license, base_model, tags, datasets
| license | base_model | tags | datasets | ||||||
|---|---|---|---|---|---|---|---|---|---|
| apache-2.0 | laion/GLM-4_7-swesmith-sandboxes-with_tests-oracle_verified_120s-maxeps-131k-fixthink |
|
|
a3-rl-SankalpKJ_swesmith-oracle-filtered-40-8B
RL-tuned (SkyRL) agentic SWE model. This is the global_step 40 checkpoint, selected as the best checkpoint by EMA reward (EMA reward 0.0877).
- Base model: laion/GLM-4_7-swesmith-sandboxes-with_tests-oracle_verified_120s-maxeps-131k-fixthink (a Qwen3-8B SFT)
- Training dataset: SankalpKJ/swesmith-oracle-filtered
- Architecture: Qwen3-8B
- Training framework: SkyRL (agentic RL, a3 series)
The RL training configuration is included in this repo as rl_config.yaml.
Parsed training metrics and the raw training logs are in training_logs/.
Training Traces
The full agentic rollout traces from this RL run are published as a dataset:
Note
Published to the penfever/ namespace pending a laion/ write-role bump
(may be re-homed to laion/ later).