laion / a3-rl-DCAgent_exp_rpt_e2egit-large_global_step_15

huggingface.co
Total runs: 140
24-hour runs: 1
7-day runs: 1
30-day runs: 134
Model's Last Updated: September 05 2026
text-generation

Introduction of a3-rl-DCAgent_exp_rpt_e2egit-large_global_step_15

Model Details of a3-rl-DCAgent_exp_rpt_e2egit-large_global_step_15

a3-rl-DCAgent_exp_rpt_e2egit-large — global_step_15

SkyRL terminal-bench RL run. Checkpoint global_step_15 was selected by EMA(reward/avg_raw_reward, 5-step) across all 80 trained steps.

  • Base model: laion/GLM-4_7-swesmith-sandboxes-with_tests-oracle_verified_120s-maxeps-131k-fixthink (Qwen3-8B SFT)
  • Task dataset: /e/scratch/jureap59/feuer1/tasks/exp_rpt_e2egit-large (DCAgent/exp_rpt_e2egit-large)
  • Algorithm: RLOO-n, eps_clip_low=0.2, eps_clip_high=0.05, kl=0, lr=8e-6
  • Trainer: SkyRL FSDP2, 14 nodes \u00d7 4 GPU/node, train_batch=64, 48 vLLM engines
  • Total steps trained: 80 (job CANCELLED 2026-05-28 03:37:31 UTC after collapse beyond step 65)
  • EMA selection: step=15 ema=0.8639 reward=0.8418
Training Traces

Training-time Daytona/Harbor rollouts for this run are uploaded as a companion dataset: penfever/a3-rl-DCAgent_exp_rpt_e2egit-large

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.

Training Logs

training_logs/ contains metrics.csv , vllm_metrics.csv , trial_stats.csv , report.md , and reward_plot.png from parse_skyrl_metrics.py , plus the raw trainer_log.jsonl and *.out files for archival (Jupiter has no W&B network access).

RL Config

See rl_config.json for the full Hydra overrides used to launch the run.

Runs of laion a3-rl-DCAgent_exp_rpt_e2egit-large_global_step_15 on huggingface.co

140
Total runs
1
24-hour runs
0
3-day runs
1
7-day runs
134
30-day runs

More Information About a3-rl-DCAgent_exp_rpt_e2egit-large_global_step_15 huggingface.co Model

More a3-rl-DCAgent_exp_rpt_e2egit-large_global_step_15 license Visit here:

https://choosealicense.com/licenses/apache-2.0

a3-rl-DCAgent_exp_rpt_e2egit-large_global_step_15 huggingface.co

a3-rl-DCAgent_exp_rpt_e2egit-large_global_step_15 huggingface.co is an AI model on huggingface.co that provides a3-rl-DCAgent_exp_rpt_e2egit-large_global_step_15's model effect (), which can be used instantly with this laion a3-rl-DCAgent_exp_rpt_e2egit-large_global_step_15 model. huggingface.co supports a free trial of the a3-rl-DCAgent_exp_rpt_e2egit-large_global_step_15 model, and also provides paid use of the a3-rl-DCAgent_exp_rpt_e2egit-large_global_step_15. Support call a3-rl-DCAgent_exp_rpt_e2egit-large_global_step_15 model through api, including Node.js, Python, http.

a3-rl-DCAgent_exp_rpt_e2egit-large_global_step_15 huggingface.co Url

https://huggingface.co/laion/a3-rl-DCAgent_exp_rpt_e2egit-large_global_step_15

laion a3-rl-DCAgent_exp_rpt_e2egit-large_global_step_15 online free

a3-rl-DCAgent_exp_rpt_e2egit-large_global_step_15 huggingface.co is an online trial and call api platform, which integrates a3-rl-DCAgent_exp_rpt_e2egit-large_global_step_15's modeling effects, including api services, and provides a free online trial of a3-rl-DCAgent_exp_rpt_e2egit-large_global_step_15, you can try a3-rl-DCAgent_exp_rpt_e2egit-large_global_step_15 online for free by clicking the link below.

laion a3-rl-DCAgent_exp_rpt_e2egit-large_global_step_15 online free url in huggingface.co:

https://huggingface.co/laion/a3-rl-DCAgent_exp_rpt_e2egit-large_global_step_15

a3-rl-DCAgent_exp_rpt_e2egit-large_global_step_15 install

a3-rl-DCAgent_exp_rpt_e2egit-large_global_step_15 is an open source model from GitHub that offers a free installation service, and any user can find a3-rl-DCAgent_exp_rpt_e2egit-large_global_step_15 on GitHub to install. At the same time, huggingface.co provides the effect of a3-rl-DCAgent_exp_rpt_e2egit-large_global_step_15 install, users can directly use a3-rl-DCAgent_exp_rpt_e2egit-large_global_step_15 installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

a3-rl-DCAgent_exp_rpt_e2egit-large_global_step_15 install url in huggingface.co:

https://huggingface.co/laion/a3-rl-DCAgent_exp_rpt_e2egit-large_global_step_15

Url of a3-rl-DCAgent_exp_rpt_e2egit-large_global_step_15

a3-rl-DCAgent_exp_rpt_e2egit-large_global_step_15 huggingface.co Url

Provider of a3-rl-DCAgent_exp_rpt_e2egit-large_global_step_15 huggingface.co

laion
ORGANIZATIONS

Other API from laion

huggingface.co

Total runs: 5.4K
Run Growth: 4.5K
Growth Rate: 82.12%
Updated:June 20 2025
huggingface.co

Total runs: 89
Run Growth: -56
Growth Rate: -62.92%
Updated:May 06 2026