Skip to content

v1.0 — Track v1 frozen, two verified records

Choose a tag to compare

@Saivineeth147 Saivineeth147 released this 19 Jul 01:50

First public release of the LoRA Speedrun.

Track v1 (gsm8k-qwen2.5-1.5b-l40s) is frozen — base model, dataset, eval protocol, hardware, constraints, and target are locked (tag `spec-v1-frozen`). Times are comparable from here on.

Verified records so far

# Technique Train time GSM8K
0 Baseline — plain LoRA, no tricks 11m 57s 59.4%
1 + sequence packing + completion-only masking 6m 05s 61.1%

Both were re-run 3× with fresh seeds on identical hardware (Modal L40S, network-blocked sandbox). Full verification reports are in records/verifications/.

The task

Fine-tune Qwen/Qwen2.5-1.5B to ≥57% on GSM8K using only the GSM8K train split, on one L40S. Score = training wall-clock. Lowest wins. ≤30M adapter params, base frozen.

Attempting and re-verifying any record is free (Modal's monthly credits cover full runs).

Beat the record

Current record to beat: 6m 05s. Open lanes with no record yet: 1-epoch schedules, data pruning, QLoRA, torch.compile, custom kernels. See the pinned "open lane" issues and CONTRIBUTING.md.