laion/a3-rl-DCAgent_selfinstruct-naive-sandboxes-2-verified-70-8B
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: laion/a3-rl-DCAgent_selfinstruct-naive-sandboxes-2-verified-70-8B
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-08-07 10:27:18 +08:00
commit 3e52217125
33 changed files with 226712 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

18
README.md Normal file
View File

@@ -0,0 +1,18 @@
# 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](https://huggingface.co/datasets/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)