laion / a3-rl-DCAgent_mix_h4_binary_easy-50-8B

huggingface.co
Total runs: 7
24-hour runs: 0
7-day runs: -1
30-day runs: -56
Model's Last Updated: September 05 2026

Introduction of a3-rl-DCAgent_mix_h4_binary_easy-50-8B

Model Details of a3-rl-DCAgent_mix_h4_binary_easy-50-8B

a3-rl-DCAgent_mix_h4_binary_easy-50-8B

RL (SkyRL) checkpoint trained on the DCAgent/mix_h4_binary_easy task mix, starting from the a3 GLM-SFT base laion/GLM-4_7-swesmith-sandboxes-with_tests-oracle_verified_120s-maxeps-131k-fixthink .

  • Run : a3-rl-DCAgent_mix_h4_binary_easy (Jupiter chain 573271→573276)
  • Training : 2 epochs, completed at global_step 67 ( max_steps=80 was a ceiling; 67 = epoch-data completion, a legit deployable endpoint — not collapse).
  • Checkpoint selected : global_step 50 by trailing-5 EMA (α=1/3) of reward/avg_raw_reward across the full chain.
    • EMA at step 50 = 0.4991 (highest of all aligned eligible checkpoints)
    • raw avg_raw_reward at step 50 = 0.529
    • pass@8 at step 50 = 0.672
  • hf_save_interval=5
Training Traces

Training-time Daytona/Harbor rollouts for this run are uploaded as a companion dataset: penfever/a3-rl-DCAgent_mix_h4_binary_easy

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

See training_logs/ for the parsed metrics ( metrics.csv , report.md , reward_plot.png ) and the raw chain .out logs (Jupiter has no W&B network access).

Runs of laion a3-rl-DCAgent_mix_h4_binary_easy-50-8B on huggingface.co

7
Total runs
0
24-hour runs
0
3-day runs
-1
7-day runs
-56
30-day runs

More Information About a3-rl-DCAgent_mix_h4_binary_easy-50-8B huggingface.co Model

More a3-rl-DCAgent_mix_h4_binary_easy-50-8B license Visit here:

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

a3-rl-DCAgent_mix_h4_binary_easy-50-8B huggingface.co

a3-rl-DCAgent_mix_h4_binary_easy-50-8B huggingface.co is an AI model on huggingface.co that provides a3-rl-DCAgent_mix_h4_binary_easy-50-8B's model effect (), which can be used instantly with this laion a3-rl-DCAgent_mix_h4_binary_easy-50-8B model. huggingface.co supports a free trial of the a3-rl-DCAgent_mix_h4_binary_easy-50-8B model, and also provides paid use of the a3-rl-DCAgent_mix_h4_binary_easy-50-8B. Support call a3-rl-DCAgent_mix_h4_binary_easy-50-8B model through api, including Node.js, Python, http.

a3-rl-DCAgent_mix_h4_binary_easy-50-8B huggingface.co Url

https://huggingface.co/laion/a3-rl-DCAgent_mix_h4_binary_easy-50-8B

laion a3-rl-DCAgent_mix_h4_binary_easy-50-8B online free

a3-rl-DCAgent_mix_h4_binary_easy-50-8B huggingface.co is an online trial and call api platform, which integrates a3-rl-DCAgent_mix_h4_binary_easy-50-8B's modeling effects, including api services, and provides a free online trial of a3-rl-DCAgent_mix_h4_binary_easy-50-8B, you can try a3-rl-DCAgent_mix_h4_binary_easy-50-8B online for free by clicking the link below.

laion a3-rl-DCAgent_mix_h4_binary_easy-50-8B online free url in huggingface.co:

https://huggingface.co/laion/a3-rl-DCAgent_mix_h4_binary_easy-50-8B

a3-rl-DCAgent_mix_h4_binary_easy-50-8B install

a3-rl-DCAgent_mix_h4_binary_easy-50-8B is an open source model from GitHub that offers a free installation service, and any user can find a3-rl-DCAgent_mix_h4_binary_easy-50-8B on GitHub to install. At the same time, huggingface.co provides the effect of a3-rl-DCAgent_mix_h4_binary_easy-50-8B install, users can directly use a3-rl-DCAgent_mix_h4_binary_easy-50-8B installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

a3-rl-DCAgent_mix_h4_binary_easy-50-8B install url in huggingface.co:

https://huggingface.co/laion/a3-rl-DCAgent_mix_h4_binary_easy-50-8B

Url of a3-rl-DCAgent_mix_h4_binary_easy-50-8B

a3-rl-DCAgent_mix_h4_binary_easy-50-8B huggingface.co Url

Provider of a3-rl-DCAgent_mix_h4_binary_easy-50-8B huggingface.co

laion
ORGANIZATIONS

Other API from laion

huggingface.co

Total runs: 7.6M
Run Growth: -307.4K
Growth Rate: -4.02%
Updated:January 12 2026
huggingface.co

Total runs: 5.9K
Run Growth: 4.4K
Growth Rate: 73.62%
Updated:June 20 2025
huggingface.co

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