Skip to page content
SAVRN
Search Plan a project

Dataset

grpo-qwen3-1.7b-nemotron-leetcode-clean-3.2k-bs32-n8-verl091-epoch2-146102-rollouts

by Jiahao Zhang hi-todayis-jh/grpo-qwen3-1.7b-nemotron-leetcode-clean-3.2k-bs32-n8-verl091-epoch2-146102-rollouts

grpoQwen3-1.7BNemotron-LeetCode-clean-3.2kbs32n8seqs1632kepoch2verl091 One verified gzip JSONL shard per training step; 256 responses per shard. LCB binary grading after thinking, without an EOS gate.

Rows—
Configurations—
Size1.2 GB
Licenseapache-2.0
AccessPublicly accessible
Monthly Downloads—

Dataset Card

By Jiahao Zhang, published under apache-2.0, revision d3ca7ece280a.

Coding RL rollouts

grpo_Qwen3-1.7B_Nemotron-LeetCode-clean-3.2k_bs32_n8_seqs16_32k_epoch2_verl091

One verified gzip JSONL shard per training step; 256 responses per shard. LCB binary grading after thinking, without an EOS gate.

Details

Repository
hi-todayis-jh/grpo-qwen3-1.7b-nemotron-leetcode-clean-3.2k-bs32-n8-verl091-epoch2-146102-rollouts
Publisher
Jiahao Zhang
Task category
Not stated by the source
Tags
Not stated by the source
Size category
Not stated by the source
Languages
Not stated by the source
Revision
d3ca7ece280a2f46b93db74eed0fbdf9143ee84c
Last updated
2026-09-30

Files

93 files, 1.2 GB in total.

Data91 files · 1.2 GB
Documentation1 file · 260 B
Repository1 file · 2.5 KB
Every file
FileTypeSizeSHA-256
data/step_000101.jsonl.gzData3.2 MB1080e86a43de
data/step_000102.jsonl.gzData3.3 MB76351d9faf2f
data/step_000103.jsonl.gzData3.0 MBa99035491676
data/step_000104.jsonl.gzData122.7 MB32390db02066
data/step_000105.jsonl.gzData3.1 MB2cdd8a8c57d7
data/step_000106.jsonl.gzData12.2 MB91b4a8003b8b
data/step_000107.jsonl.gzData2.9 MB383db8e72c20
data/step_000108.jsonl.gzData3.6 MB25de3becddbb
data/step_000109.jsonl.gzData2.9 MB755c23ca9002
data/step_000110.jsonl.gzData3.5 MB4dae92454f2e
data/step_000111.jsonl.gzData3.2 MB12a0bebb8c33
data/step_000112.jsonl.gzData3.4 MB4bd0fd37f9cd
data/step_000113.jsonl.gzData2.6 MBf73e0a2fa6e3
data/step_000114.jsonl.gzData3.0 MB2a5b4661ecc3
data/step_000115.jsonl.gzData3.3 MB3ea223c585bc
data/step_000116.jsonl.gzData3.7 MB6113a4b000ae
data/step_000117.jsonl.gzData80.8 MBec8a2ff8edfd
data/step_000118.jsonl.gzData3.6 MBbf154cb6c0a9
data/step_000119.jsonl.gzData3.2 MBdfc38f176ed3
data/step_000120.jsonl.gzData3.0 MBfcbc4258bde4
data/step_000121.jsonl.gzData39.7 MBece007eaf803
data/step_000122.jsonl.gzData3.0 MB788caf0fd108
data/step_000123.jsonl.gzData3.1 MB4e27471481ce
data/step_000124.jsonl.gzData3.3 MB04b9778735e5
data/step_000125.jsonl.gzData3.2 MB93312bc754e6
data/step_000126.jsonl.gzData3.1 MB55a3dd635217
data/step_000127.jsonl.gzData3.0 MB3c05539e4b13
data/step_000128.jsonl.gzData83.0 MB8cc523dad8e7
data/step_000129.jsonl.gzData3.1 MB55a34a2f5a24
data/step_000130.jsonl.gzData3.2 MB37cb25d66e6e
data/step_000131.jsonl.gzData3.4 MB147601a209d4
data/step_000132.jsonl.gzData3.0 MBec357741df65
data/step_000133.jsonl.gzData2.8 MBc810310cf1a6
data/step_000134.jsonl.gzData3.1 MB366a9664f639
data/step_000135.jsonl.gzData3.0 MB69bca1166a5c
data/step_000136.jsonl.gzData3.0 MBbae52abdd6c7
data/step_000137.jsonl.gzData19.1 MB1c9a623b2867
data/step_000138.jsonl.gzData2.9 MB4d4411df5f47
data/step_000139.jsonl.gzData3.5 MB8ff062f0422b
data/step_000140.jsonl.gzData3.2 MBc892a2bce673
data/step_000141.jsonl.gzData18.5 MBae1c143647a8
data/step_000142.jsonl.gzData2.7 MBeae0c0367336
data/step_000143.jsonl.gzData3.2 MB53fcd6f4cce2
data/step_000144.jsonl.gzData3.2 MB227708648044
data/step_000145.jsonl.gzData2.5 MB4a9217fea69e
data/step_000146.jsonl.gzData4.0 MBbab65c8bc402
data/step_000147.jsonl.gzData3.2 MBf10236c6febe
data/step_000148.jsonl.gzData2.9 MBc63809c5a7fa
data/step_000149.jsonl.gzData14.0 MB356b73afdc7d
data/step_000150.jsonl.gzData3.4 MB95b690dc8834
data/step_000151.jsonl.gzData10.9 MBea61b43ffe4c
data/step_000152.jsonl.gzData3.4 MBd0966a0cf893
data/step_000153.jsonl.gzData3.1 MB7b26ffa921d4
data/step_000154.jsonl.gzData3.5 MBc05201bbcf5a
data/step_000155.jsonl.gzData18.2 MBb03974d3aacf
data/step_000156.jsonl.gzData3.1 MB2494f03cda16
data/step_000157.jsonl.gzData3.1 MBa0ac02e90d7f
data/step_000158.jsonl.gzData415.9 MB953d4f171a58
data/step_000159.jsonl.gzData3.0 MB1918272b86df
data/step_000160.jsonl.gzData3.6 MBa1d94fc450f5
data/step_000161.jsonl.gzData3.1 MB26cbad33c0da
data/step_000162.jsonl.gzData3.5 MB6a4dce9ee7b7
data/step_000163.jsonl.gzData3.3 MB885fffe525c4
data/step_000164.jsonl.gzData2.9 MBee20ee6a1554
data/step_000165.jsonl.gzData3.2 MB4196006dea0c
data/step_000166.jsonl.gzData3.8 MB30ee625eef1e
data/step_000167.jsonl.gzData3.5 MB9d844c836dce
data/step_000168.jsonl.gzData3.2 MBec3f302471e2
data/step_000169.jsonl.gzData3.4 MBa33a82d2a02a
data/step_000170.jsonl.gzData3.1 MBd1cc51479b69
data/step_000171.jsonl.gzData24.1 MB4526d43bd266
data/step_000172.jsonl.gzData3.2 MB58b39e4481a5
data/step_000173.jsonl.gzData3.2 MB926e77ebc367
data/step_000174.jsonl.gzData3.4 MB10c13947c230
data/step_000175.jsonl.gzData3.2 MB19dcba47fcbd
data/step_000176.jsonl.gzData4.1 MBd5b85e89f683
data/step_000177.jsonl.gzData3.2 MB16756b93aa79
data/step_000178.jsonl.gzData3.9 MBf09279f04a4f
data/step_000179.jsonl.gzData3.7 MB1f909eafaa09
data/step_000180.jsonl.gzData23.0 MB0a5fd1d00d78
data/step_000181.jsonl.gzData12.4 MBdd37d38d6e32
data/step_000182.jsonl.gzData9.7 MB06c2e7bf9e29
data/step_000183.jsonl.gzData3.4 MB7fff4e7d0f9d
data/step_000184.jsonl.gzData3.1 MB19191514ab03
data/step_000185.jsonl.gzData3.2 MB42faf916b947
data/step_000186.jsonl.gzData14.6 MBfca6bd92b52b
data/step_000187.jsonl.gzData3.7 MB543e0112ac72
data/step_000188.jsonl.gzData12.9 MB1ab5d0a7aa9d
data/step_000189.jsonl.gzData3.4 MB49fc768277ff
data/step_000190.jsonl.gzData3.0 MB7a8dc4528cf0
data/step_000191.jsonl.gzData3.4 MBa1f30e38d171
README.mdDocumentation260 B—
.gitattributesRepository2.5 KB—

License and Download

License
apache-2.0
Access
No access gate
Download from Jiahao Zhang

Released by Jiahao Zhang through its official repository on Hugging Face. Read the license.