Skip to page content
SAVRN
Search Plan a project

Open-weight model

tmp-all

by Shirley Shirleyzhao/tmp-all

tmp-all is an open-weight model from Shirley. Its published files total 2.0 TB.

Parameters—
Context—
Weights1.9 TB
License—
AccessOpen weights
Monthly Downloads—

Model Card

The publisher has not written a card for this model.

Identity and Version

Repository
Shirleyzhao/tmp-all
Publisher
Shirley
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
e5f83223c100841565f579ac84a26bf98a6aa334
First published
2026-10-09
Last updated
2026-10-10

Files and Weights

4,187 files, 2.0 TB in total. The weights are 410 files totalling 1.9 TB in pt, safetensors.

Weights410 files · 1.9 TB
Configuration2335 files · 41.1 MB
Documentation140 files · 1.4 MB
Other115 files · 62.0 MB
Every file (first 3,000)
FileTypeSizeSHA-256
code_public/_hf_release/HybridAgent-14B-Agentic/adapter.ptWeights104.9 MB 635118c97907
code_public/_hf_release/HybridAgent-14B-Agentic/model.safetensorsWeights29.5 GB 478cc3a0855e
code_public/_hf_release/HybridAgent-8B-Agentic/adapter.ptWeights67.2 MB e5e91f8c61e6
code_public/_hf_release/HybridAgent-8B-Agentic/model.safetensorsWeights16.4 GB 2de074d380f4
code_public/_smoke/hf_cache/hub/models--Elphan--tmp-all/snapshots/66afffed09178e66821d195d1a8b06a720328732/models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-120/adapter.ptWeights67.2 MB e5e91f8c61e6
code_public/_smoke/hf_cache/hub/models--Elphan--tmp-all/snapshots/66afffed09178e66821d195d1a8b06a720328732/models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-120/model.safetensorsWeights16.4 GB 2de074d380f4
code_public/_smoke/hf_cache/hub/models--Elphan--tmp-all/snapshots/66afffed09178e66821d195d1a8b06a720328732/models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-90/adapter.ptWeights104.9 MB 635118c97907
code_public/_smoke/hf_cache/hub/models--Elphan--tmp-all/snapshots/66afffed09178e66821d195d1a8b06a720328732/models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-90/model.safetensorsWeights29.5 GB 478cc3a0855e
code_public/_smoke/hf_cache/hub/models--Qwen--Qwen3-0.6B-Base/snapshots/da87bfb608c14b7cf20ba1ce41287e8de496c0cd/model.safetensorsWeights1.2 GB cd2a512003e2
code_public/_smoke/out_rl/math/checkpoint-1/adapter.ptWeights67.2 MB 537e557b902f
code_public/_smoke/out_rl/math/checkpoint-1/model.safetensorsWeights16.4 GB 47662a4b50fa
code_public/_smoke/out_rl/math/checkpoint-2/adapter.ptWeights67.2 MB 537e557b902f
code_public/_smoke/out_rl/math/checkpoint-2/model.safetensorsWeights16.4 GB 8887ec3d5860
code_public/_smoke/out_rl/search/checkpoint-1/adapter.ptWeights67.2 MB 537e557b902f
code_public/_smoke/out_rl/search/checkpoint-1/model.safetensorsWeights16.4 GB 802dc3459c16
code_public/_smoke/out_rl/search/checkpoint-2/adapter.ptWeights67.2 MB 537e557b902f
code_public/_smoke/out_rl/search/checkpoint-2/model.safetensorsWeights16.4 GB 40ffc08cc7e2
code_public/_smoke/out_sft/format_activation/adapter.ptWeights4.2 MB a3ed2019d180
code_public/_smoke/out_sft/format_activation/checkpoint-10/adapter.ptWeights4.2 MB a3ed2019d180
code_public/_smoke/out_sft/format_activation/checkpoint-10/model.safetensorsWeights1.5 GB f97bd7541173
code_public/_smoke/out_sft/format_activation/checkpoint-5/adapter.ptWeights4.2 MB a3ed2019d180
code_public/_smoke/out_sft/format_activation/checkpoint-5/model.safetensorsWeights1.5 GB ecdd8c3579fc
code_public/_smoke/out_sft/format_activation/model.safetensorsWeights1.5 GB f97bd7541173
code_public/_smoke/out_sft/hybridlink_activation/adapter.ptWeights4.2 MB 7fcd76963ebc
code_public/_smoke/out_sft/hybridlink_activation/checkpoint-10/adapter.ptWeights4.2 MB 48c19c927e78
code_public/_smoke/out_sft/hybridlink_activation/checkpoint-10/model.safetensorsWeights1.5 GB f97bd7541173
code_public/_smoke/out_sft/hybridlink_activation/checkpoint-15/adapter.ptWeights4.2 MB 780480a917a9
code_public/_smoke/out_sft/hybridlink_activation/checkpoint-15/model.safetensorsWeights1.5 GB f97bd7541173
code_public/_smoke/out_sft/hybridlink_activation/checkpoint-20/adapter.ptWeights4.2 MB 7fcd76963ebc
code_public/_smoke/out_sft/hybridlink_activation/checkpoint-20/model.safetensorsWeights1.5 GB f97bd7541173
code_public/_smoke/out_sft/hybridlink_activation/checkpoint-5/adapter.ptWeights4.2 MB 08778779044b
code_public/_smoke/out_sft/hybridlink_activation/checkpoint-5/model.safetensorsWeights1.5 GB f97bd7541173
code_public/_smoke/out_sft/hybridlink_activation/model.safetensorsWeights1.5 GB f97bd7541173
code_public/_smoke/out_sft/self_conditioned/adapter.ptWeights4.2 MB e74c90fd13a4
code_public/_smoke/out_sft/self_conditioned/checkpoint-10/adapter.ptWeights4.2 MB 0b5633ece61a
code_public/_smoke/out_sft/self_conditioned/checkpoint-10/model.safetensorsWeights1.5 GB da8a2c29f621
code_public/_smoke/out_sft/self_conditioned/checkpoint-15/adapter.ptWeights4.2 MB 43e062be4c74
code_public/_smoke/out_sft/self_conditioned/checkpoint-15/model.safetensorsWeights1.5 GB 83d34310ad40
code_public/_smoke/out_sft/self_conditioned/checkpoint-20/adapter.ptWeights4.2 MB e74c90fd13a4
code_public/_smoke/out_sft/self_conditioned/checkpoint-20/model.safetensorsWeights1.5 GB 8a54893e0dfa
code_public/_smoke/out_sft/self_conditioned/checkpoint-5/adapter.ptWeights4.2 MB e119e694c811
code_public/_smoke/out_sft/self_conditioned/checkpoint-5/model.safetensorsWeights1.5 GB 49b8af022410
code_public/_smoke/out_sft/self_conditioned/model.safetensorsWeights1.5 GB 8a54893e0dfa
code_public/_smoke/out_sft_offload/self_conditioned/adapter.ptWeights4.2 MB e97104f12d44
code_public/_smoke/out_sft_offload/self_conditioned/checkpoint-10/adapter.ptWeights4.2 MB 3611cc6b23e4
code_public/_smoke/out_sft_offload/self_conditioned/checkpoint-10/model.safetensorsWeights1.5 GB fec3c9eb458d
code_public/_smoke/out_sft_offload/self_conditioned/checkpoint-15/adapter.ptWeights4.2 MB 2a34d36b2bb2
code_public/_smoke/out_sft_offload/self_conditioned/checkpoint-15/model.safetensorsWeights1.5 GB ca63e9b41c97
code_public/_smoke/out_sft_offload/self_conditioned/checkpoint-20/adapter.ptWeights4.2 MB e97104f12d44
code_public/_smoke/out_sft_offload/self_conditioned/checkpoint-20/model.safetensorsWeights1.5 GB a480208727d8
code_public/_smoke/out_sft_offload/self_conditioned/checkpoint-5/adapter.ptWeights4.2 MB 8e436684b313
code_public/_smoke/out_sft_offload/self_conditioned/checkpoint-5/model.safetensorsWeights1.5 GB 1b5f480047cd
code_public/_smoke/out_sft_offload/self_conditioned/model.safetensorsWeights1.5 GB a480208727d8
models/rl_new_v2/run12_qwen3b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-140/adapter.ptWeights52.5 MB a5ebd0c9ddf1
models/rl_new_v2/run12_qwen3b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-140/model.safetensorsWeights16.1 GB c3da439eb164
models/rl_new_v2/run12_qwen3b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-140/trainer_state/rank_000.ptWeights3.1 GB e2c241eb0114
models/rl_new_v2/run12_qwen3b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-140/trainer_state/rank_001.ptWeights943.7 MB ef51cf2c9233
models/rl_new_v2/run12_qwen3b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-140/trainer_state/rank_002.ptWeights943.7 MB a56eee88d2fb
models/rl_new_v2/run12_qwen3b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-140/trainer_state/rank_003.ptWeights943.7 MB eb7e82e46acb
models/rl_new_v2/run12_qwen3b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-140/trainer_state/rank_004.ptWeights943.7 MB 4b5b0d806065
models/rl_new_v2/run12_qwen3b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-140/trainer_state/rank_005.ptWeights943.7 MB 10dcbf545959
models/rl_new_v2/run12_qwen3b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-140/trainer_state/rank_006.ptWeights943.7 MB 5115a1c4206a
models/rl_new_v2/run12_qwen3b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-140/trainer_state/rank_007.ptWeights943.7 MB 628efeeef5ce
models/rl_new_v2/run12_qwen3b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-140/trainer_state/rank_008.ptWeights943.7 MB 5e9f4d0826be
models/rl_new_v2/run12_qwen3b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-140/trainer_state/rank_009.ptWeights943.7 MB 028650314677
models/rl_new_v2/run12_qwen3b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-140/trainer_state/rank_010.ptWeights943.7 MB 9c1dee865a35
models/rl_new_v2/run12_qwen3b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-140/trainer_state/rank_011.ptWeights943.7 MB 05549be5498b
models/rl_new_v2/run12_qwen3b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-140/trainer_state/rank_012.ptWeights943.7 MB 1f170298b67e
models/rl_new_v2/run12_qwen3b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-140/trainer_state/rank_013.ptWeights943.7 MB 1c68f0d77718
models/rl_new_v2/run12_qwen3b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-140/trainer_state/rank_014.ptWeights943.7 MB c25048413b8b
models/rl_new_v2/run12_qwen3b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-140/trainer_state/rank_015.ptWeights924.4 MB a6ca9aacca9f
models/rl_new_v2/run12_qwen3b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-140/trainer_state/rank_016.ptWeights933.3 MB 2a7d596a9d89
models/rl_new_v2/run12_qwen3b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-140/trainer_state/rank_017.ptWeights933.3 MB c09f33aba363
models/rl_new_v2/run12_qwen3b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-140/trainer_state/rank_018.ptWeights933.3 MB 6fee1d4f86bd
models/rl_new_v2/run12_qwen3b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-140/trainer_state/rank_019.ptWeights933.3 MB 344f3a5609d0
models/rl_new_v2/run12_qwen3b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-140/trainer_state/rank_020.ptWeights933.3 MB e4bae5a5cce9
models/rl_new_v2/run12_qwen3b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-140/trainer_state/rank_021.ptWeights933.3 MB 0e5a4476d889
models/rl_new_v2/run12_qwen3b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-140/trainer_state/rank_022.ptWeights933.3 MB 1bcdc60918dc
models/rl_new_v2/run12_qwen3b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-140/trainer_state/rank_023.ptWeights933.3 MB e717f001eb05
models/rl_new_v2/run12_qwen3b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-140/trainer_state/rank_024.ptWeights933.3 MB a95fb4030a09
models/rl_new_v2/run12_qwen3b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-140/trainer_state/rank_025.ptWeights933.3 MB 73bdc480e1c8
models/rl_new_v2/run12_qwen3b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-140/trainer_state/rank_026.ptWeights933.3 MB 21d35a89eb90
models/rl_new_v2/run12_qwen3b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-140/trainer_state/rank_027.ptWeights933.3 MB 861a9b5852c8
models/rl_new_v2/run12_qwen3b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-140/trainer_state/rank_028.ptWeights933.3 MB 1a386ec09c10
models/rl_new_v2/run12_qwen3b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-140/trainer_state/rank_029.ptWeights933.3 MB aba1807a5ad3
models/rl_new_v2/run12_qwen3b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-140/trainer_state/rank_030.ptWeights933.3 MB b03446716693
models/rl_new_v2/run12_qwen3b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-140/trainer_state/rank_031.ptWeights933.3 MB 6835df963193
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-110/adapter.ptWeights67.2 MB e5e91f8c61e6
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-110/model.safetensorsWeights16.4 GB d822e66def43
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-140/adapter.ptWeights67.2 MB e5e91f8c61e6
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-140/model.safetensorsWeights16.4 GB 6564909319eb
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-150/adapter.ptWeights67.2 MB e5e91f8c61e6
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-150/model.safetensorsWeights16.4 GB 0529e408e65d
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-160/adapter.ptWeights67.2 MB e5e91f8c61e6
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-160/model.safetensorsWeights16.4 GB b73bdfdf0889
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-170/adapter.ptWeights67.2 MB e5e91f8c61e6
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-170/model.safetensorsWeights16.4 GB 84b59ba1674b
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-180/adapter.ptWeights67.2 MB e5e91f8c61e6
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-180/model.safetensorsWeights16.4 GB a23e34117c02
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-180/trainer_state/rank_000.ptWeights7.5 GB 921e26d8f6e3
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-180/trainer_state/rank_001.ptWeights7.5 GB 5c1a18e29e13
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-180/trainer_state/rank_002.ptWeights2.8 GB b77f5633d3ff
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-180/trainer_state/rank_003.ptWeights2.8 GB 4e789653b4e8
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-180/trainer_state/rank_004.ptWeights2.8 GB 85c3e7ae6695
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-180/trainer_state/rank_005.ptWeights2.8 GB 65796cd3baad
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-180/trainer_state/rank_006.ptWeights2.8 GB 5f60d3f5e813
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-180/trainer_state/rank_007.ptWeights2.8 GB 9e2a8cfdcba2
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-180/trainer_state/rank_008.ptWeights2.8 GB bad39a77a5a3
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-180/trainer_state/rank_009.ptWeights2.8 GB 9413405cd31a
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-180/trainer_state/rank_010.ptWeights2.8 GB 81b76995e1e5
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-180/trainer_state/rank_011.ptWeights2.8 GB 8f909e3eba80
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-180/trainer_state/rank_012.ptWeights2.8 GB 73d7e8b98ced
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-180/trainer_state/rank_013.ptWeights2.8 GB 94fa42bfbcee
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-180/trainer_state/rank_014.ptWeights2.8 GB 942cc5e08ea6
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-180/trainer_state/rank_015.ptWeights2.8 GB d667793225fe
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-180/trainer_state/rank_016.ptWeights2.8 GB d3a0e5f03c48
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-180/trainer_state/rank_017.ptWeights2.8 GB 3d05b6011d94
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-180/trainer_state/rank_018.ptWeights2.8 GB 8764ad70a419
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-180/trainer_state/rank_019.ptWeights2.8 GB 17015b61f39b
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-180/trainer_state/rank_020.ptWeights2.8 GB b41469a72677
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-180/trainer_state/rank_021.ptWeights2.8 GB 225b7144bebb
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-180/trainer_state/rank_022.ptWeights2.8 GB e540ae20ce2c
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-180/trainer_state/rank_023.ptWeights2.8 GB e2476ca36e76
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-180/trainer_state/rank_024.ptWeights2.8 GB b8142fce59e5
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-180/trainer_state/rank_025.ptWeights2.8 GB 5cf84d514ee1
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-180/trainer_state/rank_026.ptWeights2.8 GB 33cc512b9aa9
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-180/trainer_state/rank_027.ptWeights2.8 GB 11a46a03f554
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-180/trainer_state/rank_028.ptWeights2.8 GB afd8db169b5a
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-180/trainer_state/rank_029.ptWeights2.8 GB 2ae122565dfb
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-180/trainer_state/rank_030.ptWeights2.8 GB 16cc058f93f0
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-180/trainer_state/rank_031.ptWeights2.8 GB 0432145337a1
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-90/adapter.ptWeights67.2 MB e5e91f8c61e6
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-90/model.safetensorsWeights16.4 GB 4da90ec988fd
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/adapter.ptWeights67.2 MB e5e91f8c61e6
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-110/adapter.ptWeights67.2 MB e5e91f8c61e6
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-110/model.safetensorsWeights16.4 GB 27949ae5dc2d
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-130/adapter.ptWeights67.2 MB e5e91f8c61e6
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-130/model.safetensorsWeights16.4 GB 2ca28611def6
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-140/adapter.ptWeights67.2 MB e5e91f8c61e6
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-140/model.safetensorsWeights16.4 GB 40a07d52eb80
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-160/adapter.ptWeights67.2 MB e5e91f8c61e6
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-160/model.safetensorsWeights16.4 GB 4fe47555b6ff
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-180/adapter.ptWeights67.2 MB e5e91f8c61e6
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-180/model.safetensorsWeights16.4 GB 324e7fe7135b
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-180/trainer_state/rank_000.ptWeights7.5 GB cc185c31aefe
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-180/trainer_state/rank_001.ptWeights7.5 GB c02367041002
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-180/trainer_state/rank_002.ptWeights2.8 GB e042f121f798
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-180/trainer_state/rank_003.ptWeights2.8 GB bb67589538e9
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-180/trainer_state/rank_004.ptWeights2.8 GB 21d3e83df44e
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-180/trainer_state/rank_005.ptWeights2.8 GB 7bb27bfda8db
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-180/trainer_state/rank_006.ptWeights2.8 GB eded3b4c1a17
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-180/trainer_state/rank_007.ptWeights2.8 GB 5f3fb75e044a
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-180/trainer_state/rank_008.ptWeights2.8 GB 36390f5b300d
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-180/trainer_state/rank_009.ptWeights2.8 GB 3b8d38dbe9e4
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-180/trainer_state/rank_010.ptWeights2.8 GB f82e37d167b6
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-180/trainer_state/rank_011.ptWeights2.8 GB 9449687289ca
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-180/trainer_state/rank_012.ptWeights2.8 GB 6adfbf75b3b2
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-180/trainer_state/rank_013.ptWeights2.8 GB 661c6082e2a0
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-180/trainer_state/rank_014.ptWeights2.8 GB fb2487f56a8d
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-180/trainer_state/rank_015.ptWeights2.8 GB 1859d3914071
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-180/trainer_state/rank_016.ptWeights2.8 GB 3f6300c26bcb
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-180/trainer_state/rank_017.ptWeights2.8 GB a43182319a96
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-180/trainer_state/rank_018.ptWeights2.8 GB 433d59d23c01
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-180/trainer_state/rank_019.ptWeights2.8 GB 3f0eeb9c088a
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-180/trainer_state/rank_020.ptWeights2.8 GB ab532f9b783e
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-180/trainer_state/rank_021.ptWeights2.8 GB fe6ab2b4e085
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-180/trainer_state/rank_022.ptWeights2.8 GB a43d32221942
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-180/trainer_state/rank_023.ptWeights2.8 GB d3fdccac3e05
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-180/trainer_state/rank_024.ptWeights2.8 GB 56146b6164b0
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-180/trainer_state/rank_025.ptWeights2.8 GB f1be8c5c5fa7
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-180/trainer_state/rank_026.ptWeights2.8 GB ee8284f96d44
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-180/trainer_state/rank_027.ptWeights2.8 GB db2dbad342ca
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-180/trainer_state/rank_028.ptWeights2.8 GB 89f936a2fbdc
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-180/trainer_state/rank_029.ptWeights2.8 GB f57d1f58a5f1
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-180/trainer_state/rank_030.ptWeights2.8 GB 1b9babf8b910
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-180/trainer_state/rank_031.ptWeights2.8 GB f0da02e5ecd6
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-90/adapter.ptWeights67.2 MB e5e91f8c61e6
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-90/model.safetensorsWeights16.4 GB edea1fa6e520
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-100/adapter.ptWeights67.2 MB e5e91f8c61e6
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-100/model.safetensorsWeights16.4 GB f854b469cf0f
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-110/adapter.ptWeights67.2 MB e5e91f8c61e6
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-110/model.safetensorsWeights16.4 GB 8001f58b90c8
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-110/trainer_state/rank_000.ptWeights7.5 GB a2d2b6a03e71
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-110/trainer_state/rank_001.ptWeights7.5 GB e51d9764bae7
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-110/trainer_state/rank_002.ptWeights2.8 GB d695abf6c0ec
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-110/trainer_state/rank_003.ptWeights2.8 GB 227ea6015c25
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-110/trainer_state/rank_004.ptWeights2.8 GB 32a3707880aa
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-110/trainer_state/rank_005.ptWeights2.8 GB 998d369d3328
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-110/trainer_state/rank_006.ptWeights2.8 GB 75e6db1e2c91
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-110/trainer_state/rank_007.ptWeights2.8 GB 2035b710736e
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-110/trainer_state/rank_008.ptWeights2.8 GB 83a257d97b02
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-110/trainer_state/rank_009.ptWeights2.8 GB 4926c5441ec1
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-110/trainer_state/rank_010.ptWeights2.8 GB 0143b5152b21
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-110/trainer_state/rank_011.ptWeights2.8 GB ec40d013dd4c
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-110/trainer_state/rank_012.ptWeights2.8 GB 90a76ead5cbe
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-110/trainer_state/rank_013.ptWeights2.8 GB 895e5668d418
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-110/trainer_state/rank_014.ptWeights2.8 GB c60d3cee2f1d
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-110/trainer_state/rank_015.ptWeights2.8 GB 4f8feb1a1365
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-110/trainer_state/rank_016.ptWeights2.8 GB b9ef6dbe0ddd
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-110/trainer_state/rank_017.ptWeights2.8 GB b85d390d61a8
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-110/trainer_state/rank_018.ptWeights2.8 GB 4ae06c7bded5
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-110/trainer_state/rank_019.ptWeights2.8 GB 1fce3f981ea9
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-110/trainer_state/rank_020.ptWeights2.8 GB 2fafb4f0fc2c
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-110/trainer_state/rank_021.ptWeights2.8 GB 414246235963
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-110/trainer_state/rank_022.ptWeights2.8 GB 0469caf10a50
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-110/trainer_state/rank_023.ptWeights2.8 GB 2774bf3e19c4
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-110/trainer_state/rank_024.ptWeights2.8 GB 606be0b03d3e
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-110/trainer_state/rank_025.ptWeights2.8 GB c57a656682ba
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-110/trainer_state/rank_026.ptWeights2.8 GB 97fd7b2120a1
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-110/trainer_state/rank_027.ptWeights2.8 GB 5d17150d69b3
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-110/trainer_state/rank_028.ptWeights2.8 GB 04a937b49782
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-110/trainer_state/rank_029.ptWeights2.8 GB b3351afc09af
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-110/trainer_state/rank_030.ptWeights2.8 GB b1221236ac8e
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-110/trainer_state/rank_031.ptWeights2.8 GB 9208aaa67bdc
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-120/adapter.ptWeights67.2 MB e5e91f8c61e6
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-120/model.safetensorsWeights16.4 GB 2de074d380f4
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-120/trainer_state/rank_000.ptWeights7.5 GB 23b2dda09257
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-120/trainer_state/rank_001.ptWeights7.5 GB 54b0ac698712
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-120/trainer_state/rank_002.ptWeights2.8 GB 3f51dda299f3
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-120/trainer_state/rank_003.ptWeights2.8 GB 185ded998b60
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-120/trainer_state/rank_004.ptWeights2.8 GB 68ac527ca07b
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-120/trainer_state/rank_005.ptWeights2.8 GB 68edb4827b48
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-120/trainer_state/rank_006.ptWeights2.8 GB 37e7253eef7c
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-120/trainer_state/rank_007.ptWeights2.8 GB c2f596d4a5ee
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-120/trainer_state/rank_008.ptWeights2.8 GB a5973d96ab16
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-120/trainer_state/rank_009.ptWeights2.8 GB 87a1a7f73b34
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-120/trainer_state/rank_010.ptWeights2.8 GB 314686ecc1c3
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-120/trainer_state/rank_011.ptWeights2.8 GB 60df9ffde393
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-120/trainer_state/rank_012.ptWeights2.8 GB 5281fc5c2e53
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-120/trainer_state/rank_013.ptWeights2.8 GB 1a844620619a
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-120/trainer_state/rank_014.ptWeights2.8 GB 2fc501d9eb5d
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-120/trainer_state/rank_015.ptWeights2.8 GB d8de8b4c7ed5
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-120/trainer_state/rank_016.ptWeights2.8 GB 91123b35b838
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-120/trainer_state/rank_017.ptWeights2.8 GB 4f5aa3fbdb89
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-120/trainer_state/rank_018.ptWeights2.8 GB 063ca67f749d
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-120/trainer_state/rank_019.ptWeights2.8 GB 7f21f7344546
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-120/trainer_state/rank_020.ptWeights2.8 GB b8853cc8280d
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-120/trainer_state/rank_021.ptWeights2.8 GB b1e6cac8468e
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-120/trainer_state/rank_022.ptWeights2.8 GB c046b3a9c140
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-120/trainer_state/rank_023.ptWeights2.8 GB 981384f5add4
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-120/trainer_state/rank_024.ptWeights2.8 GB 560803d963a7
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-120/trainer_state/rank_025.ptWeights2.8 GB e6b9200c6e00
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-120/trainer_state/rank_026.ptWeights2.8 GB 1b99dcabe8e0
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-120/trainer_state/rank_027.ptWeights2.8 GB 19da17937920
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-120/trainer_state/rank_028.ptWeights2.8 GB 89afe1f8272d
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-120/trainer_state/rank_029.ptWeights2.8 GB 59f41ab7631f
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-120/trainer_state/rank_030.ptWeights2.8 GB f26228435495
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-120/trainer_state/rank_031.ptWeights2.8 GB 0490fb766e3f
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-80/adapter.ptWeights67.2 MB e5e91f8c61e6
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-80/model.safetensorsWeights16.4 GB 1f3bf190c620
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-90/adapter.ptWeights67.2 MB e5e91f8c61e6
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-90/model.safetensorsWeights16.4 GB 498c8febd338
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/adapter.ptWeights104.9 MB 635118c97907
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-100/adapter.ptWeights104.9 MB 635118c97907
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-100/model.safetensorsWeights29.5 GB 93d710a0b145
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-110/adapter.ptWeights104.9 MB 635118c97907
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-110/model.safetensorsWeights29.5 GB 9cda8a6ee506
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-110/trainer_state/rank_000.ptWeights9.3 GB 95a62a78a59e
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-110/trainer_state/rank_001.ptWeights9.3 GB 7010a215eb0c
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-110/trainer_state/rank_002.ptWeights5.3 GB ce620cda46e6
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-110/trainer_state/rank_003.ptWeights5.3 GB 7987f0ff832a
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-110/trainer_state/rank_004.ptWeights5.3 GB 0f7be887881c
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-110/trainer_state/rank_005.ptWeights5.3 GB c8feae086763
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-110/trainer_state/rank_006.ptWeights5.3 GB 7c8bcac9eaa8
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-110/trainer_state/rank_007.ptWeights5.3 GB 9de9b9742fa0
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-110/trainer_state/rank_008.ptWeights5.3 GB c6feeeb8c71e
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-110/trainer_state/rank_009.ptWeights5.3 GB 9cecfa424955
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-110/trainer_state/rank_010.ptWeights5.3 GB 97e83395a711
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-110/trainer_state/rank_011.ptWeights5.3 GB fab90d23e00c
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-110/trainer_state/rank_012.ptWeights5.3 GB 3ac4343a7d4f
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-110/trainer_state/rank_013.ptWeights5.3 GB 2ab9b47dc78e
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-110/trainer_state/rank_014.ptWeights5.3 GB 7b1a8667b29d
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-110/trainer_state/rank_015.ptWeights5.3 GB dfcedcf443c3
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-110/trainer_state/rank_016.ptWeights5.3 GB 9b80f376f687
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-110/trainer_state/rank_017.ptWeights5.3 GB 38782748c378
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-110/trainer_state/rank_018.ptWeights5.3 GB 57f1d7dc6391
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-110/trainer_state/rank_019.ptWeights5.3 GB a34dd272cceb
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-110/trainer_state/rank_020.ptWeights5.3 GB 789d85a9fe6c
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-110/trainer_state/rank_021.ptWeights5.3 GB 679c69e95476
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-110/trainer_state/rank_022.ptWeights5.3 GB 5c1cc90041a8
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-110/trainer_state/rank_023.ptWeights5.3 GB c4fcf3855bf7
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-110/trainer_state/rank_024.ptWeights5.3 GB 92f864229949
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-110/trainer_state/rank_025.ptWeights5.3 GB 4326da15167e
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-110/trainer_state/rank_026.ptWeights5.3 GB 214831716274
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-110/trainer_state/rank_027.ptWeights5.3 GB 398320f22382
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-110/trainer_state/rank_028.ptWeights5.3 GB ce62c46982f3
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-110/trainer_state/rank_029.ptWeights5.3 GB 1b67a6eb0f8b
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-110/trainer_state/rank_030.ptWeights5.3 GB 748db051b8cc
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-110/trainer_state/rank_031.ptWeights5.3 GB 30083fdbb51c
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-120/adapter.ptWeights104.9 MB 635118c97907
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-120/model.safetensorsWeights29.5 GB 6b3720aa7f3e
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-120/trainer_state/rank_000.ptWeights9.3 GB d87c7fadec50
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-120/trainer_state/rank_001.ptWeights9.3 GB 65de99ed6d8b
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-120/trainer_state/rank_002.ptWeights5.3 GB 1dc3255a14e0
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-120/trainer_state/rank_003.ptWeights5.3 GB 8ab6ac127c5c
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-120/trainer_state/rank_004.ptWeights5.3 GB a27601ed3f88
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-120/trainer_state/rank_005.ptWeights5.3 GB ba0693eea273
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-120/trainer_state/rank_006.ptWeights5.3 GB fee22df757c2
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-120/trainer_state/rank_007.ptWeights5.3 GB c21361bf0f7e
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-120/trainer_state/rank_008.ptWeights5.3 GB 66e54d09a978
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-120/trainer_state/rank_009.ptWeights5.3 GB 2a9192a40bf4
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-120/trainer_state/rank_010.ptWeights5.3 GB 260bd265d54b
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-120/trainer_state/rank_011.ptWeights5.3 GB 8803af13a435
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-120/trainer_state/rank_012.ptWeights5.3 GB 599a0e119685
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-120/trainer_state/rank_013.ptWeights5.3 GB 8b7f3897a88f
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-120/trainer_state/rank_014.ptWeights5.3 GB 04b1cc2fe57f
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-120/trainer_state/rank_015.ptWeights5.3 GB bad6d77d5d95
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-120/trainer_state/rank_016.ptWeights5.3 GB 86ffd01bc1f1
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-120/trainer_state/rank_017.ptWeights5.3 GB 5ca7e6dfc5a7
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-120/trainer_state/rank_018.ptWeights5.3 GB 544882ed7a39
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-120/trainer_state/rank_019.ptWeights5.3 GB f2a2a3d8aecb
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-120/trainer_state/rank_020.ptWeights5.3 GB a34bb8547dd9
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-120/trainer_state/rank_021.ptWeights5.3 GB 1f8d9d470a57
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-120/trainer_state/rank_022.ptWeights5.3 GB ced39a9918e1
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-120/trainer_state/rank_023.ptWeights5.3 GB 4605d23c2326
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-120/trainer_state/rank_024.ptWeights5.3 GB ccd409d94fbc
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-120/trainer_state/rank_025.ptWeights5.3 GB c7b45a81e3a4
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-120/trainer_state/rank_026.ptWeights5.3 GB e30274ef98ab
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-120/trainer_state/rank_027.ptWeights5.3 GB 6b4a869dfc55
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-120/trainer_state/rank_028.ptWeights5.3 GB c598244ec5e3
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-120/trainer_state/rank_029.ptWeights5.3 GB 323072983db0
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-120/trainer_state/rank_030.ptWeights5.3 GB 47ae88597f34
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-120/trainer_state/rank_031.ptWeights5.3 GB d94919e588f6
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-80/adapter.ptWeights104.9 MB 635118c97907
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-80/model.safetensorsWeights29.5 GB f81551bd463a
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-90/adapter.ptWeights104.9 MB 635118c97907
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-90/model.safetensorsWeights29.5 GB 478cc3a0855e
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/adapter.ptWeights104.9 MB 635118c97907
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/checkpoint-100/adapter.ptWeights104.9 MB 635118c97907
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/checkpoint-100/model.safetensorsWeights29.5 GB 254126a55b0a
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/checkpoint-120/adapter.ptWeights104.9 MB 635118c97907
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/checkpoint-120/model.safetensorsWeights29.5 GB 54237f2c0666
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/checkpoint-140/adapter.ptWeights104.9 MB 635118c97907
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/checkpoint-140/model.safetensorsWeights29.5 GB 2f696f70de4b
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/checkpoint-160/adapter.ptWeights104.9 MB 635118c97907
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/checkpoint-160/model.safetensorsWeights29.5 GB 87a88871cd5f
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/checkpoint-180/adapter.ptWeights104.9 MB 635118c97907
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/checkpoint-180/model.safetensorsWeights29.5 GB a338a9eb1e11
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/checkpoint-180/trainer_state/rank_000.ptWeights9.3 GB 8542f71758c1
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/checkpoint-180/trainer_state/rank_001.ptWeights9.3 GB ec495664a6b9
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/checkpoint-180/trainer_state/rank_002.ptWeights5.3 GB ff032c371378
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/checkpoint-180/trainer_state/rank_003.ptWeights5.3 GB d6228f2f62d1
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/checkpoint-180/trainer_state/rank_004.ptWeights5.3 GB 0fd0672196ad
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/checkpoint-180/trainer_state/rank_005.ptWeights5.3 GB 356150352711
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/checkpoint-180/trainer_state/rank_006.ptWeights5.3 GB 55b5ffb148ee
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/checkpoint-180/trainer_state/rank_007.ptWeights5.3 GB 47855c7c4114
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/checkpoint-180/trainer_state/rank_008.ptWeights5.3 GB d6163e420345
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/checkpoint-180/trainer_state/rank_009.ptWeights5.3 GB 4f7c672c149f
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/checkpoint-180/trainer_state/rank_010.ptWeights5.3 GB 410dd7b36ef1
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/checkpoint-180/trainer_state/rank_011.ptWeights5.3 GB 0488ce9f7887
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/checkpoint-180/trainer_state/rank_012.ptWeights5.3 GB 3711aa404fc3
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/checkpoint-180/trainer_state/rank_013.ptWeights5.3 GB 07af40dd3152
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/checkpoint-180/trainer_state/rank_014.ptWeights5.3 GB d12fc6055efc
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/checkpoint-180/trainer_state/rank_015.ptWeights5.3 GB 15af20bba91b
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/checkpoint-180/trainer_state/rank_016.ptWeights5.3 GB ff433410409e
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/checkpoint-180/trainer_state/rank_017.ptWeights5.3 GB 2d56acb622e5
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/checkpoint-180/trainer_state/rank_018.ptWeights5.3 GB 5f4d3fb6d675
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/checkpoint-180/trainer_state/rank_019.ptWeights5.3 GB 90adba026d19
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/checkpoint-180/trainer_state/rank_020.ptWeights5.3 GB 619f43ec83b3
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/checkpoint-180/trainer_state/rank_021.ptWeights5.3 GB 81e1cc6d9870
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/checkpoint-180/trainer_state/rank_022.ptWeights5.3 GB 37eb421d319a
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/checkpoint-180/trainer_state/rank_023.ptWeights5.3 GB bda32300ae44
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/checkpoint-180/trainer_state/rank_024.ptWeights5.3 GB 76fc0256282d
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/checkpoint-180/trainer_state/rank_025.ptWeights5.3 GB 131bddbeb981
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/checkpoint-180/trainer_state/rank_026.ptWeights5.3 GB 063e9f14c2c9
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/checkpoint-180/trainer_state/rank_027.ptWeights5.3 GB fcbc0fc14c7e
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/checkpoint-180/trainer_state/rank_028.ptWeights5.3 GB 9a6662a0ab18
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/checkpoint-180/trainer_state/rank_029.ptWeights5.3 GB 995f68f882c5
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/checkpoint-180/trainer_state/rank_030.ptWeights5.3 GB 171ca9fd45c0
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/checkpoint-180/trainer_state/rank_031.ptWeights5.3 GB b20e560fd2cf
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/checkpoint-80/adapter.ptWeights104.9 MB 635118c97907
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/checkpoint-80/model.safetensorsWeights29.5 GB 01c7d79e07a1
models/smoke_hybrid_submission/sft_out/stage1/adapter.ptWeights4.2 MB 316286b5b015
models/smoke_hybrid_submission/sft_out/stage1/checkpoint-3/adapter.ptWeights4.2 MB 316286b5b015
models/smoke_hybrid_submission/sft_out/stage1/checkpoint-3/model.safetensorsWeights1.2 GB 771c445c3d89
models/smoke_hybrid_submission/sft_out/stage1/model.safetensorsWeights1.2 GB 771c445c3d89
models/smoke_hybrid_submission/sft_out/stage2/adapter.ptWeights4.2 MB c9218c6263cf
models/smoke_hybrid_submission/sft_out/stage2/checkpoint-3/adapter.ptWeights4.2 MB c9218c6263cf
models/smoke_hybrid_submission/sft_out/stage2/checkpoint-3/model.safetensorsWeights1.2 GB 771c445c3d89
models/smoke_hybrid_submission/sft_out/stage2/model.safetensorsWeights1.2 GB 771c445c3d89
models/smoke_hybrid_submission/sft_out/stage3_full/adapter.ptWeights4.2 MB 886a16b9d480
models/smoke_hybrid_submission/sft_out/stage3_full/checkpoint-3/adapter.ptWeights4.2 MB 886a16b9d480
models/smoke_hybrid_submission/sft_out/stage3_full/checkpoint-3/model.safetensorsWeights1.2 GB 8160d47b8519
models/smoke_hybrid_submission/sft_out/stage3_full/model.safetensorsWeights1.2 GB 8160d47b8519
models/smoke_hybrid_submission/sft_out2/stage1/adapter.ptWeights4.2 MB 316286b5b015
models/smoke_hybrid_submission/sft_out2/stage1/checkpoint-1/adapter.ptWeights4.2 MB 316286b5b015
models/smoke_hybrid_submission/sft_out2/stage1/checkpoint-1/model.safetensorsWeights1.2 GB f3b0a28e0bb5
models/smoke_hybrid_submission/sft_out2/stage1/model.safetensorsWeights1.2 GB f3b0a28e0bb5
models/smoke_hybrid_submission/sft_out2/stage2/adapter.ptWeights4.2 MB 316286b5b015
models/smoke_hybrid_submission/sft_out2/stage2/checkpoint-1/adapter.ptWeights4.2 MB 316286b5b015
models/smoke_hybrid_submission/sft_out2/stage2/checkpoint-1/model.safetensorsWeights1.2 GB f3b0a28e0bb5
models/smoke_hybrid_submission/sft_out2/stage2/model.safetensorsWeights1.2 GB f3b0a28e0bb5
models/smoke_hybrid_submission/sft_out2/stage3/adapter.ptWeights4.2 MB 316286b5b015
models/smoke_hybrid_submission/sft_out2/stage3/checkpoint-1/adapter.ptWeights4.2 MB 316286b5b015
models/smoke_hybrid_submission/sft_out2/stage3/checkpoint-1/model.safetensorsWeights1.2 GB f3b0a28e0bb5
models/smoke_hybrid_submission/sft_out2/stage3/model.safetensorsWeights1.2 GB f3b0a28e0bb5
models/version_7_base/qwen3_14b/stage3_full/checkpoint-2000/adapter.ptWeights104.9 MB 804406ceec05
models/version_7_base/qwen3_14b/stage3_full/checkpoint-2000/model.safetensorsWeights29.5 GB 71c70f63994a
models/version_7_base/qwen3_4b_base_hybrid_ns2lr2e4_ckpt7000/adapter.ptWeights26.2 MB 55261e859843
models/version_7_base/qwen3_4b_base_hybrid_ns2lr2e4_ckpt7000/model.safetensorsWeights8.8 GB fb6abc0a394a
models/version_7_base/qwen3_8b/stage3_full/checkpoint-2000/adapter.ptWeights67.2 MB 3c33cf626715
models/version_7_base/qwen3_8b/stage3_full/checkpoint-2000/model.safetensorsWeights16.4 GB b664aff638b9
models/version_8_hsftv2/qwen3_14b/stage1/adapter.ptWeights104.9 MB dd3c4ff6ec4b
models/version_8_hsftv2/qwen3_14b/stage1/model.safetensorsWeights29.5 GB f0286dad6b43
models/version_8_hsftv2/qwen3_14b/stage2/adapter.ptWeights104.9 MB 28bf489bb04b
models/version_8_hsftv2/qwen3_14b/stage2/model.safetensorsWeights29.5 GB f0286dad6b43
models/version_8_hsftv2/qwen3_14b/stage3_full/checkpoint-1000/adapter.ptWeights104.9 MB 34dbd58f7c04
models/version_8_hsftv2/qwen3_14b/stage3_full/checkpoint-1000/model.safetensorsWeights29.5 GB 88975ac0220d
related_works/ARPO/AEPO/verl_aepo_entropy/tests/e2e/arithmetic_sequence/model/model.safetensorsWeights1.6 MB 3dcf33555c12
related_works/ARPO/ARPO/verl_arpo_entropy/tests/e2e/arithmetic_sequence/model/model.safetensorsWeights1.6 MB 3dcf33555c12
MANIFEST.jsonConfiguration2.2 MB —
code_public/HybridAgent/hybrid_agent/__init__.pyConfiguration1.2 KB —
code_public/HybridAgent/hybrid_agent/answer.pyConfiguration2.2 KB —
code_public/HybridAgent/hybrid_agent/constants.pyConfiguration1.1 KB —
code_public/HybridAgent/hybrid_agent/engine.pyConfiguration27.7 KB —
code_public/HybridAgent/hybrid_agent/hybridlink.pyConfiguration1.1 KB —
code_public/HybridAgent/hybrid_agent/model.pyConfiguration5.9 KB —
code_public/HybridAgent/hybrid_agent/prompts.pyConfiguration2.7 KB —
code_public/HybridAgent/hybrid_agent/readout.pyConfiguration2.7 KB —
code_public/HybridAgent/hybrid_agent/sampling.pyConfiguration4.2 KB —
code_public/HybridAgent/hybrid_agent/tools/__init__.pyConfiguration489 B —
code_public/HybridAgent/hybrid_agent/tools/base.pyConfiguration540 B —
code_public/HybridAgent/hybrid_agent/tools/executor.pyConfiguration3.7 KB —
code_public/HybridAgent/hybrid_agent/tools/python_tool.pyConfiguration18.7 KB —
code_public/HybridAgent/hybrid_agent/tools/search_cache.pyConfiguration4.3 KB —
code_public/HybridAgent/hybrid_agent/tools/search_tool.pyConfiguration3.5 KB —
code_public/HybridAgent/hybrid_inference/__init__.pyConfiguration59 B —
code_public/HybridAgent/hybrid_inference/run_batch.pyConfiguration8.6 KB —
code_public/HybridAgent/hybrid_rl/__init__.pyConfiguration162 B —
code_public/HybridAgent/hybrid_rl/config.pyConfiguration3.2 KB —
code_public/HybridAgent/hybrid_rl/data.pyConfiguration3.0 KB —
code_public/HybridAgent/hybrid_rl/dist.pyConfiguration2.2 KB —
code_public/HybridAgent/hybrid_rl/grpo.pyConfiguration2.7 KB —
code_public/HybridAgent/hybrid_rl/minibatch.pyConfiguration2.2 KB —
code_public/HybridAgent/hybrid_rl/optimizer.pyConfiguration7.8 KB —
code_public/HybridAgent/hybrid_rl/policy.pyConfiguration3.6 KB —
code_public/HybridAgent/hybrid_rl/replay.pyConfiguration8.1 KB —
code_public/HybridAgent/hybrid_rl/reward.pyConfiguration5.7 KB —
code_public/HybridAgent/hybrid_rl/rollout.pyConfiguration8.9 KB —
code_public/HybridAgent/hybrid_rl/train.pyConfiguration19.4 KB —
code_public/HybridAgent/hybrid_rl/trajectory.pyConfiguration1.4 KB —
code_public/HybridAgent/hybrid_sft/__init__.pyConfiguration345 B —
code_public/HybridAgent/hybrid_sft/configs/accelerate_zero2.yamlConfiguration459 B —
code_public/HybridAgent/hybrid_sft/configs/accelerate_zero2_offload.yamlConfiguration478 B —
code_public/HybridAgent/hybrid_sft/configs/deepspeed_zero2_offload.jsonConfiguration453 B —
code_public/HybridAgent/hybrid_sft/data.pyConfiguration8.9 KB —
code_public/HybridAgent/hybrid_sft/model.pyConfiguration6.8 KB —
code_public/HybridAgent/hybrid_sft/train.pyConfiguration10.3 KB —
code_public/HybridAgent/interpretable_latent_mode/__init__.pyConfiguration687 B —
code_public/HybridAgent/interpretable_latent_mode/__main__.pyConfiguration4.6 KB —
code_public/HybridAgent/interpretable_latent_mode/render.pyConfiguration16.0 KB —
code_public/HybridAgent/interpretable_latent_mode/trace.pyConfiguration7.1 KB —
code_public/_hf_release/HybridAgent-14B-Agentic/adapter_config.jsonConfiguration38 B —
code_public/_hf_release/HybridAgent-14B-Agentic/config.jsonConfiguration1.7 KB —
code_public/_hf_release/HybridAgent-14B-Agentic/generation_config.jsonConfiguration139 B —
code_public/_hf_release/HybridAgent-8B-Agentic/adapter_config.jsonConfiguration38 B —
code_public/_hf_release/HybridAgent-8B-Agentic/config.jsonConfiguration1.6 KB —
code_public/_hf_release/HybridAgent-8B-Agentic/generation_config.jsonConfiguration139 B —
code_public/_smoke/hf_cache/.agent_harnesses.jsonConfiguration5.8 KB —
code_public/_smoke/hf_cache/hub/models--Elphan--tmp-all/snapshots/66afffed09178e66821d195d1a8b06a720328732/models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-120/adapter_config.jsonConfiguration38 B —
code_public/_smoke/hf_cache/hub/models--Elphan--tmp-all/snapshots/66afffed09178e66821d195d1a8b06a720328732/models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-120/config.jsonConfiguration1.6 KB —
code_public/_smoke/hf_cache/hub/models--Elphan--tmp-all/snapshots/66afffed09178e66821d195d1a8b06a720328732/models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-120/generation_config.jsonConfiguration139 B —
code_public/_smoke/hf_cache/hub/models--Elphan--tmp-all/snapshots/66afffed09178e66821d195d1a8b06a720328732/models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-120/rl_args.jsonConfiguration3.0 KB —
code_public/_smoke/hf_cache/hub/models--Elphan--tmp-all/snapshots/66afffed09178e66821d195d1a8b06a720328732/models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-90/adapter_config.jsonConfiguration38 B —
code_public/_smoke/hf_cache/hub/models--Elphan--tmp-all/snapshots/66afffed09178e66821d195d1a8b06a720328732/models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-90/config.jsonConfiguration1.7 KB —
code_public/_smoke/hf_cache/hub/models--Elphan--tmp-all/snapshots/66afffed09178e66821d195d1a8b06a720328732/models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-90/generation_config.jsonConfiguration139 B —
code_public/_smoke/hf_cache/hub/models--Elphan--tmp-all/snapshots/66afffed09178e66821d195d1a8b06a720328732/models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-90/rl_args.jsonConfiguration3.0 KB —
code_public/_smoke/hf_cache/hub/models--Elphan--tmp-all/trees/66afffed09178e66821d195d1a8b06a720328732.jsonConfiguration1.1 MB —
code_public/_smoke/hf_cache/hub/models--JasonChenn--HybridAgent-8B-Agentic/trees/c5c10bd4c125c24a5100b7d632a58689973d096f.jsonConfiguration1.7 KB —
code_public/_smoke/hf_cache/hub/models--Qwen--Qwen3-0.6B-Base/.no_exist/da87bfb608c14b7cf20ba1ce41287e8de496c0cd/added_tokens.jsonConfiguration —
code_public/_smoke/hf_cache/hub/models--Qwen--Qwen3-0.6B-Base/.no_exist/da87bfb608c14b7cf20ba1ce41287e8de496c0cd/special_tokens_map.jsonConfiguration —
code_public/_smoke/hf_cache/hub/models--Qwen--Qwen3-0.6B-Base/snapshots/da87bfb608c14b7cf20ba1ce41287e8de496c0cd/config.jsonConfiguration727 B —
code_public/_smoke/hf_cache/hub/models--Qwen--Qwen3-0.6B-Base/snapshots/da87bfb608c14b7cf20ba1ce41287e8de496c0cd/generation_config.jsonConfiguration138 B —
code_public/_smoke/hf_cache/hub/models--Qwen--Qwen3-0.6B-Base/trees/da87bfb608c14b7cf20ba1ce41287e8de496c0cd.jsonConfiguration1.3 KB —
code_public/_smoke/out_rl/math/checkpoint-1/adapter_config.jsonConfiguration38 B —
code_public/_smoke/out_rl/math/checkpoint-1/config.jsonConfiguration1.6 KB —
code_public/_smoke/out_rl/math/checkpoint-1/generation_config.jsonConfiguration139 B —
code_public/_smoke/out_rl/math/checkpoint-1/rl_config.jsonConfiguration501 B —
code_public/_smoke/out_rl/math/checkpoint-2/adapter_config.jsonConfiguration38 B —
code_public/_smoke/out_rl/math/checkpoint-2/config.jsonConfiguration1.6 KB —
code_public/_smoke/out_rl/math/checkpoint-2/generation_config.jsonConfiguration139 B —
code_public/_smoke/out_rl/math/checkpoint-2/rl_config.jsonConfiguration501 B —
code_public/_smoke/out_rl/math/rl_config.jsonConfiguration501 B —
code_public/_smoke/out_rl/search/checkpoint-1/adapter_config.jsonConfiguration38 B —
code_public/_smoke/out_rl/search/checkpoint-1/config.jsonConfiguration1.6 KB —
code_public/_smoke/out_rl/search/checkpoint-1/generation_config.jsonConfiguration139 B —
code_public/_smoke/out_rl/search/checkpoint-1/rl_config.jsonConfiguration507 B —
code_public/_smoke/out_rl/search/checkpoint-2/adapter_config.jsonConfiguration38 B —
code_public/_smoke/out_rl/search/checkpoint-2/config.jsonConfiguration1.6 KB —
code_public/_smoke/out_rl/search/checkpoint-2/generation_config.jsonConfiguration139 B —
code_public/_smoke/out_rl/search/checkpoint-2/rl_config.jsonConfiguration507 B —
code_public/_smoke/out_rl/search/rl_config.jsonConfiguration507 B —
code_public/_smoke/out_sft/format_activation/adapter_config.jsonConfiguration38 B —
code_public/_smoke/out_sft/format_activation/checkpoint-10/adapter_config.jsonConfiguration38 B —
code_public/_smoke/out_sft/format_activation/checkpoint-10/config.jsonConfiguration1.4 KB —
code_public/_smoke/out_sft/format_activation/checkpoint-10/generation_config.jsonConfiguration139 B —
code_public/_smoke/out_sft/format_activation/checkpoint-5/adapter_config.jsonConfiguration38 B —
code_public/_smoke/out_sft/format_activation/checkpoint-5/config.jsonConfiguration1.4 KB —
code_public/_smoke/out_sft/format_activation/checkpoint-5/generation_config.jsonConfiguration139 B —
code_public/_smoke/out_sft/format_activation/config.jsonConfiguration1.4 KB —
code_public/_smoke/out_sft/format_activation/generation_config.jsonConfiguration139 B —
code_public/_smoke/out_sft/format_activation/train_args.jsonConfiguration384 B —
code_public/_smoke/out_sft/hybridlink_activation/adapter_config.jsonConfiguration38 B —
code_public/_smoke/out_sft/hybridlink_activation/checkpoint-10/adapter_config.jsonConfiguration38 B —
code_public/_smoke/out_sft/hybridlink_activation/checkpoint-10/config.jsonConfiguration1.4 KB —
code_public/_smoke/out_sft/hybridlink_activation/checkpoint-10/generation_config.jsonConfiguration139 B —
code_public/_smoke/out_sft/hybridlink_activation/checkpoint-15/adapter_config.jsonConfiguration38 B —
code_public/_smoke/out_sft/hybridlink_activation/checkpoint-15/config.jsonConfiguration1.4 KB —
code_public/_smoke/out_sft/hybridlink_activation/checkpoint-15/generation_config.jsonConfiguration139 B —
code_public/_smoke/out_sft/hybridlink_activation/checkpoint-20/adapter_config.jsonConfiguration38 B —
code_public/_smoke/out_sft/hybridlink_activation/checkpoint-20/config.jsonConfiguration1.4 KB —
code_public/_smoke/out_sft/hybridlink_activation/checkpoint-20/generation_config.jsonConfiguration139 B —
code_public/_smoke/out_sft/hybridlink_activation/checkpoint-5/adapter_config.jsonConfiguration38 B —
code_public/_smoke/out_sft/hybridlink_activation/checkpoint-5/config.jsonConfiguration1.4 KB —
code_public/_smoke/out_sft/hybridlink_activation/checkpoint-5/generation_config.jsonConfiguration139 B —
code_public/_smoke/out_sft/hybridlink_activation/config.jsonConfiguration1.4 KB —
code_public/_smoke/out_sft/hybridlink_activation/generation_config.jsonConfiguration139 B —
code_public/_smoke/out_sft/hybridlink_activation/train_args.jsonConfiguration408 B —
code_public/_smoke/out_sft/self_conditioned/adapter_config.jsonConfiguration38 B —
code_public/_smoke/out_sft/self_conditioned/checkpoint-10/adapter_config.jsonConfiguration38 B —
code_public/_smoke/out_sft/self_conditioned/checkpoint-10/config.jsonConfiguration1.4 KB —
code_public/_smoke/out_sft/self_conditioned/checkpoint-10/generation_config.jsonConfiguration139 B —
code_public/_smoke/out_sft/self_conditioned/checkpoint-15/adapter_config.jsonConfiguration38 B —
code_public/_smoke/out_sft/self_conditioned/checkpoint-15/config.jsonConfiguration1.4 KB —
code_public/_smoke/out_sft/self_conditioned/checkpoint-15/generation_config.jsonConfiguration139 B —
code_public/_smoke/out_sft/self_conditioned/checkpoint-20/adapter_config.jsonConfiguration38 B —
code_public/_smoke/out_sft/self_conditioned/checkpoint-20/config.jsonConfiguration1.4 KB —
code_public/_smoke/out_sft/self_conditioned/checkpoint-20/generation_config.jsonConfiguration139 B —
code_public/_smoke/out_sft/self_conditioned/checkpoint-5/adapter_config.jsonConfiguration38 B —
code_public/_smoke/out_sft/self_conditioned/checkpoint-5/config.jsonConfiguration1.4 KB —
code_public/_smoke/out_sft/self_conditioned/checkpoint-5/generation_config.jsonConfiguration139 B —
code_public/_smoke/out_sft/self_conditioned/config.jsonConfiguration1.4 KB —
code_public/_smoke/out_sft/self_conditioned/generation_config.jsonConfiguration139 B —
code_public/_smoke/out_sft/self_conditioned/train_args.jsonConfiguration401 B —
code_public/_smoke/out_sft_offload/self_conditioned/adapter_config.jsonConfiguration38 B —
code_public/_smoke/out_sft_offload/self_conditioned/checkpoint-10/adapter_config.jsonConfiguration38 B —
code_public/_smoke/out_sft_offload/self_conditioned/checkpoint-10/config.jsonConfiguration1.4 KB —
code_public/_smoke/out_sft_offload/self_conditioned/checkpoint-10/generation_config.jsonConfiguration139 B —
code_public/_smoke/out_sft_offload/self_conditioned/checkpoint-15/adapter_config.jsonConfiguration38 B —
code_public/_smoke/out_sft_offload/self_conditioned/checkpoint-15/config.jsonConfiguration1.4 KB —
code_public/_smoke/out_sft_offload/self_conditioned/checkpoint-15/generation_config.jsonConfiguration139 B —
code_public/_smoke/out_sft_offload/self_conditioned/checkpoint-20/adapter_config.jsonConfiguration38 B —
code_public/_smoke/out_sft_offload/self_conditioned/checkpoint-20/config.jsonConfiguration1.4 KB —
code_public/_smoke/out_sft_offload/self_conditioned/checkpoint-20/generation_config.jsonConfiguration139 B —
code_public/_smoke/out_sft_offload/self_conditioned/checkpoint-5/adapter_config.jsonConfiguration38 B —
code_public/_smoke/out_sft_offload/self_conditioned/checkpoint-5/config.jsonConfiguration1.4 KB —
code_public/_smoke/out_sft_offload/self_conditioned/checkpoint-5/generation_config.jsonConfiguration139 B —
code_public/_smoke/out_sft_offload/self_conditioned/config.jsonConfiguration1.4 KB —
code_public/_smoke/out_sft_offload/self_conditioned/generation_config.jsonConfiguration139 B —
code_public/_smoke/out_sft_offload/self_conditioned/train_args.jsonConfiguration409 B —
code_public/_smoke/tests/check_rl_ckpt.pyConfiguration2.2 KB —
code_public/_smoke/tests/check_sft.pyConfiguration3.1 KB —
code_public/_smoke/tests/curate_examples.pyConfiguration3.2 KB —
code_public/_smoke/tests/engine_equivalence_report.jsonConfiguration2.5 KB —
code_public/_smoke/tests/hf_upload_release.pyConfiguration2.3 KB —
code_public/_smoke/tests/test_engine_equivalence.pyConfiguration8.0 KB —
code_public/_smoke/tests/test_rl_cpu.pyConfiguration6.3 KB —
code_public/_smoke/tests/test_sft_equivalence.pyConfiguration4.3 KB —
curate_labeled_cot.pyConfiguration5.1 KB —
curate_labeled_cot_v2.pyConfiguration18.8 KB —
data/HybridSFT_v2/build/stats.run1_superseded.jsonConfiguration872 B —
data/HybridSFT_v2/build/stats_pilot.jsonConfiguration849 B —
data/HybridSFT_v2/build/stats_sample.jsonConfiguration726 B —
data/HybridSFT_v2/build/stats_sample2.jsonConfiguration700 B —
data/HybridSFT_v2/build/stats_sweep0.5.jsonConfiguration790 B —
data/HybridSFT_v2/build/stats_sweep0.58.jsonConfiguration790 B —
data/HybridSFT_v2/build/stats_sweep0.65.jsonConfiguration790 B —
data/HybridSFT_v2/build/stats_sweep0.75.jsonConfiguration790 B —
data/HybridSFT_v2/pilot/agreement.jsonConfiguration893 B —
data/HybridSFT_v2/pilot/theta_sweep.jsonConfiguration561 B —
data/HybridSFT_v2/smoke/smoke_api_results.jsonConfiguration3.7 KB —
data/HybridSFT_v2/source/manifest.jsonConfiguration301 B —
data/HybridSFT_v2/stats/ARPO-SFT-54K-HybridSFT-v2.run1_superseded.validation.jsonConfiguration825 B —
data/HybridSFT_v2/stats/ARPO-SFT-54K-HybridSFT-v2.validation.jsonConfiguration1.2 KB —
data/HybridSFT_v2/stats/ARPO-SFT-54K-HybridSFT-v2_pilot.validation.jsonConfiguration819 B —
data/HybridSFT_v2/stats/ARPO-SFT-54K-HybridSFT-v2_sample.validation.jsonConfiguration570 B —
data/HybridSFT_v2/stats/aggregate.jsonConfiguration323 B —
data/HybridSFT_v2/stats/canonical.jsonConfiguration1.7 KB —
data/HybridSFT_v2/stats/segment.jsonConfiguration1.8 KB —
data/deepsearch/webwalker_difficulty.jsonConfiguration3.1 KB —
data_label_hybridSFT/__init__.pyConfiguration364 B —
data_label_hybridSFT/common.pyConfiguration8.4 KB —
data_label_hybridSFT/llm_client.pyConfiguration21.4 KB —
data_label_hybridSFT/pilot.pyConfiguration8.0 KB —
data_label_hybridSFT/prompts.pyConfiguration10.6 KB —
data_label_hybridSFT/render.pyConfiguration3.7 KB —
data_label_hybridSFT/s0_fetch_source.pyConfiguration2.8 KB —
data_label_hybridSFT/s1_canonicalize.pyConfiguration23.1 KB —
data_label_hybridSFT/s1b_repair_llm.pyConfiguration9.3 KB —
data_label_hybridSFT/s2_segment.pyConfiguration27.3 KB —
data_label_hybridSFT/s2b_anchor_llm.pyConfiguration13.3 KB —
data_label_hybridSFT/s3_judge.pyConfiguration12.0 KB —
data_label_hybridSFT/s4_aggregate.pyConfiguration6.9 KB —
data_label_hybridSFT/s5_audit.pyConfiguration11.8 KB —
data_label_hybridSFT/s6_construct.pyConfiguration19.8 KB —
data_label_hybridSFT/s7_validate.pyConfiguration8.1 KB —
data_label_hybridSFT/show_example.pyConfiguration7.5 KB —
data_label_hybridSFT/smoke_api.pyConfiguration9.8 KB —
docs/aug2026_analysis_artifacts/followup_behavior_stats.pyConfiguration5.3 KB —
eval_rl.MANIFEST.jsonConfiguration9.0 MB —
eval_rl/run20_gpqa/judge_c100.jsonConfiguration25.0 KB —
eval_rl/run20_gpqa/judge_c120.jsonConfiguration24.7 KB —
eval_rl/run20_gpqa/judge_c140.jsonConfiguration25.0 KB —
eval_rl/run20_gpqa/judge_c160.jsonConfiguration25.0 KB —
eval_rl/run20_gpqa/judge_c180.jsonConfiguration25.2 KB —
eval_rl/run20_gpqa/judge_c80.jsonConfiguration25.4 KB —
eval_rl/run20_p64/scored_c100.jsonConfiguration3.5 KB —
eval_rl/run20_p64/scored_c120.jsonConfiguration3.5 KB —
eval_rl/run20_p64/scored_c140.jsonConfiguration3.5 KB —
eval_rl/run20_p64/scored_c160.jsonConfiguration3.4 KB —
eval_rl/run20_p64/scored_c180.jsonConfiguration3.5 KB —
eval_rl/run20_p64/scored_c80.jsonConfiguration3.5 KB —
eval_rl/run20_scores/gpqa_scored_c100.jsonConfiguration71 B —
eval_rl/run20_scores/gpqa_scored_c120.jsonConfiguration71 B —
eval_rl/run20_scores/gpqa_scored_c140.jsonConfiguration71 B —
eval_rl/run20_scores/gpqa_scored_c160.jsonConfiguration71 B —
eval_rl/run20_scores/gpqa_scored_c180.jsonConfiguration71 B —
eval_rl/run20_scores/gpqa_scored_c80.jsonConfiguration70 B —
eval_rl/run20_scores/math500_scored_c100.jsonConfiguration53 B —
eval_rl/run20_scores/math500_scored_c120.jsonConfiguration53 B —
eval_rl/run20_scores/math500_scored_c140.jsonConfiguration52 B —
eval_rl/run20_scores/math500_scored_c160.jsonConfiguration53 B —
eval_rl/run20_scores/math500_scored_c180.jsonConfiguration53 B —
eval_rl/run20_scores/math500_scored_c80.jsonConfiguration52 B —
eval_rl_new_v2/baseline_aime_avg3.pyConfiguration7.1 KB —
eval_rl_new_v2/bcplus_search_tool.pyConfiguration4.8 KB —
eval_rl_new_v2/closedbook_llm_qa.pyConfiguration14.0 KB —
eval_rl_new_v2/medqa_judge.pyConfiguration6.7 KB —
eval_rl_new_v2/medqa_oneshot.pyConfiguration7.5 KB —
eval_rl_new_v2/musique_failure_audit.pyConfiguration6.8 KB —
eval_rl_new_v2/qa_ablation_report.pyConfiguration4.6 KB —
eval_rl_new_v2/qa_judge.pyConfiguration24.0 KB —
eval_rl_new_v2/qa_oneshot.pyConfiguration17.3 KB —
eval_rl_new_v2/r11c70_batch_verify.pyConfiguration5.3 KB —
eval_rl_new_v2/recover_c200s3.pyConfiguration4.3 KB —
eval_rl_new_v2/run12_avg5_12k.pyConfiguration5.6 KB —
eval_rl_new_v2/run12_campaign_check.pyConfiguration1.9 KB —
eval_rl_new_v2/run12_gpqa_judge.pyConfiguration5.6 KB —
eval_rl_new_v2/run12_oneshot.pyConfiguration6.6 KB —
eval_rl_new_v2/run12c120_batch_avg3.pyConfiguration5.6 KB —
eval_rl_new_v2/run14_aggregate.pyConfiguration5.5 KB —
eval_rl_new_v2/run14_avg5_12k.pyConfiguration5.8 KB —
eval_rl_new_v2/run14_campaign_check.pyConfiguration2.1 KB —
eval_rl_new_v2/run14_gpqa_judge.pyConfiguration5.8 KB —
eval_rl_new_v2/run14_oneshot.pyConfiguration6.4 KB —
eval_rl_new_v2/run14_pass64.pyConfiguration7.0 KB —
eval_rl_new_v2/run14_pass64_aggregate.pyConfiguration3.1 KB —
eval_rl_new_v2/run16_aggregate.pyConfiguration5.4 KB —
eval_rl_new_v2/run16_avg5_12k.pyConfiguration5.8 KB —
eval_rl_new_v2/run16_campaign_check.pyConfiguration2.0 KB —
eval_rl_new_v2/run16_gpqa_judge.pyConfiguration5.8 KB —
eval_rl_new_v2/run16_oneshot.pyConfiguration6.4 KB —
eval_rl_new_v2/run17_build_benchmarks.pyConfiguration4.0 KB —
eval_rl_new_v2/run17_ds_arpo_table.pyConfiguration7.9 KB —
eval_rl_new_v2/run17_ds_eval.pyConfiguration12.7 KB —
eval_rl_new_v2/run17_ds_hle_diagnose.pyConfiguration7.7 KB —
eval_rl_new_v2/run17_ds_passk.pyConfiguration5.7 KB —
eval_rl_new_v2/run17_ds_score.pyConfiguration9.6 KB —
eval_rl_new_v2/run1x_pass64_12k.pyConfiguration5.9 KB —
eval_rl_new_v2/score_pass64.pyConfiguration2.1 KB —
eval_rl_new_v2/sds_search_tool.pyConfiguration11.7 KB —
eval_rl_new_v2/websearch_llm_qa.pyConfiguration10.7 KB —
eval_rl_v7/score.pyConfiguration3.3 KB —
eval_v6_campaign/harvest.pyConfiguration3.5 KB —
evaluation/__init__.pyConfiguration141 B —
evaluation/data.pyConfiguration4.3 KB —
evaluation/grade_multi.pyConfiguration11.0 KB —
evaluation/grading.pyConfiguration2.6 KB —
evaluation/run_eval.pyConfiguration29.2 KB —
finetune/__init__.pyConfiguration36 B —
finetune/data.pyConfiguration16.0 KB —
finetune/model.pyConfiguration16.6 KB —
finetune/train.pyConfiguration23.2 KB —
finetune_cudnn_off.pyConfiguration2.7 KB —
finetune_hsftv2_entry.pyConfiguration2.9 KB —
inference/inference.pyConfiguration20.2 KB —
inference/inference_multi_turn.pyConfiguration164 B —
inference_batch/__init__.pyConfiguration —
inference_batch/batched.pyConfiguration9.3 KB —
label_cot_modes.pyConfiguration13.0 KB —
label_cot_modes_batch.pyConfiguration11.0 KB —
latent_analysis/__init__.pyConfiguration —
latent_analysis/analyze_latent_semantics.pyConfiguration7.6 KB —
latent_analysis/measure_latent_vs_labels.pyConfiguration8.4 KB —
latent_analysis/report_latent_semantics.pyConfiguration4.3 KB —
latent_analysis/results/sweep_ctrl_8b_math.jsonConfiguration20.8 KB —
latent_analysis/results/sweep_run14c100_math.jsonConfiguration25.6 KB —
latent_analysis/results/sweep_run14c110_math.jsonConfiguration26.2 KB —
latent_analysis/results/sweep_run14c120_math.jsonConfiguration29.0 KB —
latent_analysis/results/sweep_run14c130_math.jsonConfiguration33.9 KB —
latent_analysis/results/sweep_run14c140_math.jsonConfiguration27.6 KB —
latent_analysis/results/sweep_run14c150_math.jsonConfiguration29.6 KB —
latent_analysis/results/sweep_run14c160_math.jsonConfiguration29.3 KB —
latent_analysis/results/sweep_run14c170_math.jsonConfiguration31.4 KB —
latent_analysis/results/sweep_run14c180_math.jsonConfiguration26.9 KB —
latent_analysis/results/sweep_run16c100_math.jsonConfiguration37.1 KB —
latent_analysis/results/sweep_run16c110_math.jsonConfiguration23.1 KB —
latent_analysis/results/sweep_run16c120_math.jsonConfiguration32.2 KB —
latent_analysis/results/sweep_run16c130_math.jsonConfiguration40.4 KB —
latent_analysis/results/sweep_run16c140_math.jsonConfiguration30.9 KB —
latent_analysis/results/sweep_run16c150_math.jsonConfiguration28.4 KB —
latent_analysis/results/sweep_run16c160_math.jsonConfiguration27.2 KB —
latent_analysis/results/sweep_run16c170_math.jsonConfiguration31.7 KB —
latent_analysis/results/sweep_run16c180_math.jsonConfiguration20.1 KB —
latent_analysis/results/sweep_run16c80_math.jsonConfiguration25.3 KB —
latent_analysis/results/sweep_run16c90_math.jsonConfiguration28.2 KB —
latent_analysis/verify_latent_decoding.pyConfiguration8.4 KB —
models/rl_new_v2/_run20_g8_monitor/run19_noir816j.jsonConfiguration81.9 KB —
models/rl_new_v2/_run20_g8_monitor/slack_reporter_state.attempt1-crashed-at-save.jsonConfiguration4.9 KB —
models/rl_new_v2/_run20_g8_monitor/slack_reporter_state.attempt2-misparsed.jsonConfiguration4.9 KB —
models/rl_new_v2/_run20_g8_monitor/slack_reporter_state.final.jsonConfiguration81.8 KB —
models/rl_new_v2/_run20_g8_monitor/slack_reporter_state.jsonConfiguration81.8 KB —
models/rl_new_v2/run12_qwen3b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-140/adapter_config.jsonConfiguration38 B —
models/rl_new_v2/run12_qwen3b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-140/config.jsonConfiguration1.6 KB —
models/rl_new_v2/run12_qwen3b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-140/generation_config.jsonConfiguration139 B —
models/rl_new_v2/run12_qwen3b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-140/rl_args.jsonConfiguration3.1 KB —
models/rl_new_v2/run12_qwen3b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-140/trainer_state/meta.jsonConfiguration448 B —
models/rl_new_v2/run12_qwen3b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260827_233053-yzejimqr/files/media/table/samples/rollouts_149_65fa41200327dbf89d96.table.jsonConfiguration10.8 KB —
models/rl_new_v2/run12_qwen3b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260827_233053-yzejimqr/files/media/table/samples/rollouts_149_f5b54a51fd31d6d8ad20.table.jsonConfiguration13.7 KB —
models/rl_new_v2/run12_qwen3b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260827_233053-yzejimqr/files/wandb-metadata.jsonConfiguration7.1 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-110/adapter_config.jsonConfiguration38 B —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-110/config.jsonConfiguration1.6 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-110/generation_config.jsonConfiguration139 B —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-110/rl_args.jsonConfiguration2.9 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-140/adapter_config.jsonConfiguration38 B —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-140/config.jsonConfiguration1.6 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-140/generation_config.jsonConfiguration139 B —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-140/rl_args.jsonConfiguration2.9 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-150/adapter_config.jsonConfiguration38 B —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-150/config.jsonConfiguration1.6 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-150/generation_config.jsonConfiguration139 B —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-150/rl_args.jsonConfiguration2.9 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-160/adapter_config.jsonConfiguration38 B —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-160/config.jsonConfiguration1.6 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-160/generation_config.jsonConfiguration139 B —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-160/rl_args.jsonConfiguration2.9 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-170/adapter_config.jsonConfiguration38 B —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-170/config.jsonConfiguration1.6 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-170/generation_config.jsonConfiguration139 B —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-170/rl_args.jsonConfiguration2.9 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-180/adapter_config.jsonConfiguration38 B —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-180/config.jsonConfiguration1.6 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-180/generation_config.jsonConfiguration139 B —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-180/rl_args.jsonConfiguration2.9 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-180/trainer_state/meta.jsonConfiguration473 B —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-90/adapter_config.jsonConfiguration38 B —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-90/config.jsonConfiguration1.6 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-90/generation_config.jsonConfiguration139 B —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-90/rl_args.jsonConfiguration2.9 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/slack_reporter_state.jsonConfiguration727 B —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_011928-jfw4iq53/files/config.yamlConfiguration13.8 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_011928-jfw4iq53/files/wandb-metadata.jsonConfiguration6.9 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_011928-jfw4iq53/files/wandb-summary.jsonConfiguration41 B —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_015336-mcrr2z2e/files/config.yamlConfiguration13.9 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_015336-mcrr2z2e/files/media/table/samples/rollouts_0_f6415d3c004984b2467b.table.jsonConfiguration11.1 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_015336-mcrr2z2e/files/media/table/samples/rollouts_1_ca9b19c7536a0f2b78d6.table.jsonConfiguration11.9 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_015336-mcrr2z2e/files/media/table/samples/rollouts_2_33405af8ffb835045865.table.jsonConfiguration13.9 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_015336-mcrr2z2e/files/media/table/samples/rollouts_3_5f0eae3b8bce2bd7f349.table.jsonConfiguration11.7 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_015336-mcrr2z2e/files/media/table/samples/rollouts_4_f8a977a98149affff15d.table.jsonConfiguration15.1 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_015336-mcrr2z2e/files/media/table/samples/rollouts_5_dd4bfd3fee9216f70010.table.jsonConfiguration12.4 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_015336-mcrr2z2e/files/media/table/samples/rollouts_6_f8a7a6b619b847325a0a.table.jsonConfiguration12.4 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_015336-mcrr2z2e/files/media/table/samples/rollouts_7_1b780eaa8c9f1021a180.table.jsonConfiguration16.3 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_015336-mcrr2z2e/files/media/table/samples/rollouts_8_a316be08a5dbb1da99af.table.jsonConfiguration14.8 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_015336-mcrr2z2e/files/media/table/samples/rollouts_9_d534fafe024876bf5063.table.jsonConfiguration15.9 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_015336-mcrr2z2e/files/wandb-metadata.jsonConfiguration6.9 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_015336-mcrr2z2e/files/wandb-summary.jsonConfiguration13.7 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_0_f6415d3c004984b2467b.table.jsonConfiguration11.1 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_100_393e7b2cb165bf96ac27.table.jsonConfiguration14.5 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_101_64863940147925fc1f8e.table.jsonConfiguration12.3 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_102_d9225382452a996ad026.table.jsonConfiguration10.7 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_103_0bb7477f89be006c144e.table.jsonConfiguration13.6 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_104_6d976e6bff9e8f36755b.table.jsonConfiguration13.1 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_105_486a304bec1521c01ef7.table.jsonConfiguration16.2 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_106_d2db5182c64058559879.table.jsonConfiguration12.9 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_107_a115a8fb301e952e4016.table.jsonConfiguration13.4 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_108_91961773d7ecb24debb6.table.jsonConfiguration16.0 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_109_a413cfa9e280da72fa72.table.jsonConfiguration13.6 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_10_7863e6b88a0c9bd92712.table.jsonConfiguration7.6 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_110_3a642b64e6a6a204a733.table.jsonConfiguration14.1 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_111_d4dea579fdd1565efe83.table.jsonConfiguration16.8 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_112_5d5af0c067b3ea3f0c83.table.jsonConfiguration14.7 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_113_8065dd04c5031e2a5bc2.table.jsonConfiguration15.6 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_114_09958126b8a68fd70c6d.table.jsonConfiguration10.6 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_115_fb17dac07ff615a6d009.table.jsonConfiguration12.0 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_116_740f2b5b9c7d36095f03.table.jsonConfiguration10.6 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_117_c1323280a18b93bd9c86.table.jsonConfiguration10.0 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_118_3715ba2d71ad46bd26b5.table.jsonConfiguration14.1 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_119_4ffd7b9e71d90e42f92e.table.jsonConfiguration17.3 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_11_b4b51e34b4f1351df092.table.jsonConfiguration8.5 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_120_536b4869dd77ffe6db3a.table.jsonConfiguration14.0 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_121_5fda45b338a5a5ded681.table.jsonConfiguration13.0 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_122_aa79db064942e88b4236.table.jsonConfiguration15.4 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_123_4e11cfdd44a617963069.table.jsonConfiguration16.0 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_124_eb0cf2ef9e595da69fa7.table.jsonConfiguration10.7 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_125_ef9101259e5b31f2e331.table.jsonConfiguration13.0 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_126_d05e7b20f9ea7cea57db.table.jsonConfiguration16.7 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_127_870c4277b9510e16d66e.table.jsonConfiguration18.3 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_128_f2cfee81187b10a7a907.table.jsonConfiguration14.3 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_129_27ddfcedfaede5521cf4.table.jsonConfiguration16.4 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_12_3d6a1dd48e482833b401.table.jsonConfiguration9.6 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_130_f8abcf0c218fa37af37e.table.jsonConfiguration14.0 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_131_99b150546ea9bd84d2c0.table.jsonConfiguration9.8 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_132_2982f07efe1664f4cafd.table.jsonConfiguration13.0 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_133_83c4a84dcc704a9679c0.table.jsonConfiguration11.4 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_134_2f2607769a79ab0fbe16.table.jsonConfiguration16.1 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_135_f2311d5ce2ca543ff6c1.table.jsonConfiguration9.0 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_136_0beeb6a87937e9f2d052.table.jsonConfiguration11.8 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_137_c736626d1cd8a0ad0690.table.jsonConfiguration13.8 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_138_62bc7280cf52d001067e.table.jsonConfiguration12.1 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_139_c4255ec54139ab87ad62.table.jsonConfiguration7.8 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_13_2c8b9c544ebdf847e53b.table.jsonConfiguration9.9 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_140_3e432ccd1f926c4096da.table.jsonConfiguration15.5 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_141_45b1a47fc37273dd3249.table.jsonConfiguration12.3 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_142_e554f219ecb41e4e48c0.table.jsonConfiguration14.3 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_143_8f4c3db680c466499655.table.jsonConfiguration13.0 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_144_d44e34f7f5300c0c9bc4.table.jsonConfiguration12.4 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_145_801920158679c65e09a6.table.jsonConfiguration11.6 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_146_9a9192a7235f09f4aa87.table.jsonConfiguration15.6 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_147_86df980ce51c4903bc92.table.jsonConfiguration13.6 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_148_de775d290f75072f2dd3.table.jsonConfiguration15.5 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_149_f1712cfda3b5454f77bf.table.jsonConfiguration15.9 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_14_37c004b98758bdce88eb.table.jsonConfiguration15.7 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_150_d2daf0265c6df05a6fa8.table.jsonConfiguration15.8 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_151_52d7080e8cb7d777cc22.table.jsonConfiguration11.5 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_152_f7bd29563652108c02cd.table.jsonConfiguration18.8 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_153_3957ccfc540ddab4c26a.table.jsonConfiguration17.0 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_154_6d3866214b3c35bba75b.table.jsonConfiguration10.8 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_155_e13766f9f553ee6f0ba7.table.jsonConfiguration10.8 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_156_ad37d639a83a04aee385.table.jsonConfiguration12.9 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_157_b1ce1ba1424c8a2b623e.table.jsonConfiguration9.6 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_158_db75da7c28ebf19c5cb5.table.jsonConfiguration16.2 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_159_d737b23af293b2d9ff98.table.jsonConfiguration12.1 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_15_4804e77fa4976efa5a05.table.jsonConfiguration9.4 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_160_da826cc1968dbf0ac2b5.table.jsonConfiguration11.6 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_161_79be1c8c6b398d16ef4c.table.jsonConfiguration14.8 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_162_0631023187eb017c06e4.table.jsonConfiguration10.1 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_163_59cc6a59af050ecb2f36.table.jsonConfiguration5.6 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_164_5f327c19ce29803c0d57.table.jsonConfiguration11.2 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_165_d3f332dde3e27564929c.table.jsonConfiguration15.3 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_166_7b129e9d6d8f5d80cad9.table.jsonConfiguration10.2 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_167_109d24ad2b39bc0312aa.table.jsonConfiguration11.1 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_168_c0b9484fc78d3ff9c452.table.jsonConfiguration13.6 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_169_967bd338b519e4949018.table.jsonConfiguration11.4 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_16_d0e0a8f6bd6987c16f2f.table.jsonConfiguration12.2 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_170_620a2a1fe9e716711841.table.jsonConfiguration11.8 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_171_02683e696a8b80d0a5b6.table.jsonConfiguration13.3 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_172_145b938438b073424e78.table.jsonConfiguration12.8 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_173_6e956064109358770de8.table.jsonConfiguration11.5 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_174_ed312442b8051262316c.table.jsonConfiguration14.1 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_175_9ffe4c88d198691346f4.table.jsonConfiguration10.3 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_176_feda54f88580108af9c6.table.jsonConfiguration12.5 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_177_871e62d8935140beb427.table.jsonConfiguration12.3 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_178_cda735bca520203362ec.table.jsonConfiguration15.9 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_179_345d5833378344e36d50.table.jsonConfiguration12.3 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_17_2601e0244764496615d7.table.jsonConfiguration13.3 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_180_5408a3308a1999bcd831.table.jsonConfiguration10.0 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_181_948d6efb92b1f1b88cff.table.jsonConfiguration14.6 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_182_8c2ceb9b37d41042aeb0.table.jsonConfiguration12.5 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_183_273f87ea60f8e1a28e20.table.jsonConfiguration16.2 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_184_de9e70fcc8d4068347fd.table.jsonConfiguration14.5 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_18_cc623d2ff967d251ecb0.table.jsonConfiguration10.4 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_19_702197961796a0a1b1ac.table.jsonConfiguration11.0 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_1_6b70ad7b9b85310d3f1c.table.jsonConfiguration10.6 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_20_5aaf19b5998500e55756.table.jsonConfiguration10.9 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_21_78c4f44a926148b72ee4.table.jsonConfiguration9.5 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_22_13282b55d3cdb4ad01f7.table.jsonConfiguration11.8 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_23_70a9d81f46776096b2fb.table.jsonConfiguration10.3 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_24_cc5148b6e75ec48108e0.table.jsonConfiguration11.8 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_25_b573a2dd5d3e3fba425b.table.jsonConfiguration15.3 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_26_0190e65dc796d637c283.table.jsonConfiguration7.4 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_27_50eba4a82aa18b2d74d1.table.jsonConfiguration10.7 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_28_fccdf46f55a863751f96.table.jsonConfiguration9.2 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_29_3bfa0754c8ff260f3aa0.table.jsonConfiguration11.7 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_2_79a30b74693befa50fec.table.jsonConfiguration9.2 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_30_caa6c10faf36a082de83.table.jsonConfiguration7.8 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_31_a750f343f7c630d7c6af.table.jsonConfiguration11.8 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_32_ed0e92f9ca3798627e4f.table.jsonConfiguration13.6 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_33_30b7abf217f33e802cb8.table.jsonConfiguration11.2 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_34_caf3bc865226641d793f.table.jsonConfiguration13.8 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_35_d22af0ad66ed68c57b25.table.jsonConfiguration10.1 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_36_7af67870875cd7c97910.table.jsonConfiguration10.9 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_37_b8c368b559fc27769a8b.table.jsonConfiguration9.5 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_38_3a3fd415e479968b8034.table.jsonConfiguration13.4 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_39_4dc88e4f2f0624dcaeba.table.jsonConfiguration12.1 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_3_1dbf1df8b56f553f68ff.table.jsonConfiguration8.9 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_40_01f20825441739fae176.table.jsonConfiguration9.9 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_41_917d122da4cb8ce607ce.table.jsonConfiguration10.6 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_42_7fca9963dadfed116131.table.jsonConfiguration14.1 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_43_26d201c733be5a3be560.table.jsonConfiguration11.7 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_44_2ab839e0e09894bd31b2.table.jsonConfiguration9.2 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_45_b2216a05b9ddb322a3b5.table.jsonConfiguration13.7 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_46_2fe7f1e052487a0b232c.table.jsonConfiguration8.9 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_47_bfc90782c2d42d76dd4b.table.jsonConfiguration16.4 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_48_d55505662abc10ce0bbc.table.jsonConfiguration13.0 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_49_bfb891d9ac896d4f7b99.table.jsonConfiguration14.8 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_4_b14b81eaf9df6de7ff87.table.jsonConfiguration14.9 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_50_ea6fd570e073bfc73a02.table.jsonConfiguration7.2 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_51_b84a8bce7acbca38f8e0.table.jsonConfiguration8.8 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_52_64d6fb21864a8e6ccd3f.table.jsonConfiguration9.7 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_53_0517b047deed22190794.table.jsonConfiguration15.1 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_54_c51fc9971ee86c43db17.table.jsonConfiguration9.9 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_55_f187b8b52bcaf67194f7.table.jsonConfiguration10.9 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_56_be2cef59ab5124120039.table.jsonConfiguration10.1 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_57_1b6c7e07db4b0c2b094f.table.jsonConfiguration9.7 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_58_92edb440feb62663d341.table.jsonConfiguration13.8 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_59_736d37393a52df8c9f5d.table.jsonConfiguration11.4 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_5_33ff172314cf4b93dfd8.table.jsonConfiguration13.7 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_60_9988a7a7dedba7b6e10a.table.jsonConfiguration10.5 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_61_beb7f89827646eaf890b.table.jsonConfiguration11.5 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_62_04b0826ad28854dd7373.table.jsonConfiguration11.6 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_63_94aeacf32f02c32ade4e.table.jsonConfiguration8.7 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_64_49804e0aa3828cc936d5.table.jsonConfiguration11.6 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_65_008c4bfc2885cfc22f4e.table.jsonConfiguration12.6 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_66_597b2f459dd309bb3fb2.table.jsonConfiguration11.7 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_67_b066969679526a454b7f.table.jsonConfiguration16.1 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_68_96e1a634b256057cdc30.table.jsonConfiguration13.2 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_69_fbebe8aa171f4966daf8.table.jsonConfiguration10.3 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_6_753bf27d5f0b808df37f.table.jsonConfiguration11.5 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_70_5244eb31791f19a8a955.table.jsonConfiguration14.2 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_71_5874d2da11dcd3725def.table.jsonConfiguration15.0 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_72_3e0f0631af53fb94c9f6.table.jsonConfiguration16.1 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_73_8bf5eabeb80931e33833.table.jsonConfiguration11.5 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_74_702b698488e16f290853.table.jsonConfiguration10.6 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_75_04cec5708afd78e20af4.table.jsonConfiguration10.9 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_76_1c6693e9931853619c63.table.jsonConfiguration9.3 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_77_329c7afbab7c2242e22f.table.jsonConfiguration7.6 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_78_6165d0c6a5afc4a04dc2.table.jsonConfiguration10.1 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_79_62f8241eda8b60f5c362.table.jsonConfiguration10.6 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_7_1d8a5f8d16dd5e520b11.table.jsonConfiguration16.7 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_80_386a5d87890cd77a8a6d.table.jsonConfiguration12.4 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_81_da1575dc602090c25975.table.jsonConfiguration14.6 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_82_2a903eea96e11fac0b78.table.jsonConfiguration12.0 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_83_115d6455fbf381597f80.table.jsonConfiguration12.0 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_84_6b8cc0371f0902cb097e.table.jsonConfiguration12.9 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_85_0628d746bf1749967856.table.jsonConfiguration13.8 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_86_65c85a6cb94b6363246f.table.jsonConfiguration8.7 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_87_c13caf225b015503f038.table.jsonConfiguration10.9 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_88_2d8dbc0ec7a007ebad7b.table.jsonConfiguration11.4 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_89_e7bdf59a9fc43671be7a.table.jsonConfiguration15.9 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_8_ffe985cd460257741383.table.jsonConfiguration10.8 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_90_c77ccd9fb10b70b879ae.table.jsonConfiguration11.2 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_91_f71a41ada00b4ecad82c.table.jsonConfiguration10.4 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_92_07d7904609e85a81cd22.table.jsonConfiguration9.4 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_93_d7dad38129ecd6ecd893.table.jsonConfiguration13.0 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_94_83153708d414de54b669.table.jsonConfiguration10.2 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_95_9e5f0cf025172e0029e0.table.jsonConfiguration14.6 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_96_79a2c42db639f985312c.table.jsonConfiguration14.3 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_97_c9730cfd850f41f1a7f4.table.jsonConfiguration15.2 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_98_652e2e7e6f062b277fb5.table.jsonConfiguration12.5 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_99_2fd87ae3edf2bc1eaf6f.table.jsonConfiguration9.6 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/media/table/samples/rollouts_9_a5003b454f251550be25.table.jsonConfiguration9.7 KB —
models/rl_new_v2/run14_qwen38b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260828_043047-1m8d44p3/files/wandb-metadata.jsonConfiguration6.9 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/adapter_config.jsonConfiguration38 B —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-110/adapter_config.jsonConfiguration38 B —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-110/config.jsonConfiguration1.6 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-110/generation_config.jsonConfiguration139 B —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-110/rl_args.jsonConfiguration2.9 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-130/adapter_config.jsonConfiguration38 B —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-130/config.jsonConfiguration1.6 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-130/generation_config.jsonConfiguration139 B —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-130/rl_args.jsonConfiguration2.9 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-140/adapter_config.jsonConfiguration38 B —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-140/config.jsonConfiguration1.6 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-140/generation_config.jsonConfiguration139 B —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-140/rl_args.jsonConfiguration2.9 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-160/adapter_config.jsonConfiguration38 B —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-160/config.jsonConfiguration1.6 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-160/generation_config.jsonConfiguration139 B —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-160/rl_args.jsonConfiguration2.9 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-180/adapter_config.jsonConfiguration38 B —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-180/config.jsonConfiguration1.6 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-180/generation_config.jsonConfiguration139 B —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-180/rl_args.jsonConfiguration2.9 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-180/trainer_state/meta.jsonConfiguration445 B —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-90/adapter_config.jsonConfiguration38 B —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-90/config.jsonConfiguration1.6 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-90/generation_config.jsonConfiguration139 B —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-90/rl_args.jsonConfiguration2.9 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/config.jsonConfiguration1.6 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/generation_config.jsonConfiguration139 B —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/rl_args.jsonConfiguration2.9 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/slack_reporter_state.jsonConfiguration96 B —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011355-dlkijkpu/files/wandb-metadata.jsonConfiguration6.9 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/config.yamlConfiguration14.0 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_0_b76097403ce7bf6a7583.table.jsonConfiguration11.3 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_100_b9d0f4b89a208713eb5f.table.jsonConfiguration14.9 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_101_5aaa5b6970a4a54b3c6e.table.jsonConfiguration10.2 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_102_5a6dd9e352e22d1f53e3.table.jsonConfiguration10.0 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_103_6b7b09473d8859f67a22.table.jsonConfiguration11.1 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_104_e87ad3e7907f892eeece.table.jsonConfiguration12.1 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_105_762cf93c68fffa812edd.table.jsonConfiguration11.5 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_106_4d2964ee55e08826a87c.table.jsonConfiguration11.4 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_107_7b6ce74717fb48ee7a05.table.jsonConfiguration14.6 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_108_9a6ad0efd12cacf6dbff.table.jsonConfiguration10.1 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_109_f83366b398d156c2bb56.table.jsonConfiguration11.2 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_10_71e1cb6a70ff1087baad.table.jsonConfiguration12.6 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_110_b40e7682db55c5176972.table.jsonConfiguration14.1 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_111_0114664b6f2178dba24e.table.jsonConfiguration9.2 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_112_f089eece3365fb35908b.table.jsonConfiguration8.1 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_113_deb2528b2a2f687e20f7.table.jsonConfiguration11.6 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_114_4a73b7139687be793342.table.jsonConfiguration11.9 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_115_5d06e76fc93279f580ff.table.jsonConfiguration9.9 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_116_376dcf3518fb6f993155.table.jsonConfiguration14.1 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_117_9db0e196f718f35dc607.table.jsonConfiguration8.9 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_118_30f295d409fc6c4b219b.table.jsonConfiguration10.4 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_119_3cfdb6123a38a204300f.table.jsonConfiguration11.0 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_11_0965e092880b97198481.table.jsonConfiguration12.4 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_120_4b7c32bd281917f48837.table.jsonConfiguration14.5 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_121_ba9f3e1f6129ac8c77bf.table.jsonConfiguration13.5 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_122_555451a36b4139a6506c.table.jsonConfiguration16.7 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_123_d9272a1c38ce45f9ed15.table.jsonConfiguration13.3 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_124_11d6c9de94336f7c5f01.table.jsonConfiguration13.1 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_125_783785fe6e0c56058665.table.jsonConfiguration14.1 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_126_4ba1b27541eb1f460ccc.table.jsonConfiguration13.6 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_127_1f7c247c8c48c135d154.table.jsonConfiguration12.6 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_128_124eb96b26a3873914fc.table.jsonConfiguration9.1 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_129_7c62fd0f1693625e0c80.table.jsonConfiguration7.2 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_12_ad7ab15b22d2f100c029.table.jsonConfiguration15.7 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_130_05ad7b11c0df9f36d98c.table.jsonConfiguration8.4 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_131_b6de98872ced94028270.table.jsonConfiguration15.5 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_132_ee36658d866de4f876c2.table.jsonConfiguration14.0 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_133_11f58d2c4033f9d3bd32.table.jsonConfiguration11.9 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_134_69b3a647862f1091ee4b.table.jsonConfiguration8.6 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_135_5757bb343277aa828239.table.jsonConfiguration12.6 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_136_11430aacba109108f893.table.jsonConfiguration11.5 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_137_7b1a602c3fcd016bd0b2.table.jsonConfiguration12.8 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_138_eb75500d728bb74d4b99.table.jsonConfiguration14.6 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_139_199f9d57baf5701ee53a.table.jsonConfiguration14.5 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_13_4d6f5db1eada46c0c06b.table.jsonConfiguration13.0 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_140_efbfb2cb4386b0916684.table.jsonConfiguration13.6 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_141_106f547eb55cf0dfe5ed.table.jsonConfiguration8.3 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_142_55e9deef65c24f8a4984.table.jsonConfiguration11.3 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_143_fb33ec69cd013f565b5e.table.jsonConfiguration10.3 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_144_de71a0b875e1aa9326ca.table.jsonConfiguration13.9 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_145_24597f7a2f29ee820dbd.table.jsonConfiguration15.3 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_146_1310ea750e03b653f98d.table.jsonConfiguration8.7 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_147_f8838520cd2b433abd23.table.jsonConfiguration10.7 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_148_49f0bd32d985a4fcd5a8.table.jsonConfiguration14.5 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_149_2c477102453edbd54e26.table.jsonConfiguration12.1 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_14_2ede9b14756a11363b34.table.jsonConfiguration13.7 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_150_3fe6c1199aad8c97b30a.table.jsonConfiguration12.7 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_151_fcd167ea501e105b0218.table.jsonConfiguration11.6 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_152_d346f3ba8ab8a649382a.table.jsonConfiguration10.0 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_153_2243151af0a13534b814.table.jsonConfiguration8.9 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_154_5c799232bc984ec76128.table.jsonConfiguration14.2 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_155_57a7dc81c98cec2028ac.table.jsonConfiguration14.5 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_156_239fbac15b38c6617845.table.jsonConfiguration9.7 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_157_51c69ac37191f15d1ae0.table.jsonConfiguration12.5 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_158_d8d01251d91d29ff7c8a.table.jsonConfiguration10.3 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_159_012248574e73b0cd0dfc.table.jsonConfiguration12.2 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_15_f229517261edb73dfadd.table.jsonConfiguration11.4 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_160_5573b72b63423f404cd5.table.jsonConfiguration10.4 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_161_5fdc25a628bb7a81f1ca.table.jsonConfiguration7.8 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_162_9f37cb0fcc45d2556889.table.jsonConfiguration17.0 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_163_a0056d7d453fce067d84.table.jsonConfiguration9.5 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_164_fdd2f5a36e221b1582ac.table.jsonConfiguration14.3 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_165_b4f711afcbce41487e68.table.jsonConfiguration10.2 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_166_691047c9f34c4cdbbc54.table.jsonConfiguration12.8 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_167_a79d725618b5c958e248.table.jsonConfiguration14.8 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_168_cdc757ad3765486c401c.table.jsonConfiguration8.8 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_169_5e32fbaecc01acc4b351.table.jsonConfiguration13.4 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_16_5e527033928e3de5381c.table.jsonConfiguration11.4 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_170_c5fb7a3bae6dde96eb02.table.jsonConfiguration9.7 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_171_36360b4ca2328016b2e6.table.jsonConfiguration10.0 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_172_ac97c5c88eaf06083153.table.jsonConfiguration11.9 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_173_02cd6792b2c5593d57ee.table.jsonConfiguration9.2 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_174_5f4591ce0c6bd95e6274.table.jsonConfiguration14.7 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_175_103131081be380dd9704.table.jsonConfiguration11.1 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_176_c873c60ced5ec03bbdea.table.jsonConfiguration12.6 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_177_8a77320ac573a817e93b.table.jsonConfiguration8.6 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_178_fb81937c20eb942df8cb.table.jsonConfiguration14.3 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_179_41b7758f618ebabab6c1.table.jsonConfiguration10.6 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_17_2e3fc3671d4b5f418d97.table.jsonConfiguration14.6 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_18_1ed8dbd596bda17114e3.table.jsonConfiguration11.0 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_19_086c17d90c36248786f4.table.jsonConfiguration10.3 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_1_fddb9874c7843eb43408.table.jsonConfiguration13.2 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_20_18ff4fcbace86153388d.table.jsonConfiguration14.4 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_21_39491669304744e16739.table.jsonConfiguration16.8 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_22_9f51d38359f6d5d8dd71.table.jsonConfiguration10.0 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_23_869d1d66efe771d39a25.table.jsonConfiguration11.7 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_24_de9291f4968d7f060d74.table.jsonConfiguration13.4 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_25_5e3ec741dcb89fe26fe7.table.jsonConfiguration11.1 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_26_5d8e1b9b889144626926.table.jsonConfiguration8.7 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_27_a02c90482f50c982876f.table.jsonConfiguration13.1 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_28_7a9d0c930444b5adb0a9.table.jsonConfiguration11.4 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_29_312d022b4e4345146285.table.jsonConfiguration16.2 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_2_bc71c410748a9a19d618.table.jsonConfiguration12.4 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_30_e8eaefcbf8ed3228e255.table.jsonConfiguration8.4 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_31_62e9e852f4938d68a102.table.jsonConfiguration13.5 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_32_a7341dfa83afac337306.table.jsonConfiguration10.6 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_33_3f556cd6fe65c8ac37e7.table.jsonConfiguration13.8 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_34_113c92531bd7e77a2bd3.table.jsonConfiguration9.3 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_35_ce8aeac8d25046dec98f.table.jsonConfiguration11.4 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_36_e1e27ccac4baaea64382.table.jsonConfiguration13.1 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_37_731eeaf5576c284589be.table.jsonConfiguration12.9 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_38_d40dc53db62b1a045eac.table.jsonConfiguration7.9 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_39_f7e1fe10ab3641c66807.table.jsonConfiguration9.8 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_3_9a872899ed9539286e23.table.jsonConfiguration11.5 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_40_a370e19fe308d5914af8.table.jsonConfiguration10.0 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_41_1cc68de3ac74e5bc3b41.table.jsonConfiguration9.3 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_42_655c89967e0a61c7cfcb.table.jsonConfiguration6.1 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_43_c6c39413ca36ab1cf228.table.jsonConfiguration16.0 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_44_2c52fc17eb9d79d8e9d9.table.jsonConfiguration11.9 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_45_7c049cc59227fc35ca00.table.jsonConfiguration7.9 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_46_8c5368753a62cfbcb658.table.jsonConfiguration10.8 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_47_3d7d773659c476ab3255.table.jsonConfiguration10.7 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_48_bbbc70e23828e4d80e0e.table.jsonConfiguration10.5 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_49_99cf1cc66a914a12e1d7.table.jsonConfiguration14.8 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_4_04a03aef9f508787c7cd.table.jsonConfiguration12.9 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_50_1b47f2ac7c2797e2e00e.table.jsonConfiguration9.6 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_51_c3b75dd8e8ca79b1bb06.table.jsonConfiguration12.5 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_52_de489d4a0e9c8c170d16.table.jsonConfiguration12.1 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_53_69715a32f1ea8ac9ffc7.table.jsonConfiguration17.2 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_54_9df871cab5d5f2a0ae45.table.jsonConfiguration14.7 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_55_6a7bd278f5bf46a9fccd.table.jsonConfiguration10.2 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_56_51634bb4f06ff990f039.table.jsonConfiguration9.9 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_57_bae2478d51c7e1e6964f.table.jsonConfiguration17.1 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_58_6366075944af7bf3cc83.table.jsonConfiguration11.1 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_59_540dfd67eafdb76a1c49.table.jsonConfiguration9.8 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_5_1e79a2d282eef70e7637.table.jsonConfiguration9.9 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_60_11e403d44b211283a2b6.table.jsonConfiguration10.2 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_61_1722ad58e6fe557f1062.table.jsonConfiguration12.0 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_62_fb6a1fa29602e9f8cf6d.table.jsonConfiguration10.9 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_63_d847e323f734a3a474c4.table.jsonConfiguration13.6 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_64_1b93a18460404338f0ce.table.jsonConfiguration9.7 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_65_869097b2cbcca93a830f.table.jsonConfiguration13.4 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_66_cbdb09af46b5f409bd23.table.jsonConfiguration7.7 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_67_178eb91728f332e7f7b5.table.jsonConfiguration12.6 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_68_f74f95f64ef17210fcb5.table.jsonConfiguration8.8 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_69_69348c1e4c635d688420.table.jsonConfiguration10.4 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_6_68ae022cb83bda1418a2.table.jsonConfiguration12.9 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_70_0b4cdf5e7e1febf4559b.table.jsonConfiguration8.0 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_71_c67b1346fe2d08ee4a07.table.jsonConfiguration9.4 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_72_22b4145c93dc2c43e3c0.table.jsonConfiguration14.2 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_73_e7f64bd6dff9fc428262.table.jsonConfiguration11.5 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_74_8e78b13ea6c94fc41d70.table.jsonConfiguration14.1 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_75_79eaa293455a073a0083.table.jsonConfiguration10.5 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_76_292d58cbb9089170cf6a.table.jsonConfiguration10.3 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_77_2c2a00463ad3efcae24c.table.jsonConfiguration14.1 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_78_f18b77e32c95bdf8e983.table.jsonConfiguration10.3 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_79_83fef5197e304604ad87.table.jsonConfiguration11.8 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_7_fb570c425779639362c9.table.jsonConfiguration10.8 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_80_16be0ee33db5b10c58a8.table.jsonConfiguration10.4 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_81_3d3240a7725e7dd159cf.table.jsonConfiguration11.8 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_82_0a15d079f7d7ff4342b2.table.jsonConfiguration11.4 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_83_4ae40b1b64c7c34a8f58.table.jsonConfiguration8.8 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_84_ccfe7cac5a8743fa9a26.table.jsonConfiguration13.8 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_85_efb805fbe572e4d7870d.table.jsonConfiguration16.7 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_86_a10d1936c36a1677d0b5.table.jsonConfiguration16.7 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_87_2c298c8c8b0c08deb9e4.table.jsonConfiguration8.5 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_88_03e1bff586f57e4528fe.table.jsonConfiguration12.4 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_89_5a2f4845ba331b865539.table.jsonConfiguration10.3 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_8_45d58c5c44474dcbedc1.table.jsonConfiguration12.9 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_90_6fb36c69a3c0f0ebe9df.table.jsonConfiguration14.2 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_91_dd3b78087f2b02869a93.table.jsonConfiguration14.3 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_92_9a84f6e052e3d4423a22.table.jsonConfiguration14.3 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_93_2a86e1590de1e92dbaee.table.jsonConfiguration10.4 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_94_40a533396d3b14e91543.table.jsonConfiguration9.4 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_95_efa93ce5800a2f891029.table.jsonConfiguration11.0 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_96_8c1f316b3b8c381615dd.table.jsonConfiguration12.1 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_97_c7c99381dbbaa0b77bb5.table.jsonConfiguration10.5 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_98_410265a874664a2292e2.table.jsonConfiguration12.1 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_99_c852ad29a4c61d516edf.table.jsonConfiguration10.6 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/media/table/samples/rollouts_9_d6f4db19edbe6d5f4597.table.jsonConfiguration14.5 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/wandb-metadata.jsonConfiguration6.9 KB —
models/rl_new_v2/run16_qwen38b_arpo5k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/wandb/run-20260830_011839-0wzqsmc2/files/wandb-summary.jsonConfiguration13.3 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/_aborted_launch_20260901/slack_reporter_state.jsonConfiguration93 B —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/_aborted_launch_20260901/wandb/run-20260901_045650-o3adwyvc/files/media/table/samples/rollouts_0_3db2b5bb42d28313ebfa.table.jsonConfiguration15.5 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/_aborted_launch_20260901/wandb/run-20260901_045650-o3adwyvc/files/media/table/samples/rollouts_1_bcfe8a0c03600f420178.table.jsonConfiguration10.6 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/_aborted_launch_20260901/wandb/run-20260901_045650-o3adwyvc/files/wandb-metadata.jsonConfiguration7.0 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/_aborted_launch_20260901/wandb/run-20260901_054839-5nqgderh/files/wandb-metadata.jsonConfiguration7.0 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/_aborted_launch_20260901/wandb/run-20260901_055730-xjb06bb9/files/wandb-metadata.jsonConfiguration7.0 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-100/adapter_config.jsonConfiguration38 B —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-100/config.jsonConfiguration1.6 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-100/generation_config.jsonConfiguration139 B —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-100/rl_args.jsonConfiguration3.0 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-110/adapter_config.jsonConfiguration38 B —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-110/config.jsonConfiguration1.6 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-110/generation_config.jsonConfiguration139 B —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-110/rl_args.jsonConfiguration3.0 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-110/trainer_state/meta.jsonConfiguration430 B —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-120/adapter_config.jsonConfiguration38 B —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-120/config.jsonConfiguration1.6 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-120/generation_config.jsonConfiguration139 B —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-120/rl_args.jsonConfiguration3.0 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-120/trainer_state/meta.jsonConfiguration430 B —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-80/adapter_config.jsonConfiguration38 B —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-80/config.jsonConfiguration1.6 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-80/generation_config.jsonConfiguration139 B —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-80/rl_args.jsonConfiguration3.0 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-90/adapter_config.jsonConfiguration38 B —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-90/config.jsonConfiguration1.6 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-90/generation_config.jsonConfiguration139 B —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-90/rl_args.jsonConfiguration3.0 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/slack_reporter_state.jsonConfiguration218 B —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260901_061044-r1ruudn6/files/media/table/samples/rollouts_0_ec3d4507e7395bd8d1d0.table.jsonConfiguration16.7 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260901_061044-r1ruudn6/files/media/table/samples/rollouts_100_9a0fe5388048122a5a94.table.jsonConfiguration18.1 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260901_061044-r1ruudn6/files/media/table/samples/rollouts_101_21cdbac671dc3a9b21fd.table.jsonConfiguration17.6 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260901_061044-r1ruudn6/files/media/table/samples/rollouts_102_646aec1854bd9731c5aa.table.jsonConfiguration17.9 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260901_061044-r1ruudn6/files/media/table/samples/rollouts_103_c962a9287945dfe233fe.table.jsonConfiguration16.6 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260901_061044-r1ruudn6/files/media/table/samples/rollouts_104_36d76fd0614f11f7d658.table.jsonConfiguration17.1 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260901_061044-r1ruudn6/files/media/table/samples/rollouts_105_b419a54a6dc267e99543.table.jsonConfiguration17.5 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260901_061044-r1ruudn6/files/media/table/samples/rollouts_106_5c64823c2d38a0872909.table.jsonConfiguration16.9 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260901_061044-r1ruudn6/files/media/table/samples/rollouts_107_6d5cac386ab963bc397c.table.jsonConfiguration17.4 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260901_061044-r1ruudn6/files/media/table/samples/rollouts_108_98520562922f24a4550a.table.jsonConfiguration17.5 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260901_061044-r1ruudn6/files/media/table/samples/rollouts_109_8dce115e40e60b97a669.table.jsonConfiguration18.2 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260901_061044-r1ruudn6/files/media/table/samples/rollouts_10_d360c0925be2738c94d8.table.jsonConfiguration16.7 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260901_061044-r1ruudn6/files/media/table/samples/rollouts_110_009b933d73cbe7096f76.table.jsonConfiguration18.2 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260901_061044-r1ruudn6/files/media/table/samples/rollouts_111_c9778094dd2a03b7fad2.table.jsonConfiguration17.6 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260901_061044-r1ruudn6/files/media/table/samples/rollouts_112_4c06cde4ce8934cf05ec.table.jsonConfiguration17.5 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260901_061044-r1ruudn6/files/media/table/samples/rollouts_113_fe466bd32d0d22ddb28a.table.jsonConfiguration17.5 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260901_061044-r1ruudn6/files/media/table/samples/rollouts_114_4bec1a2cb7af3a93e565.table.jsonConfiguration17.4 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260901_061044-r1ruudn6/files/media/table/samples/rollouts_115_d71575ae2b3600396bf3.table.jsonConfiguration18.2 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260901_061044-r1ruudn6/files/media/table/samples/rollouts_116_bb2c08734ebb8ffcff2b.table.jsonConfiguration16.5 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260901_061044-r1ruudn6/files/media/table/samples/rollouts_117_37491d25a64e66445dd2.table.jsonConfiguration16.5 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260901_061044-r1ruudn6/files/media/table/samples/rollouts_118_0f8cb179c1d9187d04cc.table.jsonConfiguration17.5 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260901_061044-r1ruudn6/files/media/table/samples/rollouts_119_29c2371c430e4b2d07c0.table.jsonConfiguration17.9 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260901_061044-r1ruudn6/files/media/table/samples/rollouts_11_b0e27396265eda1fb5f9.table.jsonConfiguration17.6 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260901_061044-r1ruudn6/files/media/table/samples/rollouts_120_a0ae5f3900eeeda9a0b3.table.jsonConfiguration17.5 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260901_061044-r1ruudn6/files/media/table/samples/rollouts_121_0d6407d4748ca73e54c6.table.jsonConfiguration17.5 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260901_061044-r1ruudn6/files/media/table/samples/rollouts_122_69baa00369b59dd584ec.table.jsonConfiguration17.4 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260901_061044-r1ruudn6/files/media/table/samples/rollouts_123_92c3a19395848a4312ce.table.jsonConfiguration17.7 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260901_061044-r1ruudn6/files/media/table/samples/rollouts_124_59f9cb073b85350fb5f7.table.jsonConfiguration17.1 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260901_061044-r1ruudn6/files/media/table/samples/rollouts_125_24313be2626f2af77bcc.table.jsonConfiguration17.6 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260901_061044-r1ruudn6/files/media/table/samples/rollouts_126_845fede338fa529ba7e9.table.jsonConfiguration16.4 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260901_061044-r1ruudn6/files/media/table/samples/rollouts_12_30a86c26e24e5ec4f73b.table.jsonConfiguration17.1 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260901_061044-r1ruudn6/files/media/table/samples/rollouts_13_020b9ef7968e68c70c5b.table.jsonConfiguration17.6 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260901_061044-r1ruudn6/files/media/table/samples/rollouts_14_646a7d645f89e99e10fd.table.jsonConfiguration17.2 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260901_061044-r1ruudn6/files/media/table/samples/rollouts_15_fb452107b4016eef8885.table.jsonConfiguration17.8 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260901_061044-r1ruudn6/files/media/table/samples/rollouts_16_d5ac5f4a4df7d00371f7.table.jsonConfiguration17.3 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260901_061044-r1ruudn6/files/media/table/samples/rollouts_17_d3aa4177a249360af51d.table.jsonConfiguration17.0 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260901_061044-r1ruudn6/files/media/table/samples/rollouts_18_724fd30ac909abec7bfa.table.jsonConfiguration18.0 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260901_061044-r1ruudn6/files/media/table/samples/rollouts_19_9bc37a55b9d91e083caa.table.jsonConfiguration15.2 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260901_061044-r1ruudn6/files/media/table/samples/rollouts_1_d9b589814259f6906e67.table.jsonConfiguration15.1 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260901_061044-r1ruudn6/files/media/table/samples/rollouts_20_3eacc4f64222e3e305c4.table.jsonConfiguration17.4 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260901_061044-r1ruudn6/files/media/table/samples/rollouts_21_1a6c606a404377ab5d49.table.jsonConfiguration16.9 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260901_061044-r1ruudn6/files/media/table/samples/rollouts_22_c3dc464e12ca4ab4d9b5.table.jsonConfiguration17.4 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260901_061044-r1ruudn6/files/media/table/samples/rollouts_23_dd15e3edcace2da5b23c.table.jsonConfiguration17.5 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260901_061044-r1ruudn6/files/media/table/samples/rollouts_24_e5fbd307c9ba32dd3ccc.table.jsonConfiguration16.6 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260901_061044-r1ruudn6/files/media/table/samples/rollouts_25_7d962d75fa01f8881e4c.table.jsonConfiguration17.5 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260901_061044-r1ruudn6/files/media/table/samples/rollouts_26_c3fd01aa54314b379fe4.table.jsonConfiguration15.7 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260901_061044-r1ruudn6/files/media/table/samples/rollouts_27_f33c53c6535640c9a18e.table.jsonConfiguration18.2 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260901_061044-r1ruudn6/files/media/table/samples/rollouts_28_6c35dff7915783fe2de3.table.jsonConfiguration17.6 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260901_061044-r1ruudn6/files/media/table/samples/rollouts_29_2a5bcb8f7b243553d75d.table.jsonConfiguration17.5 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260901_061044-r1ruudn6/files/media/table/samples/rollouts_2_4c52b76e631a5ab8d94d.table.jsonConfiguration17.9 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260901_061044-r1ruudn6/files/media/table/samples/rollouts_30_cdcd04ded3b1d105c748.table.jsonConfiguration17.1 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260901_061044-r1ruudn6/files/media/table/samples/rollouts_31_fc750695826c768b1e7e.table.jsonConfiguration16.4 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260901_061044-r1ruudn6/files/media/table/samples/rollouts_32_06f2008b5d2f172ec739.table.jsonConfiguration17.7 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260901_061044-r1ruudn6/files/media/table/samples/rollouts_33_f6a016a76bae3a1ccd92.table.jsonConfiguration18.4 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260901_061044-r1ruudn6/files/media/table/samples/rollouts_34_57a801ba0351ab9f5930.table.jsonConfiguration15.9 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260901_061044-r1ruudn6/files/media/table/samples/rollouts_35_b72f6b4b632c0e4d1118.table.jsonConfiguration16.8 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260901_061044-r1ruudn6/files/media/table/samples/rollouts_36_bb2b629918a7afcb8029.table.jsonConfiguration17.4 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260901_061044-r1ruudn6/files/media/table/samples/rollouts_37_45ed7cca00702258cc4b.table.jsonConfiguration16.8 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260901_061044-r1ruudn6/files/media/table/samples/rollouts_38_d56077b6e84c91eef9ae.table.jsonConfiguration16.3 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260901_061044-r1ruudn6/files/media/table/samples/rollouts_39_f8048e16cc4f5d73099d.table.jsonConfiguration17.6 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260901_061044-r1ruudn6/files/media/table/samples/rollouts_3_fa127e80d78dabe37af4.table.jsonConfiguration17.8 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260901_061044-r1ruudn6/files/media/table/samples/rollouts_40_bd4572c8261d7cbce583.table.jsonConfiguration17.8 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260901_061044-r1ruudn6/files/media/table/samples/rollouts_41_405a7a5acc5deba27541.table.jsonConfiguration17.8 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260901_061044-r1ruudn6/files/media/table/samples/rollouts_42_e5836bfd82053fa38f25.table.jsonConfiguration17.5 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260901_061044-r1ruudn6/files/media/table/samples/rollouts_43_cc45a446e697dba61fcc.table.jsonConfiguration17.3 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260901_061044-r1ruudn6/files/media/table/samples/rollouts_44_4b7f787bba8b8d3490fd.table.jsonConfiguration17.5 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260901_061044-r1ruudn6/files/media/table/samples/rollouts_45_ce48bfb55bd8fb865166.table.jsonConfiguration17.8 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260901_061044-r1ruudn6/files/media/table/samples/rollouts_46_33fddbb665170a757a5f.table.jsonConfiguration17.8 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260901_061044-r1ruudn6/files/media/table/samples/rollouts_47_17194c8bf6865a751a17.table.jsonConfiguration17.5 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260901_061044-r1ruudn6/files/media/table/samples/rollouts_48_06caf90c86b460fdf10f.table.jsonConfiguration16.4 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260901_061044-r1ruudn6/files/media/table/samples/rollouts_49_ddc8c06d55ee84cf84c4.table.jsonConfiguration17.5 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260901_061044-r1ruudn6/files/media/table/samples/rollouts_4_48ea625bbfcb8f8c769e.table.jsonConfiguration17.7 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260901_061044-r1ruudn6/files/media/table/samples/rollouts_50_5d053fdb73a32ebb3998.table.jsonConfiguration17.4 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260901_061044-r1ruudn6/files/media/table/samples/rollouts_51_a305aeff51f276df59b8.table.jsonConfiguration17.4 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260901_061044-r1ruudn6/files/media/table/samples/rollouts_52_6d5875c128b0d858a9ab.table.jsonConfiguration17.5 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260901_061044-r1ruudn6/files/media/table/samples/rollouts_53_68d581d0f6e8643789ac.table.jsonConfiguration17.2 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260901_061044-r1ruudn6/files/media/table/samples/rollouts_54_426a34e33f9e803352a5.table.jsonConfiguration17.3 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260901_061044-r1ruudn6/files/media/table/samples/rollouts_55_0ae409ceaad9b7371fb0.table.jsonConfiguration17.8 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260901_061044-r1ruudn6/files/media/table/samples/rollouts_56_536c2b72dc32bf05f445.table.jsonConfiguration18.0 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260901_061044-r1ruudn6/files/media/table/samples/rollouts_57_677002cfe69f6c214c57.table.jsonConfiguration17.7 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260901_061044-r1ruudn6/files/media/table/samples/rollouts_58_d2c926483d5431d4d0ac.table.jsonConfiguration17.5 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260901_061044-r1ruudn6/files/media/table/samples/rollouts_59_a97a8e5d934bf9ca5826.table.jsonConfiguration17.6 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260901_061044-r1ruudn6/files/media/table/samples/rollouts_5_45b0cd26727bfb4c146d.table.jsonConfiguration17.8 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260901_061044-r1ruudn6/files/media/table/samples/rollouts_60_dc22c2bd47a40fca81d4.table.jsonConfiguration17.5 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260901_061044-r1ruudn6/files/media/table/samples/rollouts_61_7e78035788d0c980b81d.table.jsonConfiguration17.7 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260901_061044-r1ruudn6/files/media/table/samples/rollouts_62_16c572aa798f0f644cf3.table.jsonConfiguration15.5 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260901_061044-r1ruudn6/files/media/table/samples/rollouts_63_f4fdebe0c604796b4050.table.jsonConfiguration16.1 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260901_061044-r1ruudn6/files/media/table/samples/rollouts_64_efe88d4c7833da87a641.table.jsonConfiguration17.7 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260901_061044-r1ruudn6/files/media/table/samples/rollouts_65_d49e1e3fa593218a74b1.table.jsonConfiguration17.9 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260901_061044-r1ruudn6/files/media/table/samples/rollouts_66_6bed00910c309200e55d.table.jsonConfiguration16.7 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260901_061044-r1ruudn6/files/media/table/samples/rollouts_67_adb63b3ff44e037fd39e.table.jsonConfiguration17.1 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260901_061044-r1ruudn6/files/media/table/samples/rollouts_68_6ca214109499d83ab773.table.jsonConfiguration17.0 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260901_061044-r1ruudn6/files/media/table/samples/rollouts_69_ee796ab9578fa6bbc153.table.jsonConfiguration17.3 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260901_061044-r1ruudn6/files/media/table/samples/rollouts_6_a90eb034f109b4240426.table.jsonConfiguration17.5 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260901_061044-r1ruudn6/files/media/table/samples/rollouts_70_c03645e7011b9fd00d28.table.jsonConfiguration17.6 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260901_061044-r1ruudn6/files/media/table/samples/rollouts_71_75ad46294c957e1462b8.table.jsonConfiguration17.6 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260901_061044-r1ruudn6/files/media/table/samples/rollouts_72_cebebd37790210618695.table.jsonConfiguration16.9 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260901_061044-r1ruudn6/files/media/table/samples/rollouts_73_3c81491251d403b4e02b.table.jsonConfiguration17.0 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260901_061044-r1ruudn6/files/media/table/samples/rollouts_74_6740e7872bd9467005b6.table.jsonConfiguration15.2 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260901_061044-r1ruudn6/files/media/table/samples/rollouts_75_fc44d5f0ef320ceb62c4.table.jsonConfiguration17.5 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260901_061044-r1ruudn6/files/media/table/samples/rollouts_76_2654052b78669bc6e268.table.jsonConfiguration17.6 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260901_061044-r1ruudn6/files/media/table/samples/rollouts_77_3f781161fb7c5db219c3.table.jsonConfiguration17.5 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260901_061044-r1ruudn6/files/media/table/samples/rollouts_78_f0ad3dfaf9eaa407cf3c.table.jsonConfiguration17.5 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260901_061044-r1ruudn6/files/media/table/samples/rollouts_79_201820813042224990ec.table.jsonConfiguration17.5 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260901_061044-r1ruudn6/files/media/table/samples/rollouts_7_6475b8c6dc59d322aca9.table.jsonConfiguration17.6 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260901_061044-r1ruudn6/files/media/table/samples/rollouts_80_909fc22622c40c39f2b7.table.jsonConfiguration18.1 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260901_061044-r1ruudn6/files/media/table/samples/rollouts_81_237c7e4f3f979856fa8b.table.jsonConfiguration15.9 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260901_061044-r1ruudn6/files/media/table/samples/rollouts_82_e08f22132eec8f45b826.table.jsonConfiguration16.7 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260901_061044-r1ruudn6/files/media/table/samples/rollouts_83_524631230cbacd3f6d2d.table.jsonConfiguration17.2 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260901_061044-r1ruudn6/files/media/table/samples/rollouts_84_84584ffa65af4fce19bd.table.jsonConfiguration15.5 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260901_061044-r1ruudn6/files/media/table/samples/rollouts_85_405afdb154d6e6eb5301.table.jsonConfiguration17.0 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260901_061044-r1ruudn6/files/media/table/samples/rollouts_86_00e4077de9a921a939a9.table.jsonConfiguration18.0 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260901_061044-r1ruudn6/files/media/table/samples/rollouts_87_edb7129327e2fd688811.table.jsonConfiguration18.1 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260901_061044-r1ruudn6/files/media/table/samples/rollouts_88_6cfd1dd2667d944edb53.table.jsonConfiguration17.3 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260901_061044-r1ruudn6/files/media/table/samples/rollouts_89_ef86f6ed431f96e637a4.table.jsonConfiguration16.1 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260901_061044-r1ruudn6/files/media/table/samples/rollouts_8_07bfb83ffaa39b869cfa.table.jsonConfiguration17.4 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260901_061044-r1ruudn6/files/media/table/samples/rollouts_90_8cb2ed81c55261161c81.table.jsonConfiguration16.5 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260901_061044-r1ruudn6/files/media/table/samples/rollouts_91_99ade9241ed195037dca.table.jsonConfiguration17.4 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260901_061044-r1ruudn6/files/media/table/samples/rollouts_92_022aef047c642bb2e346.table.jsonConfiguration17.1 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260901_061044-r1ruudn6/files/media/table/samples/rollouts_93_dfd173824445aa981af5.table.jsonConfiguration17.8 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260901_061044-r1ruudn6/files/media/table/samples/rollouts_94_dc4d9ae0737a0167e595.table.jsonConfiguration17.8 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260901_061044-r1ruudn6/files/media/table/samples/rollouts_95_730d994a5e40a3cb1bcb.table.jsonConfiguration17.4 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260901_061044-r1ruudn6/files/media/table/samples/rollouts_96_6f6e5a78802f64ef39ec.table.jsonConfiguration16.1 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260901_061044-r1ruudn6/files/media/table/samples/rollouts_97_3176cf68c85f5705a4e8.table.jsonConfiguration16.7 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260901_061044-r1ruudn6/files/media/table/samples/rollouts_98_16630321cd7e37d48ab0.table.jsonConfiguration13.7 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260901_061044-r1ruudn6/files/media/table/samples/rollouts_99_e3abcb80cd19ce9d91dd.table.jsonConfiguration17.7 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260901_061044-r1ruudn6/files/media/table/samples/rollouts_9_0b227cb64c3d82138c87.table.jsonConfiguration16.6 KB —
models/rl_new_v2/run17_qwen38b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260901_061044-r1ruudn6/files/wandb-metadata.jsonConfiguration7.0 KB —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/adapter_config.jsonConfiguration38 B —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-100/adapter_config.jsonConfiguration38 B —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-100/config.jsonConfiguration1.7 KB —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-100/generation_config.jsonConfiguration139 B —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-100/rl_args.jsonConfiguration3.0 KB —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-110/adapter_config.jsonConfiguration38 B —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-110/config.jsonConfiguration1.7 KB —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-110/generation_config.jsonConfiguration139 B —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-110/rl_args.jsonConfiguration3.0 KB —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-110/trainer_state/meta.jsonConfiguration431 B —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-120/adapter_config.jsonConfiguration38 B —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-120/config.jsonConfiguration1.7 KB —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-120/generation_config.jsonConfiguration139 B —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-120/rl_args.jsonConfiguration3.0 KB —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-120/trainer_state/meta.jsonConfiguration431 B —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-80/adapter_config.jsonConfiguration38 B —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-80/config.jsonConfiguration1.7 KB —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-80/generation_config.jsonConfiguration139 B —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-80/rl_args.jsonConfiguration3.0 KB —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-90/adapter_config.jsonConfiguration38 B —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-90/config.jsonConfiguration1.7 KB —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-90/generation_config.jsonConfiguration139 B —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/checkpoint-90/rl_args.jsonConfiguration3.0 KB —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/config.jsonConfiguration1.7 KB —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/generation_config.jsonConfiguration139 B —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/rl_args.jsonConfiguration3.0 KB —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/slack_reporter_state.jsonConfiguration96 B —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260904_035118-ktardbpf/files/config.yamlConfiguration14.3 KB —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260904_035118-ktardbpf/files/media/table/samples/rollouts_0_9c68340a29e224e2ece2.table.jsonConfiguration16.6 KB —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260904_035118-ktardbpf/files/media/table/samples/rollouts_100_9c87f3ef2c7627a51625.table.jsonConfiguration17.4 KB —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260904_035118-ktardbpf/files/media/table/samples/rollouts_101_60f40fc27e3b80326025.table.jsonConfiguration15.9 KB —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260904_035118-ktardbpf/files/media/table/samples/rollouts_102_3519937c9495e004e988.table.jsonConfiguration17.8 KB —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260904_035118-ktardbpf/files/media/table/samples/rollouts_103_aea06cb8abbddfdd6821.table.jsonConfiguration16.6 KB —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260904_035118-ktardbpf/files/media/table/samples/rollouts_104_6d8e340ac046628c55dd.table.jsonConfiguration17.5 KB —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260904_035118-ktardbpf/files/media/table/samples/rollouts_105_eaef22cc76782b3962f3.table.jsonConfiguration17.0 KB —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260904_035118-ktardbpf/files/media/table/samples/rollouts_106_5641c9e76f78dec8b569.table.jsonConfiguration17.1 KB —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260904_035118-ktardbpf/files/media/table/samples/rollouts_107_875e6aca1842265f0337.table.jsonConfiguration17.5 KB —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260904_035118-ktardbpf/files/media/table/samples/rollouts_108_844af7d1b8ea47bee01c.table.jsonConfiguration17.8 KB —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260904_035118-ktardbpf/files/media/table/samples/rollouts_109_4b7cbf636361545979fa.table.jsonConfiguration18.2 KB —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260904_035118-ktardbpf/files/media/table/samples/rollouts_10_82c168e5c389bc803234.table.jsonConfiguration16.1 KB —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260904_035118-ktardbpf/files/media/table/samples/rollouts_110_1673b897a61b04111d50.table.jsonConfiguration18.2 KB —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260904_035118-ktardbpf/files/media/table/samples/rollouts_111_94db88d6f9ec49bb8d8d.table.jsonConfiguration17.6 KB —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260904_035118-ktardbpf/files/media/table/samples/rollouts_112_89efd2aa79c8471a8dfa.table.jsonConfiguration17.5 KB —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260904_035118-ktardbpf/files/media/table/samples/rollouts_113_cdd1534da6b087d091f8.table.jsonConfiguration17.8 KB —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260904_035118-ktardbpf/files/media/table/samples/rollouts_114_c44b6e1401c7924156fc.table.jsonConfiguration18.5 KB —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260904_035118-ktardbpf/files/media/table/samples/rollouts_115_cf664b785aaa080eb91a.table.jsonConfiguration18.2 KB —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260904_035118-ktardbpf/files/media/table/samples/rollouts_116_d231dc22c451a594102b.table.jsonConfiguration16.3 KB —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260904_035118-ktardbpf/files/media/table/samples/rollouts_117_62b057419d08985ee666.table.jsonConfiguration17.5 KB —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260904_035118-ktardbpf/files/media/table/samples/rollouts_118_5cee1debaeb8fc7f5f0a.table.jsonConfiguration17.3 KB —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260904_035118-ktardbpf/files/media/table/samples/rollouts_119_94e0f3d3f5ff8dfd14b3.table.jsonConfiguration18.0 KB —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260904_035118-ktardbpf/files/media/table/samples/rollouts_11_1d37a0c5461628c50098.table.jsonConfiguration17.7 KB —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260904_035118-ktardbpf/files/media/table/samples/rollouts_12_e4c00df1c8fc8c911e34.table.jsonConfiguration17.5 KB —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260904_035118-ktardbpf/files/media/table/samples/rollouts_13_9d29c2311a673fa614e3.table.jsonConfiguration17.4 KB —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260904_035118-ktardbpf/files/media/table/samples/rollouts_14_2b061f0e4718744fec7d.table.jsonConfiguration17.6 KB —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260904_035118-ktardbpf/files/media/table/samples/rollouts_15_e01762cd458d5ce053ef.table.jsonConfiguration17.0 KB —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260904_035118-ktardbpf/files/media/table/samples/rollouts_16_578a8ca1d57c97141532.table.jsonConfiguration17.6 KB —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260904_035118-ktardbpf/files/media/table/samples/rollouts_17_ac2bbd89a0c858a13fb1.table.jsonConfiguration17.7 KB —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260904_035118-ktardbpf/files/media/table/samples/rollouts_18_3a4d631d396fa93f1f02.table.jsonConfiguration17.2 KB —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260904_035118-ktardbpf/files/media/table/samples/rollouts_19_050332e3de30e62b8b70.table.jsonConfiguration17.4 KB —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260904_035118-ktardbpf/files/media/table/samples/rollouts_1_6e00dc1f8e81db95acce.table.jsonConfiguration17.5 KB —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260904_035118-ktardbpf/files/media/table/samples/rollouts_20_365615065d06cc7a2cd5.table.jsonConfiguration17.5 KB —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260904_035118-ktardbpf/files/media/table/samples/rollouts_21_fdc125ed63f4b9f8cd09.table.jsonConfiguration16.8 KB —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260904_035118-ktardbpf/files/media/table/samples/rollouts_22_efcd075f88b5a2b90451.table.jsonConfiguration17.9 KB —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260904_035118-ktardbpf/files/media/table/samples/rollouts_23_965cffc65ea4a696be43.table.jsonConfiguration17.5 KB —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260904_035118-ktardbpf/files/media/table/samples/rollouts_24_147ce77b7465e4ce7bdf.table.jsonConfiguration17.5 KB —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260904_035118-ktardbpf/files/media/table/samples/rollouts_25_879dbd446b545d9bcd61.table.jsonConfiguration18.0 KB —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260904_035118-ktardbpf/files/media/table/samples/rollouts_26_4cf2e42e31d4cea62749.table.jsonConfiguration16.1 KB —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260904_035118-ktardbpf/files/media/table/samples/rollouts_27_a0298145213ed605bef6.table.jsonConfiguration17.8 KB —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260904_035118-ktardbpf/files/media/table/samples/rollouts_28_3aabe72c938efcec0b0d.table.jsonConfiguration16.3 KB —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260904_035118-ktardbpf/files/media/table/samples/rollouts_29_8fe558630155d989f3d6.table.jsonConfiguration17.6 KB —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260904_035118-ktardbpf/files/media/table/samples/rollouts_2_975c13304604819bd6e3.table.jsonConfiguration17.7 KB —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260904_035118-ktardbpf/files/media/table/samples/rollouts_30_bb06ab313a1d24f15a77.table.jsonConfiguration18.1 KB —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260904_035118-ktardbpf/files/media/table/samples/rollouts_31_4a55dccfaaac17c31084.table.jsonConfiguration17.9 KB —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260904_035118-ktardbpf/files/media/table/samples/rollouts_32_d79d656418a915e18734.table.jsonConfiguration17.3 KB —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260904_035118-ktardbpf/files/media/table/samples/rollouts_33_7e022e18ba28c526c6a2.table.jsonConfiguration18.3 KB —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260904_035118-ktardbpf/files/media/table/samples/rollouts_34_5f425b7c15c9cd14a2b1.table.jsonConfiguration16.3 KB —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260904_035118-ktardbpf/files/media/table/samples/rollouts_35_877f224a2576c0f75b55.table.jsonConfiguration17.9 KB —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260904_035118-ktardbpf/files/media/table/samples/rollouts_36_30bee58bbe2ea0d85b64.table.jsonConfiguration16.8 KB —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260904_035118-ktardbpf/files/media/table/samples/rollouts_37_634bd3ab3c4099fa740f.table.jsonConfiguration15.1 KB —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260904_035118-ktardbpf/files/media/table/samples/rollouts_38_3eaacbc67e52005b09b6.table.jsonConfiguration16.3 KB —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260904_035118-ktardbpf/files/media/table/samples/rollouts_39_f4ee142dc1ec0423ef6c.table.jsonConfiguration17.5 KB —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260904_035118-ktardbpf/files/media/table/samples/rollouts_3_e41075b55e42de3de107.table.jsonConfiguration17.6 KB —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260904_035118-ktardbpf/files/media/table/samples/rollouts_40_c8084ae755cd55b801ae.table.jsonConfiguration17.5 KB —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260904_035118-ktardbpf/files/media/table/samples/rollouts_41_60339e7b46baf032a5bd.table.jsonConfiguration17.7 KB —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260904_035118-ktardbpf/files/media/table/samples/rollouts_42_4b1df3bebe2cfa2b1c3b.table.jsonConfiguration17.1 KB —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260904_035118-ktardbpf/files/media/table/samples/rollouts_43_325282d02be78a3523a8.table.jsonConfiguration16.4 KB —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260904_035118-ktardbpf/files/media/table/samples/rollouts_44_0c40173e53e3d6024bca.table.jsonConfiguration14.4 KB —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260904_035118-ktardbpf/files/media/table/samples/rollouts_45_3d383057f62d990e66a2.table.jsonConfiguration17.2 KB —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260904_035118-ktardbpf/files/media/table/samples/rollouts_46_5105dd9f0f27ee752579.table.jsonConfiguration16.9 KB —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260904_035118-ktardbpf/files/media/table/samples/rollouts_47_a1970dd90a3360a87a68.table.jsonConfiguration16.6 KB —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260904_035118-ktardbpf/files/media/table/samples/rollouts_48_aecf9bf3c7a7c696674b.table.jsonConfiguration17.5 KB —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260904_035118-ktardbpf/files/media/table/samples/rollouts_49_2c0dc1dcc11c9e6bf263.table.jsonConfiguration15.9 KB —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260904_035118-ktardbpf/files/media/table/samples/rollouts_4_7cffb9e9b8fe67956261.table.jsonConfiguration17.6 KB —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260904_035118-ktardbpf/files/media/table/samples/rollouts_50_30af26888936cd5032e3.table.jsonConfiguration16.5 KB —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260904_035118-ktardbpf/files/media/table/samples/rollouts_51_17686e963d8f01306d47.table.jsonConfiguration17.7 KB —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260904_035118-ktardbpf/files/media/table/samples/rollouts_52_a84c8aed0bf03432e429.table.jsonConfiguration17.4 KB —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260904_035118-ktardbpf/files/media/table/samples/rollouts_53_6e58f8e6c0294b8125ad.table.jsonConfiguration17.9 KB —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260904_035118-ktardbpf/files/media/table/samples/rollouts_54_99b810927f8090e1722f.table.jsonConfiguration16.8 KB —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260904_035118-ktardbpf/files/media/table/samples/rollouts_55_7475f39dcc6d58a61f3b.table.jsonConfiguration18.4 KB —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260904_035118-ktardbpf/files/media/table/samples/rollouts_56_1f69aaa72e221b7a665c.table.jsonConfiguration18.1 KB —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260904_035118-ktardbpf/files/media/table/samples/rollouts_57_a51407dceb3bc4da29f1.table.jsonConfiguration17.5 KB —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260904_035118-ktardbpf/files/media/table/samples/rollouts_58_c7d80a1a0f30c37ce5ca.table.jsonConfiguration17.5 KB —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260904_035118-ktardbpf/files/media/table/samples/rollouts_59_6f819958a1170be44ccc.table.jsonConfiguration17.4 KB —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260904_035118-ktardbpf/files/media/table/samples/rollouts_5_ef181fec8a600dc68d49.table.jsonConfiguration17.9 KB —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260904_035118-ktardbpf/files/media/table/samples/rollouts_60_145421be55e0336d55f5.table.jsonConfiguration17.4 KB —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260904_035118-ktardbpf/files/media/table/samples/rollouts_61_da96a696ed81e4ffcf1b.table.jsonConfiguration17.4 KB —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260904_035118-ktardbpf/files/media/table/samples/rollouts_62_381d57f6f5896c668285.table.jsonConfiguration15.7 KB —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260904_035118-ktardbpf/files/media/table/samples/rollouts_63_365ee9d258e61fad73ae.table.jsonConfiguration16.2 KB —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260904_035118-ktardbpf/files/media/table/samples/rollouts_64_08a53627ba8cb1a8c482.table.jsonConfiguration17.7 KB —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260904_035118-ktardbpf/files/media/table/samples/rollouts_65_647fd53efee3284d4ab4.table.jsonConfiguration18.0 KB —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260904_035118-ktardbpf/files/media/table/samples/rollouts_66_ed89f3b8c8d68f49db01.table.jsonConfiguration17.6 KB —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260904_035118-ktardbpf/files/media/table/samples/rollouts_67_b73e094c63f54b48700a.table.jsonConfiguration16.8 KB —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260904_035118-ktardbpf/files/media/table/samples/rollouts_68_fde49e8af27caa880f02.table.jsonConfiguration17.3 KB —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260904_035118-ktardbpf/files/media/table/samples/rollouts_69_ae1b1333013adb47c9ed.table.jsonConfiguration17.6 KB —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260904_035118-ktardbpf/files/media/table/samples/rollouts_6_c926e5df6d2e19465a19.table.jsonConfiguration17.4 KB —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260904_035118-ktardbpf/files/media/table/samples/rollouts_70_31be3659bda3e81c1e96.table.jsonConfiguration17.6 KB —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260904_035118-ktardbpf/files/media/table/samples/rollouts_71_11fcbc51abdf576d2540.table.jsonConfiguration15.8 KB —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260904_035118-ktardbpf/files/media/table/samples/rollouts_72_87a851d0f27e52735980.table.jsonConfiguration16.7 KB —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260904_035118-ktardbpf/files/media/table/samples/rollouts_73_65624ba7983754c00e21.table.jsonConfiguration16.6 KB —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260904_035118-ktardbpf/files/media/table/samples/rollouts_74_aacbd4fcf4e23632552d.table.jsonConfiguration14.7 KB —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260904_035118-ktardbpf/files/media/table/samples/rollouts_75_df621b50b90ea3863e44.table.jsonConfiguration17.6 KB —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260904_035118-ktardbpf/files/media/table/samples/rollouts_76_0b18452fb7d6494b2296.table.jsonConfiguration17.8 KB —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260904_035118-ktardbpf/files/media/table/samples/rollouts_77_62f14aa93948822b5922.table.jsonConfiguration17.0 KB —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260904_035118-ktardbpf/files/media/table/samples/rollouts_78_5577588ec0678bf0ed68.table.jsonConfiguration16.2 KB —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260904_035118-ktardbpf/files/media/table/samples/rollouts_79_e1df9ecbd96cff847ca1.table.jsonConfiguration17.3 KB —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260904_035118-ktardbpf/files/media/table/samples/rollouts_7_b18f370ba4ece614e38a.table.jsonConfiguration17.6 KB —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260904_035118-ktardbpf/files/media/table/samples/rollouts_80_94789cc342b94fb57b48.table.jsonConfiguration18.1 KB —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260904_035118-ktardbpf/files/media/table/samples/rollouts_81_4ff6e4f5365da1f69ae5.table.jsonConfiguration15.0 KB —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260904_035118-ktardbpf/files/media/table/samples/rollouts_82_85fb6542b0b08b6d077d.table.jsonConfiguration16.2 KB —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260904_035118-ktardbpf/files/media/table/samples/rollouts_83_dc017d3fa548ba316672.table.jsonConfiguration17.1 KB —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260904_035118-ktardbpf/files/media/table/samples/rollouts_84_1e57bacaae60fd1d6a92.table.jsonConfiguration17.5 KB —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260904_035118-ktardbpf/files/media/table/samples/rollouts_85_a10b8864770e1e20bd9b.table.jsonConfiguration17.4 KB —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260904_035118-ktardbpf/files/media/table/samples/rollouts_86_0e652ce4fdb65cdbd70b.table.jsonConfiguration18.0 KB —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260904_035118-ktardbpf/files/media/table/samples/rollouts_87_4babdda034f79f9ecd31.table.jsonConfiguration17.6 KB —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260904_035118-ktardbpf/files/media/table/samples/rollouts_88_4eb9ed25f8bba8144b91.table.jsonConfiguration17.4 KB —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260904_035118-ktardbpf/files/media/table/samples/rollouts_89_92a613a9d971093a6296.table.jsonConfiguration18.0 KB —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260904_035118-ktardbpf/files/media/table/samples/rollouts_8_53ddbd3bccda8246e570.table.jsonConfiguration17.9 KB —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260904_035118-ktardbpf/files/media/table/samples/rollouts_90_d86c22741fe76ed2224b.table.jsonConfiguration16.5 KB —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260904_035118-ktardbpf/files/media/table/samples/rollouts_91_ed3b1b3b9bcc80bce4ea.table.jsonConfiguration16.9 KB —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260904_035118-ktardbpf/files/media/table/samples/rollouts_92_47d11218aafbdb974e02.table.jsonConfiguration16.4 KB —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260904_035118-ktardbpf/files/media/table/samples/rollouts_93_4f406f685792045dab01.table.jsonConfiguration18.0 KB —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260904_035118-ktardbpf/files/media/table/samples/rollouts_94_9bbb27962e819dd66872.table.jsonConfiguration17.8 KB —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260904_035118-ktardbpf/files/media/table/samples/rollouts_95_15a3d509a61598c78b7e.table.jsonConfiguration18.0 KB —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260904_035118-ktardbpf/files/media/table/samples/rollouts_96_20a465f504c8e663eac6.table.jsonConfiguration15.0 KB —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260904_035118-ktardbpf/files/media/table/samples/rollouts_97_ff4bb301f39b96d16fe8.table.jsonConfiguration17.1 KB —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260904_035118-ktardbpf/files/media/table/samples/rollouts_98_86af37cbeb905a69cef5.table.jsonConfiguration14.4 KB —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260904_035118-ktardbpf/files/media/table/samples/rollouts_99_bcd92a4dd5a38c33e001.table.jsonConfiguration17.6 KB —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260904_035118-ktardbpf/files/media/table/samples/rollouts_9_ea1863239b94861c487f.table.jsonConfiguration16.7 KB —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260904_035118-ktardbpf/files/wandb-metadata.jsonConfiguration7.0 KB —
models/rl_new_v2/run18_qwen314b_ds1k_arpoaddqaf1_latentfmt_batch_p64_q12000_lat200_sr300_tc6_valgh3S3tf15_seed123_4node/wandb/run-20260904_035118-ktardbpf/files/wandb-summary.jsonConfiguration14.2 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g16_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_061730-8p3mzn9e/files/media/table/samples/rollouts_0_4ec95b2c91c879d3780e.table.jsonConfiguration12.8 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g16_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_061730-8p3mzn9e/files/media/table/samples/rollouts_1_d2077e42c03b5fbd0eff.table.jsonConfiguration10.0 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g16_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_061730-8p3mzn9e/files/media/table/samples/rollouts_2_bd8543c1140127819364.table.jsonConfiguration11.3 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g16_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_061730-8p3mzn9e/files/media/table/samples/rollouts_3_576d276b0e1de5d45f65.table.jsonConfiguration13.3 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g16_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_061730-8p3mzn9e/files/media/table/samples/rollouts_4_57781bf8f00067bec399.table.jsonConfiguration8.8 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g16_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_061730-8p3mzn9e/files/media/table/samples/rollouts_5_2311e415ad6038041656.table.jsonConfiguration8.6 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g16_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_061730-8p3mzn9e/files/media/table/samples/rollouts_6_e14e1837953da51894f3.table.jsonConfiguration13.4 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g16_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_061730-8p3mzn9e/files/wandb-metadata.jsonConfiguration5.7 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/adapter_config.jsonConfiguration38 B —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/checkpoint-100/adapter_config.jsonConfiguration38 B —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/checkpoint-100/config.jsonConfiguration1.7 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/checkpoint-100/generation_config.jsonConfiguration139 B —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/checkpoint-100/rl_args.jsonConfiguration3.1 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/checkpoint-120/adapter_config.jsonConfiguration38 B —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/checkpoint-120/config.jsonConfiguration1.7 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/checkpoint-120/generation_config.jsonConfiguration139 B —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/checkpoint-120/rl_args.jsonConfiguration3.1 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/checkpoint-140/adapter_config.jsonConfiguration38 B —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/checkpoint-140/config.jsonConfiguration1.7 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/checkpoint-140/generation_config.jsonConfiguration139 B —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/checkpoint-140/rl_args.jsonConfiguration3.1 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/checkpoint-160/adapter_config.jsonConfiguration38 B —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/checkpoint-160/config.jsonConfiguration1.7 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/checkpoint-160/generation_config.jsonConfiguration139 B —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/checkpoint-160/rl_args.jsonConfiguration3.1 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/checkpoint-180/adapter_config.jsonConfiguration38 B —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/checkpoint-180/config.jsonConfiguration1.7 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/checkpoint-180/generation_config.jsonConfiguration139 B —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/checkpoint-180/rl_args.jsonConfiguration3.1 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/checkpoint-180/trainer_state/meta.jsonConfiguration474 B —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/checkpoint-80/adapter_config.jsonConfiguration38 B —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/checkpoint-80/config.jsonConfiguration1.7 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/checkpoint-80/generation_config.jsonConfiguration139 B —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/checkpoint-80/rl_args.jsonConfiguration3.1 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/config.jsonConfiguration1.7 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/generation_config.jsonConfiguration139 B —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/rl_args.jsonConfiguration3.1 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_094036-1ycjajw3/files/config.yamlConfiguration12.5 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_094036-1ycjajw3/files/media/table/samples/rollouts_0_7f3af6cf7073550bebcb.table.jsonConfiguration13.9 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_094036-1ycjajw3/files/media/table/samples/rollouts_1_221425add44ab39a6987.table.jsonConfiguration9.7 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_094036-1ycjajw3/files/media/table/samples/rollouts_2_5aaf2f92f0947037fd6e.table.jsonConfiguration12.2 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_094036-1ycjajw3/files/media/table/samples/rollouts_3_be33f0bf1f8209450691.table.jsonConfiguration14.0 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_094036-1ycjajw3/files/media/table/samples/rollouts_4_7376ddbc2a62bbf06f7d.table.jsonConfiguration11.6 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_094036-1ycjajw3/files/media/table/samples/rollouts_5_4b6c6c20cde03cdd427f.table.jsonConfiguration13.1 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_094036-1ycjajw3/files/media/table/samples/rollouts_6_37612c4f66439792b4e7.table.jsonConfiguration12.2 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_094036-1ycjajw3/files/media/table/samples/rollouts_7_1ff5fbf7a45c62e1cd0f.table.jsonConfiguration15.3 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_094036-1ycjajw3/files/media/table/samples/rollouts_8_8ca856d4ed1572e9b79d.table.jsonConfiguration13.3 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_094036-1ycjajw3/files/media/table/samples/rollouts_9_cc076dd6295568e26710.table.jsonConfiguration12.7 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_094036-1ycjajw3/files/wandb-metadata.jsonConfiguration5.7 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_094036-1ycjajw3/files/wandb-summary.jsonConfiguration13.7 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/config.yamlConfiguration12.5 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_0_7f3af6cf7073550bebcb.table.jsonConfiguration13.9 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_100_9bc75e4e47ded85d3abe.table.jsonConfiguration14.7 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_101_1a28698b665783d95f4c.table.jsonConfiguration11.0 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_102_cdb4cf2fe0764c78a3f3.table.jsonConfiguration9.0 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_103_f709cd04ce393c909752.table.jsonConfiguration11.4 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_104_80aaf1712858c408a850.table.jsonConfiguration12.9 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_105_3c22a93eb5f1472bc293.table.jsonConfiguration16.7 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_106_f166ced52c82fa8d2478.table.jsonConfiguration11.8 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_107_9abca6bad8d8b984c920.table.jsonConfiguration12.3 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_108_4ff5f6397825c2cfd8e8.table.jsonConfiguration12.7 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_109_14a69d45eb10c41122d9.table.jsonConfiguration9.1 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_10_15383e1d7dac9d49b72d.table.jsonConfiguration8.4 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_110_c460e85c030a839bbe97.table.jsonConfiguration10.9 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_111_182a1c937884e1904595.table.jsonConfiguration13.6 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_112_a24163b610570546533a.table.jsonConfiguration12.4 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_113_32b5bedaa15df9ab02e2.table.jsonConfiguration15.0 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_114_f09acb13367a4e6afc5f.table.jsonConfiguration8.4 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_115_e6bd51c26cfc516ba45d.table.jsonConfiguration13.9 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_116_c0df0ac8a3ab05caa1dc.table.jsonConfiguration10.7 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_117_958a13395c7fde19712f.table.jsonConfiguration8.3 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_118_4b4ee6d71251ea5b8383.table.jsonConfiguration12.2 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_119_e54a75c7fadb38ac13d0.table.jsonConfiguration16.1 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_11_9cddca48d691546ad7cd.table.jsonConfiguration9.2 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_120_8b9cea8ebf2b9d7dd8ac.table.jsonConfiguration9.9 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_121_407a98e53a6ed70afb27.table.jsonConfiguration9.6 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_122_2c5dfd952fa2630ab55a.table.jsonConfiguration11.4 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_123_2a2d24fd4267af11a381.table.jsonConfiguration13.8 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_124_ba539be1147c8fbf53e6.table.jsonConfiguration8.2 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_125_531d8eb2701fa8bb3d1c.table.jsonConfiguration10.7 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_126_f744d4e8483e9b084669.table.jsonConfiguration12.6 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_127_7ab8d9c4740d9ee2cd6d.table.jsonConfiguration15.2 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_128_7a7d154566f0cdbf54f9.table.jsonConfiguration13.0 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_129_2b16c0df5ef3f45a8a80.table.jsonConfiguration14.1 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_12_f4d92e330a4db4928e2f.table.jsonConfiguration11.6 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_130_3f93880dcafc34a0efba.table.jsonConfiguration12.6 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_131_16bf5dab117d8af087dc.table.jsonConfiguration8.0 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_132_1e35b99e12a9ac360341.table.jsonConfiguration14.0 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_133_ad29d014f6289c028687.table.jsonConfiguration9.8 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_134_1aadfe503655e01ce8f6.table.jsonConfiguration15.5 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_135_66892e6a88c8c742dca8.table.jsonConfiguration7.9 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_136_682a9440e915daa6f078.table.jsonConfiguration11.7 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_137_3a4af60843d10938c7f3.table.jsonConfiguration14.0 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_138_fdb4baa03363241d25fd.table.jsonConfiguration10.8 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_139_6c144723e2b5047fcaf2.table.jsonConfiguration8.7 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_13_9432e337997922131c42.table.jsonConfiguration10.4 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_140_1fc694178035eae9fd94.table.jsonConfiguration14.4 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_141_14f23c4f606837f8b384.table.jsonConfiguration8.4 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_142_48d9df02ae5f543c54ae.table.jsonConfiguration12.4 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_143_f28806496c4d4822dbf3.table.jsonConfiguration10.1 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_144_b000f806fad54a8d523e.table.jsonConfiguration10.8 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_145_ab3b22953c93899f7e9c.table.jsonConfiguration6.6 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_146_063e61e419568470cbc9.table.jsonConfiguration12.1 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_147_17e1f44d3efb3f900c3a.table.jsonConfiguration12.2 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_148_f305e6137f4dfcd6b30f.table.jsonConfiguration12.9 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_149_81122368492cbf5df6be.table.jsonConfiguration15.7 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_14_5ea9556c42623568747c.table.jsonConfiguration16.0 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_150_f008f95dba723c644f26.table.jsonConfiguration13.7 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_151_302b840a2b9940a4eda1.table.jsonConfiguration10.4 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_152_be790699622fb29d3a9d.table.jsonConfiguration14.4 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_153_10b2a1597eb80cb8e449.table.jsonConfiguration13.1 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_154_579a1b34e673f28c4b3c.table.jsonConfiguration7.1 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_155_86adfaf5fca1ddda282a.table.jsonConfiguration8.0 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_156_0e18ecfb1e244d488c25.table.jsonConfiguration10.8 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_157_575c651d81165e38f410.table.jsonConfiguration8.9 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_158_7510f45d869cfdcc96b3.table.jsonConfiguration14.9 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_159_2f1c4188ddd76c1aca3d.table.jsonConfiguration10.4 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_15_9880e159a6dcc16bdb98.table.jsonConfiguration9.5 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_160_2a081808b0a93ac7ea92.table.jsonConfiguration9.0 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_161_4102134256e7f279ea4f.table.jsonConfiguration11.8 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_162_8afd4ab257a46ddc14d4.table.jsonConfiguration6.8 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_163_59411178436f1c1d44f3.table.jsonConfiguration5.1 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_164_b516528e64f83f8f168b.table.jsonConfiguration12.5 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_165_9548aebb4e19a8485f14.table.jsonConfiguration11.4 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_166_e6f090eceb87ffd534ac.table.jsonConfiguration6.3 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_167_88f4310ce15f678f6388.table.jsonConfiguration7.0 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_168_54a9a105296d0ab82686.table.jsonConfiguration8.6 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_169_df2cc6fc0bad53fa0448.table.jsonConfiguration10.9 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_16_df81beeb1e5f0cb8a826.table.jsonConfiguration15.3 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_170_f77e5d8ddbccad62b0a1.table.jsonConfiguration9.1 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_171_c094f3737c9a4662516b.table.jsonConfiguration10.1 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_172_0ec2e12709ea84a36d5b.table.jsonConfiguration12.9 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_173_45aa1d22eb7a10af4046.table.jsonConfiguration11.7 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_174_478894f1bd6c90162b2f.table.jsonConfiguration13.5 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_175_81cb3040df9d0a464a2b.table.jsonConfiguration11.3 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_176_30e09d0543c9c391503f.table.jsonConfiguration11.9 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_177_68ac886de5a9f6cee70e.table.jsonConfiguration11.1 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_178_d76684845216fdcb2e18.table.jsonConfiguration9.2 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_179_decdf0293e648d3143ea.table.jsonConfiguration10.4 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_17_9ee5ea18cfeb74c03c09.table.jsonConfiguration10.1 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_18_86ac96d6103c7c08b8a6.table.jsonConfiguration8.7 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_19_60b9048faea983eeb306.table.jsonConfiguration7.7 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_1_1ef115da8e3193c4e1e7.table.jsonConfiguration11.8 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_20_7a2552a2ca0217427ee9.table.jsonConfiguration11.9 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_21_9249751c34ecfde1a3f8.table.jsonConfiguration9.7 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_22_e70b9baf3e41bc2b0eb4.table.jsonConfiguration10.7 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_23_a6ae2c608114e5764b2e.table.jsonConfiguration10.6 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_24_0d0b0799faed044f9597.table.jsonConfiguration11.0 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_25_590ef9e11fbe56ebf83b.table.jsonConfiguration16.4 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_26_337c30bc062cbc138b02.table.jsonConfiguration11.1 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_27_d83c42cce8afc3ced671.table.jsonConfiguration7.7 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_28_4855f47d6c6b7b91ef62.table.jsonConfiguration8.9 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_29_7f3142f9fb3015f0fff5.table.jsonConfiguration13.4 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_2_3c2e40a69fd7ffa83dd6.table.jsonConfiguration11.2 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_30_9a238c2a4316032671b6.table.jsonConfiguration8.4 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_31_09ce7c1437e2f7f906a1.table.jsonConfiguration11.3 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_32_07be344af3692fe8c169.table.jsonConfiguration15.0 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_33_6c741036b5a0fbd89be4.table.jsonConfiguration8.9 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_34_33ed7c814db2cf7cff7d.table.jsonConfiguration16.6 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_35_5cfe2d340a9ae55b1853.table.jsonConfiguration8.4 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_36_f67485e1a4b6bad17eeb.table.jsonConfiguration10.7 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_37_45ef8460251aebfaf23b.table.jsonConfiguration7.6 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_38_46b0f1643007280afdf1.table.jsonConfiguration12.1 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_39_af5703bb88b703b53277.table.jsonConfiguration11.8 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_3_1092b40498eb95dc4ded.table.jsonConfiguration11.4 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_40_c2e89ff878b1576972d8.table.jsonConfiguration11.6 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_41_6bdd8452552806584869.table.jsonConfiguration9.3 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_42_914994fbc579cfaad8b4.table.jsonConfiguration11.7 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_43_0a912866ebe41fabeb98.table.jsonConfiguration12.0 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_44_0391855758bc4e54b4fe.table.jsonConfiguration6.8 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_45_e86c44bfc59e7a6ad3e4.table.jsonConfiguration13.3 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_46_74088b9a1d140ae6d032.table.jsonConfiguration10.1 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_47_c5e71f864ab44c8f600c.table.jsonConfiguration11.3 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_48_af636abbd7f1290c2f44.table.jsonConfiguration10.8 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_49_b6f96896334c22c6884c.table.jsonConfiguration11.4 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_4_4c79652dc7ee661b6e99.table.jsonConfiguration12.7 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_50_ca62ccb847082b034a19.table.jsonConfiguration7.8 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_51_81da943423450833e270.table.jsonConfiguration8.8 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_52_3d827ebe51e5f9c4a0b5.table.jsonConfiguration10.7 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_53_aff5cfe2caed726a4f26.table.jsonConfiguration17.3 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_54_a05209bede8827d1e423.table.jsonConfiguration9.1 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_55_af6857539b784f93bec4.table.jsonConfiguration8.0 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_56_5a070adb37e091358e10.table.jsonConfiguration11.7 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_57_5a7a1e3a826d837d8b0a.table.jsonConfiguration10.2 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_58_6928388aa9a0b80eba1b.table.jsonConfiguration15.4 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_59_99482c74cdf85f921380.table.jsonConfiguration9.5 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_5_b69bc1dc0c24c3af9406.table.jsonConfiguration13.0 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_60_a7c2a46a798ca4709206.table.jsonConfiguration10.7 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_61_b6f5b42dc5a04a580614.table.jsonConfiguration9.7 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_62_83fb0d4e12a88d6bc1ba.table.jsonConfiguration8.2 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_63_bbe525f1ec411a3acb1b.table.jsonConfiguration9.1 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_64_2c8041b0eb0486633b74.table.jsonConfiguration11.4 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_65_2bc88bfc934854d9555f.table.jsonConfiguration12.5 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_66_58a5f180d273f74afae6.table.jsonConfiguration8.4 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_67_cfbec99ea9567499dc6b.table.jsonConfiguration16.5 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_68_dc72761119d23fcb09a9.table.jsonConfiguration9.9 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_69_3ced60860e3c5ea3a484.table.jsonConfiguration11.2 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_6_f34d098f87f775c888f3.table.jsonConfiguration12.5 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_70_63aacf1178137398454c.table.jsonConfiguration11.0 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_71_9fe9169c304fdb0cf7df.table.jsonConfiguration13.1 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_72_c7f2093f21dde5b63b0e.table.jsonConfiguration16.1 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_73_e032dc41c0a949c901fe.table.jsonConfiguration10.3 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_74_cd670bc6854e844add62.table.jsonConfiguration8.9 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_75_49539843bca58ffb2553.table.jsonConfiguration9.8 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_76_8551e39e23e2ceb2ba57.table.jsonConfiguration11.1 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_77_aec4972533389de0851e.table.jsonConfiguration7.1 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_78_0a91210a7e72f5e704cf.table.jsonConfiguration9.2 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_79_d7ec99d7a2ad3f6d41b4.table.jsonConfiguration9.1 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_7_06c272649b8f7003acb9.table.jsonConfiguration15.7 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_80_1f4d1db4c41c317c8f5f.table.jsonConfiguration13.6 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_81_9f206b6ae78dad3428a3.table.jsonConfiguration10.4 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_82_21d029c6625cc818233e.table.jsonConfiguration15.3 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_83_4e9154fc5001d1123212.table.jsonConfiguration10.7 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_84_3419c0f62c70c49417ac.table.jsonConfiguration10.0 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_85_4a5c47897ce0088e020f.table.jsonConfiguration14.4 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_86_b7ae9affe16034d799f8.table.jsonConfiguration7.5 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_87_fd973233f9db70c6f440.table.jsonConfiguration10.4 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_88_af03f1f73d2486f0aba8.table.jsonConfiguration11.9 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_89_626dc661cf2b036aa750.table.jsonConfiguration12.5 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_8_0ca10b41be141b9307b1.table.jsonConfiguration15.1 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_90_c8083d5dd89545de6b87.table.jsonConfiguration7.8 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_91_5618d362af4dc4564132.table.jsonConfiguration7.8 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_92_ceeea26b947f84fa4e72.table.jsonConfiguration12.0 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_93_e3bcf8e3523be71de762.table.jsonConfiguration9.7 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_94_2476aa15e618c81fe81e.table.jsonConfiguration10.0 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_95_09dbb1dfa4cefaf12493.table.jsonConfiguration13.7 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_96_4af53d4a6a8b70fe7012.table.jsonConfiguration11.3 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_97_0806426ce218e23b19d1.table.jsonConfiguration14.3 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_98_b68d31c83203c1d1f386.table.jsonConfiguration13.6 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_99_d86adf179bd1998f5a63.table.jsonConfiguration9.4 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/media/table/samples/rollouts_9_92e8e113c161bfa1385a.table.jsonConfiguration10.8 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/wandb-metadata.jsonConfiguration5.7 KB —
models/rl_new_v2/run20_qwen314b_dapo12k_arpoadditive_latentfmt_batch_p64g8_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_32gpu/wandb/run-20261007_121038-jseabb29/files/wandb-summary.jsonConfiguration13.4 KB —
models/smoke_hybrid_submission/sft_out/stage1/adapter_config.jsonConfiguration38 B —
models/smoke_hybrid_submission/sft_out/stage1/checkpoint-3/adapter_config.jsonConfiguration38 B —
models/smoke_hybrid_submission/sft_out/stage1/checkpoint-3/config.jsonConfiguration1.4 KB —
models/smoke_hybrid_submission/sft_out/stage1/checkpoint-3/generation_config.jsonConfiguration139 B —
models/smoke_hybrid_submission/sft_out/stage1/config.jsonConfiguration1.4 KB —
models/smoke_hybrid_submission/sft_out/stage1/generation_config.jsonConfiguration139 B —
models/smoke_hybrid_submission/sft_out/stage1/train_args.jsonConfiguration1.1 KB —
models/smoke_hybrid_submission/sft_out/stage2/adapter_config.jsonConfiguration38 B —
models/smoke_hybrid_submission/sft_out/stage2/checkpoint-3/adapter_config.jsonConfiguration38 B —
models/smoke_hybrid_submission/sft_out/stage2/checkpoint-3/config.jsonConfiguration1.4 KB —
models/smoke_hybrid_submission/sft_out/stage2/checkpoint-3/generation_config.jsonConfiguration139 B —
models/smoke_hybrid_submission/sft_out/stage2/config.jsonConfiguration1.4 KB —
models/smoke_hybrid_submission/sft_out/stage2/generation_config.jsonConfiguration139 B —
models/smoke_hybrid_submission/sft_out/stage2/train_args.jsonConfiguration1.1 KB —
models/smoke_hybrid_submission/sft_out/stage3_full/adapter_config.jsonConfiguration38 B —
models/smoke_hybrid_submission/sft_out/stage3_full/checkpoint-3/adapter_config.jsonConfiguration38 B —
models/smoke_hybrid_submission/sft_out/stage3_full/checkpoint-3/config.jsonConfiguration1.4 KB —
models/smoke_hybrid_submission/sft_out/stage3_full/checkpoint-3/generation_config.jsonConfiguration139 B —
models/smoke_hybrid_submission/sft_out/stage3_full/config.jsonConfiguration1.4 KB —
models/smoke_hybrid_submission/sft_out/stage3_full/generation_config.jsonConfiguration139 B —
models/smoke_hybrid_submission/sft_out/stage3_full/train_args.jsonConfiguration1.1 KB —
models/smoke_hybrid_submission/sft_out2/stage1/adapter_config.jsonConfiguration38 B —
models/smoke_hybrid_submission/sft_out2/stage1/checkpoint-1/adapter_config.jsonConfiguration38 B —
models/smoke_hybrid_submission/sft_out2/stage1/checkpoint-1/config.jsonConfiguration1.4 KB —
models/smoke_hybrid_submission/sft_out2/stage1/checkpoint-1/generation_config.jsonConfiguration139 B —
models/smoke_hybrid_submission/sft_out2/stage1/config.jsonConfiguration1.4 KB —
models/smoke_hybrid_submission/sft_out2/stage1/generation_config.jsonConfiguration139 B —
models/smoke_hybrid_submission/sft_out2/stage1/train_args.jsonConfiguration1.1 KB —
models/smoke_hybrid_submission/sft_out2/stage2/adapter_config.jsonConfiguration38 B —
models/smoke_hybrid_submission/sft_out2/stage2/checkpoint-1/adapter_config.jsonConfiguration38 B —
models/smoke_hybrid_submission/sft_out2/stage2/checkpoint-1/config.jsonConfiguration1.4 KB —
models/smoke_hybrid_submission/sft_out2/stage2/checkpoint-1/generation_config.jsonConfiguration139 B —
models/smoke_hybrid_submission/sft_out2/stage2/config.jsonConfiguration1.4 KB —
models/smoke_hybrid_submission/sft_out2/stage2/generation_config.jsonConfiguration139 B —
models/smoke_hybrid_submission/sft_out2/stage2/train_args.jsonConfiguration1.1 KB —
models/smoke_hybrid_submission/sft_out2/stage3/adapter_config.jsonConfiguration38 B —
models/smoke_hybrid_submission/sft_out2/stage3/checkpoint-1/adapter_config.jsonConfiguration38 B —
models/smoke_hybrid_submission/sft_out2/stage3/checkpoint-1/config.jsonConfiguration1.4 KB —
models/smoke_hybrid_submission/sft_out2/stage3/checkpoint-1/generation_config.jsonConfiguration139 B —
models/smoke_hybrid_submission/sft_out2/stage3/config.jsonConfiguration1.4 KB —
models/smoke_hybrid_submission/sft_out2/stage3/generation_config.jsonConfiguration139 B —
models/smoke_hybrid_submission/sft_out2/stage3/train_args.jsonConfiguration1.1 KB —
models/version_7_base/qwen3_14b/stage3_full/checkpoint-2000/adapter_config.jsonConfiguration38 B —
models/version_7_base/qwen3_14b/stage3_full/checkpoint-2000/config.jsonConfiguration1.7 KB —
models/version_7_base/qwen3_14b/stage3_full/checkpoint-2000/generation_config.jsonConfiguration139 B —
models/version_7_base/qwen3_4b_base_hybrid_ns2lr2e4_ckpt7000/adapter_config.jsonConfiguration38 B —
models/version_7_base/qwen3_4b_base_hybrid_ns2lr2e4_ckpt7000/config.jsonConfiguration1.6 KB —
models/version_7_base/qwen3_4b_base_hybrid_ns2lr2e4_ckpt7000/generation_config.jsonConfiguration139 B —
models/version_7_base/qwen3_8b/stage3_full/checkpoint-2000/adapter_config.jsonConfiguration38 B —
models/version_7_base/qwen3_8b/stage3_full/checkpoint-2000/config.jsonConfiguration1.6 KB —
models/version_7_base/qwen3_8b/stage3_full/checkpoint-2000/generation_config.jsonConfiguration139 B —
models/version_8_hsftv2/qwen3_14b/stage1/adapter_config.jsonConfiguration38 B —
models/version_8_hsftv2/qwen3_14b/stage1/config.jsonConfiguration1.7 KB —
models/version_8_hsftv2/qwen3_14b/stage1/generation_config.jsonConfiguration139 B —
models/version_8_hsftv2/qwen3_14b/stage1/train_args.jsonConfiguration992 B —
models/version_8_hsftv2/qwen3_14b/stage1/wandb/run-20261009_072657-2qi8eug7/files/config.yamlConfiguration6.3 KB —
models/version_8_hsftv2/qwen3_14b/stage1/wandb/run-20261009_072657-2qi8eug7/files/wandb-metadata.jsonConfiguration3.3 KB —
models/version_8_hsftv2/qwen3_14b/stage1/wandb/run-20261009_072657-2qi8eug7/files/wandb-summary.jsonConfiguration246 B —
models/version_8_hsftv2/qwen3_14b/stage2/adapter_config.jsonConfiguration38 B —
models/version_8_hsftv2/qwen3_14b/stage2/config.jsonConfiguration1.7 KB —
models/version_8_hsftv2/qwen3_14b/stage2/generation_config.jsonConfiguration139 B —
models/version_8_hsftv2/qwen3_14b/stage2/train_args.jsonConfiguration1.0 KB —
models/version_8_hsftv2/qwen3_14b/stage2/wandb/run-20261009_110609-mge338y6/files/config.yamlConfiguration6.6 KB —
models/version_8_hsftv2/qwen3_14b/stage2/wandb/run-20261009_110609-mge338y6/files/wandb-metadata.jsonConfiguration3.4 KB —
models/version_8_hsftv2/qwen3_14b/stage2/wandb/run-20261009_110609-mge338y6/files/wandb-summary.jsonConfiguration263 B —
models/version_8_hsftv2/qwen3_14b/stage3_full/checkpoint-1000/adapter_config.jsonConfiguration38 B —
models/version_8_hsftv2/qwen3_14b/stage3_full/checkpoint-1000/config.jsonConfiguration1.7 KB —
models/version_8_hsftv2/qwen3_14b/stage3_full/checkpoint-1000/generation_config.jsonConfiguration139 B —
models/version_8_hsftv2/qwen3_14b/stage3_full/train_args.jsonConfiguration1.0 KB —
models/version_8_hsftv2/qwen3_14b/stage3_full/wandb/run-20261009_164650-thjfkhvs/files/wandb-metadata.jsonConfiguration3.4 KB —
models/version_8_hsftv2/qwen3_14b/stage3_full/wandb/run-20261009_193951-oi1grlta/files/wandb-metadata.jsonConfiguration3.4 KB —
models/version_8_hsftv2/qwen3_14b/stage3_full/wandb/run-20261009_201532-v6fh7vcd/files/wandb-metadata.jsonConfiguration3.4 KB —
paper_writing/HybridAgent_Submission/__init__.pyConfiguration1 B —
paper_writing/HybridAgent_Submission/engine/__init__.pyConfiguration1 B —
paper_writing/HybridAgent_Submission/engine/batched.pyConfiguration6.5 KB —
paper_writing/HybridAgent_Submission/engine/batched_hybrid_processor.pyConfiguration26.1 KB —
paper_writing/HybridAgent_Submission/engine/hybrid_processor.pyConfiguration33.0 KB —
paper_writing/HybridAgent_Submission/engine/inference.pyConfiguration18.2 KB —
paper_writing/HybridAgent_Submission/engine/prompt_manager.pyConfiguration299 B —
paper_writing/HybridAgent_Submission/engine/tools/__init__.pyConfiguration150 B —
paper_writing/HybridAgent_Submission/engine/tools/base_tool.pyConfiguration394 B —
paper_writing/HybridAgent_Submission/engine/tools/python_tool.pyConfiguration17.2 KB —
paper_writing/HybridAgent_Submission/engine/tools/search_cache.pyConfiguration4.7 KB —
paper_writing/HybridAgent_Submission/engine/tools/search_tool.pyConfiguration3.5 KB —
paper_writing/HybridAgent_Submission/engine/tools/tool_executor.pyConfiguration1.6 KB —
paper_writing/HybridAgent_Submission/engine/utils.pyConfiguration2.7 KB —
paper_writing/HybridAgent_Submission/prompts.pyConfiguration2.5 KB —
paper_writing/HybridAgent_Submission/rl/__init__.pyConfiguration94 B —
paper_writing/HybridAgent_Submission/rl/_arpo_math_equivalence.pyConfiguration4.6 KB —
paper_writing/HybridAgent_Submission/rl/config.pyConfiguration17.2 KB —
paper_writing/HybridAgent_Submission/rl/data.pyConfiguration2.9 KB —
paper_writing/HybridAgent_Submission/rl/dist.pyConfiguration4.0 KB —
paper_writing/HybridAgent_Submission/rl/grpo.pyConfiguration4.3 KB —
paper_writing/HybridAgent_Submission/rl/minibatch.pyConfiguration2.5 KB —
paper_writing/HybridAgent_Submission/rl/monitor.pyConfiguration4.3 KB —
paper_writing/HybridAgent_Submission/rl/oom_telemetry.pyConfiguration3.7 KB —
paper_writing/HybridAgent_Submission/rl/parity_gate.pyConfiguration10.9 KB —
paper_writing/HybridAgent_Submission/rl/policy.pyConfiguration16.7 KB —
paper_writing/HybridAgent_Submission/rl/replay.pyConfiguration28.6 KB —
paper_writing/HybridAgent_Submission/rl/reward.pyConfiguration18.4 KB —
paper_writing/HybridAgent_Submission/rl/reward_arpo.pyConfiguration16.0 KB —
paper_writing/HybridAgent_Submission/rl/reward_arpo_additive.pyConfiguration4.9 KB —
paper_writing/HybridAgent_Submission/rl/rollout.pyConfiguration18.2 KB —
paper_writing/HybridAgent_Submission/rl/rollout_audit.pyConfiguration6.5 KB —
paper_writing/HybridAgent_Submission/rl/rollout_batch.pyConfiguration11.6 KB —
paper_writing/HybridAgent_Submission/rl/sampling.pyConfiguration6.0 KB —
paper_writing/HybridAgent_Submission/rl/train.pyConfiguration83.6 KB —
paper_writing/HybridAgent_Submission/rl/trainer_state.pyConfiguration6.4 KB —
paper_writing/HybridAgent_Submission/rl/training_metrics.pyConfiguration12.6 KB —
paper_writing/HybridAgent_Submission/rl/trajectory.pyConfiguration1.7 KB —
paper_writing/HybridAgent_Submission/rl/val_downstream.pyConfiguration2.6 KB —
paper_writing/HybridAgent_Submission/rl/validation.pyConfiguration29.5 KB —
paper_writing/HybridAgent_Submission/rl/validation_common.pyConfiguration28.0 KB —
paper_writing/HybridAgent_Submission/rl/validation_sampled.pyConfiguration5.4 KB —
paper_writing/HybridAgent_Submission/rl/zero1_adamw.pyConfiguration12.5 KB —
paper_writing/HybridAgent_Submission/run.pyConfiguration12.5 KB —
paper_writing/HybridAgent_Submission/scripts/accelerate_ds_z2_ga2.yamlConfiguration372 B —
paper_writing/HybridAgent_Submission/sft/__init__.pyConfiguration61 B —
paper_writing/HybridAgent_Submission/sft/data.pyConfiguration13.2 KB —
paper_writing/HybridAgent_Submission/sft/model.pyConfiguration16.5 KB —
paper_writing/HybridAgent_Submission/sft/train.pyConfiguration21.4 KB —
pass_k_eval/aggregate_passk.pyConfiguration2.4 KB —
pass_k_eval/baseline_passk.pyConfiguration8.1 KB —
pass_k_eval/hybrid_passk.pyConfiguration6.0 KB —
related_works/ARPO/AEPO/scripts/config/ppo_trainer.yamlConfiguration13.4 KB —
related_works/ARPO/AEPO/scripts/config/ppo_trainer_dr.yamlConfiguration13.4 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/.pre-commit-config.yamlConfiguration228 B —
related_works/ARPO/AEPO/verl_aepo_entropy/.readthedocs.yamlConfiguration333 B —
related_works/ARPO/AEPO/verl_aepo_entropy/docs/conf.pyConfiguration3.4 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/examples/data_preprocess/aime2024_multiturn_w_tool.pyConfiguration2.2 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/examples/data_preprocess/dapo_multiturn_w_tool.pyConfiguration2.2 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/examples/data_preprocess/full_hh_rlhf.pyConfiguration4.8 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/examples/data_preprocess/geo3k.pyConfiguration2.9 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/examples/data_preprocess/gsm8k.pyConfiguration3.0 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/examples/data_preprocess/gsm8k_multiturn_w_tool.pyConfiguration4.1 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/examples/data_preprocess/hellaswag.pyConfiguration3.2 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/examples/data_preprocess/math_dataset.pyConfiguration2.8 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/examples/data_preprocess/multiturn.pyConfiguration4.5 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/examples/data_preprocess/preprocess_search_r1_dataset.pyConfiguration6.8 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/examples/ppo_trainer/naive_chat_scheduler.pyConfiguration6.1 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/examples/sglang_multiturn/config/gsm8k_multiturn_grpo.yamlConfiguration416 B —
related_works/ARPO/AEPO/verl_aepo_entropy/examples/sglang_multiturn/config/gsm8k_multiturn_megatron_grpo.yamlConfiguration429 B —
related_works/ARPO/AEPO/verl_aepo_entropy/examples/sglang_multiturn/config/retool_multiturn_grpo.yamlConfiguration410 B —
related_works/ARPO/AEPO/verl_aepo_entropy/examples/sglang_multiturn/config/search_multiturn_grpo.yamlConfiguration367 B —
related_works/ARPO/AEPO/verl_aepo_entropy/examples/sglang_multiturn/config/tool_config/gsm8k_tool_config.yamlConfiguration561 B —
related_works/ARPO/AEPO/verl_aepo_entropy/examples/sglang_multiturn/config/tool_config/sandbox_fusion_tool_config.yamlConfiguration643 B —
related_works/ARPO/AEPO/verl_aepo_entropy/examples/sglang_multiturn/config/tool_config/search_tool_config.yamlConfiguration685 B —
related_works/ARPO/AEPO/verl_aepo_entropy/examples/sglang_multiturn/search_r1_like/local_dense_retriever/download.pyConfiguration1.6 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/examples/sglang_multiturn/search_r1_like/local_dense_retriever/retrieval_server.pyConfiguration14.2 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/examples/split_placement/config/ppo_trainer_split.yamlConfiguration6.6 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/examples/split_placement/main_ppo_split.pyConfiguration7.9 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/examples/split_placement/split_monkey_patch.pyConfiguration9.6 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/recipe/dapo/config/dapo_trainer.yamlConfiguration575 B —
related_works/ARPO/AEPO/verl_aepo_entropy/recipe/dapo/dapo_ray_trainer.pyConfiguration16.4 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/recipe/dapo/main_dapo.pyConfiguration6.6 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/recipe/prime/__init__.pyConfiguration596 B —
related_works/ARPO/AEPO/verl_aepo_entropy/recipe/prime/config/prime_trainer.yamlConfiguration2.3 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/recipe/prime/main_prime.pyConfiguration5.3 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/recipe/prime/prime_core_algos.pyConfiguration6.3 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/recipe/prime/prime_dp_rm.pyConfiguration16.7 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/recipe/prime/prime_fsdp_workers.pyConfiguration16.1 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/recipe/prime/prime_ray_trainer.pyConfiguration24.8 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/recipe/r1/__init__.pyConfiguration600 B —
related_works/ARPO/AEPO/verl_aepo_entropy/recipe/r1/config/evaluation.yamlConfiguration373 B —
related_works/ARPO/AEPO/verl_aepo_entropy/recipe/r1/data_process.pyConfiguration7.9 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/recipe/r1/main_eval.pyConfiguration2.7 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/recipe/r1/reward_score.pyConfiguration1.3 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/recipe/r1/tasks/__init__.pyConfiguration600 B —
related_works/ARPO/AEPO/verl_aepo_entropy/recipe/r1/tasks/gpqa.pyConfiguration1.1 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/recipe/r1/tasks/livecodebench.pyConfiguration2.4 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/recipe/r1/tasks/math.pyConfiguration1.4 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/recipe/spin/config/spin_trainer.yamlConfiguration488 B —
related_works/ARPO/AEPO/verl_aepo_entropy/recipe/spin/core_algos.pyConfiguration8.6 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/recipe/spin/dp_actor.pyConfiguration14.4 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/recipe/spin/fsdp_workers.pyConfiguration27.9 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/recipe/spin/main_spin.pyConfiguration6.3 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/recipe/spin/spin_trainer.pyConfiguration72.3 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/recipe/sppo/__init__.pyConfiguration634 B —
related_works/ARPO/AEPO/verl_aepo_entropy/recipe/sppo/config/sppo_trainer.yamlConfiguration483 B —
related_works/ARPO/AEPO/verl_aepo_entropy/recipe/sppo/dp_actor.pyConfiguration8.2 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/recipe/sppo/main_sppo.pyConfiguration5.9 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/recipe/sppo/sppo_ray_trainer.pyConfiguration15.9 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/recipe/sppo/sppo_worker.pyConfiguration5.5 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/scripts/converter_hf_to_mcore.pyConfiguration14.8 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/scripts/diagnose.pyConfiguration10.0 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/scripts/model_merger.pyConfiguration28.9 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/setup.pyConfiguration2.7 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/tests/__init__.pyConfiguration600 B —
related_works/ARPO/AEPO/verl_aepo_entropy/tests/distributed/test_tensor_dict.pyConfiguration4.7 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/tests/e2e/__init__.pyConfiguration600 B —
related_works/ARPO/AEPO/verl_aepo_entropy/tests/e2e/arithmetic_sequence/data/create_dataset.pyConfiguration1.7 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/tests/e2e/arithmetic_sequence/model/config.jsonConfiguration674 B —
related_works/ARPO/AEPO/verl_aepo_entropy/tests/e2e/arithmetic_sequence/model/generation_config.jsonConfiguration111 B —
related_works/ARPO/AEPO/verl_aepo_entropy/tests/e2e/arithmetic_sequence/rl/main_trainer.pyConfiguration5.7 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/tests/e2e/check_custom_rwd_fn.pyConfiguration1.2 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/tests/e2e/check_results.pyConfiguration1.8 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/tests/e2e/envs/__init__.pyConfiguration678 B —
related_works/ARPO/AEPO/verl_aepo_entropy/tests/e2e/envs/digit_completion/__init__.pyConfiguration906 B —
related_works/ARPO/AEPO/verl_aepo_entropy/tests/e2e/envs/digit_completion/task.pyConfiguration6.3 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/tests/e2e/sft/test_sp_loss_match.pyConfiguration5.9 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/tests/gpu_utility/test_memory_buffers.pyConfiguration2.3 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/tests/gpu_utility/test_ops.pyConfiguration1.8 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/tests/gpu_utility/test_torch_functional.pyConfiguration4.0 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/tests/kernels/test_linear_cross_entropy.pyConfiguration12.2 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/tests/models/test_transformer.pyConfiguration6.1 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/tests/models/test_transformers_ulysses.pyConfiguration10.1 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/tests/ray_cpu/check_worker_alive/main.pyConfiguration1.9 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/tests/ray_cpu/test_auto_padding.pyConfiguration4.1 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/tests/ray_cpu/test_check_worker_alive.pyConfiguration1.6 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/tests/ray_cpu/test_decorator.pyConfiguration6.0 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/tests/ray_cpu/test_fused_workers.pyConfiguration2.4 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/tests/ray_cpu/test_ray_local_envs.pyConfiguration1.7 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/tests/ray_cpu/test_ray_utils.pyConfiguration1.7 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/tests/ray_gpu/detached_worker/client.pyConfiguration2.0 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/tests/ray_gpu/detached_worker/server.pyConfiguration5.6 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/tests/ray_gpu/test_colocated_workers.pyConfiguration2.8 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/tests/ray_gpu/test_colocated_workers_fused.pyConfiguration2.8 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/tests/ray_gpu/test_data_transfer.pyConfiguration3.4 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/tests/ray_gpu/test_driverfunc_to_worker.pyConfiguration2.4 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/tests/ray_gpu/test_high_level_scheduling_api.pyConfiguration3.7 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/tests/ray_gpu/test_rvdz.pyConfiguration1.6 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/tests/ray_gpu/test_worker_group_basics.pyConfiguration4.0 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/tests/ray_gpu/test_worker_group_torch.pyConfiguration3.6 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/tests/reward_score/test_sandbox_fusion.pyConfiguration26.6 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/tests/sandbox/test_sandbox.pyConfiguration9.9 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/tests/sanity/check_license.pyConfiguration2.1 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/tests/sanity/test_import.pyConfiguration786 B —
related_works/ARPO/AEPO/verl_aepo_entropy/tests/single_controller/base/test_decorator.pyConfiguration2.3 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/tests/test_protocol.pyConfiguration22.7 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/tests/trainer/__init__.pyConfiguration637 B —
related_works/ARPO/AEPO/verl_aepo_entropy/tests/trainer/ppo/__init__.pyConfiguration642 B —
related_works/ARPO/AEPO/verl_aepo_entropy/tests/trainer/ppo/test_metric_utils.pyConfiguration12.0 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/tests/utils/cpu_tests/_test_module.pyConfiguration959 B —
related_works/ARPO/AEPO/verl_aepo_entropy/tests/utils/cpu_tests/test_fs.pyConfiguration3.3 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/tests/utils/cpu_tests/test_import_utils.pyConfiguration3.1 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/tests/utils/cpu_tests/test_model.pyConfiguration2.5 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/tests/utils/cpu_tests/test_timeout_decorator.pyConfiguration9.9 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/tests/utils/gpu_tests/checkpoint/test_fsdp_ckpt.pyConfiguration5.1 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/tests/utils/gpu_tests/dataset/test_multiturn_sft_dataset.pyConfiguration8.0 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/tests/utils/gpu_tests/dataset/test_rl_dataset.pyConfiguration3.5 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/tests/utils/gpu_tests/dataset/test_rm_dataset.pyConfiguration1.3 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/tests/utils/gpu_tests/dataset/test_sft_dataset.pyConfiguration2.3 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/tests/utils/gpu_tests/megatron/test_pipeline_parallel.pyConfiguration1.5 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/tests/utils/gpu_tests/test_activation_offload.pyConfiguration5.7 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/tests/utils/gpu_tests/test_flops_counter.pyConfiguration6.6 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/tests/utils/gpu_tests/test_seqlen_balancing.pyConfiguration4.4 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/tests/utils/gpu_tests/test_torch_functional.pyConfiguration3.5 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/tests/workers/rollout/async_rollout_utils.pyConfiguration3.0 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/tests/workers/rollout/run_fsdp_vllm.pyConfiguration6.1 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/tests/workers/rollout/test_async_sglang_server.pyConfiguration2.8 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/tests/workers/rollout/test_hf_rollout.pyConfiguration7.4 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/tests/workers/rollout/test_sglang_async_rollout_search_tools.pyConfiguration17.0 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/tests/workers/rollout/test_sglang_async_rollout_sf_tools.pyConfiguration27.4 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/tests/workers/rollout/test_sglang_async_rollout_w_tools.pyConfiguration5.1 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/tests/workers/rollout/test_sglang_spmd.pyConfiguration4.0 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/tests/workers/rollout/test_vllm_hf_loader.pyConfiguration5.9 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/tests/workers/rollout/test_vllm_multi_turn.pyConfiguration7.6 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/tests/workers/rollout/test_vllm_spmd.pyConfiguration6.6 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/tests/workers/rollout/test_vllm_tool_calling.pyConfiguration10.9 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/tests/workers/rollout/utils_sglang.pyConfiguration6.0 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/__init__.pyConfiguration2.2 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/models/__init__.pyConfiguration600 B —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/models/llama/__init__.pyConfiguration600 B —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/models/llama/megatron/__init__.pyConfiguration1.2 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/models/llama/megatron/checkpoint_utils/__init__.pyConfiguration600 B —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/models/llama/megatron/checkpoint_utils/llama_loader.pyConfiguration13.6 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/models/llama/megatron/checkpoint_utils/llama_loader_depracated.pyConfiguration19.0 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/models/llama/megatron/checkpoint_utils/llama_saver.pyConfiguration17.8 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/models/llama/megatron/layers/__init__.pyConfiguration1.2 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/models/llama/megatron/layers/parallel_attention.pyConfiguration20.9 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/models/llama/megatron/layers/parallel_decoder.pyConfiguration6.2 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/models/llama/megatron/layers/parallel_linear.pyConfiguration3.3 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/models/llama/megatron/layers/parallel_mlp.pyConfiguration3.2 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/models/llama/megatron/layers/parallel_rmsnorm.pyConfiguration1.8 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/models/llama/megatron/modeling_llama_megatron.pyConfiguration28.3 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/models/mcore/__init__.pyConfiguration881 B —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/models/mcore/config_converter.pyConfiguration11.8 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/models/mcore/loader.pyConfiguration21.9 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/models/mcore/model_forward.pyConfiguration3.2 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/models/mcore/model_initializer.pyConfiguration7.4 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/models/mcore/patch_v012.pyConfiguration9.5 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/models/mcore/registry.pyConfiguration7.1 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/models/mcore/saver.pyConfiguration20.8 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/models/mcore/util.pyConfiguration8.4 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/models/mcore/weight_converter.pyConfiguration17.9 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/models/qwen2/__init__.pyConfiguration600 B —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/models/qwen2/megatron/__init__.pyConfiguration1.2 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/models/qwen2/megatron/checkpoint_utils/__init__.pyConfiguration600 B —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/models/qwen2/megatron/checkpoint_utils/qwen2_loader.pyConfiguration14.6 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/models/qwen2/megatron/checkpoint_utils/qwen2_loader_depracated.pyConfiguration19.8 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/models/qwen2/megatron/checkpoint_utils/qwen2_saver.pyConfiguration18.0 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/models/qwen2/megatron/layers/__init__.pyConfiguration983 B —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/models/qwen2/megatron/layers/parallel_attention.pyConfiguration17.7 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/models/qwen2/megatron/layers/parallel_decoder.pyConfiguration6.2 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/models/qwen2/megatron/layers/parallel_linear.pyConfiguration2.5 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/models/qwen2/megatron/layers/parallel_mlp.pyConfiguration3.2 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/models/qwen2/megatron/layers/parallel_rmsnorm.pyConfiguration1.8 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/models/qwen2/megatron/modeling_qwen2_megatron.pyConfiguration30.7 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/models/registry.pyConfiguration2.0 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/models/transformers/__init__.pyConfiguration600 B —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/models/transformers/kimi_vl.pyConfiguration10.5 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/models/transformers/llama.pyConfiguration13.3 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/models/transformers/monkey_patch.pyConfiguration11.6 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/models/transformers/qwen2.pyConfiguration10.1 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/models/transformers/qwen2_5_vl.pyConfiguration7.5 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/models/transformers/qwen2_vl.pyConfiguration19.5 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/models/weight_loader_registry.pyConfiguration2.2 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/protocol.pyConfiguration35.7 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/single_controller/__init__.pyConfiguration940 B —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/single_controller/base/__init__.pyConfiguration773 B —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/single_controller/base/decorator.pyConfiguration20.9 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/single_controller/base/megatron/__init__.pyConfiguration600 B —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/single_controller/base/megatron/worker.pyConfiguration4.6 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/single_controller/base/megatron/worker_group.pyConfiguration2.3 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/single_controller/base/register_center/__init__.pyConfiguration600 B —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/single_controller/base/register_center/ray.pyConfiguration1.2 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/single_controller/base/worker.pyConfiguration11.2 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/single_controller/base/worker_group.pyConfiguration9.7 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/single_controller/ray/__init__.pyConfiguration878 B —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/single_controller/ray/base.pyConfiguration35.4 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/single_controller/ray/megatron.pyConfiguration3.3 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/third_party/__init__.pyConfiguration600 B —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/third_party/sglang/__init__.pyConfiguration1.3 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/third_party/sglang/parallel_state.pyConfiguration14.0 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/third_party/vllm/__init__.pyConfiguration1.8 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/third_party/vllm/vllm_v_0_5_4/__init__.pyConfiguration600 B —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/third_party/vllm/vllm_v_0_5_4/arg_utils.pyConfiguration20.8 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/third_party/vllm/vllm_v_0_5_4/config.pyConfiguration11.6 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/third_party/vllm/vllm_v_0_5_4/dtensor_weight_loaders.pyConfiguration15.5 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/third_party/vllm/vllm_v_0_5_4/hf_weight_loader.pyConfiguration1.8 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/third_party/vllm/vllm_v_0_5_4/llm.pyConfiguration11.4 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/third_party/vllm/vllm_v_0_5_4/llm_engine_sp.pyConfiguration14.4 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/third_party/vllm/vllm_v_0_5_4/megatron_weight_loaders.pyConfiguration10.0 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/third_party/vllm/vllm_v_0_5_4/model_loader.pyConfiguration14.2 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/third_party/vllm/vllm_v_0_5_4/model_runner.pyConfiguration6.5 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/third_party/vllm/vllm_v_0_5_4/parallel_state.pyConfiguration12.8 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/third_party/vllm/vllm_v_0_5_4/spmd_gpu_executor.pyConfiguration10.0 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/third_party/vllm/vllm_v_0_5_4/worker.pyConfiguration14.9 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/third_party/vllm/vllm_v_0_6_3/__init__.pyConfiguration600 B —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/third_party/vllm/vllm_v_0_6_3/arg_utils.pyConfiguration3.1 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/third_party/vllm/vllm_v_0_6_3/config.pyConfiguration4.1 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/third_party/vllm/vllm_v_0_6_3/dtensor_weight_loaders.pyConfiguration17.2 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/third_party/vllm/vllm_v_0_6_3/hf_weight_loader.pyConfiguration1.8 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/third_party/vllm/vllm_v_0_6_3/llm.pyConfiguration10.2 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/third_party/vllm/vllm_v_0_6_3/llm_engine_sp.pyConfiguration17.4 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/third_party/vllm/vllm_v_0_6_3/megatron_weight_loaders.pyConfiguration11.0 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/third_party/vllm/vllm_v_0_6_3/model_loader.pyConfiguration14.2 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/third_party/vllm/vllm_v_0_6_3/model_runner.pyConfiguration7.4 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/third_party/vllm/vllm_v_0_6_3/parallel_state.pyConfiguration12.8 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/third_party/vllm/vllm_v_0_6_3/spmd_gpu_executor.pyConfiguration10.0 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/third_party/vllm/vllm_v_0_6_3/worker.pyConfiguration14.8 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/tools/__init__.pyConfiguration634 B —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/tools/base_tool.pyConfiguration2.8 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/tools/gsm8k_tool.pyConfiguration3.8 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/tools/sandbox_fusion_tools.pyConfiguration7.1 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/tools/schemas.pyConfiguration2.6 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/tools/search_tool.pyConfiguration10.5 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/tools/utils/__init__.pyConfiguration634 B —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/tools/utils/search_r1_like_utils.pyConfiguration9.5 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/trainer/__init__.pyConfiguration600 B —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/trainer/config/evaluation.yamlConfiguration373 B —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/trainer/config/generation.yamlConfiguration1.4 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/trainer/config/ppo_megatron_trainer.yamlConfiguration13.0 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/trainer/config/ppo_trainer.yamlConfiguration11.9 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/trainer/config/sft_trainer.yamlConfiguration1.8 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/trainer/fsdp_sft_trainer.pyConfiguration28.0 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/trainer/main_eval.pyConfiguration2.7 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/trainer/main_generation.pyConfiguration5.7 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/trainer/main_ppo.pyConfiguration8.7 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/trainer/ppo/__init__.pyConfiguration600 B —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/trainer/ppo/core_algos.pyConfiguration29.3 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/trainer/ppo/metric_utils.pyConfiguration18.9 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/trainer/ppo/ray_trainer.pyConfiguration62.9 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/trainer/ppo/reward.pyConfiguration4.7 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/trainer/runtime_env.yamlConfiguration230 B —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/utils/__init__.pyConfiguration739 B —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/utils/activation_offload.pyConfiguration22.4 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/utils/checkpoint/__init__.pyConfiguration600 B —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/utils/checkpoint/checkpoint_manager.pyConfiguration5.9 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/utils/checkpoint/fsdp_checkpoint_manager.pyConfiguration12.4 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/utils/checkpoint/megatron_checkpoint_manager.pyConfiguration14.2 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/utils/config.pyConfiguration839 B —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/utils/dataset/__init__.pyConfiguration761 B —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/utils/dataset/multiturn_sft_dataset.pyConfiguration6.2 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/utils/dataset/rl_dataset.pyConfiguration12.3 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/utils/dataset/rm_dataset.pyConfiguration5.3 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/utils/dataset/sft_dataset.pyConfiguration7.3 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/utils/dataset/vision_utils.pyConfiguration2.7 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/utils/debug/__init__.pyConfiguration730 B —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/utils/debug/performance.pyConfiguration4.2 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/utils/debug/profile.pyConfiguration3.6 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/utils/debug/trajectory_tracker.pyConfiguration3.1 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/utils/device.pyConfiguration1.6 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/utils/distributed.pyConfiguration1.4 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/utils/experimental/__init__.pyConfiguration600 B —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/utils/experimental/torch_functional.pyConfiguration8.0 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/utils/flops_counter.pyConfiguration9.6 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/utils/fs.pyConfiguration9.4 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/utils/fsdp_utils.pyConfiguration20.3 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/utils/hdfs_io.pyConfiguration4.6 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/utils/import_utils.pyConfiguration3.3 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/utils/logger/__init__.pyConfiguration600 B —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/utils/logger/aggregate_logger.pyConfiguration2.3 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/utils/logging_utils.pyConfiguration1.1 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/utils/megatron/__init__.pyConfiguration600 B —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/utils/megatron/memory.pyConfiguration1.4 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/utils/megatron/optimizer.pyConfiguration1.3 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/utils/megatron/pipeline_parallel.pyConfiguration2.7 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/utils/megatron/sequence_parallel.pyConfiguration1.8 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/utils/megatron/tensor_parallel.pyConfiguration7.1 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/utils/megatron_utils.pyConfiguration42.7 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/utils/memory_buffer.pyConfiguration8.0 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/utils/metric/__init__.pyConfiguration665 B —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/utils/metric/utils.pyConfiguration1.8 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/utils/model.pyConfiguration17.5 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/utils/net_utils.pyConfiguration2.0 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/utils/py_functional.pyConfiguration10.9 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/utils/ray_utils.pyConfiguration3.8 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/utils/rendezvous/__init__.pyConfiguration600 B —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/utils/rendezvous/ray_backend.pyConfiguration2.6 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/utils/reward_score/__init__.pyConfiguration4.6 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/utils/reward_score/deep_research.pyConfiguration16.6 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/utils/reward_score/geo3k.pyConfiguration1.2 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/utils/reward_score/gsm8k.pyConfiguration2.4 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/utils/reward_score/math.pyConfiguration6.7 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/utils/reward_score/math_batch.pyConfiguration1.0 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/utils/reward_score/math_dapo.pyConfiguration7.7 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/utils/reward_score/math_verify.pyConfiguration1.5 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/utils/reward_score/prime_code/__init__.pyConfiguration3.1 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/utils/reward_score/prime_code/testing_util.pyConfiguration25.2 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/utils/reward_score/prime_code/utils.pyConfiguration2.2 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/utils/reward_score/prime_math/__init__.pyConfiguration12.4 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/utils/reward_score/prime_math/grader.pyConfiguration13.9 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/utils/reward_score/prime_math/math_normalize.pyConfiguration6.3 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/utils/reward_score/sandbox_fusion/__init__.pyConfiguration4.8 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/utils/reward_score/sandbox_fusion/utils.pyConfiguration22.6 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/utils/reward_score/search_r1_like_qa_em.pyConfiguration5.3 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/utils/seqlen_balancing.pyConfiguration12.2 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/utils/torch_dtypes.pyConfiguration2.3 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/utils/torch_functional.pyConfiguration28.1 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/utils/tracking.pyConfiguration13.1 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/utils/ulysses.pyConfiguration11.7 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/utils/vllm_utils.pyConfiguration8.8 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/workers/__init__.pyConfiguration600 B —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/workers/actor/__init__.pyConfiguration727 B —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/workers/actor/base.pyConfiguration2.1 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/workers/actor/dp_actor.pyConfiguration25.4 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/workers/actor/megatron_actor.pyConfiguration26.6 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/workers/agent/__init__.pyConfiguration2.6 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/workers/agent/agent.yamlConfiguration727 B —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/workers/agent/base.pyConfiguration3.0 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/workers/agent/tool_agent.pyConfiguration20.1 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/workers/agent/tools/__init__.pyConfiguration —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/workers/agent/tools/base_tool.pyConfiguration473 B —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/workers/agent/tools/python_tool.pyConfiguration4.5 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/workers/agent/tools/search_tool.pyConfiguration17.1 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/workers/agent/tools/tool_executor.pyConfiguration6.4 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/workers/critic/__init__.pyConfiguration732 B —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/workers/critic/base.pyConfiguration1.1 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/workers/critic/dp_critic.pyConfiguration12.7 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/workers/critic/megatron_critic.pyConfiguration13.6 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/workers/fsdp_workers.pyConfiguration73.2 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/workers/megatron_workers.pyConfiguration46.4 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/workers/reward_manager/__init__.pyConfiguration846 B —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/workers/reward_manager/batch.pyConfiguration4.4 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/workers/reward_manager/dapo.pyConfiguration5.5 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/workers/reward_manager/naive.pyConfiguration4.4 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/workers/reward_manager/prime.pyConfiguration7.4 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/workers/reward_model/__init__.pyConfiguration672 B —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/workers/reward_model/base.pyConfiguration1.7 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/workers/reward_model/megatron/__init__.pyConfiguration682 B —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/workers/reward_model/megatron/reward_model.pyConfiguration14.8 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/workers/rollout/__init__.pyConfiguration753 B —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/workers/rollout/async_server.pyConfiguration14.5 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/workers/rollout/base.pyConfiguration886 B —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/workers/rollout/hf_rollout.pyConfiguration7.3 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/workers/rollout/naive/__init__.pyConfiguration669 B —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/workers/rollout/naive/naive_rollout.pyConfiguration4.8 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/workers/rollout/schemas.pyConfiguration11.9 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/workers/rollout/sglang_rollout/__init__.pyConfiguration639 B —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/workers/rollout/sglang_rollout/async_sglang_server.pyConfiguration2.8 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/workers/rollout/sglang_rollout/sglang_rollout.pyConfiguration52.7 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/workers/rollout/sglang_rollout/utils.pyConfiguration2.5 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/workers/rollout/tools/base_tool.pyConfiguration473 B —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/workers/rollout/tools/config_example.yamlConfiguration911 B —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/workers/rollout/tools/python_tool.pyConfiguration4.5 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/workers/rollout/tools/search_tool.pyConfiguration17.1 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/workers/rollout/vllm_rollout/__init__.pyConfiguration1.9 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/workers/rollout/vllm_rollout/fire_vllm_rollout.pyConfiguration9.8 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/workers/rollout/vllm_rollout/vllm_agent_rollout.pyConfiguration6.8 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/workers/rollout/vllm_rollout/vllm_async_server.pyConfiguration11.0 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/workers/rollout/vllm_rollout/vllm_rollout.pyConfiguration13.0 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/workers/rollout/vllm_rollout/vllm_rollout_spmd.pyConfiguration19.1 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/workers/rollout/vllm_rollout/vllm_rollout_with_tools.pyConfiguration54.4 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/workers/sharding_manager/__init__.pyConfiguration600 B —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/workers/sharding_manager/base.pyConfiguration981 B —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/workers/sharding_manager/fsdp_sglang.pyConfiguration8.0 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/workers/sharding_manager/fsdp_ulysses.pyConfiguration2.8 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/workers/sharding_manager/fsdp_vllm.pyConfiguration13.8 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/workers/sharding_manager/megatron_sglang.pyConfiguration6.3 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/workers/sharding_manager/megatron_vllm.pyConfiguration16.3 KB —
related_works/ARPO/ARPO/merge_ckpt/convert_checkpoint_from_verl_to_hf.pyConfiguration30.9 KB —
related_works/ARPO/ARPO/scripts/config/ppo_trainer.yamlConfiguration13.0 KB —
related_works/ARPO/ARPO/scripts/config/ppo_trainer_dr.yamlConfiguration13.1 KB —
related_works/ARPO/ARPO/search_cache/search_cache.jsonConfiguration1.7 MB —
related_works/ARPO/ARPO/verl_arpo_entropy/docs/conf.pyConfiguration3.4 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/examples/data_preprocess/aime2024_multiturn_w_tool.pyConfiguration2.2 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/examples/data_preprocess/dapo_multiturn_w_tool.pyConfiguration2.2 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/examples/data_preprocess/full_hh_rlhf.pyConfiguration4.8 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/examples/data_preprocess/geo3k.pyConfiguration2.9 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/examples/data_preprocess/gsm8k.pyConfiguration3.0 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/examples/data_preprocess/gsm8k_multiturn_w_tool.pyConfiguration4.1 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/examples/data_preprocess/hellaswag.pyConfiguration3.2 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/examples/data_preprocess/math_dataset.pyConfiguration2.8 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/examples/data_preprocess/multiturn.pyConfiguration4.5 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/examples/data_preprocess/preprocess_search_r1_dataset.pyConfiguration6.8 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/examples/ppo_trainer/naive_chat_scheduler.pyConfiguration6.1 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/examples/sglang_multiturn/config/gsm8k_multiturn_grpo.yamlConfiguration416 B —
related_works/ARPO/ARPO/verl_arpo_entropy/examples/sglang_multiturn/config/gsm8k_multiturn_megatron_grpo.yamlConfiguration429 B —
related_works/ARPO/ARPO/verl_arpo_entropy/examples/sglang_multiturn/config/retool_multiturn_grpo.yamlConfiguration410 B —
related_works/ARPO/ARPO/verl_arpo_entropy/examples/sglang_multiturn/config/search_multiturn_grpo.yamlConfiguration367 B —
related_works/ARPO/ARPO/verl_arpo_entropy/examples/sglang_multiturn/config/tool_config/gsm8k_tool_config.yamlConfiguration561 B —
related_works/ARPO/ARPO/verl_arpo_entropy/examples/sglang_multiturn/config/tool_config/sandbox_fusion_tool_config.yamlConfiguration643 B —
related_works/ARPO/ARPO/verl_arpo_entropy/examples/sglang_multiturn/config/tool_config/search_tool_config.yamlConfiguration685 B —
related_works/ARPO/ARPO/verl_arpo_entropy/examples/sglang_multiturn/search_r1_like/local_dense_retriever/download.pyConfiguration1.6 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/examples/sglang_multiturn/search_r1_like/local_dense_retriever/retrieval_server.pyConfiguration14.2 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/examples/split_placement/config/ppo_trainer_split.yamlConfiguration6.6 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/examples/split_placement/main_ppo_split.pyConfiguration7.9 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/examples/split_placement/split_monkey_patch.pyConfiguration9.6 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/recipe/dapo/config/dapo_trainer.yamlConfiguration575 B —
related_works/ARPO/ARPO/verl_arpo_entropy/recipe/dapo/dapo_ray_trainer.pyConfiguration16.4 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/recipe/dapo/main_dapo.pyConfiguration6.6 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/recipe/prime/__init__.pyConfiguration596 B —
related_works/ARPO/ARPO/verl_arpo_entropy/recipe/prime/config/prime_trainer.yamlConfiguration2.3 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/recipe/prime/main_prime.pyConfiguration5.3 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/recipe/prime/prime_core_algos.pyConfiguration6.3 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/recipe/prime/prime_dp_rm.pyConfiguration16.7 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/recipe/prime/prime_fsdp_workers.pyConfiguration16.1 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/recipe/prime/prime_ray_trainer.pyConfiguration24.8 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/recipe/r1/__init__.pyConfiguration600 B —
related_works/ARPO/ARPO/verl_arpo_entropy/recipe/r1/config/evaluation.yamlConfiguration373 B —
related_works/ARPO/ARPO/verl_arpo_entropy/recipe/r1/data_process.pyConfiguration7.9 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/recipe/r1/main_eval.pyConfiguration2.7 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/recipe/r1/reward_score.pyConfiguration1.3 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/recipe/r1/tasks/__init__.pyConfiguration600 B —
related_works/ARPO/ARPO/verl_arpo_entropy/recipe/r1/tasks/gpqa.pyConfiguration1.1 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/recipe/r1/tasks/livecodebench.pyConfiguration2.4 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/recipe/r1/tasks/math.pyConfiguration1.4 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/recipe/spin/config/spin_trainer.yamlConfiguration488 B —
related_works/ARPO/ARPO/verl_arpo_entropy/recipe/spin/core_algos.pyConfiguration8.6 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/recipe/spin/dp_actor.pyConfiguration14.4 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/recipe/spin/fsdp_workers.pyConfiguration27.9 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/recipe/spin/main_spin.pyConfiguration6.3 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/recipe/spin/spin_trainer.pyConfiguration72.3 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/recipe/sppo/__init__.pyConfiguration634 B —
related_works/ARPO/ARPO/verl_arpo_entropy/recipe/sppo/config/sppo_trainer.yamlConfiguration483 B —
related_works/ARPO/ARPO/verl_arpo_entropy/recipe/sppo/dp_actor.pyConfiguration8.2 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/recipe/sppo/main_sppo.pyConfiguration5.9 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/recipe/sppo/sppo_ray_trainer.pyConfiguration15.9 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/recipe/sppo/sppo_worker.pyConfiguration5.5 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/scripts/converter_hf_to_mcore.pyConfiguration14.8 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/scripts/diagnose.pyConfiguration10.0 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/scripts/model_merger.pyConfiguration28.9 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/setup.pyConfiguration2.7 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/tests/__init__.pyConfiguration600 B —
related_works/ARPO/ARPO/verl_arpo_entropy/tests/distributed/test_tensor_dict.pyConfiguration4.7 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/tests/e2e/__init__.pyConfiguration600 B —
related_works/ARPO/ARPO/verl_arpo_entropy/tests/e2e/arithmetic_sequence/data/create_dataset.pyConfiguration1.7 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/tests/e2e/arithmetic_sequence/model/config.jsonConfiguration674 B —
related_works/ARPO/ARPO/verl_arpo_entropy/tests/e2e/arithmetic_sequence/model/generation_config.jsonConfiguration111 B —
related_works/ARPO/ARPO/verl_arpo_entropy/tests/e2e/arithmetic_sequence/rl/main_trainer.pyConfiguration5.7 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/tests/e2e/check_custom_rwd_fn.pyConfiguration1.2 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/tests/e2e/check_results.pyConfiguration1.8 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/tests/e2e/envs/__init__.pyConfiguration678 B —
related_works/ARPO/ARPO/verl_arpo_entropy/tests/e2e/envs/digit_completion/__init__.pyConfiguration906 B —
related_works/ARPO/ARPO/verl_arpo_entropy/tests/e2e/envs/digit_completion/task.pyConfiguration6.3 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/tests/e2e/sft/test_sp_loss_match.pyConfiguration5.9 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/tests/gpu_utility/test_memory_buffers.pyConfiguration2.3 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/tests/gpu_utility/test_ops.pyConfiguration1.8 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/tests/gpu_utility/test_torch_functional.pyConfiguration4.0 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/tests/kernels/test_linear_cross_entropy.pyConfiguration12.2 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/tests/models/test_transformer.pyConfiguration6.1 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/tests/models/test_transformers_ulysses.pyConfiguration10.1 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/tests/ray_cpu/check_worker_alive/main.pyConfiguration1.9 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/tests/ray_cpu/test_auto_padding.pyConfiguration4.1 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/tests/ray_cpu/test_check_worker_alive.pyConfiguration1.6 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/tests/ray_cpu/test_decorator.pyConfiguration6.0 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/tests/ray_cpu/test_fused_workers.pyConfiguration2.4 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/tests/ray_cpu/test_ray_local_envs.pyConfiguration1.7 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/tests/ray_cpu/test_ray_utils.pyConfiguration1.7 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/tests/ray_gpu/detached_worker/client.pyConfiguration2.0 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/tests/ray_gpu/detached_worker/server.pyConfiguration5.6 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/tests/ray_gpu/test_colocated_workers.pyConfiguration2.8 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/tests/ray_gpu/test_colocated_workers_fused.pyConfiguration2.8 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/tests/ray_gpu/test_data_transfer.pyConfiguration3.4 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/tests/ray_gpu/test_driverfunc_to_worker.pyConfiguration2.4 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/tests/ray_gpu/test_high_level_scheduling_api.pyConfiguration3.7 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/tests/ray_gpu/test_rvdz.pyConfiguration1.6 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/tests/ray_gpu/test_worker_group_basics.pyConfiguration4.0 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/tests/ray_gpu/test_worker_group_torch.pyConfiguration3.6 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/tests/reward_score/test_sandbox_fusion.pyConfiguration26.6 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/tests/sandbox/test_sandbox.pyConfiguration9.9 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/tests/sanity/check_license.pyConfiguration2.1 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/tests/sanity/test_import.pyConfiguration786 B —
related_works/ARPO/ARPO/verl_arpo_entropy/tests/single_controller/base/test_decorator.pyConfiguration2.3 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/tests/test_protocol.pyConfiguration22.7 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/tests/trainer/__init__.pyConfiguration637 B —
related_works/ARPO/ARPO/verl_arpo_entropy/tests/trainer/ppo/__init__.pyConfiguration642 B —
related_works/ARPO/ARPO/verl_arpo_entropy/tests/trainer/ppo/test_metric_utils.pyConfiguration12.0 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/tests/utils/cpu_tests/_test_module.pyConfiguration959 B —
related_works/ARPO/ARPO/verl_arpo_entropy/tests/utils/cpu_tests/test_fs.pyConfiguration3.3 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/tests/utils/cpu_tests/test_import_utils.pyConfiguration3.1 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/tests/utils/cpu_tests/test_model.pyConfiguration2.5 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/tests/utils/cpu_tests/test_timeout_decorator.pyConfiguration9.9 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/tests/utils/gpu_tests/checkpoint/test_fsdp_ckpt.pyConfiguration5.1 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/tests/utils/gpu_tests/dataset/test_multiturn_sft_dataset.pyConfiguration8.0 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/tests/utils/gpu_tests/dataset/test_rl_dataset.pyConfiguration3.5 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/tests/utils/gpu_tests/dataset/test_rm_dataset.pyConfiguration1.3 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/tests/utils/gpu_tests/dataset/test_sft_dataset.pyConfiguration2.3 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/tests/utils/gpu_tests/megatron/test_pipeline_parallel.pyConfiguration1.5 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/tests/utils/gpu_tests/test_activation_offload.pyConfiguration5.7 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/tests/utils/gpu_tests/test_flops_counter.pyConfiguration6.6 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/tests/utils/gpu_tests/test_seqlen_balancing.pyConfiguration4.4 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/tests/utils/gpu_tests/test_torch_functional.pyConfiguration3.5 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/tests/workers/rollout/async_rollout_utils.pyConfiguration3.0 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/tests/workers/rollout/run_fsdp_vllm.pyConfiguration6.1 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/tests/workers/rollout/test_async_sglang_server.pyConfiguration2.8 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/tests/workers/rollout/test_hf_rollout.pyConfiguration7.4 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/tests/workers/rollout/test_sglang_async_rollout_search_tools.pyConfiguration17.0 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/tests/workers/rollout/test_sglang_async_rollout_sf_tools.pyConfiguration27.4 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/tests/workers/rollout/test_sglang_async_rollout_w_tools.pyConfiguration5.1 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/tests/workers/rollout/test_sglang_spmd.pyConfiguration4.0 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/tests/workers/rollout/test_vllm_hf_loader.pyConfiguration5.9 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/tests/workers/rollout/test_vllm_multi_turn.pyConfiguration7.6 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/tests/workers/rollout/test_vllm_spmd.pyConfiguration6.6 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/tests/workers/rollout/test_vllm_tool_calling.pyConfiguration10.9 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/tests/workers/rollout/utils_sglang.pyConfiguration6.0 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/__init__.pyConfiguration2.2 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/models/__init__.pyConfiguration600 B —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/models/llama/__init__.pyConfiguration600 B —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/models/llama/megatron/__init__.pyConfiguration1.2 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/models/llama/megatron/checkpoint_utils/__init__.pyConfiguration600 B —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/models/llama/megatron/checkpoint_utils/llama_loader.pyConfiguration13.6 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/models/llama/megatron/checkpoint_utils/llama_loader_depracated.pyConfiguration19.0 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/models/llama/megatron/checkpoint_utils/llama_saver.pyConfiguration17.8 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/models/llama/megatron/layers/__init__.pyConfiguration1.2 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/models/llama/megatron/layers/parallel_attention.pyConfiguration20.9 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/models/llama/megatron/layers/parallel_decoder.pyConfiguration6.2 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/models/llama/megatron/layers/parallel_linear.pyConfiguration3.3 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/models/llama/megatron/layers/parallel_mlp.pyConfiguration3.2 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/models/llama/megatron/layers/parallel_rmsnorm.pyConfiguration1.8 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/models/llama/megatron/modeling_llama_megatron.pyConfiguration28.3 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/models/mcore/__init__.pyConfiguration881 B —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/models/mcore/config_converter.pyConfiguration11.8 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/models/mcore/loader.pyConfiguration21.9 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/models/mcore/model_forward.pyConfiguration3.2 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/models/mcore/model_initializer.pyConfiguration7.4 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/models/mcore/patch_v012.pyConfiguration9.5 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/models/mcore/registry.pyConfiguration7.1 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/models/mcore/saver.pyConfiguration20.8 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/models/mcore/util.pyConfiguration8.4 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/models/mcore/weight_converter.pyConfiguration17.9 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/models/qwen2/__init__.pyConfiguration600 B —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/models/qwen2/megatron/__init__.pyConfiguration1.2 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/models/qwen2/megatron/checkpoint_utils/__init__.pyConfiguration600 B —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/models/qwen2/megatron/checkpoint_utils/qwen2_loader.pyConfiguration14.6 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/models/qwen2/megatron/checkpoint_utils/qwen2_loader_depracated.pyConfiguration19.8 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/models/qwen2/megatron/checkpoint_utils/qwen2_saver.pyConfiguration18.0 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/models/qwen2/megatron/layers/__init__.pyConfiguration983 B —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/models/qwen2/megatron/layers/parallel_attention.pyConfiguration17.7 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/models/qwen2/megatron/layers/parallel_decoder.pyConfiguration6.2 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/models/qwen2/megatron/layers/parallel_linear.pyConfiguration2.5 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/models/qwen2/megatron/layers/parallel_mlp.pyConfiguration3.2 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/models/qwen2/megatron/layers/parallel_rmsnorm.pyConfiguration1.8 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/models/qwen2/megatron/modeling_qwen2_megatron.pyConfiguration30.7 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/models/registry.pyConfiguration2.0 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/models/transformers/__init__.pyConfiguration600 B —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/models/transformers/kimi_vl.pyConfiguration10.5 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/models/transformers/llama.pyConfiguration13.3 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/models/transformers/monkey_patch.pyConfiguration11.6 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/models/transformers/qwen2.pyConfiguration10.1 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/models/transformers/qwen2_5_vl.pyConfiguration7.5 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/models/transformers/qwen2_vl.pyConfiguration19.5 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/models/weight_loader_registry.pyConfiguration2.2 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/protocol.pyConfiguration35.7 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/single_controller/__init__.pyConfiguration940 B —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/single_controller/base/__init__.pyConfiguration773 B —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/single_controller/base/decorator.pyConfiguration20.9 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/single_controller/base/megatron/__init__.pyConfiguration600 B —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/single_controller/base/megatron/worker.pyConfiguration4.6 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/single_controller/base/megatron/worker_group.pyConfiguration2.3 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/single_controller/base/register_center/__init__.pyConfiguration600 B —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/single_controller/base/register_center/ray.pyConfiguration1.2 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/single_controller/base/worker.pyConfiguration11.2 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/single_controller/base/worker_group.pyConfiguration9.7 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/single_controller/ray/__init__.pyConfiguration878 B —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/single_controller/ray/base.pyConfiguration35.4 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/single_controller/ray/megatron.pyConfiguration3.3 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/third_party/__init__.pyConfiguration600 B —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/third_party/sglang/__init__.pyConfiguration1.3 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/third_party/sglang/parallel_state.pyConfiguration14.0 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/third_party/vllm/__init__.pyConfiguration1.8 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/third_party/vllm/vllm_v_0_5_4/__init__.pyConfiguration600 B —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/third_party/vllm/vllm_v_0_5_4/arg_utils.pyConfiguration20.8 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/third_party/vllm/vllm_v_0_5_4/config.pyConfiguration11.6 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/third_party/vllm/vllm_v_0_5_4/dtensor_weight_loaders.pyConfiguration15.5 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/third_party/vllm/vllm_v_0_5_4/hf_weight_loader.pyConfiguration1.8 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/third_party/vllm/vllm_v_0_5_4/llm.pyConfiguration11.4 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/third_party/vllm/vllm_v_0_5_4/llm_engine_sp.pyConfiguration14.4 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/third_party/vllm/vllm_v_0_5_4/megatron_weight_loaders.pyConfiguration10.0 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/third_party/vllm/vllm_v_0_5_4/model_loader.pyConfiguration14.2 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/third_party/vllm/vllm_v_0_5_4/model_runner.pyConfiguration6.5 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/third_party/vllm/vllm_v_0_5_4/parallel_state.pyConfiguration12.8 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/third_party/vllm/vllm_v_0_5_4/spmd_gpu_executor.pyConfiguration10.0 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/third_party/vllm/vllm_v_0_5_4/worker.pyConfiguration14.9 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/third_party/vllm/vllm_v_0_6_3/__init__.pyConfiguration600 B —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/third_party/vllm/vllm_v_0_6_3/arg_utils.pyConfiguration3.1 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/third_party/vllm/vllm_v_0_6_3/config.pyConfiguration4.1 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/third_party/vllm/vllm_v_0_6_3/dtensor_weight_loaders.pyConfiguration17.2 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/third_party/vllm/vllm_v_0_6_3/hf_weight_loader.pyConfiguration1.8 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/third_party/vllm/vllm_v_0_6_3/llm.pyConfiguration10.2 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/third_party/vllm/vllm_v_0_6_3/llm_engine_sp.pyConfiguration17.4 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/third_party/vllm/vllm_v_0_6_3/megatron_weight_loaders.pyConfiguration11.0 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/third_party/vllm/vllm_v_0_6_3/model_loader.pyConfiguration14.2 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/third_party/vllm/vllm_v_0_6_3/model_runner.pyConfiguration7.4 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/third_party/vllm/vllm_v_0_6_3/parallel_state.pyConfiguration12.8 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/third_party/vllm/vllm_v_0_6_3/spmd_gpu_executor.pyConfiguration10.0 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/third_party/vllm/vllm_v_0_6_3/worker.pyConfiguration14.8 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/tools/__init__.pyConfiguration634 B —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/tools/base_tool.pyConfiguration2.8 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/tools/gsm8k_tool.pyConfiguration3.8 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/tools/sandbox_fusion_tools.pyConfiguration7.1 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/tools/schemas.pyConfiguration2.6 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/tools/search_tool.pyConfiguration10.5 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/tools/utils/__init__.pyConfiguration634 B —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/tools/utils/search_r1_like_utils.pyConfiguration9.5 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/trainer/__init__.pyConfiguration600 B —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/trainer/config/evaluation.yamlConfiguration373 B —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/trainer/config/generation.yamlConfiguration1.4 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/trainer/config/ppo_megatron_trainer.yamlConfiguration13.0 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/trainer/config/ppo_trainer.yamlConfiguration11.9 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/trainer/config/sft_trainer.yamlConfiguration1.8 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/trainer/fsdp_sft_trainer.pyConfiguration28.0 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/trainer/main_eval.pyConfiguration2.7 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/trainer/main_generation.pyConfiguration5.7 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/trainer/main_ppo.pyConfiguration8.7 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/trainer/ppo/__init__.pyConfiguration600 B —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/trainer/ppo/core_algos.pyConfiguration25.5 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/trainer/ppo/metric_utils.pyConfiguration18.9 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/trainer/ppo/ray_trainer.pyConfiguration62.9 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/trainer/ppo/reward.pyConfiguration4.7 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/trainer/runtime_env.yamlConfiguration230 B —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/utils/__init__.pyConfiguration739 B —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/utils/activation_offload.pyConfiguration22.4 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/utils/checkpoint/__init__.pyConfiguration600 B —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/utils/checkpoint/checkpoint_manager.pyConfiguration5.9 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/utils/checkpoint/fsdp_checkpoint_manager.pyConfiguration12.4 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/utils/checkpoint/megatron_checkpoint_manager.pyConfiguration14.2 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/utils/config.pyConfiguration839 B —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/utils/dataset/__init__.pyConfiguration761 B —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/utils/dataset/multiturn_sft_dataset.pyConfiguration6.2 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/utils/dataset/rl_dataset.pyConfiguration12.3 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/utils/dataset/rm_dataset.pyConfiguration5.3 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/utils/dataset/sft_dataset.pyConfiguration7.3 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/utils/dataset/vision_utils.pyConfiguration2.7 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/utils/debug/__init__.pyConfiguration730 B —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/utils/debug/performance.pyConfiguration4.2 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/utils/debug/profile.pyConfiguration3.6 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/utils/debug/trajectory_tracker.pyConfiguration3.1 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/utils/device.pyConfiguration1.6 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/utils/distributed.pyConfiguration1.4 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/utils/experimental/__init__.pyConfiguration600 B —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/utils/experimental/torch_functional.pyConfiguration8.0 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/utils/flops_counter.pyConfiguration9.6 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/utils/fs.pyConfiguration9.4 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/utils/fsdp_utils.pyConfiguration20.3 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/utils/hdfs_io.pyConfiguration4.6 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/utils/import_utils.pyConfiguration3.3 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/utils/logger/__init__.pyConfiguration600 B —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/utils/logger/aggregate_logger.pyConfiguration2.3 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/utils/logging_utils.pyConfiguration1.1 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/utils/megatron/__init__.pyConfiguration600 B —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/utils/megatron/memory.pyConfiguration1.4 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/utils/megatron/optimizer.pyConfiguration1.3 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/utils/megatron/pipeline_parallel.pyConfiguration2.7 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/utils/megatron/sequence_parallel.pyConfiguration1.8 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/utils/megatron/tensor_parallel.pyConfiguration7.1 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/utils/megatron_utils.pyConfiguration42.7 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/utils/memory_buffer.pyConfiguration8.0 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/utils/metric/__init__.pyConfiguration665 B —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/utils/metric/utils.pyConfiguration1.8 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/utils/model.pyConfiguration17.5 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/utils/net_utils.pyConfiguration2.0 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/utils/py_functional.pyConfiguration10.9 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/utils/ray_utils.pyConfiguration3.8 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/utils/rendezvous/__init__.pyConfiguration600 B —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/utils/rendezvous/ray_backend.pyConfiguration2.6 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/utils/reward_score/__init__.pyConfiguration4.6 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/utils/reward_score/deep_research.pyConfiguration16.6 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/utils/reward_score/geo3k.pyConfiguration1.2 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/utils/reward_score/gsm8k.pyConfiguration2.4 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/utils/reward_score/math.pyConfiguration6.7 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/utils/reward_score/math_batch.pyConfiguration1.0 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/utils/reward_score/math_dapo.pyConfiguration7.7 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/utils/reward_score/math_verify.pyConfiguration1.5 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/utils/reward_score/prime_code/__init__.pyConfiguration3.1 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/utils/reward_score/prime_code/testing_util.pyConfiguration25.2 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/utils/reward_score/prime_code/utils.pyConfiguration2.2 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/utils/reward_score/prime_math/__init__.pyConfiguration12.4 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/utils/reward_score/prime_math/grader.pyConfiguration13.9 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/utils/reward_score/prime_math/math_normalize.pyConfiguration6.3 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/utils/reward_score/sandbox_fusion/__init__.pyConfiguration4.8 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/utils/reward_score/sandbox_fusion/utils.pyConfiguration22.6 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/utils/reward_score/search_r1_like_qa_em.pyConfiguration5.3 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/utils/seqlen_balancing.pyConfiguration12.2 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/utils/torch_dtypes.pyConfiguration2.3 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/utils/torch_functional.pyConfiguration28.1 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/utils/tracking.pyConfiguration13.1 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/utils/ulysses.pyConfiguration11.7 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/utils/vllm_utils.pyConfiguration8.8 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/workers/__init__.pyConfiguration600 B —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/workers/actor/__init__.pyConfiguration727 B —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/workers/actor/base.pyConfiguration2.1 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/workers/actor/dp_actor.pyConfiguration21.6 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/workers/actor/megatron_actor.pyConfiguration26.6 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/workers/agent/__init__.pyConfiguration2.6 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/workers/agent/agent.yamlConfiguration727 B —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/workers/agent/base.pyConfiguration3.0 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/workers/agent/tool_agent.pyConfiguration20.1 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/workers/agent/tools/__init__.pyConfiguration —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/workers/agent/tools/base_tool.pyConfiguration473 B —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/workers/agent/tools/python_tool.pyConfiguration4.5 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/workers/agent/tools/search_tool.pyConfiguration17.1 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/workers/agent/tools/tool_executor.pyConfiguration6.4 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/workers/critic/__init__.pyConfiguration732 B —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/workers/critic/base.pyConfiguration1.1 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/workers/critic/dp_critic.pyConfiguration12.7 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/workers/critic/megatron_critic.pyConfiguration13.6 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/workers/fsdp_workers.pyConfiguration73.2 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/workers/megatron_workers.pyConfiguration46.4 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/workers/reward_manager/__init__.pyConfiguration846 B —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/workers/reward_manager/batch.pyConfiguration4.4 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/workers/reward_manager/dapo.pyConfiguration5.5 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/workers/reward_manager/naive.pyConfiguration4.4 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/workers/reward_manager/prime.pyConfiguration7.4 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/workers/reward_model/__init__.pyConfiguration672 B —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/workers/reward_model/base.pyConfiguration1.7 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/workers/reward_model/megatron/__init__.pyConfiguration682 B —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/workers/reward_model/megatron/reward_model.pyConfiguration14.8 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/workers/rollout/__init__.pyConfiguration753 B —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/workers/rollout/async_server.pyConfiguration14.5 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/workers/rollout/base.pyConfiguration886 B —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/workers/rollout/hf_rollout.pyConfiguration7.3 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/workers/rollout/naive/__init__.pyConfiguration669 B —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/workers/rollout/naive/naive_rollout.pyConfiguration4.8 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/workers/rollout/schemas.pyConfiguration11.9 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/workers/rollout/sglang_rollout/__init__.pyConfiguration639 B —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/workers/rollout/sglang_rollout/async_sglang_server.pyConfiguration2.8 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/workers/rollout/sglang_rollout/sglang_rollout.pyConfiguration52.7 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/workers/rollout/sglang_rollout/utils.pyConfiguration2.5 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/workers/rollout/tools/base_tool.pyConfiguration473 B —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/workers/rollout/tools/config_example.yamlConfiguration911 B —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/workers/rollout/tools/python_tool.pyConfiguration4.5 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/workers/rollout/tools/search_tool.pyConfiguration17.1 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/workers/rollout/vllm_rollout/__init__.pyConfiguration1.9 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/workers/rollout/vllm_rollout/fire_vllm_rollout.pyConfiguration9.8 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/workers/rollout/vllm_rollout/vllm_agent_rollout.pyConfiguration6.8 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/workers/rollout/vllm_rollout/vllm_async_server.pyConfiguration11.0 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/workers/rollout/vllm_rollout/vllm_rollout.pyConfiguration13.0 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/workers/rollout/vllm_rollout/vllm_rollout_spmd.pyConfiguration19.1 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/workers/rollout/vllm_rollout/vllm_rollout_with_tools.pyConfiguration32.2 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/workers/sharding_manager/__init__.pyConfiguration600 B —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/workers/sharding_manager/base.pyConfiguration981 B —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/workers/sharding_manager/fsdp_sglang.pyConfiguration8.0 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/workers/sharding_manager/fsdp_ulysses.pyConfiguration2.8 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/workers/sharding_manager/fsdp_vllm.pyConfiguration13.8 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/workers/sharding_manager/megatron_sglang.pyConfiguration6.3 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/workers/sharding_manager/megatron_vllm.pyConfiguration16.3 KB —
related_works/ARPO/LLaMA-Factory/.github/ISSUE_TEMPLATE/1-bug-report.ymlConfiguration2.4 KB —
related_works/ARPO/LLaMA-Factory/.github/ISSUE_TEMPLATE/2-feature-request.ymlConfiguration1.3 KB —
related_works/ARPO/LLaMA-Factory/.github/ISSUE_TEMPLATE/config.ymlConfiguration384 B —
related_works/ARPO/LLaMA-Factory/.github/workflows/docker.ymlConfiguration3.1 KB —
related_works/ARPO/LLaMA-Factory/.github/workflows/label_issue.ymlConfiguration830 B —
related_works/ARPO/LLaMA-Factory/.github/workflows/publish.ymlConfiguration611 B —
related_works/ARPO/LLaMA-Factory/.github/workflows/tests.ymlConfiguration2.4 KB —
related_works/ARPO/LLaMA-Factory/.pre-commit-config.yamlConfiguration712 B —
related_works/ARPO/LLaMA-Factory/arpo_train_sft/dataset_info/dataset_info.jsonConfiguration641 B —
related_works/ARPO/LLaMA-Factory/arpo_train_sft/yaml/qwen.yamlConfiguration877 B —
related_works/ARPO/LLaMA-Factory/data/alpaca_en_demo.jsonConfiguration860.9 KB —
related_works/ARPO/LLaMA-Factory/data/alpaca_zh_demo.jsonConfiguration636.0 KB —
related_works/ARPO/LLaMA-Factory/data/belle_multiturn/belle_multiturn.pyConfiguration3.4 KB —
related_works/ARPO/LLaMA-Factory/data/dataset_info.jsonConfiguration17.2 KB —
related_works/ARPO/LLaMA-Factory/data/dpo_en_demo.jsonConfiguration1.6 MB —
related_works/ARPO/LLaMA-Factory/data/dpo_zh_demo.jsonConfiguration853.3 KB —
related_works/ARPO/LLaMA-Factory/data/glaive_toolcall_en_demo.jsonConfiguration738.9 KB —
related_works/ARPO/LLaMA-Factory/data/glaive_toolcall_zh_demo.jsonConfiguration680.7 KB —
related_works/ARPO/LLaMA-Factory/data/hh_rlhf_en/hh_rlhf_en.pyConfiguration4.0 KB —
related_works/ARPO/LLaMA-Factory/data/identity.jsonConfiguration20.3 KB —
related_works/ARPO/LLaMA-Factory/data/kto_en_demo.jsonConfiguration913.5 KB —
related_works/ARPO/LLaMA-Factory/data/mllm_audio_demo.jsonConfiguration877 B —
related_works/ARPO/LLaMA-Factory/data/mllm_demo.jsonConfiguration3.3 KB —
related_works/ARPO/LLaMA-Factory/data/mllm_video_audio_demo.jsonConfiguration1.1 KB —
related_works/ARPO/LLaMA-Factory/data/mllm_video_demo.jsonConfiguration828 B —
related_works/ARPO/LLaMA-Factory/data/ultra_chat/ultra_chat.pyConfiguration2.9 KB —
related_works/ARPO/LLaMA-Factory/docker/docker-cuda/docker-compose.ymlConfiguration565 B —
related_works/ARPO/LLaMA-Factory/docker/docker-npu/docker-compose.ymlConfiguration750 B —
related_works/ARPO/LLaMA-Factory/docker/docker-rocm/docker-compose.ymlConfiguration474 B —
related_works/ARPO/LLaMA-Factory/evaluation/ceval/ceval.pyConfiguration5.0 KB —
related_works/ARPO/LLaMA-Factory/evaluation/ceval/mapping.jsonConfiguration4.6 KB —
related_works/ARPO/LLaMA-Factory/evaluation/cmmlu/cmmlu.pyConfiguration5.0 KB —
related_works/ARPO/LLaMA-Factory/evaluation/cmmlu/mapping.jsonConfiguration5.8 KB —
related_works/ARPO/LLaMA-Factory/evaluation/mmlu/mapping.jsonConfiguration5.2 KB —
related_works/ARPO/LLaMA-Factory/evaluation/mmlu/mmlu.pyConfiguration4.8 KB —
related_works/ARPO/LLaMA-Factory/examples/accelerate/fsdp_config.yamlConfiguration707 B —
related_works/ARPO/LLaMA-Factory/examples/accelerate/fsdp_config_offload.yamlConfiguration743 B —
related_works/ARPO/LLaMA-Factory/examples/deepspeed/ds_z0_config.jsonConfiguration665 B —
related_works/ARPO/LLaMA-Factory/examples/deepspeed/ds_z2_config.jsonConfiguration665 B —
related_works/ARPO/LLaMA-Factory/examples/deepspeed/ds_z2_offload_config.jsonConfiguration747 B —
related_works/ARPO/LLaMA-Factory/examples/deepspeed/ds_z3_config.jsonConfiguration789 B —
related_works/ARPO/LLaMA-Factory/examples/deepspeed/ds_z3_offload_config.jsonConfiguration949 B —
related_works/ARPO/LLaMA-Factory/examples/extras/adam_mini/qwen2_full_sft.yamlConfiguration849 B —
related_works/ARPO/LLaMA-Factory/examples/extras/apollo/llama3_full_sft.yamlConfiguration1.1 KB —
related_works/ARPO/LLaMA-Factory/examples/extras/badam/llama3_full_sft.yamlConfiguration963 B —
related_works/ARPO/LLaMA-Factory/examples/extras/fsdp_qlora/llama3_lora_sft.yamlConfiguration891 B —
related_works/ARPO/LLaMA-Factory/examples/extras/galore/llama3_full_sft.yamlConfiguration1.0 KB —
related_works/ARPO/LLaMA-Factory/examples/extras/llama_pro/llama3_freeze_sft.yamlConfiguration911 B —
related_works/ARPO/LLaMA-Factory/examples/extras/loraplus/llama3_lora_sft.yamlConfiguration895 B —
related_works/ARPO/LLaMA-Factory/examples/extras/mod/llama3_full_sft.yamlConfiguration901 B —
related_works/ARPO/LLaMA-Factory/examples/extras/muon/qwen2_full_sft.yamlConfiguration844 B —
related_works/ARPO/LLaMA-Factory/examples/extras/nlg_eval/llama3_lora_predict.yamlConfiguration745 B —
related_works/ARPO/LLaMA-Factory/examples/extras/pissa/llama3_lora_sft.yamlConfiguration923 B —
related_works/ARPO/LLaMA-Factory/examples/inference/llama3.yamlConfiguration164 B —
related_works/ARPO/LLaMA-Factory/examples/inference/llama3_full_sft.yamlConfiguration153 B —
related_works/ARPO/LLaMA-Factory/examples/inference/llama3_lora_sft.yamlConfiguration211 B —
related_works/ARPO/LLaMA-Factory/examples/inference/qwen2_5vl.yamlConfiguration158 B —
related_works/ARPO/LLaMA-Factory/examples/merge_lora/llama3_full_sft.yamlConfiguration229 B —
related_works/ARPO/LLaMA-Factory/examples/merge_lora/llama3_gptq.yamlConfiguration311 B —
related_works/ARPO/LLaMA-Factory/examples/merge_lora/llama3_lora_sft.yamlConfiguration372 B —
related_works/ARPO/LLaMA-Factory/examples/merge_lora/qwen2_5vl_lora_sft.yamlConfiguration372 B —
related_works/ARPO/LLaMA-Factory/examples/train_full/llama3_full_sft.yamlConfiguration1.0 KB —
related_works/ARPO/LLaMA-Factory/examples/train_full/qwen2_5vl_full_sft.yamlConfiguration1.1 KB —
related_works/ARPO/LLaMA-Factory/examples/train_lora/llama3_lora_dpo.yamlConfiguration991 B —
related_works/ARPO/LLaMA-Factory/examples/train_lora/llama3_lora_eval.yamlConfiguration363 B —
related_works/ARPO/LLaMA-Factory/examples/train_lora/llama3_lora_kto.yamlConfiguration851 B —
related_works/ARPO/LLaMA-Factory/examples/train_lora/llama3_lora_ppo.yamlConfiguration845 B —
related_works/ARPO/LLaMA-Factory/examples/train_lora/llama3_lora_pretrain.yamlConfiguration895 B —
related_works/ARPO/LLaMA-Factory/examples/train_lora/llama3_lora_reward.yamlConfiguration918 B —
related_works/ARPO/LLaMA-Factory/examples/train_lora/llama3_lora_sft.yamlConfiguration931 B —
related_works/ARPO/LLaMA-Factory/examples/train_lora/llama3_lora_sft_ds3.yamlConfiguration1.0 KB —
related_works/ARPO/LLaMA-Factory/examples/train_lora/llama3_lora_sft_ray.yamlConfiguration1.3 KB —
related_works/ARPO/LLaMA-Factory/examples/train_lora/llama3_preprocess.yamlConfiguration450 B —
related_works/ARPO/LLaMA-Factory/examples/train_lora/llama4_lora_sft_ds3.yamlConfiguration1.1 KB —
related_works/ARPO/LLaMA-Factory/examples/train_lora/qwen2_5vl_lora_dpo.yamlConfiguration1.0 KB —
related_works/ARPO/LLaMA-Factory/examples/train_lora/qwen2_5vl_lora_sft.yamlConfiguration982 B —
related_works/ARPO/LLaMA-Factory/examples/train_qlora/llama3_lora_sft_aqlm.yamlConfiguration887 B —
related_works/ARPO/LLaMA-Factory/examples/train_qlora/llama3_lora_sft_awq.yamlConfiguration875 B —
related_works/ARPO/LLaMA-Factory/examples/train_qlora/llama3_lora_sft_bnb_npu.yamlConfiguration943 B —
related_works/ARPO/LLaMA-Factory/examples/train_qlora/llama3_lora_sft_gptq.yamlConfiguration876 B —
related_works/ARPO/LLaMA-Factory/examples/train_qlora/llama3_lora_sft_otfq.yamlConfiguration1.0 KB —
related_works/ARPO/LLaMA-Factory/scripts/api_example/test_image.pyConfiguration2.3 KB —
related_works/ARPO/LLaMA-Factory/scripts/api_example/test_toolcall.pyConfiguration3.1 KB —
related_works/ARPO/LLaMA-Factory/scripts/convert_ckpt/llamafy_baichuan2.pyConfiguration4.7 KB —
related_works/ARPO/LLaMA-Factory/scripts/convert_ckpt/llamafy_qwen.pyConfiguration7.5 KB —
related_works/ARPO/LLaMA-Factory/scripts/convert_ckpt/tiny_llama4.pyConfiguration1.4 KB —
related_works/ARPO/LLaMA-Factory/scripts/eval_bleu_rouge.pyConfiguration2.6 KB —
related_works/ARPO/LLaMA-Factory/scripts/llama_pro.pyConfiguration5.4 KB —
related_works/ARPO/LLaMA-Factory/scripts/loftq_init.pyConfiguration3.3 KB —
related_works/ARPO/LLaMA-Factory/scripts/pissa_init.pyConfiguration3.2 KB —
related_works/ARPO/LLaMA-Factory/scripts/qwen_omni_merge.pyConfiguration6.0 KB —
related_works/ARPO/LLaMA-Factory/scripts/stat_utils/cal_flops.pyConfiguration1.9 KB —
related_works/ARPO/LLaMA-Factory/scripts/stat_utils/cal_lr.pyConfiguration3.9 KB —
related_works/ARPO/LLaMA-Factory/scripts/stat_utils/cal_mfu.pyConfiguration5.8 KB —
related_works/ARPO/LLaMA-Factory/scripts/stat_utils/cal_ppl.pyConfiguration5.5 KB —
related_works/ARPO/LLaMA-Factory/scripts/stat_utils/length_cdf.pyConfiguration2.5 KB —
related_works/ARPO/LLaMA-Factory/scripts/vllm_infer.pyConfiguration7.9 KB —
related_works/ARPO/LLaMA-Factory/setup.pyConfiguration4.0 KB —
related_works/ARPO/LLaMA-Factory/src/api.pyConfiguration1.0 KB —
related_works/ARPO/LLaMA-Factory/src/llamafactory/__init__.pyConfiguration1.0 KB —
related_works/ARPO/LLaMA-Factory/src/llamafactory/api/__init__.pyConfiguration —
related_works/ARPO/LLaMA-Factory/src/llamafactory/api/app.pyConfiguration4.5 KB —
related_works/ARPO/LLaMA-Factory/src/llamafactory/api/chat.pyConfiguration11.4 KB —
related_works/ARPO/LLaMA-Factory/src/llamafactory/api/common.pyConfiguration1.2 KB —
related_works/ARPO/LLaMA-Factory/src/llamafactory/api/protocol.pyConfiguration4.0 KB —
related_works/ARPO/LLaMA-Factory/src/llamafactory/chat/__init__.pyConfiguration697 B —
related_works/ARPO/LLaMA-Factory/src/llamafactory/chat/base_engine.pyConfiguration3.1 KB —
related_works/ARPO/LLaMA-Factory/src/llamafactory/chat/chat_model.pyConfiguration6.9 KB —
related_works/ARPO/LLaMA-Factory/src/llamafactory/chat/hf_engine.pyConfiguration16.5 KB —
related_works/ARPO/LLaMA-Factory/src/llamafactory/chat/sglang_engine.pyConfiguration12.7 KB —
related_works/ARPO/LLaMA-Factory/src/llamafactory/chat/vllm_engine.pyConfiguration11.7 KB —
related_works/ARPO/LLaMA-Factory/src/llamafactory/cli.pyConfiguration6.2 KB —
related_works/ARPO/LLaMA-Factory/src/llamafactory/data/__init__.pyConfiguration1.2 KB —
related_works/ARPO/LLaMA-Factory/src/llamafactory/data/collator.pyConfiguration14.3 KB —
related_works/ARPO/LLaMA-Factory/src/llamafactory/data/converter.pyConfiguration12.0 KB —
related_works/ARPO/LLaMA-Factory/src/llamafactory/data/data_utils.pyConfiguration7.0 KB —
related_works/ARPO/LLaMA-Factory/src/llamafactory/data/formatter.pyConfiguration4.8 KB —
related_works/ARPO/LLaMA-Factory/src/llamafactory/data/loader.pyConfiguration14.0 KB —
related_works/ARPO/LLaMA-Factory/src/llamafactory/data/mm_plugin.pyConfiguration80.2 KB —
related_works/ARPO/LLaMA-Factory/src/llamafactory/data/parser.pyConfiguration5.7 KB —
related_works/ARPO/LLaMA-Factory/src/llamafactory/data/processor/__init__.pyConfiguration1.2 KB —
related_works/ARPO/LLaMA-Factory/src/llamafactory/data/processor/feedback.pyConfiguration6.1 KB —
related_works/ARPO/LLaMA-Factory/src/llamafactory/data/processor/pairwise.pyConfiguration5.6 KB —
related_works/ARPO/LLaMA-Factory/src/llamafactory/data/processor/pretrain.pyConfiguration2.8 KB —
related_works/ARPO/LLaMA-Factory/src/llamafactory/data/processor/processor_utils.pyConfiguration3.1 KB —
related_works/ARPO/LLaMA-Factory/src/llamafactory/data/processor/supervised.pyConfiguration9.7 KB —
related_works/ARPO/LLaMA-Factory/src/llamafactory/data/processor/unsupervised.pyConfiguration3.9 KB —
related_works/ARPO/LLaMA-Factory/src/llamafactory/data/template.pyConfiguration81.5 KB —
related_works/ARPO/LLaMA-Factory/src/llamafactory/data/tool_utils.pyConfiguration11.6 KB —
related_works/ARPO/LLaMA-Factory/src/llamafactory/eval/__init__.pyConfiguration —
related_works/ARPO/LLaMA-Factory/src/llamafactory/eval/evaluator.pyConfiguration7.4 KB —
related_works/ARPO/LLaMA-Factory/src/llamafactory/eval/template.pyConfiguration2.9 KB —
related_works/ARPO/LLaMA-Factory/src/llamafactory/extras/__init__.pyConfiguration —
related_works/ARPO/LLaMA-Factory/src/llamafactory/extras/constants.pyConfiguration121.7 KB —
related_works/ARPO/LLaMA-Factory/src/llamafactory/extras/env.pyConfiguration2.8 KB —
related_works/ARPO/LLaMA-Factory/src/llamafactory/extras/logging.pyConfiguration5.3 KB —
related_works/ARPO/LLaMA-Factory/src/llamafactory/extras/misc.pyConfiguration11.3 KB —
related_works/ARPO/LLaMA-Factory/src/llamafactory/extras/packages.pyConfiguration2.5 KB —
related_works/ARPO/LLaMA-Factory/src/llamafactory/extras/ploting.pyConfiguration3.2 KB —
related_works/ARPO/LLaMA-Factory/src/llamafactory/hparams/__init__.pyConfiguration1.2 KB —
related_works/ARPO/LLaMA-Factory/src/llamafactory/hparams/data_args.pyConfiguration7.7 KB —
related_works/ARPO/LLaMA-Factory/src/llamafactory/hparams/evaluation_args.pyConfiguration2.0 KB —
related_works/ARPO/LLaMA-Factory/src/llamafactory/hparams/finetuning_args.pyConfiguration19.3 KB —
related_works/ARPO/LLaMA-Factory/src/llamafactory/hparams/generating_args.pyConfiguration3.0 KB —
related_works/ARPO/LLaMA-Factory/src/llamafactory/hparams/model_args.pyConfiguration16.6 KB —
related_works/ARPO/LLaMA-Factory/src/llamafactory/hparams/parser.pyConfiguration21.1 KB —
related_works/ARPO/LLaMA-Factory/src/llamafactory/hparams/training_args.pyConfiguration3.3 KB —
related_works/ARPO/LLaMA-Factory/src/llamafactory/launcher.pyConfiguration727 B —
related_works/ARPO/LLaMA-Factory/src/llamafactory/model/__init__.pyConfiguration976 B —
related_works/ARPO/LLaMA-Factory/src/llamafactory/model/adapter.pyConfiguration13.1 KB —
related_works/ARPO/LLaMA-Factory/src/llamafactory/model/loader.pyConfiguration8.6 KB —
related_works/ARPO/LLaMA-Factory/src/llamafactory/model/model_utils/__init__.pyConfiguration —
related_works/ARPO/LLaMA-Factory/src/llamafactory/model/model_utils/attention.pyConfiguration3.8 KB —
related_works/ARPO/LLaMA-Factory/src/llamafactory/model/model_utils/checkpointing.pyConfiguration7.6 KB —
related_works/ARPO/LLaMA-Factory/src/llamafactory/model/model_utils/embedding.pyConfiguration2.9 KB —
related_works/ARPO/LLaMA-Factory/src/llamafactory/model/model_utils/kv_cache.pyConfiguration1.5 KB —
related_works/ARPO/LLaMA-Factory/src/llamafactory/model/model_utils/liger_kernel.pyConfiguration4.1 KB —
related_works/ARPO/LLaMA-Factory/src/llamafactory/model/model_utils/longlora.pyConfiguration16.1 KB —
related_works/ARPO/LLaMA-Factory/src/llamafactory/model/model_utils/misc.pyConfiguration3.5 KB —
related_works/ARPO/LLaMA-Factory/src/llamafactory/model/model_utils/mod.pyConfiguration1.4 KB —
related_works/ARPO/LLaMA-Factory/src/llamafactory/model/model_utils/moe.pyConfiguration4.4 KB —
CLAUDE.mdDocumentation6.9 KB —
README.mdDocumentation —
SNAPSHOT_README.mdDocumentation7.0 KB —
code_public/HybridAgent/LICENSEDocumentation1.1 KB —
code_public/HybridAgent/README.mdDocumentation7.7 KB —
code_public/HybridAgent/hybrid_agent/README.mdDocumentation3.9 KB —
code_public/HybridAgent/hybrid_inference/README.mdDocumentation2.5 KB —
code_public/HybridAgent/hybrid_rl/README.mdDocumentation2.6 KB —
code_public/HybridAgent/hybrid_sft/README.mdDocumentation3.6 KB —
code_public/HybridAgent/interpretable_latent_mode/README.mdDocumentation7.4 KB —
code_public/_hf_release/HybridAgent-14B-Agentic/README.mdDocumentation3.0 KB —
code_public/_hf_release/HybridAgent-8B-Agentic/README.mdDocumentation3.0 KB —
code_public/_hf_release/HybridAgent-HybridRL/README.mdDocumentation1.9 KB —
code_public/_hf_release/HybridAgent-HybridSFT-v1/README.mdDocumentation2.2 KB —
code_public/_hf_release/HybridAgent-HybridSFT-v2/README.mdDocumentation2.2 KB —
code_public/_smoke/hf_cache/hub/models--Qwen--Qwen3-0.6B-Base/snapshots/da87bfb608c14b7cf20ba1ce41287e8de496c0cd/LICENSEDocumentation11.3 KB —
code_public/_smoke/hf_cache/hub/models--Qwen--Qwen3-0.6B-Base/snapshots/da87bfb608c14b7cf20ba1ce41287e8de496c0cd/README.mdDocumentation3.0 KB —
data/HybridSFT_v2/pilot/review_examples.mdDocumentation130.7 KB —
data/HybridSFT_v2/pilot/review_examples_pilot.mdDocumentation184.8 KB —
data_label_hybridSFT/PLAN.mdDocumentation74.6 KB —
data_label_hybridSFT/README.mdDocumentation4.2 KB —
docs/AIME25_AIME26_4B_8B_random_best_avg_pass_k4_5_8_12.mdDocumentation11.2 KB —
docs/MIGRATION.mdDocumentation16.0 KB —
docs/arpo32b_baseline_eval.mdDocumentation11.3 KB —
docs/arpo8bsft_baseline_eval.mdDocumentation7.1 KB —
docs/baseline/AIME25_AIME26_GRPO_4B_8B_pass_at_k.mdDocumentation5.1 KB —
docs/browsecomp_eval.mdDocumentation3.8 KB —
docs/closedbook_llm_baselines.mdDocumentation25.1 KB —
docs/data_comparison_dapo12k_vs_arpo5k.mdDocumentation3.6 KB —
docs/dsrl_gpqa_eval.mdDocumentation4.6 KB —
docs/dsrl_medqa_eval.mdDocumentation10.5 KB —
docs/dsrl_sealqa_dsqa_eval.mdDocumentation62.0 KB —
docs/eval_setup_handoff.mdDocumentation9.8 KB —
docs/experiments_aug2026_summary.mdDocumentation10.3 KB —
docs/fillgaps_oneshot_eval_2026-09-16.mdDocumentation8.3 KB —
docs/grpo14b_baseline_eval.mdDocumentation16.6 KB —
docs/grpo_baseline_14B_eval.mdDocumentation16.6 KB —
docs/hybrid_sft_vs_rl_eval.mdDocumentation6.0 KB —
docs/hybridsft_v2_data.mdDocumentation7.0 KB —
docs/math500_gpqa_master_table.mdDocumentation6.5 KB —
docs/musique_eval.mdDocumentation23.8 KB —
docs/passk_master_table.mdDocumentation30.2 KB —
docs/run12_eval_aime.mdDocumentation3.4 KB —
docs/run12_eval_gpqa.mdDocumentation2.9 KB —
docs/run12_eval_latent_probes.mdDocumentation5.0 KB —
docs/run12_eval_math500.mdDocumentation1.5 KB —
docs/run12_eval_overview.mdDocumentation3.1 KB —
docs/run12_run15_pass64.mdDocumentation5.5 KB —
docs/run14_eval_aime.mdDocumentation4.5 KB —
docs/run14_eval_gpqa.mdDocumentation3.2 KB —
docs/run14_eval_math500.mdDocumentation1.9 KB —
docs/run14_eval_overview.mdDocumentation7.3 KB —
docs/run14_eval_pass64.mdDocumentation4.5 KB —
docs/run15_eval_campaign.mdDocumentation4.0 KB —
docs/run16_eval_aime.mdDocumentation2.9 KB —
docs/run16_eval_gpqa.mdDocumentation6.5 KB —
docs/run16_eval_math500.mdDocumentation1.5 KB —
docs/run16_eval_overview.mdDocumentation5.9 KB —
docs/run19_eval_campaign.mdDocumentation5.5 KB —
docs/run20_eval_campaign.mdDocumentation6.9 KB —
docs/run20_launch.mdDocumentation16.0 KB —
docs/sft14b_c2000_eval_report.mdDocumentation4.8 KB —
eval_rl/run20_scores/run20_eval_table.mdDocumentation2.1 KB —
eval_rl_new_v2/results/dsrl_sealqa_dsqa_2026-09-11/README.mdDocumentation1.2 KB —
eval_v6_campaign/FINAL_REPORT.mdDocumentation2.8 KB —
eval_v6_campaign/STATUS.mdDocumentation1.4 KB —
finetune/README.mdDocumentation1.8 KB —
models/rl_new_v2/run12_qwen3b_dapo12k_arpoadditive_latentfmt_batch_p64_m5000_lat180_sr500_tc3_valmath5mvS5_seed123_4node/checkpoint-140/README.mdDocumentation2.3 KB —
models/version_7_base/qwen3_14b/stage3_full/checkpoint-2000/README.mdDocumentation1.4 KB —
models/version_7_base/qwen3_4b_base_hybrid_ns2lr2e4_ckpt7000/README.mdDocumentation1.5 KB —
models/version_7_base/qwen3_8b/stage3_full/checkpoint-2000/README.mdDocumentation925 B —
paper_writing/HybridAgent_Submission/README.mdDocumentation1.5 KB —
paper_writing/README_prompts.mdDocumentation23.3 KB —
paper_writing/best_of_4_qwen3_8b.mdDocumentation2.0 KB —
paper_writing/qwen3_4b_experiments.mdDocumentation5.0 KB —
pass_k_eval/RESULTS.mdDocumentation4.6 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/LICENSEDocumentation11.4 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/README.mdDocumentation23.6 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/docs/README.mdDocumentation321 B —
related_works/ARPO/AEPO/verl_aepo_entropy/docs/README_vllm0.7.mdDocumentation3.1 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/docs/README_vllm0.8.mdDocumentation1.7 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/docs/algo/baseline.mdDocumentation5.0 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/docs/algo/dapo.mdDocumentation7.1 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/docs/algo/grpo.mdDocumentation5.3 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/docs/algo/opo.mdDocumentation2.2 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/docs/algo/ppo.mdDocumentation6.6 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/docs/algo/spin.mdDocumentation11.5 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/docs/algo/sppo.mdDocumentation3.2 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/examples/grpo_trainer/README.mdDocumentation5.3 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/examples/ppo_trainer/README.mdDocumentation6.6 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/examples/sglang_multiturn/README.mdDocumentation946 B —
related_works/ARPO/AEPO/verl_aepo_entropy/examples/split_placement/README.mdDocumentation2.7 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/recipe/README.mdDocumentation3.2 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/recipe/dapo/README.mdDocumentation8.1 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/recipe/r1/README.mdDocumentation672 B —
related_works/ARPO/AEPO/verl_aepo_entropy/recipe/spin/README.mdDocumentation11.5 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/recipe/sppo/README.mdDocumentation3.2 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/tests/e2e/arithmetic_sequence/rl/README.mdDocumentation760 B —
related_works/ARPO/AEPO/verl_aepo_entropy/tests/ray_gpu/detached_worker/README.mdDocumentation242 B —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/models/README.mdDocumentation1.7 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/models/mcore/readme.mdDocumentation6.4 KB —
related_works/ARPO/AEPO/verl_aepo_entropy/verl/utils/dataset/README.mdDocumentation797 B —
related_works/ARPO/ARPO/verl_arpo_entropy/LICENSEDocumentation11.4 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/README.mdDocumentation23.6 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/docs/README.mdDocumentation321 B —
related_works/ARPO/ARPO/verl_arpo_entropy/docs/README_vllm0.7.mdDocumentation3.1 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/docs/README_vllm0.8.mdDocumentation1.7 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/docs/algo/baseline.mdDocumentation5.0 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/docs/algo/dapo.mdDocumentation7.1 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/docs/algo/grpo.mdDocumentation5.3 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/docs/algo/opo.mdDocumentation2.2 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/docs/algo/ppo.mdDocumentation6.6 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/docs/algo/spin.mdDocumentation11.5 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/docs/algo/sppo.mdDocumentation3.2 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/examples/grpo_trainer/README.mdDocumentation5.3 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/examples/ppo_trainer/README.mdDocumentation6.6 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/examples/sglang_multiturn/README.mdDocumentation946 B —
related_works/ARPO/ARPO/verl_arpo_entropy/examples/split_placement/README.mdDocumentation2.7 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/recipe/README.mdDocumentation3.2 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/recipe/dapo/README.mdDocumentation8.1 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/recipe/r1/README.mdDocumentation672 B —
related_works/ARPO/ARPO/verl_arpo_entropy/recipe/spin/README.mdDocumentation11.5 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/recipe/sppo/README.mdDocumentation3.2 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/tests/e2e/arithmetic_sequence/rl/README.mdDocumentation760 B —
related_works/ARPO/ARPO/verl_arpo_entropy/tests/ray_gpu/detached_worker/README.mdDocumentation242 B —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/models/README.mdDocumentation1.7 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/models/mcore/readme.mdDocumentation6.4 KB —
related_works/ARPO/ARPO/verl_arpo_entropy/verl/utils/dataset/README.mdDocumentation797 B —
related_works/ARPO/LLaMA-Factory/.github/CODE_OF_CONDUCT.mdDocumentation5.2 KB —
related_works/ARPO/LLaMA-Factory/.github/CONTRIBUTING.mdDocumentation2.4 KB —
related_works/ARPO/LLaMA-Factory/.github/PULL_REQUEST_TEMPLATE.mdDocumentation233 B —
related_works/ARPO/LLaMA-Factory/.github/SECURITY.mdDocumentation548 B —
related_works/ARPO/LLaMA-Factory/LICENSEDocumentation11.3 KB —
related_works/ARPO/LLaMA-Factory/README.mdDocumentation68.1 KB —
related_works/ARPO/LLaMA-Factory/README_zh.mdDocumentation67.1 KB —
related_works/ARPO/LLaMA-Factory/data/README.mdDocumentation13.7 KB —
related_works/ARPO/LLaMA-Factory/data/README_zh.mdDocumentation13.0 KB —
related_works/ARPO/LLaMA-Factory/docker/docker-cuda/README.mdDocumentation3.1 KB —
related_works/ARPO/LLaMA-Factory/examples/README.mdDocumentation7.1 KB —
related_works/ARPO/LLaMA-Factory/examples/README_zh.mdDocumentation6.9 KB —
angle_construction.pngOther27.0 KB —
code.bundleOther1.5 MB 699917ebc3d7
code.bundle.HEADOther41 B —
code_public/HybridAgent/assets/hybrid_agent_overview.pngOther154.6 KB e006652af49c
code_public/HybridAgent/assets/hybrid_sft.pngOther109.4 KB 550782a7bcbd
code_public/HybridAgent/assets/working_memory.pngOther84.2 KB —
code_public/HybridAgent/examples/questions.jsonlOther831 B —
code_public/HybridAgent/hybrid_agent/__pycache__/__init__.cpython-311.pycOther1.6 KB —
code_public/HybridAgent/hybrid_agent/__pycache__/answer.cpython-311.pycOther3.6 KB —
code_public/HybridAgent/hybrid_agent/__pycache__/constants.cpython-311.pycOther1.8 KB —
code_public/HybridAgent/hybrid_agent/__pycache__/engine.cpython-311.pycOther36.1 KB —
code_public/HybridAgent/hybrid_agent/__pycache__/hybridlink.cpython-311.pycOther2.3 KB —
code_public/HybridAgent/hybrid_agent/__pycache__/model.cpython-311.pycOther10.2 KB —
code_public/HybridAgent/hybrid_agent/__pycache__/prompts.cpython-311.pycOther2.9 KB —
code_public/HybridAgent/hybrid_agent/__pycache__/readout.cpython-311.pycOther5.9 KB —
code_public/HybridAgent/hybrid_agent/__pycache__/sampling.cpython-311.pycOther6.7 KB —
code_public/HybridAgent/hybrid_agent/tools/__pycache__/__init__.cpython-311.pycOther757 B —
code_public/HybridAgent/hybrid_agent/tools/__pycache__/base.cpython-311.pycOther1.4 KB —
code_public/HybridAgent/hybrid_agent/tools/__pycache__/executor.cpython-311.pycOther7.3 KB —
code_public/HybridAgent/hybrid_agent/tools/__pycache__/python_tool.cpython-311.pycOther22.1 KB —
code_public/HybridAgent/hybrid_agent/tools/__pycache__/search_cache.cpython-311.pycOther9.9 KB —
code_public/HybridAgent/hybrid_agent/tools/__pycache__/search_tool.cpython-311.pycOther5.2 KB —
code_public/HybridAgent/hybrid_rl/__pycache__/__init__.cpython-311.pycOther366 B —
code_public/HybridAgent/hybrid_rl/__pycache__/data.cpython-311.pycOther5.8 KB —
code_public/HybridAgent/hybrid_sft/__pycache__/__init__.cpython-311.pycOther560 B —
code_public/HybridAgent/hybrid_sft/__pycache__/data.cpython-311.pycOther13.8 KB —
code_public/HybridAgent/hybrid_sft/__pycache__/model.cpython-311.pycOther9.3 KB —
code_public/HybridAgent/hybrid_sft/__pycache__/train.cpython-311.pycOther16.9 KB —
code_public/HybridAgent/pyproject.tomlOther839 B —
code_public/HybridAgent/requirements.txtOther447 B —
code_public/HybridAgent/scripts/run_batch_inference.shOther1.1 KB —
code_public/HybridAgent/scripts/run_hybrid_rl.shOther1.4 KB —
code_public/HybridAgent/scripts/run_hybrid_sft.shOther1.9 KB —
code_public/HybridAgent_Release.bundleOther424.6 KB 869e95c755ba
code_public/_hf_release/HybridAgent-14B-Agentic/chat_template.jinjaOther4.1 KB —
code_public/_hf_release/HybridAgent-8B-Agentic/chat_template.jinjaOther4.1 KB —
code_public/_hf_release/HybridAgent-HybridRL/math.parquetOther1.8 MB ea5172f63da0
code_public/_hf_release/HybridAgent-HybridRL/search.parquetOther114.9 KB 2134bb8413d2
code_public/_smoke/caches/torch_ext/cpu_adam/build.ninjaOther2.5 KB —
code_public/_smoke/caches/torch_ext/cpu_adam/cpu_adam.oOther15.6 MB f1103c808d93
code_public/_smoke/caches/torch_ext/cpu_adam/cpu_adam.soOther15.0 MB 078efb425c79
code_public/_smoke/caches/torch_ext/cpu_adam/cpu_adam_impl.oOther16.9 MB f3e03f01b893
code_public/_smoke/caches/triton/Fp16Matmul_2d_kernel.pickleOther5 B 926248e52d1f
code_public/_smoke/caches/triton/Fp16Matmul_2d_kernel.pickle.lockOther —
code_public/_smoke/caches/triton/Fp16Matmul_4d_kernel.pickleOther5 B 926248e52d1f
code_public/_smoke/caches/triton/Fp16Matmul_4d_kernel.pickle.lockOther —
code_public/_smoke/curate/c2_14b_s1.htmlOther373.1 KB —
code_public/_smoke/curate/c2_14b_s1.jsonlOther9.8 KB —
code_public/_smoke/curate/c2_14b_s1.logOther5.4 KB —
code_public/_smoke/curate/c2_14b_s2.htmlOther349.4 KB —
code_public/_smoke/curate/c2_14b_s2.jsonlOther9.8 KB —
code_public/_smoke/curate/c2_14b_s2.logOther5.4 KB —
code_public/_smoke/curate/c2_14b_s3.htmlOther395.6 KB —
code_public/_smoke/curate/c2_14b_s3.jsonlOther10.8 KB —
code_public/_smoke/curate/c2_14b_s3.logOther6.0 KB —
code_public/_smoke/curate/c2_14b_s4.htmlOther363.8 KB —
code_public/_smoke/curate/c2_14b_s4.jsonlOther10.3 KB —
code_public/_smoke/curate/c2_14b_s4.logOther5.4 KB —
code_public/_smoke/curate/c2_8b_s1.htmlOther410.3 KB —
code_public/_smoke/curate/c2_8b_s1.jsonlOther10.3 KB —
code_public/_smoke/curate/c2_8b_s1.logOther8.2 KB —
code_public/_smoke/curate/c2_8b_s2.htmlOther326.1 KB —
code_public/_smoke/curate/c2_8b_s2.jsonlOther8.7 KB —
code_public/_smoke/curate/c2_8b_s2.logOther7.1 KB —
code_public/_smoke/curate/c2_8b_s3.htmlOther440.3 KB —
code_public/_smoke/curate/c2_8b_s3.jsonlOther11.2 KB —
code_public/_smoke/curate/c2_8b_s3.logOther8.8 KB —
code_public/_smoke/curate/c2_8b_s4.htmlOther423.1 KB —
code_public/_smoke/curate/c2_8b_s4.jsonlOther11.4 KB —
code_public/_smoke/curate/c2_8b_s4.logOther8.2 KB —
code_public/_smoke/curate/final14b.htmlOther886.0 KB —
code_public/_smoke/curate/final14b.jsonlOther23.9 KB —
code_public/_smoke/curate/final14b.logOther12.8 KB —
code_public/_smoke/curate/final8b.htmlOther998.8 KB —
code_public/_smoke/curate/final8b.jsonlOther25.5 KB —
code_public/_smoke/curate/final8b.logOther13.6 KB —
code_public/_smoke/curate/rl14b_s1.htmlOther384.8 KB —
code_public/_smoke/curate/rl14b_s1.jsonlOther16.0 KB —
code_public/_smoke/curate/rl14b_s1.logOther10.1 KB —
code_public/_smoke/curate/rl14b_s2.htmlOther419.8 KB —
code_public/_smoke/curate/rl14b_s2.jsonlOther17.3 KB —
code_public/_smoke/curate/rl14b_s2.logOther11.0 KB —
code_public/_smoke/curate/rl14b_s3.htmlOther338.7 KB —
code_public/_smoke/curate/rl14b_s3.jsonlOther15.2 KB —
code_public/_smoke/curate/rl14b_s3.logOther9.6 KB —
code_public/_smoke/curate/rl8b_s1.htmlOther376.2 KB —
code_public/_smoke/curate/rl8b_s1.jsonlOther15.5 KB —
code_public/_smoke/curate/rl8b_s1.logOther9.9 KB —
code_public/_smoke/curate/rl8b_s2.htmlOther1.3 MB —
code_public/_smoke/curate/rl8b_s2.jsonlOther45.3 KB —
code_public/_smoke/curate/rl8b_s2.logOther29.6 KB —
code_public/_smoke/curate/rl8b_s3.htmlOther493.1 KB —
code_public/_smoke/curate/rl8b_s3.jsonlOther19.4 KB —
code_public/_smoke/curate/rl8b_s3.logOther12.2 KB —
code_public/_smoke/curate/sft8b_try.htmlOther40.9 KB —
code_public/_smoke/curate/sft8b_try.jsonlOther1.7 KB —
code_public/_smoke/curate/sft8b_try.logOther936 B —
code_public/_smoke/data/candidates.jsonlOther2.9 KB —
code_public/_smoke/data/candidates2.jsonlOther2.8 KB —
code_public/_smoke/data/hybrid_sft_train.jsonlOther1.4 MB —
code_public/_smoke/data/math_24.parquetOther21.4 KB 0d5c2a118e4e
code_public/_smoke/data/search_24.parquetOther11.1 KB a98b875330de
code_public/_smoke/hf_cache/hub/.locks/datasets--JasonChenn--HybridAgent-HybridSFT-v1/e1ae62d6ded12d9685e5e174165ced25a204f3784eeb97b91a43c993eaae344f.lockOther —
code_public/_smoke/hf_cache/hub/.locks/models--Elphan--tmp-all/0ccbc2cc093205fed07e62911ebcaf979b70d71e.lockOther —
code_public/_smoke/hf_cache/hub/.locks/models--Elphan--tmp-all/2de074d380f4d7f82812245b8d3fefb075936366136f60d03c57dcc75f4d2c1a.lockOther —
code_public/_smoke/hf_cache/hub/.locks/models--Elphan--tmp-all/478cc3a0855ef3a169bee6768c6fa8478477e440ef9364854a623a65d723d5e5.lockOther —
code_public/_smoke/hf_cache/hub/.locks/models--Elphan--tmp-all/635118c9790755a4e9baff6d9025790edd2b73e8cfe6466504101e56dd994844.lockOther —
code_public/_smoke/hf_cache/hub/.locks/models--Elphan--tmp-all/699ff8df401fe4788525e9c1f9b86a99eadd6230.lockOther —
code_public/_smoke/hf_cache/hub/.locks/models--Elphan--tmp-all/73b99ef0f0801583f8ff9a871017ab32a02b0971.lockOther —
code_public/_smoke/hf_cache/hub/.locks/models--Elphan--tmp-all/9fb820555ea0e85faf5b05246e38cf204ef9e3a7.lockOther —
code_public/_smoke/hf_cache/hub/.locks/models--Elphan--tmp-all/c140cb5efaaa47603196ace4c4254a46cfb1065c.lockOther —
code_public/_smoke/hf_cache/hub/.locks/models--Elphan--tmp-all/d34ef00de469065ba74970d7cbf1e5c1a55049a5.lockOther —
code_public/_smoke/hf_cache/hub/.locks/models--Elphan--tmp-all/e3d0e3a96786f3ad1e667f478fc7d32ef83ca61bd506a3e11b912c88508296aa.lockOther —
code_public/_smoke/hf_cache/hub/.locks/models--Elphan--tmp-all/e5e91f8c61e68be9bd858d24816722eab110e3d1a9febed64481d7ed8c7ceca5.lockOther —
code_public/_smoke/hf_cache/hub/.locks/models--Elphan--tmp-all/f6546d3a3c8e8c2c583ffd87f3b028e6adb02d32.lockOther —

License and Download

License
Not stated by the source
Access
Open weights, no gate
Download size
1.9 TB
Download from Shirley

Released by Shirley through its official repository on Hugging Face.

Memory Requirements

PrecisionWeights in memory
As published1.9 TB

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