laion/ablation-pymethods2test-seqmean-arm0-tis-15-8B
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity
Files
main
ablation-pymethods2test-seq…/README.md
ModelHub XC 9f22667c70 初始化项目，由ModelHub XC社区提供模型 
Model: laion/ablation-pymethods2test-seqmean-arm0-tis-15-8B
Source: Original Platform
2026-08-09 05:27:18 +08:00

1.1 KiB
Raw Permalink Blame History

license, base_model, tags
license base_model tags
apache-2.0 laion/GLM-4_7-swesmith-sandboxes-with_tests-oracle_verified_120s-maxeps-131k-fixthink
rl
rloo
terminal-bench
openthoughts-agent

ablation-pymethods2test-seqmean-arm0-tis (step 15)

RLOO length-bias A/B ablation, arm0 = sequence_mean loss reduction WITH TIS (truncated importance sampling). Trained with SkyRL (RLOO-n, FSDP2) on DCAgent/exp_rpt_pymethods2test-large from the Qwen3-8B pre-RL base laion/GLM-4_7-swesmith-...-fixthink.

Checkpoint selected at global_step 15 by trailing-5 EMA (alpha=1/3) of reward/avg_raw_reward over the full training chain (cap step <= 80).

Training Traces

Training-time Daytona/Harbor rollouts for this run are uploaded as a companion dataset: penfever/ablation-pymethods2test-seqmean-arm0-tis

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.