laion/a3-rl-DCAgent_selfinstruct-naive-sandboxes-2-verified-70-8B
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity
Files
3e52217125c5998e2e7177659dc62fb58bef4acf
a3-rl-DCAgent_selfinstruct-…/README.md
ModelHub XC 3e52217125 初始化项目，由ModelHub XC社区提供模型 
Model: laion/a3-rl-DCAgent_selfinstruct-naive-sandboxes-2-verified-70-8B
Source: Original Platform
2026-08-07 10:27:18 +08:00

923 B
Raw Blame History

a3-rl-DCAgent_selfinstruct-naive-sandboxes-2-verified-70-8B

Training Traces

Training-time Daytona/Harbor rollouts for this run are uploaded as a companion dataset: penfever/a3-rl-DCAgent_selfinstruct-naive-sandboxes-2-verified

The dataset contains the last episode of each trial (per make_and_upload_trace_dataset --episodes last) — the same rollouts the policy was trained on after rollback / truncation.

Provenance

  • Base (SFT) model: laion/GLM-4_7-swesmith-sandboxes-with_tests-oracle_verified_120s-maxeps-131k-fixthink
  • RL dataset: DCAgent/selfinstruct-naive-sandboxes-2-verified
  • Checkpoint: global_step_70 (EMA-best over steps 1-80, 5-period EMA α=1/3)
  • Training: SkyRL GRPO, 56 GPU / 14 nodes, fan-out K=4; chain 567548→567550→567551 (terminated early at step ~81 by user request)