Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Buckets new
  • Docs
  • Enterprise
  • Pricing
    • Website
      • Tasks
      • HuggingChat
      • Collections
      • Languages
      • Organizations
    • Community
      • Blog
      • Posts
      • Daily Papers
      • Learn
      • Discord
      • Forum
      • GitHub
    • Solutions
      • Team & Enterprise
      • Hugging Face PRO
      • Enterprise Support
      • Inference Providers
      • Inference Endpoints
      • Storage Buckets

  • Log In
  • Sign Up

Spaces:
ayhm23
/
TrustShield-Arena
Runtime error

App Files Files Community
Fetching metadata from the HF Docker repository...
TrustShield-Arena / training
446 kB
Ctrl+K
Ctrl+K
  • 6 contributors
History: 25 commits
ayhm23
Update train_grpo1.py: set NUM_STEPS=50 and optimize logging steps
43be96e 28 days ago
  • baseline_eval.py
    5.5 kB
    feat: prepare for HF Docker training with Hub integration 28 days ago
  • push_to_hf.py
    3.09 kB
    fix: harden HF cache paths and add Space push helper 28 days ago
  • test_data.json
    14 kB
    feat: prepare for HF Docker training with Hub integration 28 days ago
  • test_generalization.py
    5.11 kB
    feat: implement generalization testing pipeline and report generation for held-out evaluation scenarios 28 days ago
  • train_data.json
    62 kB
    feat: prepare for HF Docker training with Hub integration 28 days ago
  • train_grpo.ipynb
    18.9 kB
    modified ipynb train code 28 days ago
  • train_grpo.py
    16.2 kB
    Fix: 50-step GRPO training with plotting & sentinel 28 days ago
  • train_grpo1.ipynb
    26.9 kB
    Enhance: Update GRPO training process with improved plotting and sentinel integration for 50-step runs 28 days ago
  • train_grpo1.py
    22.1 kB
    Update train_grpo1.py: set NUM_STEPS=50 and optimize logging steps 28 days ago
  • training_curves_phase4.png
    269 kB
    xet
    Enhance: Update GRPO training process with improved plotting and sentinel integration for 50-step runs 28 days ago
  • training_log_phase4.json
    3.51 kB
    Enhance: Update GRPO training process with improved plotting and sentinel integration for 50-step runs 28 days ago