopd-native-8gpu-b528-teacher50-final/global_step_60/config.jsonConfiguration727 B —
checkpoints/mopd/qwen1p7b-30b-eopd-native-8gpu-b528-teacher50-final/global_step_60/generation_config.jsonConfiguration214 B —
checkpoints/mopd/qwen1p7b-30b-eopd-native-8gpu-b528-teacher50-final/global_step_60/special_tokens_map.jsonConfiguration613 B —
audits/mopd/q1p7b4g-mc-tl-m05c01-cstruct-8g6s2t-b528-s60/selection-step1-60/README.mdDocumentation1.5 KB —
audit/q1p7b-8g-mcs-mtl05-ctl01cs-sltc01-f4-b528-s60/mopd_qwen1p7b_30b_a3b_instruct_2507_8gpu_math_code_scie_1a74ccf8_20260918_191538.zipOther21.6 GB e2804bf7967f
audits/mopd/q1p7b-8g-mcs-taxonomy-toploss-topp05-fixed4-b528-s60/audit_step60.zipOther22.4 GB 1669a868095c
audits/mopd/q1p7b4g-mc-tl-m05c01-cstruct-8g6s2t-b528-s60/selection-step1-60/SHA256SUMSOther7.2 KB —
audits/mopd/q1p7b4g-mc-tl-m05c01-cstruct-8g6s2t-b528-s60/selection-step1-60/step_000001/jsonls/online_control_selection.jsonlOther25.1 KB —
audits/mopd/q1p7b4g-mc-tl-m05c01-cstruct-8g6s2t-b528-s60/selection-step1-60/step_000002/jsonls/online_control_selection.jsonlOther28.2 KB —
audits/mopd/q1p7b4g-mc-tl-m05c01-cstruct-8g6s2t-b528-s60/selection-step1-60/step_000003/jsonls/online_control_selection.jsonlOther27.6 KB —
audits/mopd/q1p7b4g-mc-tl-m05c01-cstruct-8g6s2t-b528-s60/selection-step1-60/step_000004/jsonls/online_control_selection.jsonlOther29.1 KB —
audits/mopd/q1p7b4g-mc-tl-m05c01-cstruct-8g6s2t-b528-s60/selection-step1-60/step_000005/jsonls/online_control_selection.jsonlOther31.6 KB —
audits/mopd/q1p7b4g-mc-tl-m05c01-cstruct-8g6s2t-b528-s60/selection-step1-60/step_000006/jsonls/online_control_selection.jsonlOther33.4 KB —
audits/mopd/q1p7b4g-mc-tl-m05c01-cstruct-8g6s2t-b528-s60/selection-step1-60/step_000007/jsonls/online_control_selection.jsonlOther33.5 KB —
audits/mopd/q1p7b4g-mc-tl-m05c01-cstruct-8g6s2t-b528-s60/selection-step1-60/step_000008/jsonls/online_control_selection.jsonlOther36.6 KB —
audits/mopd/q1p7b4g-mc-tl-m05c01-cstruct-8g6s2t-b528-s60/selection-step1-60/step_000009/jsonls/online_control_selection.jsonlOther39.4 KB —
audits/mopd/q1p7b4g-mc-tl-m05c01-cstruct-8g6s2t-b528-s60/selection-step1-60/step_000010/jsonls/online_control_selection.jsonlOther37.0 KB —
audits/mopd/q1p7b4g-mc-tl-m05c01-cstruct-8g6s2t-b528-s60/selection-step1-60/step_000011/jsonls/online_control_selection.jsonlOther40.5 KB —
audits/mopd/q1p7b4g-mc-tl-m05c01-cstruct-8g6s2t-b528-s60/selection-step1-60/step_000012/jsonls/online_control_selection.jsonlOther42.4 KB —
audits/mopd/q1p7b4g-mc-tl-m05c01-cstruct-8g6s2t-b528-s60/selection-step1-60/step_000013/jsonls/online_control_selection.jsonlOther41.1 KB —
audits/mopd/q1p7b4g-mc-tl-m05c01-cstruct-8g6s2t-b528-s60/selection-step1-60/step_000014/jsonls/online_control_selection.jsonlOther40.2 KB —
audits/mopd/q1p7b4g-mc-tl-m05c01-cstruct-8g6s2t-b528-s60/selection-step1-60/step_000015/jsonls/online_control_selection.jsonlOther40.8 KB —
audits/mopd/q1p7b4g-mc-tl-m05c01-cstruct-8g6s2t-b528-s60/selection-step1-60/step_000016/jsonls/online_control_selection.jsonlOther45.0 KB —
audits/mopd/q1p7b4g-mc-tl-m05c01-cstruct-8g6s2t-b528-s60/selection-step1-60/step_000017/jsonls/online_control_selection.jsonlOther41.0 KB —
audits/mopd/q1p7b4g-mc-tl-m05c01-cstruct-8g6s2t-b528-s60/selection-step1-60/step_000018/jsonls/online_control_selection.jsonlOther45.7 KB —
audits/mopd/q1p7b4g-mc-tl-m05c01-cstruct-8g6s2t-b528-s60/selection-step1-60/step_000019/jsonls/online_control_selection.jsonlOther42.8 KB —
audits/mopd/q1p7b4g-mc-tl-m05c01-cstruct-8g6s2t-b528-s60/selection-step1-60/step_000020/jsonls/online_control_selection.jsonlOther41.8 KB —
audits/mopd/q1p7b4g-mc-tl-m05c01-cstruct-8g6s2t-b528-s60/selection-step1-60/step_000021/jsonls/online_control_selection.jsonlOther44.4 KB —
audits/mopd/q1p7b4g-mc-tl-m05c01-cstruct-8g6s2t-b528-s60/selection-step1-60/step_000022/jsonls/online_control_selection.jsonlOther43.6 KB —
audits/mopd/q1p7b4g-mc-tl-m05c01-cstruct-8g6s2t-b528-s60/selection-step1-60/step_000023/jsonls/online_control_selection.jsonlOther42.9 KB —
audits/mopd/q1p7b4g-mc-tl-m05c01-cstruct-8g6s2t-b528-s60/selection-step1-60/step_000024/jsonls/online_control_selection.jsonlOther44.7 KB —
audits/mopd/q1p7b4g-mc-tl-m05c01-cstruct-8g6s2t-b528-s60/selection-step1-60/step_000025/jsonls/online_control_selection.jsonlOther43.0 KB —
audits/mopd/q1p7b4g-mc-tl-m05c01-cstruct-8g6s2t-b528-s60/selection-step1-60/step_000026/jsonls/online_control_selection.jsonlOther42.7 KB —
audits/mopd/q1p7b4g-mc-tl-m05c01-cstruct-8g6s2t-b528-s60/selection-step1-60/step_000027/jsonls/online_control_selection.jsonlOther41.8 KB —
audits/mopd/q1p7b4g-mc-tl-m05c01-cstruct-8g6s2t-b528-s60/selection-step1-60/step_000028/jsonls/online_control_selection.jsonlOther41.8 KB —
audits/mopd/q1p7b4g-mc-tl-m05c01-cstruct-8g6s2t-b528-s60/selection-step1-60/step_000029/jsonls/online_control_selection.jsonlOther43.3 KB —
audits/mopd/q1p7b4g-mc-tl-m05c01-cstruct-8g6s2t-b528-s60/selection-step1-60/step_000030/jsonls/online_control_selection.jsonlOther44.4 KB —
audits/mopd/q1p7b4g-mc-tl-m05c01-cstruct-8g6s2t-b528-s60/selection-step1-60/step_000031/jsonls/online_control_selection.jsonlOther38.7 KB —
audits/mopd/q1p7b4g-mc-tl-m05c01-cstruct-8g6s2t-b528-s60/selection-step1-60/step_000032/jsonls/online_control_selection.jsonlOther42.1 KB —
audits/mopd/q1p7b4g-mc-tl-m05c01-cstruct-8g6s2t-b528-s60/selection-step1-60/step_000033/jsonls/online_control_selection.jsonlOther43.5 KB —
audits/mopd/q1p7b4g-mc-tl-m05c01-cstruct-8g6s2t-b528-s60/selection-step1-60/step_000034/jsonls/online_control_selection.jsonlOther42.5 KB —
audits/mopd/q1p7b4g-mc-tl-m05c01-cstruct-8g6s2t-b528-s60/selection-step1-60/step_000035/jsonls/online_control_selection.jsonlOther40.5 KB —
audits/mopd/q1p7b4g-mc-tl-m05c01-cstruct-8g6s2t-b528-s60/selection-step1-60/step_000036/jsonls/online_control_selection.jsonlOther45.5 KB —
audits/mopd/q1p7b4g-mc-tl-m05c01-cstruct-8g6s2t-b528-s60/selection-step1-60/step_000037/jsonls/online_control_selection.jsonlOther44.3 KB —
audits/mopd/q1p7b4g-mc-tl-m05c01-cstruct-8g6s2t-b528-s60/selection-step1-60/step_000038/jsonls/online_control_selection.jsonlOther42.0 KB —
audits/mopd/q1p7b4g-mc-tl-m05c01-cstruct-8g6s2t-b528-s60/selection-step1-60/step_000039/jsonls/online_control_selection.jsonlOther45.5 KB —
audits/mopd/q1p7b4g-mc-tl-m05c01-cstruct-8g6s2t-b528-s60/selection-step1-60/step_000040/jsonls/online_control_selection.jsonlOther45.2 KB —
audits/mopd/q1p7b4g-mc-tl-m05c01-cstruct-8g6s2t-b528-s60/selection-step1-60/step_000041/jsonls/online_control_selection.jsonlOther46.0 KB —
audits/mopd/q1p7b4g-mc-tl-m05c01-cstruct-8g6s2t-b528-s60/selection-step1-60/step_000042/jsonls/online_control_selection.jsonlOther41.0 KB —
audits/mopd/q1p7b4g-mc-tl-m05c01-cstruct-8g6s2t-b528-s60/selection-step1-60/step_000043/jsonls/online_control_selection.jsonlOther43.7 KB —
audits/mopd/q1p7b4g-mc-tl-m05c01-cstruct-8g6s2t-b528-s60/selection-step1-60/step_000044/jsonls/online_control_selection.jsonlOther41.8 KB —
audits/mopd/q1p7b4g-mc-tl-m05c01-cstruct-8g6s2t-b528-s60/selection-step1-60/step_000045/jsonls/online_control_selection.jsonlOther46.2 KB —
audits/mopd/q1p7b4g-mc-tl-m05c01-cstruct-8g6s2t-b528-s60/selection-step1-60/step_000046/jsonls/online_control_selection.jsonlOther45.6 KB —
audits/mopd/q1p7b4g-mc-tl-m05c01-cstruct-8g6s2t-b528-s60/selection-step1-60/step_000047/jsonls/online_control_selection.jsonlOther45.6 KB —
audits/mopd/q1p7b4g-mc-tl-m05c01-cstruct-8g6s2t-b528-s60/selection-step1-60/step_000048/jsonls/online_control_selection.jsonlOther45.4 KB —
audits/mopd/q1p7b4g-mc-tl-m05c01-cstruct-8g6s2t-b528-s60/selection-step1-60/step_000049/jsonls/online_control_selection.jsonlOther44.7 KB —
audits/mopd/q1p7b4g-mc-tl-m05c01-cstruct-8g6s2t-b528-s60/selection-step1-60/step_000050/jsonls/online_control_selection.jsonlOther45.6 KB —
audits/mopd/q1p7b4g-mc-tl-m05c01-cstruct-8g6s2t-b528-s60/selection-step1-60/step_000051/jsonls/online_control_selection.jsonlOther49.3 KB —
audits/mopd/q1p7b4g-mc-tl-m05c01-cstruct-8g6s2t-b528-s60/selection-step1-60/step_000052/jsonls/online_control_selection.jsonlOther45.7 KB —
audits/mopd/q1p7b4g-mc-tl-m05c01-cstruct-8g6s2t-b528-s60/selection-step1-60/step_000053/jsonls/online_control_selection.jsonlOther49.1 KB —
audits/mopd/q1p7b4g-mc-tl-m05c01-cstruct-8g6s2t-b528-s60/selection-step1-60/step_000054/jsonls/online_control_selection.jsonlOther42.8 KB —
audits/mopd/q1p7b4g-mc-tl-m05c01-cstruct-8g6s2t-b528-s60/selection-step1-60/step_000055/jsonls/online_control_selection.jsonlOther46.6 KB —
audits/mopd/q1p7b4g-mc-tl-m05c01-cstruct-8g6s2t-b528-s60/selection-step1-60/step_000056/jsonls/online_control_selection.jsonlOther46.7 KB —
audits/mopd/q1p7b4g-mc-tl-m05c01-cstruct-8g6s2t-b528-s60/selection-step1-60/step_000057/jsonls/online_control_selection.jsonlOther46.7 KB —
audits/mopd/q1p7b4g-mc-tl-m05c01-cstruct-8g6s2t-b528-s60/selection-step1-60/step_000058/jsonls/online_control_selection.jsonlOther48.1 KB —
audits/mopd/q1p7b4g-mc-tl-m05c01-cstruct-8g6s2t-b528-s60/selection-step1-60/step_000059/jsonls/online_control_selection.jsonlOther49.0 KB —
audits/mopd/q1p7b4g-mc-tl-m05c01-cstruct-8g6s2t-b528-s60/selection-step1-60/step_000060/jsonls/online_control_selection.jsonlOther49.6 KB —
checkpoints/global_step_60/chat_template.jinjaOther4.2 KB —
checkpoints/math/q1p7b-4g-math-fullvocab-toploss-topp05-fixed4-b256-colocated-s60/global_step_60/chat_template.jinjaOther4.2 KB —
checkpoints/math/q1p7b-math-a-ns-expanded-v2-i1w1k29-5gpu-b256/global_step_55/chat_template.jinjaOther4.2 KB —
checkpoints/math/q1p7b-math-a-ns-expanded-v2-i1w1k29-5gpu-b256/global_step_60/chat_template.jinjaOther4.2 KB —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-split-i1w1k21pt-b255/global_step_55/chat_template.jinjaOther4.2 KB —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-split-i1w1k21pt-b255/global_step_60/chat_template.jinjaOther4.2 KB —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-split-i1w1k21pt-b255/global_step_65/chat_template.jinjaOther4.2 KB —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-split-i1w1k21pt-b255/global_step_70/chat_template.jinjaOther4.2 KB —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-split-topp0p05-i1w1-4gpu-3a1t-b255-r20260911/global_step_55/chat_template.jinjaOther4.2 KB —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-split-topp0p05-i1w1-4gpu-3a1t-b255-r20260911/global_step_60/chat_template.jinjaOther4.2 KB —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-split-topp0p05-i1w1-4gpu-3a1t-b255-r20260911/global_step_65/chat_template.jinjaOther4.2 KB —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p01-i1w1-5gpu-3a2t-b258-resume15/global_step_55/chat_template.jinjaOther4.2 KB —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p01-i1w1-5gpu-3a2t-b258-resume15/global_step_60/chat_template.jinjaOther4.2 KB —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p01-i1w1-5gpu-3a2t-b258-resume15/global_step_65/chat_template.jinjaOther4.2 KB —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p01-i1w1-5gpu-3a2t-b258-resume15/global_step_70/chat_template.jinjaOther4.2 KB —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p05-i1w1-5gpu-b256/global_step_55/chat_template.jinjaOther4.2 KB —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p05-i1w1-5gpu-b256/global_step_60/chat_template.jinjaOther4.2 KB —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p05-i1w1-5gpu-b256/global_step_65/chat_template.jinjaOther4.2 KB —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p075-i1w1-5gpu-4a1t-b256/global_step_55/chat_template.jinjaOther4.2 KB —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p075-i1w1-5gpu-4a1t-b256/global_step_60/chat_template.jinjaOther4.2 KB —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p1-i1w1-5gpu-3a2t-b258/global_step_55/chat_template.jinjaOther4.2 KB —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p1-i1w1-5gpu-3a2t-b258/global_step_60/chat_template.jinjaOther4.2 KB —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p1-i1w1-5gpu-3a2t-b258/global_step_65/chat_template.jinjaOther4.2 KB —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p1-i1w1-5gpu-3a2t-b258/global_step_70/chat_template.jinjaOther4.2 KB —
checkpoints/math/q1p7b-math-top32kl-taxonomy-topp05-qsel-w4-5g4a1t-b256/global_step_55/chat_template.jinjaOther4.2 KB —
checkpoints/math/q1p7b-math-top32kl-taxonomy-topp05-qsel-w4-5g4a1t-b256/global_step_60/chat_template.jinjaOther4.2 KB —
checkpoints/math/q1p7b-math-top32kl-taxonomy-topp05-qsel-w4-5g4a1t-b256/global_step_65/chat_template.jinjaOther4.2 KB —
checkpoints/math/q1p7b-math-top32kl-taxonomy-topp05-qsel-w4-5g4a1t-b256/global_step_70/chat_template.jinjaOther4.2 KB —
checkpoints/math/q1p7b-math-top32kl-taxonomy-topp05-randsel-w4-4g3a1t-b255/global_step_55/chat_template.jinjaOther4.2 KB —
checkpoints/math/q1p7b-math-top32kl-taxonomy-topp05-randsel-w4-4g3a1t-b255/global_step_60/chat_template.jinjaOther4.2 KB —
checkpoints/math/q1p7b-math-top32kl-topp05-lossratio-5g4a1t-b256/global_step_55/chat_template.jinjaOther4.2 KB —
checkpoints/math/q1p7b-math-top32kl-topp05-lossratio-5g4a1t-b256/global_step_60/chat_template.jinjaOther4.2 KB —
checkpoints/math/q1p7b-math-top32kl-topp05-lossratio-5g4a1t-b256/global_step_65/chat_template.jinjaOther4.2 KB —
checkpoints/math/q1p7b-math-top32kl-topp05-lossratio-5g4a1t-b256/global_step_70/chat_template.jinjaOther4.2 KB —
checkpoints/math/q1p7b-math-top32kl-v3-topp1-w4-5g4a1t-b256/global_step_55/chat_template.jinjaOther4.2 KB —
checkpoints/math/q1p7b-math-top32kl-v3-topp1-w4-5g4a1t-b256/global_step_60/chat_template.jinjaOther4.2 KB —
checkpoints/math/q1p7b-taxonomy-q-topp05-fixed4-5g4a1t-b256-r20260908/global_step_55/chat_template.jinjaOther4.2 KB —
checkpoints/math/q1p7b-taxonomy-q-topp05-fixed4-5g4a1t-b256-r20260908/global_step_60/chat_template.jinjaOther4.2 KB —
checkpoints/math/q1p7b-taxonomy-q-topp05-fixed4-5g4a1t-b256-r20260908/global_step_65/chat_template.jinjaOther4.2 KB —
checkpoints/math/q1p7b-taxonomy-q-topp05-fixed4-5g4a1t-b256-r20260908/global_step_70/chat_template.jinjaOther4.2 KB —
checkpoints/math/q1p7b-taxonomy-toploss-topp05-fixed2-4g3a1t-b255/global_step_55/chat_template.jinjaOther4.2 KB —
checkpoints/math/q1p7b-taxonomy-toploss-topp05-fixed2-4g3a1t-b255/global_step_60/chat_template.jinjaOther4.2 KB —
checkpoints/math/q1p7b-taxonomy-toploss-topp05-fixed2-4g3a1t-b255/global_step_65/chat_template.jinjaOther4.2 KB —
checkpoints/math/q1p7b-taxonomy-toploss-topp05-fixed2-4g3a1t-b255/global_step_70/chat_template.jinjaOther4.2 KB —
checkpoints/math/q1p7b-taxonomy-toploss-topp05-fixed6-4g3a1t-b255-r20260909/global_step_55/chat_template.jinjaOther4.2 KB —
checkpoints/math/q1p7b-taxonomy-toploss-topp05-fixed6-4g3a1t-b255-r20260909/global_step_60/chat_template.jinjaOther4.2 KB —
checkpoints/math/q1p7b-taxonomy-toploss-topp05-fixed6-4g3a1t-b255-r20260909/global_step_65/chat_template.jinjaOther4.2 KB —
checkpoints/math/q1p7b-taxonomy-toploss-topp05-fixed6-4g3a1t-b255-r20260909/global_step_70/chat_template.jinjaOther4.2 KB —
checkpoints/math/q1p7b-v3-topp05-lossratio-i1w1-5g4a1t-b256-r20260907/global_step_55/chat_template.jinjaOther4.2 KB —
checkpoints/math/q1p7b-v3-topp05-lossratio-i1w1-5g4a1t-b256-r20260907/global_step_60/chat_template.jinjaOther4.2 KB —
checkpoints/math/q1p7b-v3-topp05-lossratio-i1w1-5g4a1t-b256-r20260907/global_step_65/chat_template.jinjaOther4.2 KB —
checkpoints/math/qwen1p7b-30b-math-eopd-4gpu-b255/global_step_50/actor/huggingface/chat_template.jinjaOther4.2 KB —
checkpoints/math/qwen1p7b-30b-math-eopd-4gpu-b255/global_step_55/actor/huggingface/chat_template.jinjaOther4.2 KB —
checkpoints/math/qwen1p7b-30b-math-eopd-4gpu-b255/global_step_60/actor/huggingface/chat_template.jinjaOther4.2 KB —
checkpoints/math/qwen1p7b-30b-math-eopd-4gpu-b255/global_step_65/actor/huggingface/chat_template.jinjaOther4.2 KB —
checkpoints/math/qwen1p7b-30b-math-exopd-lambda1p25-4gpu-b255/global_step_55/actor/huggingface/chat_template.jinjaOther4.2 KB —
checkpoints/math/qwen1p7b-30b-math-exopd-lambda1p25-4gpu-b255/global_step_60/actor/huggingface/chat_template.jinjaOther4.2 KB —
checkpoints/math/qwen1p7b-30b-math-exopd-lambda1p25-4gpu-b255/global_step_65/actor/huggingface/chat_template.jinjaOther4.2 KB —
checkpoints/math/qwen1p7b-30b-math-exopd-lambda1p25-4gpu-b255/global_step_70/actor/huggingface/chat_template.jinjaOther4.2 KB —
checkpoints/math/qwen1p7b-30b-math-fire-opd-4gpu-b255/global_step_55/actor/huggingface/chat_template.jinjaOther4.2 KB —
checkpoints/math/qwen1p7b-30b-math-fire-opd-4gpu-b255/global_step_60/actor/huggingface/chat_template.jinjaOther4.2 KB —
checkpoints/math/qwen1p7b-30b-math-fire-opd-4gpu-b255/global_step_65/actor/huggingface/chat_template.jinjaOther4.2 KB —
checkpoints/math/qwen1p7b-30b-math-fire-opd-4gpu-b255/global_step_70/actor/huggingface/chat_template.jinjaOther4.2 KB —
checkpoints/math/qwen1p7b-30b-math-opd-4gpu-b255/global_step_50/actor/huggingface/chat_template.jinjaOther4.2 KB —
checkpoints/math/qwen1p7b-30b-math-opd-4gpu-b255/global_step_55/actor/huggingface/chat_template.jinjaOther4.2 KB —
checkpoints/math/qwen1p7b-30b-math-tip-topk32-rho50-4gpu-b255/global_step_55/actor/huggingface/chat_template.jinjaOther4.2 KB —
checkpoints/math/qwen1p7b-30b-math-tip-topk32-rho50-4gpu-b255/global_step_60/actor/huggingface/chat_template.jinjaOther4.2 KB —
checkpoints/math/qwen1p7b-30b-math-tip-topk32-rho50-4gpu-b255/global_step_65/actor/huggingface/chat_template.jinjaOther4.2 KB —
checkpoints/math/qwen1p7b-30b-math-tip-topk32-rho50-4gpu-b255/global_step_70/actor/huggingface/chat_template.jinjaOther4.2 KB —
checkpoints/mopd/q1p7b-4g-mcs-m05c01s01-stconf-cfkl-srkl-f4-b528-coloc-s60/global_step_60/chat_template.jinjaOther4.2 KB —
checkpoints/mopd/q1p7b-4g-mcs-mtl05-ctl01-sltc01-f4-b528-coloc-s60/global_step_60/chat_template.jinjaOther4.2 KB —
checkpoints/mopd/q1p7b-4g-mcs-mtl05-ctl01cs-stl01-f4-b528-coloc-s60/global_step_60/chat_template.jinjaOther4.2 KB —
checkpoints/mopd/q1p7b3s1t-mc-tl-m05c01-cstruct-disc33-f4-b528-s60/global_step_60/chat_template.jinjaOther4.2 KB —
checkpoints/mopd/q1p7b3s1t-mc-v6-cs-current-m05c01-f4-b528-s60/global_step_60/chat_template.jinjaOther4.2 KB —
checkpoints/mopd/q1p7b4g-mc-tl-m05c01-f4-b528-s60/global_step_60/chat_template.jinjaOther4.2 KB —
checkpoints/mopd/q1p7b4g-mc-tl-m05c02-cstruct-f4-b528-s60/global_step_60/chat_template.jinjaOther4.2 KB —
checkpoints/mopd/q1p7b4g-mc-v4-r3-cs-next-m05c01-f4-b528-s60/global_step_60/chat_template.jinjaOther4.2 KB —
.gitattributesRepository14.7 KB —
checkpoints/baselines/math_code/tip_topk32_rho50_8gpu_6s2t_b516/global_step_60/merges.txtTokenizer1.7 MB —
checkpoints/baselines/math_code/tip_topk32_rho50_8gpu_6s2t_b516/global_step_60/tokenizer.jsonTokenizer11.4 MB aeb13307a71a
checkpoints/baselines/math_code/tip_topk32_rho50_8gpu_6s2t_b516/global_step_60/tokenizer_config.jsonTokenizer9.7 KB —
checkpoints/baselines/math_code/tip_topk32_rho50_8gpu_6s2t_b516/global_step_60/vocab.jsonTokenizer2.8 MB —
checkpoints/baselines/math_code/topk32_uniform_8gpu_6s2t_b516/global_step_60/merges.txtTokenizer1.7 MB —
checkpoints/baselines/math_code/topk32_uniform_8gpu_6s2t_b516/global_step_60/tokenizer.jsonTokenizer11.4 MB aeb13307a71a
checkpoints/baselines/math_code/topk32_uniform_8gpu_6s2t_b516/global_step_60/tokenizer_config.jsonTokenizer9.7 KB —
checkpoints/baselines/math_code/topk32_uniform_8gpu_6s2t_b516/global_step_60/vocab.jsonTokenizer2.8 MB —
checkpoints/global_step_60/merges.txtTokenizer1.7 MB —
checkpoints/global_step_60/tokenizer.jsonTokenizer11.4 MB aeb13307a71a
checkpoints/global_step_60/tokenizer_config.jsonTokenizer5.4 KB —
checkpoints/global_step_60/vocab.jsonTokenizer2.8 MB —
checkpoints/math/q1p7b-4g-math-fullvocab-toploss-topp05-fixed4-b256-colocated-s60/global_step_60/merges.txtTokenizer1.7 MB —
checkpoints/math/q1p7b-4g-math-fullvocab-toploss-topp05-fixed4-b256-colocated-s60/global_step_60/tokenizer.jsonTokenizer11.4 MB aeb13307a71a
checkpoints/math/q1p7b-4g-math-fullvocab-toploss-topp05-fixed4-b256-colocated-s60/global_step_60/tokenizer_config.jsonTokenizer5.4 KB —
checkpoints/math/q1p7b-4g-math-fullvocab-toploss-topp05-fixed4-b256-colocated-s60/global_step_60/vocab.jsonTokenizer2.8 MB —
checkpoints/math/q1p7b-math-a-ns-expanded-v2-i1w1k29-5gpu-b256/global_step_55/merges.txtTokenizer1.7 MB —
checkpoints/math/q1p7b-math-a-ns-expanded-v2-i1w1k29-5gpu-b256/global_step_55/tokenizer.jsonTokenizer11.4 MB aeb13307a71a
checkpoints/math/q1p7b-math-a-ns-expanded-v2-i1w1k29-5gpu-b256/global_step_55/tokenizer_config.jsonTokenizer5.4 KB —
checkpoints/math/q1p7b-math-a-ns-expanded-v2-i1w1k29-5gpu-b256/global_step_55/vocab.jsonTokenizer2.8 MB —
checkpoints/math/q1p7b-math-a-ns-expanded-v2-i1w1k29-5gpu-b256/global_step_60/merges.txtTokenizer1.7 MB —
checkpoints/math/q1p7b-math-a-ns-expanded-v2-i1w1k29-5gpu-b256/global_step_60/tokenizer.jsonTokenizer11.4 MB aeb13307a71a
checkpoints/math/q1p7b-math-a-ns-expanded-v2-i1w1k29-5gpu-b256/global_step_60/tokenizer_config.jsonTokenizer5.4 KB —
checkpoints/math/q1p7b-math-a-ns-expanded-v2-i1w1k29-5gpu-b256/global_step_60/vocab.jsonTokenizer2.8 MB —
checkpoints/math/q1p7b-math-a-ns-v3-u-i1w1k25-8gpu_6a2t_b258/global_step_60/merges.txtTokenizer1.7 MB —
checkpoints/math/q1p7b-math-a-ns-v3-u-i1w1k25-8gpu_6a2t_b258/global_step_60/tokenizer.jsonTokenizer11.4 MB aeb13307a71a
checkpoints/math/q1p7b-math-a-ns-v3-u-i1w1k25-8gpu_6a2t_b258/global_step_60/tokenizer_config.jsonTokenizer9.8 KB —
checkpoints/math/q1p7b-math-a-ns-v3-u-i1w1k25-8gpu_6a2t_b258/global_step_60/vocab.jsonTokenizer2.8 MB —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-split-i1w1k21pt-b255/global_step_55/merges.txtTokenizer1.7 MB —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-split-i1w1k21pt-b255/global_step_55/tokenizer.jsonTokenizer11.4 MB aeb13307a71a
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-split-i1w1k21pt-b255/global_step_55/tokenizer_config.jsonTokenizer5.4 KB —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-split-i1w1k21pt-b255/global_step_55/vocab.jsonTokenizer2.8 MB —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-split-i1w1k21pt-b255/global_step_60/merges.txtTokenizer1.7 MB —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-split-i1w1k21pt-b255/global_step_60/tokenizer.jsonTokenizer11.4 MB aeb13307a71a
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-split-i1w1k21pt-b255/global_step_60/tokenizer_config.jsonTokenizer5.4 KB —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-split-i1w1k21pt-b255/global_step_60/vocab.jsonTokenizer2.8 MB —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-split-i1w1k21pt-b255/global_step_65/merges.txtTokenizer1.7 MB —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-split-i1w1k21pt-b255/global_step_65/tokenizer.jsonTokenizer11.4 MB aeb13307a71a
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-split-i1w1k21pt-b255/global_step_65/tokenizer_config.jsonTokenizer5.4 KB —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-split-i1w1k21pt-b255/global_step_65/vocab.jsonTokenizer2.8 MB —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-split-i1w1k21pt-b255/global_step_70/merges.txtTokenizer1.7 MB —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-split-i1w1k21pt-b255/global_step_70/tokenizer.jsonTokenizer11.4 MB aeb13307a71a
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-split-i1w1k21pt-b255/global_step_70/tokenizer_config.jsonTokenizer5.4 KB —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-split-i1w1k21pt-b255/global_step_70/vocab.jsonTokenizer2.8 MB —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-split-topp0p05-i1w1-4gpu-3a1t-b255-r20260911/global_step_55/merges.txtTokenizer1.7 MB —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-split-topp0p05-i1w1-4gpu-3a1t-b255-r20260911/global_step_55/tokenizer.jsonTokenizer11.4 MB aeb13307a71a
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-split-topp0p05-i1w1-4gpu-3a1t-b255-r20260911/global_step_55/tokenizer_config.jsonTokenizer5.4 KB —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-split-topp0p05-i1w1-4gpu-3a1t-b255-r20260911/global_step_55/vocab.jsonTokenizer2.8 MB —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-split-topp0p05-i1w1-4gpu-3a1t-b255-r20260911/global_step_60/merges.txtTokenizer1.7 MB —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-split-topp0p05-i1w1-4gpu-3a1t-b255-r20260911/global_step_60/tokenizer.jsonTokenizer11.4 MB aeb13307a71a
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-split-topp0p05-i1w1-4gpu-3a1t-b255-r20260911/global_step_60/tokenizer_config.jsonTokenizer5.4 KB —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-split-topp0p05-i1w1-4gpu-3a1t-b255-r20260911/global_step_60/vocab.jsonTokenizer2.8 MB —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-split-topp0p05-i1w1-4gpu-3a1t-b255-r20260911/global_step_65/merges.txtTokenizer1.7 MB —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-split-topp0p05-i1w1-4gpu-3a1t-b255-r20260911/global_step_65/tokenizer.jsonTokenizer11.4 MB aeb13307a71a
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-split-topp0p05-i1w1-4gpu-3a1t-b255-r20260911/global_step_65/tokenizer_config.jsonTokenizer5.4 KB —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-split-topp0p05-i1w1-4gpu-3a1t-b255-r20260911/global_step_65/vocab.jsonTokenizer2.8 MB —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p01-i1w1-5gpu-3a2t-b258-resume15/global_step_55/merges.txtTokenizer1.7 MB —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p01-i1w1-5gpu-3a2t-b258-resume15/global_step_55/tokenizer.jsonTokenizer11.4 MB aeb13307a71a
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p01-i1w1-5gpu-3a2t-b258-resume15/global_step_55/tokenizer_config.jsonTokenizer5.4 KB —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p01-i1w1-5gpu-3a2t-b258-resume15/global_step_55/vocab.jsonTokenizer2.8 MB —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p01-i1w1-5gpu-3a2t-b258-resume15/global_step_60/merges.txtTokenizer1.7 MB —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p01-i1w1-5gpu-3a2t-b258-resume15/global_step_60/tokenizer.jsonTokenizer11.4 MB aeb13307a71a
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p01-i1w1-5gpu-3a2t-b258-resume15/global_step_60/tokenizer_config.jsonTokenizer5.4 KB —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p01-i1w1-5gpu-3a2t-b258-resume15/global_step_60/vocab.jsonTokenizer2.8 MB —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p01-i1w1-5gpu-3a2t-b258-resume15/global_step_65/merges.txtTokenizer1.7 MB —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p01-i1w1-5gpu-3a2t-b258-resume15/global_step_65/tokenizer.jsonTokenizer11.4 MB aeb13307a71a
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p01-i1w1-5gpu-3a2t-b258-resume15/global_step_65/tokenizer_config.jsonTokenizer5.4 KB —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p01-i1w1-5gpu-3a2t-b258-resume15/global_step_65/vocab.jsonTokenizer2.8 MB —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p01-i1w1-5gpu-3a2t-b258-resume15/global_step_70/merges.txtTokenizer1.7 MB —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p01-i1w1-5gpu-3a2t-b258-resume15/global_step_70/tokenizer.jsonTokenizer11.4 MB aeb13307a71a
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p01-i1w1-5gpu-3a2t-b258-resume15/global_step_70/tokenizer_config.jsonTokenizer5.4 KB —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p01-i1w1-5gpu-3a2t-b258-resume15/global_step_70/vocab.jsonTokenizer2.8 MB —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p02-i1w1-8gpu-6a2t-b258/global_step_60/merges.txtTokenizer1.7 MB —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p02-i1w1-8gpu-6a2t-b258/global_step_60/tokenizer.jsonTokenizer11.4 MB aeb13307a71a
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p02-i1w1-8gpu-6a2t-b258/global_step_60/tokenizer_config.jsonTokenizer9.8 KB —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p02-i1w1-8gpu-6a2t-b258/global_step_60/vocab.jsonTokenizer2.8 MB —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p05-i1w1-5gpu-b256/global_step_55/merges.txtTokenizer1.7 MB —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p05-i1w1-5gpu-b256/global_step_55/tokenizer.jsonTokenizer11.4 MB aeb13307a71a
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p05-i1w1-5gpu-b256/global_step_55/tokenizer_config.jsonTokenizer5.4 KB —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p05-i1w1-5gpu-b256/global_step_55/vocab.jsonTokenizer2.8 MB —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p05-i1w1-5gpu-b256/global_step_60/merges.txtTokenizer1.7 MB —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p05-i1w1-5gpu-b256/global_step_60/tokenizer.jsonTokenizer11.4 MB aeb13307a71a
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p05-i1w1-5gpu-b256/global_step_60/tokenizer_config.jsonTokenizer5.4 KB —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p05-i1w1-5gpu-b256/global_step_60/vocab.jsonTokenizer2.8 MB —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p05-i1w1-5gpu-b256/global_step_65/merges.txtTokenizer1.7 MB —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p05-i1w1-5gpu-b256/global_step_65/tokenizer.jsonTokenizer11.4 MB aeb13307a71a
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p05-i1w1-5gpu-b256/global_step_65/tokenizer_config.jsonTokenizer5.4 KB —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p05-i1w1-5gpu-b256/global_step_65/vocab.jsonTokenizer2.8 MB —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p075-i1w1-5gpu-4a1t-b256/global_step_55/merges.txtTokenizer1.7 MB —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p075-i1w1-5gpu-4a1t-b256/global_step_55/tokenizer.jsonTokenizer11.4 MB aeb13307a71a
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p075-i1w1-5gpu-4a1t-b256/global_step_55/tokenizer_config.jsonTokenizer5.4 KB —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p075-i1w1-5gpu-4a1t-b256/global_step_55/vocab.jsonTokenizer2.8 MB —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p075-i1w1-5gpu-4a1t-b256/global_step_60/merges.txtTokenizer1.7 MB —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p075-i1w1-5gpu-4a1t-b256/global_step_60/tokenizer.jsonTokenizer11.4 MB aeb13307a71a
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p075-i1w1-5gpu-4a1t-b256/global_step_60/tokenizer_config.jsonTokenizer5.4 KB —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p075-i1w1-5gpu-4a1t-b256/global_step_60/vocab.jsonTokenizer2.8 MB —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p1-i1w1-5gpu-3a2t-b258/global_step_55/merges.txtTokenizer1.7 MB —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p1-i1w1-5gpu-3a2t-b258/global_step_55/tokenizer.jsonTokenizer11.4 MB aeb13307a71a
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p1-i1w1-5gpu-3a2t-b258/global_step_55/tokenizer_config.jsonTokenizer5.4 KB —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p1-i1w1-5gpu-3a2t-b258/global_step_55/vocab.jsonTokenizer2.8 MB —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p1-i1w1-5gpu-3a2t-b258/global_step_60/merges.txtTokenizer1.7 MB —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p1-i1w1-5gpu-3a2t-b258/global_step_60/tokenizer.jsonTokenizer11.4 MB aeb13307a71a
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p1-i1w1-5gpu-3a2t-b258/global_step_60/tokenizer_config.jsonTokenizer5.4 KB —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p1-i1w1-5gpu-3a2t-b258/global_step_60/vocab.jsonTokenizer2.8 MB —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p1-i1w1-5gpu-3a2t-b258/global_step_65/merges.txtTokenizer1.7 MB —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p1-i1w1-5gpu-3a2t-b258/global_step_65/tokenizer.jsonTokenizer11.4 MB aeb13307a71a
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p1-i1w1-5gpu-3a2t-b258/global_step_65/tokenizer_config.jsonTokenizer5.4 KB —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p1-i1w1-5gpu-3a2t-b258/global_step_65/vocab.jsonTokenizer2.8 MB —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p1-i1w1-5gpu-3a2t-b258/global_step_70/merges.txtTokenizer1.7 MB —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p1-i1w1-5gpu-3a2t-b258/global_step_70/tokenizer.jsonTokenizer11.4 MB aeb13307a71a
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p1-i1w1-5gpu-3a2t-b258/global_step_70/tokenizer_config.jsonTokenizer5.4 KB —
checkpoints/math/q1p7b-math-top32kl-ns-taxonomy-topp0p1-i1w1-5gpu-3a2t-b258/global_step_70/vocab.jsonTokenizer2.8 MB —
checkpoints/math/q1p7b-math-top32kl-taxonomy-topp05-qsel-w4-5g4a1t-b256/global_step_55/merges.txtTokenizer1.7 MB —
checkpoints/math/q1p7b-math-top32kl-taxonomy-topp05-qsel-w4-5g4a1t-b256/global_step_55/tokenizer.jsonTokenizer11.4 MB aeb13307a71a
checkpoints/math/q1p7b-math-top32kl-taxonomy-topp05-qsel-w4-5g4a1t-b256/global_step_55/tokenizer_config.jsonTokenizer5.4 KB —
checkpoints/math/q1p7b-math-top32kl-taxonomy-topp05-qsel-w4-5g4a1t-b256/global_step_55/vocab.jsonTokenizer2.8 MB —
checkpoints/math/q1p7b-math-top32kl-taxonomy-topp05-qsel-w4-5g4a1t-b256/global_step_60/merges.txtTokenizer1.7 MB —
checkpoints/math/q1p7b-math-top32kl-taxonomy-topp05-qsel-w4-5g4a1t-b256/global_step_60/tokenizer.jsonTokenizer11.4 MB aeb13307a71a
checkpoints/math/q1p7b-math-top32kl-taxonomy-topp05-qsel-w4-5g4a1t-b256/global_step_60/tokenizer_config.jsonTokenizer5.4 KB —
checkpoints/math/q1p7b-math-top32kl-taxonomy-topp05-qsel-w4-5g4a1t-b256/global_step_60/vocab.jsonTokenizer2.8 MB —
checkpoints/math/q1p7b-math-top32kl-taxonomy-topp05-qsel-w4-5g4a1t-b256/global_step_65/merges.txtTokenizer1.7 MB —
checkpoints/math/q1p7b-math-top32kl-taxonomy-topp05-qsel-w4-5g4a1t-b256/global_step_65/tokenizer.jsonTokenizer11.4 MB aeb13307a71a
checkpoints/math/q1p7b-math-top32kl-taxonomy-topp05-qsel-w4-5g4a1t-b256/global_step_65/tokenizer_config.jsonTokenizer5.4 KB —
checkpoints/math/q1p7b-math-top32kl-taxonomy-topp05-qsel-w4-5g4a1t-b256/global_step_65/vocab.jsonTokenizer2.8 MB —
checkpoints/math/q1p7b-math-top32kl-taxonomy-topp05-qsel-w4-5g4a1t-b256/global_step_70/merges.txtTokenizer1.7 MB —
checkpoints/math/q1p7b-math-top32kl-taxonomy-topp05-qsel-w4-5g4a1t-b256/global_step_70/tokenizer.jsonTokenizer11.4 MB aeb13307a71a
checkpoints/math/q1p7b-math-top32kl-taxonomy-topp05-qsel-w4-5g4a1t-b256/global_step_70/tokenizer_config.jsonTokenizer5.4 KB —
checkpoints/math/q1p7b-math-top32kl-taxonomy-topp05-qsel-w4-5g4a1t-b256/global_step_70/vocab.jsonTokenizer2.8 MB —
checkpoints/math/q1p7b-math-top32kl-taxonomy-topp05-randsel-w4-4g3a1t-b255/global_step_55/merges.txtTokenizer1.7 MB —
checkpoints/math/q1p7b-math-top32kl-taxonomy-topp05-randsel-w4-4g3a1t-b255/global_step_55/tokenizer.jsonTokenizer11.4 MB aeb13307a71a
checkpoints/math/q1p7b-math-top32kl-taxonomy-topp05-randsel-w4-4g3a1t-b255/global_step_55/tokenizer_config.jsonTokenizer5.4 KB —
checkpoints/math/q1p7b-math-top32kl-taxonomy-topp05-randsel-w4-4g3a1t-b255/global_step_55/vocab.jsonTokenizer2.8 MB —
checkpoints/math/q1p7b-math-top32kl-taxonomy-topp05-randsel-w4-4g3a1t-b255/global_step_60/merges.txtTokenizer1.7 MB —
checkpoints/math/q1p7b-math-top32kl-taxonomy-topp05-randsel-w4-4g3a1t-b255/global_step_60/tokenizer.jsonTokenizer11.4 MB aeb13307a71a
checkpoints/math/q1p7b-math-top32kl-taxonomy-topp05-randsel-w4-4g3a1t-b255/global_step_60/tokenizer_config.jsonTokenizer5.4 KB —
checkpoints/math/q1p7b-math-top32kl-taxonomy-topp05-randsel-w4-4g3a1t-b255/global_step_60/vocab.jsonTokenizer2.8 MB —
checkpoints/math/q1p7b-math-top32kl-topp05-lossratio-5g4a1t-b256/global_step_55/merges.txtTokenizer1.7 MB —
checkpoints/math/q1p7b-math-top32kl-topp05-lossratio-5g4a1t-b256/global_step_55/tokenizer.jsonTokenizer11.4 MB aeb13307a71a
checkpoints/math/q1p7b-math-top32kl-topp05-lossratio-5g4a1t-b256/global_step_55/tokenizer_config.jsonTokenizer5.4 KB —
checkpoints/math/q1p7b-math-top32kl-topp05-lossratio-5g4a1t-b256/global_step_55/vocab.jsonTokenizer2.8 MB —
checkpoints/math/q1p7b-math-top32kl-topp05-lossratio-5g4a1t-b256/global_step_60/merges.txtTokenizer1.7 MB —
checkpoints/math/q1p7b-math-top32kl-topp05-lossratio-5g4a1t-b256/global_step_60/tokenizer.jsonTokenizer11.4 MB aeb13307a71a
checkpoints/math/q1p7b-math-top32kl-topp05-lossratio-5g4a1t-b256/global_step_60/tokenizer_config.jsonTokenizer5.4 KB —
checkpoints/math/q1p7b-math-top32kl-topp05-lossratio-5g4a1t-b256/global_step_60/vocab.jsonTokenizer2.8 MB —
checkpoints/math/q1p7b-math-top32kl-topp05-lossratio-5g4a1t-b256/global_step_65/merges.txtTokenizer1.7 MB —
checkpoints/math/q1p7b-math-top32kl-topp05-lossratio-5g4a1t-b256/global_step_65/tokenizer.jsonTokenizer11.4 MB aeb13307a71a
checkpoints/math/q1p7b-math-top32kl-topp05-lossratio-5g4a1t-b256/global_step_65/tokenizer_config.jsonTokenizer5.4 KB —
checkpoints/math/q1p7b-math-top32kl-topp05-lossratio-5g4a1t-b256/global_step_65/vocab.jsonTokenizer2.8 MB —
checkpoints/math/q1p7b-math-top32kl-topp05-lossratio-5g4a1t-b256/global_step_70/merges.txtTokenizer1.7 MB —
checkpoints/math/q1p7b-math-top32kl-topp05-lossratio-5g4a1t-b256/global_step_70/tokenizer.jsonTokenizer11.4 MB aeb13307a71a
checkpoints/math/q1p7b-math-top32kl-topp05-lossratio-5g4a1t-b256/global_step_70/tokenizer_config.jsonTokenizer5.4 KB —
checkpoints/math/q1p7b-math-top32kl-topp05-lossratio-5g4a1t-b256/global_step_70/vocab.jsonTokenizer2.8 MB —
checkpoints/math/q1p7b-math-top32kl-topp05-lossratio-a1p75-8g6a2t-b258/global_step_60/merges.txtTokenizer1.7 MB —
checkpoints/math/q1p7b-math-top32kl-topp05-lossratio-a1p75-8g6a2t-b258/global_step_60/tokenizer.jsonTokenizer11.4 MB aeb13307a71a
checkpoints/math/q1p7b-math-top32kl-topp05-lossratio-a1p75-8g6a2t-b258/global_step_60/tokenizer_config.jsonTokenizer9.8 KB —
checkpoints/math/q1p7b-math-top32kl-topp05-lossratio-a1p75-8g6a2t-b258/global_step_60/vocab.jsonTokenizer2.8 MB —
checkpoints/math/q1p7b-math-top32kl-v3-topp075-w4-8g6a2t-b258/global_step_60/merges.txtTokenizer1.7 MB —
checkpoints/math/q1p7b-math-top32kl-v3-topp075-w4-8g6a2t-b258/global_step_60/tokenizer.jsonTokenizer11.4 MB aeb13307a71a
checkpoints/math/q1p7b-math-top32kl-v3-topp075-w4-8g6a2t-b258/global_step_60/tokenizer_config.jsonTokenizer9.8 KB —
checkpoints/math/q1p7b-math-top32kl-v3-topp075-w4-8g6a2t-b258/global_step_60/vocab.jsonTokenizer2.8 MB —
checkpoints/math/q1p7b-math-top32kl-v3-topp1-w4-5g4a1t-b256/global_step_55/merges.txtTokenizer1.7 MB —
checkpoints/math/q1p7b-math-top32kl-v3-topp1-w4-5g4a1t-b256/global_step_55/tokenizer.jsonTokenizer11.4 MB aeb13307a71a
checkpoints/math/q1p7b-math-top32kl-v3-topp1-w4-5g4a1t-b256/global_step_55/tokenizer_config.jsonTokenizer5.4 KB —
checkpoints/math/q1p7b-math-top32kl-v3-topp1-w4-5g4a1t-b256/global_step_55/vocab.jsonTokenizer2.8 MB —
checkpoints/math/q1p7b-math-top32kl-v3-topp1-w4-5g4a1t-b256/global_step_60/merges.txtTokenizer1.7 MB —
checkpoints/math/q1p7b-math-top32kl-v3-topp1-w4-5g4a1t-b256/global_step_60/tokenizer.jsonTokenizer11.4 MB aeb13307a71a
checkpoints/math/q1p7b-math-top32kl-v3-topp1-w4-5g4a1t-b256/global_step_60/tokenizer_config.jsonTokenizer5.4 KB —
checkpoints/math/q1p7b-math-top32kl-v3-topp1-w4-5g4a1t-b256/global_step_60/vocab.jsonTokenizer2.8 MB —
checkpoints/math/q1p7b-taxonomy-q-topp05-fixed4-5g4a1t-b256-r20260908/global_step_55/merges.txtTokenizer1.7 MB —
checkpoints/math/q1p7b-taxonomy-q-topp05-fixed4-5g4a1t-b256-r20260908/global_step_55/tokenizer.jsonTokenizer11.4 MB aeb13307a71a
checkpoints/math/q1p7b-taxonomy-q-topp05-fixed4-5g4a1t-b256-r20260908/global_step_55/tokenizer_config.jsonTokenizer5.4 KB —
checkpoints/math/q1p7b-taxonomy-q-topp05-fixed4-5g4a1t-b256-r20260908/global_step_55/vocab.jsonTokenizer2.8 MB —
checkpoints/math/q1p7b-taxonomy-q-topp05-fixed4-5g4a1t-b256-r20260908/global_step_60/merges.txtTokenizer1.7 MB —
checkpoints/math/q1p7b-taxonomy-q-topp05-fixed4-5g4a1t-b256-r20260908/global_step_60/tokenizer.jsonTokenizer11.4 MB aeb13307a71a
checkpoints/math/q1p7b-taxonomy-q-topp05-fixed4-5g4a1t-b256-r20260908/global_step_60/tokenizer_config.jsonTokenizer5.4 KB —
checkpoints/math/q1p7b-taxonomy-q-topp05-fixed4-5g4a1t-b256-r20260908/global_step_60/vocab.jsonTokenizer2.8 MB —
checkpoints/math/q1p7b-taxonomy-q-topp05-fixed4-5g4a1t-b256-r20260908/global_step_65/merges.txtTokenizer1.7 MB —
checkpoints/math/q1p7b-taxonomy-q-topp05-fixed4-5g4a1t-b256-r20260908/global_step_65/tokenizer.jsonTokenizer11.4 MB aeb13307a71a
checkpoints/math/q1p7b-taxonomy-q-topp05-fixed4-5g4a1t-b256-r20260908/global_step_65/tokenizer_config.jsonTokenizer5.4 KB —
checkpoints/math/q1p7b-taxonomy-q-topp05-fixed4-5g4a1t-b256-r20260908/global_step_65/vocab.jsonTokenizer2.8 MB —
checkpoints/math/q1p7b-taxonomy-q-topp05-fixed4-5g4a1t-b256-r20260908/global_step_70/merges.txtTokenizer1.7 MB —
checkpoints/math/q1p7b-taxonomy-q-topp05-fixed4-5g4a1t-b256-r20260908/global_step_70/tokenizer.jsonTokenizer11.4 MB aeb13307a71a
checkpoints/math/q1p7b-taxonomy-q-topp05-fixed4-5g4a1t-b256-r20260908/global_step_70/tokenizer_config.jsonTokenizer5.4 KB —
checkpoints/math/q1p7b-taxonomy-q-topp05-fixed4-5g4a1t-b256-r20260908/global_step_70/vocab.jsonTokenizer2.8 MB —
checkpoints/math/q1p7b-taxonomy-toploss-topp05-fixed2-4g3a1t-b255/global_step_55/merges.txtTokenizer1.7 MB —
checkpoints/math/q1p7b-taxonomy-toploss-topp05-fixed2-4g3a1t-b255/global_step_55/tokenizer.jsonTokenizer11.4 MB aeb13307a71a
checkpoints/math/q1p7b-taxonomy-toploss-topp05-fixed2-4g3a1t-b255/global_step_55/tokenizer_config.jsonTokenizer5.4 KB —
checkpoints/math/q1p7b-taxonomy-toploss-topp05-fixed2-4g3a1t-b255/global_step_55/vocab.jsonTokenizer2.8 MB —
checkpoints/math/q1p7b-taxonomy-toploss-topp05-fixed2-4g3a1t-b255/global_step_60/merges.txtTokenizer1.7 MB —
checkpoints/math/q1p7b-taxonomy-toploss-topp05-fixed2-4g3a1t-b255/global_step_60/tokenizer.jsonTokenizer11.4 MB aeb13307a71a
checkpoints/math/q1p7b-taxonomy-toploss-topp05-fixed2-4g3a1t-b255/global_step_60/tokenizer_config.jsonTokenizer5.4 KB —
checkpoints/math/q1p7b-taxonomy-toploss-topp05-fixed2-4g3a1t-b255/global_step_60/vocab.jsonTokenizer2.8 MB —
checkpoints/math/q1p7b-taxonomy-toploss-topp05-fixed2-4g3a1t-b255/global_step_65/merges.txtTokenizer1.7 MB —
checkpoints/math/q1p7b-taxonomy-toploss-topp05-fixed2-4g3a1t-b255/global_step_65/tokenizer.jsonTokenizer11.4 MB aeb13307a71a
checkpoints/math/q1p7b-taxonomy-toploss-topp05-fixed2-4g3a1t-b255/global_step_65/tokenizer_config.jsonTokenizer5.4 KB —
checkpoints/math/q1p7b-taxonomy-toploss-topp05-fixed2-4g3a1t-b255/global_step_65/vocab.jsonTokenizer2.8 MB —
checkpoints/math/q1p7b-taxonomy-toploss-topp05-fixed2-4g3a1t-b255/global_step_70/merges.txtTokenizer1.7 MB —
checkpoints/math/q1p7b-taxonomy-toploss-topp05-fixed2-4g3a1t-b255/global_step_70/tokenizer.jsonTokenizer11.4 MB aeb13307a71a
checkpoints/math/q1p7b-taxonomy-toploss-topp05-fixed2-4g3a1t-b255/global_step_70/tokenizer_config.jsonTokenizer5.4 KB —
checkpoints/math/q1p7b-taxonomy-toploss-topp05-fixed2-4g3a1t-b255/global_step_70/vocab.jsonTokenizer2.8 MB —
checkpoints/math/q1p7b-taxonomy-toploss-topp05-fixed6-4g3a1t-b255-r20260909/global_step_55/merges.txtTokenizer1.7 MB —
checkpoints/math/q1p7b-taxonomy-toploss-topp05-fixed6-4g3a1t-b255-r20260909/global_step_55/tokenizer.jsonTokenizer11.4 MB aeb13307a71a
checkpoints/math/q1p7b-taxonomy-toploss-topp05-fixed6-4g3a1t-b255-r20260909/global_step_55/tokenizer_config.jsonTokenizer5.4 KB —
checkpoints/math/q1p7b-taxonomy-toploss-topp05-fixed6-4g3a1t-b255-r20260909/global_step_55/vocab.jsonTokenizer2.8 MB —
checkpoints/math/q1p7b-taxonomy-toploss-topp05-fixed6-4g3a1t-b255-r20260909/global_step_60/merges.txtTokenizer1.7 MB —
checkpoints/math/q1p7b-taxonomy-toploss-topp05-fixed6-4g3a1t-b255-r20260909/global_step_60/tokenizer.jsonTokenizer11.4 MB aeb13307a71a
checkpoints/math/q1p7b-taxonomy-toploss-topp05-fixed6-4g3a1t-b255-r20260909/global_step_60/tokenizer_config.jsonTokenizer5.4 KB —
checkpoints/math/q1p7b-taxonomy-toploss-topp05-fixed6-4g3a1t-b255-r20260909/global_step_60/vocab.jsonTokenizer2.8 MB —
checkpoints/math/q1p7b-taxonomy-toploss-topp05-fixed6-4g3a1t-b255-r20260909/global_step_65/merges.txtTokenizer1.7 MB —
checkpoints/math/q1p7b-taxonomy-toploss-topp05-fixed6-4g3a1t-b255-r20260909/global_step_65/tokenizer.jsonTokenizer11.4 MB aeb13307a71a
checkpoints/math/q1p7b-taxonomy-toploss-topp05-fixed6-4g3a1t-b255-r20260909/global_step_65/tokenizer_config.jsonTokenizer5.4 KB —
checkpoints/math/q1p7b-taxonomy-toploss-topp05-fixed6-4g3a1t-b255-r20260909/global_step_65/vocab.jsonTokenizer2.8 MB —
checkpoints/math/q1p7b-taxonomy-toploss-topp05-fixed6-4g3a1t-b255-r20260909/global_step_70/merges.txtTokenizer1.7 MB —
checkpoints/math/q1p7b-taxonomy-toploss-topp05-fixed6-4g3a1t-b255-r20260909/global_step_70/tokenizer.jsonTokenizer11.4 MB aeb13307a71a
checkpoints/math/q1p7b-taxonomy-toploss-topp05-fixed6-4g3a1t-b255-r20260909/global_step_70/tokenizer_config.jsonTokenizer5.4 KB —
checkpoints/math/q1p7b-taxonomy-toploss-topp05-fixed6-4g3a1t-b255-r20260909/global_step_70/vocab.jsonTokenizer2.8 MB —
checkpoints/math/q1p7b-v3-topp05-lossratio-i1w1-5g4a1t-b256-r20260907/global_step_55/merges.txtTokenizer1.7 MB —
checkpoints/math/q1p7b-v3-topp05-lossratio-i1w1-5g4a1t-b256-r20260907/global_step_55/tokenizer.jsonTokenizer11.4 MB aeb13307a71a
checkpoints/math/q1p7b-v3-topp05-lossratio-i1w1-5g4a1t-b256-r20260907/global_step_55/tokenizer_config.jsonTokenizer5.4 KB —
checkpoints/math/q1p7b-v3-topp05-lossratio-i1w1-5g4a1t-b256-r20260907/global_step_55/vocab.jsonTokenizer2.8 MB —
checkpoints/math/q1p7b-v3-topp05-lossratio-i1w1-5g4a1t-b256-r20260907/global_step_60/merges.txtTokenizer1.7 MB —
checkpoints/math/q1p7b-v3-topp05-lossratio-i1w1-5g4a1t-b256-r20260907/global_step_60/tokenizer.jsonTokenizer11.4 MB aeb13307a71a
checkpoints/math/q1p7b-v3-topp05-lossratio-i1w1-5g4a1t-b256-r20260907/global_step_60/tokenizer_config.jsonTokenizer5.4 KB —
checkpoints/math/q1p7b-v3-topp05-lossratio-i1w1-5g4a1t-b256-r20260907/global_step_60/vocab.jsonTokenizer2.8 MB —
checkpoints/math/q1p7b-v3-topp05-lossratio-i1w1-5g4a1t-b256-r20260907/global_step_65/merges.txtTokenizer1.7 MB —
checkpoints/math/q1p7b-v3-topp05-lossratio-i1w1-5g4a1t-b256-r20260907/global_step_65/tokenizer.jsonTokenizer11.4 MB aeb13307a71a
checkpoints/math/q1p7b-v3-topp05-lossratio-i1w1-5g4a1t-b256-r20260907/global_step_65/tokenizer_config.jsonTokenizer5.4 KB —
checkpoints/math/q1p7b-v3-topp05-lossratio-i1w1-5g4a1t-b256-r20260907/global_step_65/vocab.jsonTokenizer2.8 MB —
checkpoints/math/qwen1p7b-30b-math-eopd-4gpu-b255/global_step_50/actor/huggingface/merges.txtTokenizer1.7 MB —
checkpoints/math/qwen1p7b-30b-math-eopd-4gpu-b255/global_step_50/actor/huggingface/tokenizer.jsonTokenizer11.4 MB aeb13307a71a
checkpoints/math/qwen1p7b-30b-math-eopd-4gpu-b255/global_step_50/actor/huggingface/tokenizer_config.jsonTokenizer5.4 KB —
checkpoints/math/qwen1p7b-30b-math-eopd-4gpu-b255/global_step_50/actor/huggingface/vocab.jsonTokenizer2.8 MB —
checkpoints/math/qwen1p7b-30b-math-eopd-4gpu-b255/global_step_55/actor/huggingface/merges.txtTokenizer1.7 MB —
checkpoints/math/qwen1p7b-30b-math-eopd-4gpu-b255/global_step_55/actor/huggingface/tokenizer.jsonTokenizer11.4 MB aeb13307a71a
checkpoints/math/qwen1p7b-30b-math-eopd-4gpu-b255/global_step_55/actor/huggingface/tokenizer_config.jsonTokenizer5.4 KB —
checkpoints/math/qwen1p7b-30b-math-eopd-4gpu-b255/global_step_55/actor/huggingface/vocab.jsonTokenizer2.8 MB —
checkpoints/math/qwen1p7b-30b-math-eopd-4gpu-b255/global_step_60/actor/huggingface/merges.txtTokenizer1.7 MB —
checkpoints/math/qwen1p7b-30b-math-eopd-4gpu-b255/global_step_60/actor/huggingface/tokenizer.jsonTokenizer11.4 MB aeb13307a71a
checkpoints/math/qwen1p7b-30b-math-eopd-4gpu-b255/global_step_60/actor/huggingface/tokenizer_config.jsonTokenizer5.4 KB —
checkpoints/math/qwen1p7b-30b-math-eopd-4gpu-b255/global_step_60/actor/huggingface/vocab.jsonTokenizer2.8 MB —
checkpoints/math/qwen1p7b-30b-math-eopd-4gpu-b255/global_step_65/actor/huggingface/merges.txtTokenizer1.7 MB —
checkpoints/math/qwen1p7b-30b-math-eopd-4gpu-b255/global_step_65/actor/huggingface/tokenizer.jsonTokenizer11.4 MB aeb13307a71a
checkpoints/math/qwen1p7b-30b-math-eopd-4gpu-b255/global_step_65/actor/huggingface/tokenizer_config.jsonTokenizer5.4 KB —
checkpoints/math/qwen1p7b-30b-math-eopd-4gpu-b255/global_step_65/actor/huggingface/vocab.jsonTokenizer2.8 MB —
checkpoints/math/qwen1p7b-30b-math-exopd-lambda1p25-4gpu-b255/global_step_55/actor/huggingface/merges.txtTokenizer1.7 MB —
checkpoints/math/qwen1p7b-30b-math-exopd-lambda1p25-4gpu-b255/global_step_55/actor/huggingface/tokenizer.jsonTokenizer11.4 MB aeb13307a71a
checkpoints/math/qwen1p7b-30b-math-exopd-lambda1p25-4gpu-b255/global_step_55/actor/huggingface/tokenizer_config.jsonTokenizer5.4 KB —
checkpoints/math/qwen1p7b-30b-math-exopd-lambda1p25-4gpu-b255/global_step_55/actor/huggingface/vocab.jsonTokenizer2.8 MB —
checkpoints/math/qwen1p7b-30b-math-exopd-lambda1p25-4gpu-b255/global_step_60/actor/huggingface/merges.txtTokenizer1.7 MB —
checkpoints/math/qwen1p7b-30b-math-exopd-lambda1p25-4gpu-b255/global_step_60/actor/huggingface/tokenizer.jsonTokenizer11.4 MB aeb13307a71a
checkpoints/math/qwen1p7b-30b-math-exopd-lambda1p25-4gpu-b255/global_step_60/actor/huggingface/tokenizer_config.jsonTokenizer5.4 KB —
checkpoints/math/qwen1p7b-30b-math-exopd-lambda1p25-4gpu-b255/global_step_60/actor/huggingface/vocab.jsonTokenizer2.8 MB —
checkpoints/math/qwen1p7b-30b-math-exopd-lambda1p25-4gpu-b255/global_step_65/actor/huggingface/merges.txtTokenizer1.7 MB —
checkpoints/math/qwen1p7b-30b-math-exopd-lambda1p25-4gpu-b255/global_step_65/actor/huggingface/tokenizer.jsonTokenizer11.4 MB aeb13307a71a
checkpoints/math/qwen1p7b-30b-math-exopd-lambda1p25-4gpu-b255/global_step_65/actor/huggingface/tokenizer_config.jsonTokenizer5.4 KB —
checkpoints/math/qwen1p7b-30b-math-exopd-lambda1p25-4gpu-b255/global_step_65/actor/huggingface/vocab.jsonTokenizer2.8 MB —
checkpoints/math/qwen1p7b-30b-math-exopd-lambda1p25-4gpu-b255/global_step_70/actor/huggingface/merges.txtTokenizer1.7 MB —
checkpoints/math/qwen1p7b-30b-math-exopd-lambda1p25-4gpu-b255/global_step_70/actor/huggingface/tokenizer.jsonTokenizer11.4 MB aeb13307a71a
checkpoints/math/qwen1p7b-30b-math-exopd-lambda1p25-4gpu-b255/global_step_70/actor/huggingface/tokenizer_config.jsonTokenizer5.4 KB —
checkpoints/math/qwen1p7b-30b-math-exopd-lambda1p25-4gpu-b255/global_step_70/actor/huggingface/vocab.jsonTokenizer2.8 MB —
checkpoints/math/qwen1p7b-30b-math-fire-opd-4gpu-b255/global_step_55/actor/huggingface/merges.txtTokenizer1.7 MB —
checkpoints/math/qwen1p7b-30b-math-fire-opd-4gpu-b255/global_step_55/actor/huggingface/tokenizer.jsonTokenizer11.4 MB aeb13307a71a
checkpoints/math/qwen1p7b-30b-math-fire-opd-4gpu-b255/global_step_55/actor/huggingface/tokenizer_config.jsonTokenizer5.4 KB —
checkpoints/math/qwen1p7b-30b-math-fire-opd-4gpu-b255/global_step_55/actor/huggingface/vocab.jsonTokenizer2.8 MB —
checkpoints/math/qwen1p7b-30b-math-fire-opd-4gpu-b255/global_step_60/actor/huggingface/merges.txtTokenizer1.7 MB —
checkpoints/math/qwen1p7b-30b-math-fire-opd-4gpu-b255/global_step_60/actor/huggingface/tokenizer.jsonTokenizer11.4 MB aeb13307a71a
checkpoints/math/qwen1p7b-30b-math-fire-opd-4gpu-b255/global_step_60/actor/huggingface/tokenizer_config.jsonTokenizer5.4 KB —
checkpoints/math/qwen1p7b-30b-math-fire-opd-4gpu-b255/global_step_60/actor/huggingface/vocab.jsonTokenizer2.8 MB —
checkpoints/math/qwen1p7b-30b-math-fire-opd-4gpu-b255/global_step_65/actor/huggingface/merges.txtTokenizer1.7 MB —
checkpoints/math/qwen1p7b-30b-math-fire-opd-4gpu-b255/global_step_65/actor/huggingface/tokenizer.jsonTokenizer11.4 MB aeb13307a71a
checkpoints/math/qwen1p7b-30b-math-fire-opd-4gpu-b255/global_step_65/actor/huggingface/tokenizer_config.jsonTokenizer5.4 KB —
checkpoints/math/qwen1p7b-30b-math-fire-opd-4gpu-b255/global_step_65/actor/huggingface/vocab.jsonTokenizer2.8 MB —
checkpoints/math/qwen1p7b-30b-math-fire-opd-4gpu-b255/global_step_70/actor/huggingface/merges.txtTokenizer1.7 MB —
checkpoints/math/qwen1p7b-30b-math-fire-opd-4gpu-b255/global_step_70/actor/huggingface/tokenizer.jsonTokenizer11.4 MB aeb13307a71a
checkpoints/math/qwen1p7b-30b-math-fire-opd-4gpu-b255/global_step_70/actor/huggingface/tokenizer_config.jsonTokenizer5.4 KB —
checkpoints/math/qwen1p7b-30b-math-fire-opd-4gpu-b255/global_step_70/actor/huggingface/vocab.jsonTokenizer2.8 MB —
checkpoints/math/qwen1p7b-30b-math-opd-4gpu-b255/global_step_50/actor/huggingface/merges.txtTokenizer1.7 MB —
checkpoints/math/qwen1p7b-30b-math-opd-4gpu-b255/global_step_50/actor/huggingface/tokenizer.jsonTokenizer11.4 MB aeb13307a71a
checkpoints/math/qwen1p7b-30b-math-opd-4gpu-b255/global_step_50/actor/huggingface/tokenizer_config.jsonTokenizer5.4 KB —
checkpoints/math/qwen1p7b-30b-math-opd-4gpu-b255/global_step_50/actor/huggingface/vocab.jsonTokenizer2.8 MB —
checkpoints/math/qwen1p7b-30b-math-opd-4gpu-b255/global_step_55/actor/huggingface/merges.txtTokenizer1.7 MB —
checkpoints/math/qwen1p7b-30b-math-opd-4gpu-b255/global_step_55/actor/huggingface/tokenizer.jsonTokenizer11.4 MB aeb13307a71a
checkpoints/math/qwen1p7b-30b-math-opd-4gpu-b255/global_step_55/actor/huggingface/tokenizer_config.jsonTokenizer5.4 KB —
checkpoints/math/qwen1p7b-30b-math-opd-4gpu-b255/global_step_55/actor/huggingface/vocab.jsonTokenizer2.8 MB —
checkpoints/math/qwen1p7b-30b-math-tip-topk32-rho50-4gpu-b255/global_step_55/actor/huggingface/merges.txtTokenizer1.7 MB —
checkpoints/math/qwen1p7b-30b-math-tip-topk32-rho50-4gpu-b255/global_step_55/actor/huggingface/tokenizer.jsonTokenizer11.4 MB aeb13307a71a
checkpoints/math/qwen1p7b-30b-math-tip-topk32-rho50-4gpu-b255/global_step_55/actor/huggingface/tokenizer_config.jsonTokenizer5.4 KB —
checkpoints/math/qwen1p7b-30b-math-tip-topk32-rho50-4gpu-b255/global_step_55/actor/huggingface/vocab.jsonTokenizer2.8 MB —
checkpoints/math/qwen1p7b-30b-math-tip-topk32-rho50-4gpu-b255/global_step_60/actor/huggingface/merges.txtTokenizer1.7 MB —
checkpoints/math/qwen1p7b-30b-math-tip-topk32-rho50-4gpu-b255/global_step_60/actor/huggingface/tokenizer.jsonTokenizer11.4 MB aeb13307a71a
checkpoints/math/qwen1p7b-30b-math-tip-topk32-rho50-4gpu-b255/global_step_60/actor/huggingface/tokenizer_config.jsonTokenizer5.4 KB —
checkpoints/math/qwen1p7b-30b-math-tip-topk32-rho50-4gpu-b255/global_step_60/actor/huggingface/vocab.jsonTokenizer2.8 MB —
checkpoints/math/qwen1p7b-30b-math-tip-topk32-rho50-4gpu-b255/global_step_65/actor/huggingface/merges.txtTokenizer1.7 MB —
checkpoints/math/qwen1p7b-30b-math-tip-topk32-rho50-4gpu-b255/global_step_65/actor/huggingface/tokenizer.jsonTokenizer11.4 MB aeb13307a71a
checkpoints/math/qwen1p7b-30b-math-tip-topk32-rho50-4gpu-b255/global_step_65/actor/huggingface/tokenizer_config.jsonTokenizer5.4 KB —
checkpoints/math/qwen1p7b-30b-math-tip-topk32-rho50-4gpu-b255/global_step_65/actor/huggingface/vocab.jsonTokenizer2.8 MB —
checkpoints/math/qwen1p7b-30b-math-tip-topk32-rho50-4gpu-b255/global_step_70/actor/huggingface/merges.txtTokenizer1.7 MB —
checkpoints/math/qwen1p7b-30b-math-tip-topk32-rho50-4gpu-b255/global_step_70/actor/huggingface/tokenizer.jsonTokenizer11.4 MB aeb13307a71a
checkpoints/math/qwen1p7b-30b-math-tip-topk32-rho50-4gpu-b255/global_step_70/actor/huggingface/tokenizer_config.jsonTokenizer5.4 KB —
checkpoints/math/qwen1p7b-30b-math-tip-topk32-rho50-4gpu-b255/global_step_70/actor/huggingface/vocab.jsonTokenizer2.8 MB —
checkpoints/mopd/q1p7b-4g-mcs-m05c01s01-stconf-cfkl-srkl-f4-b528-coloc-s60/global_step_60/merges.txtTokenizer1.7 MB —
checkpoints/mopd/q1p7b-4g-mcs-m05c01s01-stconf-cfkl-srkl-f4-b528-coloc-s60/global_step_60/tokenizer.jsonTokenizer11.4 MB aeb13307a71a
checkpoints/mopd/q1p7b-4g-mcs-m05c01s01-stconf-cfkl-srkl-f4-b528-coloc-s60/global_step_60/tokenizer_config.jsonTokenizer5.4 KB —
checkpoints/mopd/q1p7b-4g-mcs-m05c01s01-stconf-cfkl-srkl-f4-b528-coloc-s60/global_step_60/vocab.jsonTokenizer2.8 MB —
checkpoints/mopd/q1p7b-4g-mcs-mtl05-ctl01-sltc01-f4-b528-coloc-s60/global_step_60/merges.txtTokenizer1.7 MB —
checkpoints/mopd/q1p7b-4g-mcs-mtl05-ctl01-sltc01-f4-b528-coloc-s60/global_step_60/tokenizer.jsonTokenizer11.4 MB aeb13307a71a
checkpoints/mopd/q1p7b-4g-mcs-mtl05-ctl01-sltc01-f4-b528-coloc-s60/global_step_60/tokenizer_config.jsonTokenizer5.4 KB —
checkpoints/mopd/q1p7b-4g-mcs-mtl05-ctl01-sltc01-f4-b528-coloc-s60/global_step_60/vocab.jsonTokenizer2.8 MB —
checkpoints/mopd/q1p7b-4g-mcs-mtl05-ctl01cs-stl01-f4-b528-coloc-s60/global_step_60/merges.txtTokenizer1.7 MB —
checkpoints/mopd/q1p7b-4g-mcs-mtl05-ctl01cs-stl01-f4-b528-coloc-s60/global_step_60/tokenizer.jsonTokenizer11.4 MB aeb13307a71a
checkpoints/mopd/q1p7b-4g-mcs-mtl05-ctl01cs-stl01-f4-b528-coloc-s60/global_step_60/tokenizer_config.jsonTokenizer5.4 KB —
checkpoints/mopd/q1p7b-4g-mcs-mtl05-ctl01cs-stl01-f4-b528-coloc-s60/global_step_60/vocab.jsonTokenizer2.8 MB —
checkpoints/mopd/q1p7b-8g-mcs-m05c01s01-stloss-cfkl-srkl-f4-b528-s60/global_step_60/merges.txtTokenizer1.7 MB —
checkpoints/mopd/q1p7b-8g-mcs-m05c01s01-stloss-cfkl-srkl-f4-b528-s60/global_step_60/tokenizer.jsonTokenizer11.4 MB aeb13307a71a
checkpoints/mopd/q1p7b-8g-mcs-m05c01s01-stloss-cfkl-srkl-f4-b528-s60/global_step_60/tokenizer_config.jsonTokenizer9.8 KB —
checkpoints/mopd/q1p7b-8g-mcs-m05c01s01-stloss-cfkl-srkl-f4-b528-s60/global_step_60/vocab.jsonTokenizer2.8 MB —
checkpoints/mopd/q1p7b-8g-mcs-mtl05-ctl01cs-sltc01-f4-b528-s60/global_step_60/merges.txtTokenizer1.7 MB —
checkpoints/mopd/q1p7b-8g-mcs-mtl05-ctl01cs-sltc01-f4-b528-s60/global_step_60/tokenizer.jsonTokenizer11.4 MB aeb13307a71a
checkpoints/mopd/q1p7b-8g-mcs-mtl05-ctl01cs-sltc01-f4-b528-s60/global_step_60/tokenizer_config.jsonTokenizer9.7 KB —
checkpoints/mopd/q1p7b-8g-mcs-mtl05-ctl01cs-sltc01-f4-b528-s60/global_step_60/vocab.jsonTokenizer2.8 MB —
checkpoints/mopd/q1p7b-8g-mcs-mtl05-ctl02-sltc02-f4-b528-s60/global_step_60/merges.txtTokenizer1.7 MB —
checkpoints/mopd/q1p7b-8g-mcs-mtl05-ctl02-sltc02-f4-b528-s60/global_step_60/tokenizer.jsonTokenizer11.4 MB aeb13307a71a
checkpoints/mopd/q1p7b-8g-mcs-mtl05-ctl02-sltc02-f4-b528-s60/global_step_60/tokenizer_config.jsonTokenizer9.8 KB —
checkpoints/mopd/q1p7b-8g-mcs-mtl05-ctl02-sltc02-f4-b528-s60/global_step_60/vocab.jsonTokenizer2.8 MB —
checkpoints/mopd/q1p7b-8g-mcs-p05-toploss-cfkl-srkl-f4-b528-s60/global_step_60/merges.txtTokenizer1.7 MB —
checkpoints/mopd/q1p7b-8g-mcs-p05-toploss-cfkl-srkl-f4-b528-s60/global_step_60/tokenizer.jsonTokenizer11.4 MB aeb13307a71a
checkpoints/mopd/q1p7b-8g-mcs-p05-toploss-cfkl-srkl-f4-b528-s60/global_step_60/tokenizer_config.jsonTokenizer9.8 KB —
checkpoints/mopd/q1p7b-8g-mcs-p05-toploss-cfkl-srkl-f4-b528-s60/global_step_60/vocab.jsonTokenizer2.8 MB —
checkpoints/mopd/q1p7b-8g-mcs-taxonomy-toploss-topp05-fixed4-b528-s60/global_step_60/merges.txtTokenizer1.7 MB —
checkpoints/mopd/q1p7b-8g-mcs-taxonomy-toploss-topp05-fixed4-b528-s60/global_step_60/tokenizer.jsonTokenizer11.4 MB aeb13307a71a
checkpoints/mopd/q1p7b-8g-mcs-taxonomy-toploss-topp05-fixed4-b528-s60/global_step_60/tokenizer_config.jsonTokenizer9.8 KB —
checkpoints/mopd/q1p7b-8g-mcs-taxonomy-toploss-topp05-fixed4-b528-s60/global_step_60/vocab.jsonTokenizer2.8 MB —
checkpoints/mopd/q1p7b3s1t-mc-tl-m05c01-cstruct-disc33-f4-b528-s60/global_step_60/merges.txtTokenizer1.7 MB —
checkpoints/mopd/q1p7b3s1t-mc-tl-m05c01-cstruct-disc33-f4-b528-s60/global_step_60/tokenizer.jsonTokenizer11.4 MB aeb13307a71a
checkpoints/mopd/q1p7b3s1t-mc-tl-m05c01-cstruct-disc33-f4-b528-s60/global_step_60/tokenizer_config.jsonTokenizer5.4 KB —
checkpoints/mopd/q1p7b3s1t-mc-tl-m05c01-cstruct-disc33-f4-b528-s60/global_step_60/vocab.jsonTokenizer2.8 MB —
checkpoints/mopd/q1p7b3s1t-mc-v6-cs-current-m05c01-f4-b528-s60/global_step_60/merges.txtTokenizer1.7 MB —
checkpoints/mopd/q1p7b3s1t-mc-v6-cs-current-m05c01-f4-b528-s60/global_step_60/tokenizer.jsonTokenizer11.4 MB aeb13307a71a
checkpoints/mopd/q1p7b3s1t-mc-v6-cs-current-m05c01-f4-b528-s60/global_step_60/tokenizer_config.jsonTokenizer5.4 KB —
checkpoints/mopd/q1p7b3s1t-mc-v6-cs-current-m05c01-f4-b528-s60/global_step_60/vocab.jsonTokenizer2.8 MB —
checkpoints/mopd/q1p7b4g-mc-tl-m05c01-cstruct-8g6s2t-b528-s60/global_step_60/merges.txtTokenizer1.7 MB —
checkpoints/mopd/q1p7b4g-mc-tl-m05c01-cstruct-8g6s2t-b528-s60/global_step_60/tokenizer.jsonTokenizer11.4 MB aeb13307a71a
checkpoints/mopd/q1p7b4g-mc-tl-m05c01-cstruct-8g6s2t-b528-s60/global_step_60/tokenizer_config.jsonTokenizer9.8 KB —
checkpoints/mopd/q1p7b4g-mc-tl-m05c01-cstruct-8g6s2t-b528-s60/global_step_60/vocab.jsonTokenizer2.8 MB —
checkpoints/mopd/q1p7b4g-mc-tl-m05c01-f4-b528-s60/global_step_60/merges.txtTokenizer1.7 MB —
checkpoints/mopd/q1p7b4g-mc-tl-m05c01-f4-b528-s60/global_step_60/tokenizer.jsonTokenizer11.4 MB aeb13307a71a
checkpoints/mopd/q1p7b4g-mc-tl-m05c01-f4-b528-s60/global_step_60/tokenizer_config.jsonTokenizer5.4 KB —
checkpoints/mopd/q1p7b4g-mc-tl-m05c01-f4-b528-s60/global_step_60/vocab.jsonTokenizer2.8 MB —
checkpoints/mopd/q1p7b4g-mc-tl-m05c02-cstruct-8g6s2t-b528-s60/global_step_60/merges.txtTokenizer1.7 MB —
checkpoints/mopd/q1p7b4g-mc-tl-m05c02-cstruct-8g6s2t-b528-s60/global_step_60/tokenizer.jsonTokenizer11.4 MB aeb13307a71a
checkpoints/mopd/q1p7b4g-mc-tl-m05c02-cstruct-8g6s2t-b528-s60/global_step_60/tokenizer_config.jsonTokenizer9.8 KB —
checkpoints/mopd/q1p7b4g-mc-tl-m05c02-cstruct-8g6s2t-b528-s60/global_step_60/vocab.jsonTokenizer2.8 MB —
checkpoints/mopd/q1p7b4g-mc-tl-m05c02-cstruct-f4-b528-s60/global_step_60/merges.txtTokenizer1.7 MB —
checkpoints/mopd/q1p7b4g-mc-tl-m05c02-cstruct-f4-b528-s60/global_step_60/tokenizer.jsonTokenizer11.4 MB aeb13307a71a
checkpoints/mopd/q1p7b4g-mc-tl-m05c02-cstruct-f4-b528-s60/global_step_60/tokenizer_config.jsonTokenizer5.4 KB —
checkpoints/mopd/q1p7b4g-mc-tl-m05c02-cstruct-f4-b528-s60/global_step_60/vocab.jsonTokenizer2.8 MB —
checkpoints/mopd/q1p7b4g-mc-tl-m05c05-8g6s2t-b528-s60/global_step_60/merges.txtTokenizer1.7 MB —
checkpoints/mopd/q1p7b4g-mc-tl-m05c05-8g6s2t-b528-s60/global_step_60/tokenizer.jsonTokenizer11.4 MB aeb13307a71a
checkpoints/mopd/q1p7b4g-mc-tl-m05c05-8g6s2t-b528-s60/global_step_60/tokenizer_config.jsonTokenizer9.8 KB —
checkpoints/mopd/q1p7b4g-mc-tl-m05c05-8g6s2t-b528-s60/global_step_60/vocab.jsonTokenizer2.8 MB —
checkpoints/mopd/q1p7b4g-mc-tl-m05c05-cstruct-8g6s2t-b528-s60/global_step_60/merges.txtTokenizer1.7 MB —
checkpoints/mopd/q1p7b4g-mc-tl-m05c05-cstruct-8g6s2t-b528-s60/global_step_60/tokenizer.jsonTokenizer11.4 MB aeb13307a71a
checkpoints/mopd/q1p7b4g-mc-tl-m05c05-cstruct-8g6s2t-b528-s60/global_step_60/tokenizer_config.jsonTokenizer9.8 KB —
checkpoints/mopd/q1p7b4g-mc-tl-m05c05-cstruct-8g6s2t-b528-s60/global_step_60/vocab.jsonTokenizer2.8 MB —
checkpoints/mopd/q1p7b4g-mc-v4-r3-cs-next-m05c01-f4-b528-s60/global_step_60/merges.txtTokenizer1.7 MB —
checkpoints/mopd/q1p7b4g-mc-v4-r3-cs-next-m05c01-f4-b528-s60/global_step_60/tokenizer.jsonTokenizer11.4 MB aeb13307a71a
checkpoints/mopd/q1p7b4g-mc-v4-r3-cs-next-m05c01-f4-b528-s60/global_step_60/tokenizer_config.jsonTokenizer5.4 KB —
checkpoints/mopd/q1p7b4g-mc-v4-r3-cs-next-m05c01-f4-b528-s60/global_step_60/vocab.jsonTokenizer2.8 MB —
checkpoints/mopd/q1p7b8g-mc-legacy-cstruct-current-m05c01-f4-b528-s60-retry1/global_step_60/merges.txtTokenizer1.7 MB —
checkpoints/mopd/q1p7b8g-mc-legacy-cstruct-current-m05c01-f4-b528-s60-retry1/global_step_60/tokenizer.jsonTokenizer11.4 MB aeb13307a71a
checkpoints/mopd/q1p7b8g-mc-legacy-cstruct-current-m05c01-f4-b528-s60-retry1/global_step_60/tokenizer_config.jsonTokenizer9.7 KB —
checkpoints/mopd/q1p7b8g-mc-legacy-cstruct-current-m05c01-f4-b528-s60-retry1/global_step_60/vocab.jsonTokenizer2.8 MB —
checkpoints/mopd/q1p7b8g-mc-v5-r3-cs-next-m05c01-f4-b528-s60/global_step_60/merges.txtTokenizer1.7 MB —
checkpoints/mopd/q1p7b8g-mc-v5-r3-cs-next-m05c01-f4-b528-s60/global_step_60/tokenizer.jsonTokenizer11.4 MB aeb13307a71a
checkpoints/mopd/q1p7b8g-mc-v5-r3-cs-next-m05c01-f4-b528-s60/global_step_60/tokenizer_config.jsonTokenizer9.7 KB —
checkpoints/mopd/q1p7b8g-mc-v5-r3-cs-next-m05c01-f4-b528-s60/global_step_60/vocab.jsonTokenizer2.8 MB —
checkpoints/mopd/q1p7b8g-mc-v7-cs-current-m05c01-f4-6s2t-b528-s60/global_step_60/merges.txtTokenizer1.7 MB —
checkpoints/mopd/q1p7b8g-mc-v7-cs-current-m05c01-f4-6s2t-b528-s60/global_step_60/tokenizer.jsonTokenizer11.4 MB aeb13307a71a
checkpoints/mopd/q1p7b8g-mc-v7-cs-current-m05c01-f4-6s2t-b528-s60/global_step_60/tokenizer_config.jsonTokenizer9.8 KB —
checkpoints/mopd/q1p7b8g-mc-v7-cs-current-m05c01-f4-6s2t-b528-s60/global_step_60/vocab.jsonTokenizer2.8 MB —
checkpoints/mopd/q1p7b8g-mc-v8-cs-current-m05c01-f4-6s2t-b528-s60/global_step_60/merges.txtTokenizer1.7 MB —
checkpoints/mopd/q1p7b8g-mc-v8-cs-current-m05c01-f4-6s2t-b528-s60/global_step_60/tokenizer.jsonTokenizer11.4 MB aeb13307a71a
checkpoints/mopd/q1p7b8g-mc-v8-cs-current-m05c01-f4-6s2t-b528-s60/global_step_60/tokenizer_config.jsonTokenizer9.7 KB —
checkpoints/mopd/q1p7b8g-mc-v8-cs-current-m05c01-f4-6s2t-b528-s60/global_step_60/vocab.jsonTokenizer2.8 MB —
checkpoints/mopd/qwen1p7b-30b-eopd-native-8gpu-b528-teacher50-final/global_step_60/merges.txtTokenizer1.7 MB —
checkpoints/mopd/qwen1p7b-30b-eopd-native-8gpu-b528-teacher50-final/global_step_60/tokenizer.jsonTokenizer11.4 MB aeb13307a71a
checkpoints/mopd/qwen1p7b-30b-eopd-native-8gpu-b528-teacher50-final/global_step_60/tokenizer_config.jsonTokenizer9.8 KB —
checkpoints/mopd/qwen1p7b-30b-eopd-native-8gpu-b528-teacher50-final/global_step_60/vocab.jsonTokenizer2.8 MB —

License and Download

License
Not stated by the source
Access
Open weights, no gate
Download size
977.1 GB
Download from LINGHUA ZHANG

Released by LINGHUA ZHANG through its official repository on Hugging Face.

Memory Requirements

PrecisionWeights in memory
As published977.1 GB

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