Dataset
l1-exact-qwen3-1.7b-compression-100-4k-alpha3e-4-bs32-n8-32k-t1-146103-rollouts
by Jiahao Zhang hi-todayis-jh/l1-exact-qwen3-1.7b-compression-100-4k-alpha3e-4-bs32-n8-32k-t1-146103-rollouts
l1exactQwen3-1.7Bcompressionn100to4000alpha3e-4bs32n832k1epoch One verified gzip JSONL shard per training step; 256 responses per shard. L1-Exact: MathVerify correctness after thinking without an EOS gate, plus the original linear target-length reward.
Dataset Card
By Jiahao Zhang, published under apache-2.0, revision cd59551705ca.
RL training rollouts
l1_exact_Qwen3-1.7B_compression_n100to4000_alpha3e-4_bs32_n8_32k_1epoch
One verified gzip JSONL shard per training step; 256 responses per shard. L1-Exact: MathVerify correctness after thinking without an EOS gate, plus the original linear target-length reward. Fixed random targets 100..4000; alpha=0.0003.
Details
- Repository
- hi-todayis-jh/l1-exact-qwen3-1.7b-compression-100-4k-alpha3e-4-bs32-n8-32k-t1-146103-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
- cd59551705caefee27a82dea64f5ac474b2bc012
- Last updated
- 2026-10-05
Files
25 files, 71.0 MB in total.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| data/step_000001.jsonl.gz | Data | 3.1 MB | e6bd9834eaad |
| data/step_000002.jsonl.gz | Data | 3.3 MB | e503abdaa48d |
| data/step_000003.jsonl.gz | Data | 3.6 MB | 2cb4daa6bede |
| data/step_000004.jsonl.gz | Data | 3.2 MB | 010384d888b7 |
| data/step_000005.jsonl.gz | Data | 2.6 MB | 39fb767e1d29 |
| data/step_000006.jsonl.gz | Data | 3.1 MB | 10e0f8cb5640 |
| data/step_000007.jsonl.gz | Data | 2.5 MB | 1daae5147a5b |
| data/step_000008.jsonl.gz | Data | 4.0 MB | 02f4b5dc1b81 |
| data/step_000009.jsonl.gz | Data | 3.3 MB | 996255c9c16a |
| data/step_000010.jsonl.gz | Data | 3.7 MB | abb3a9abb1f0 |
| data/step_000011.jsonl.gz | Data | 2.8 MB | bb429e1c813f |
| data/step_000012.jsonl.gz | Data | 2.4 MB | 34e42e9878bf |
| data/step_000013.jsonl.gz | Data | 3.5 MB | 75399c3ab6a9 |
| data/step_000014.jsonl.gz | Data | 2.7 MB | 1962fb7b354b |
| data/step_000015.jsonl.gz | Data | 3.0 MB | 8c8d6499fcee |
| data/step_000016.jsonl.gz | Data | 2.7 MB | a9fdc23f61c6 |
| data/step_000017.jsonl.gz | Data | 3.0 MB | e270c4b450d5 |
| data/step_000018.jsonl.gz | Data | 3.4 MB | b594d9ae107b |
| data/step_000019.jsonl.gz | Data | 2.8 MB | feaf130394ff |
| data/step_000020.jsonl.gz | Data | 3.0 MB | 5b5c9cc2d6d4 |
| data/step_000021.jsonl.gz | Data | 3.0 MB | 8bf39e48fd5c |
| data/step_000022.jsonl.gz | Data | 3.0 MB | 608437f5e021 |
| data/step_000023.jsonl.gz | Data | 3.5 MB | 66b96e2e887e |
| README.md | Documentation | 361 B | — |
| .gitattributes | Repository | 2.5 KB | — |
License and Download
- License
- apache-2.0
- Access
- No access gate
Released by Jiahao Zhang through its official repository on Hugging Face. Read the license.