Hugging Face
Search models, datasets, users...
Ctrl K
Models
Datasets
Spaces
Buckets
Docs
Enterprise
Pricing
Website
Tasks
HuggingChat
Collections
Languages
Organizations
Community
Blog
Posts
Daily Papers
Hardware
Learn
Discord
Forum
GitHub
Solutions
Team & Enterprise
Hugging Face PRO
Enterprise Support
Inference Providers
Inference Endpoints
Storage Buckets
Log In
Sign Up
Spaces:
balloonmann
/
financial_audit_env
Like
2
Sleeping
App
Files
Files
Community
Fetching metadata from the HF Docker repository...
main
financial_audit_env
/
training
26 kB
Ctrl+K
Ctrl+K
3 contributors
History:
10 commits
balloonmann
fix: GRPO training - 5 critical fixes: NUM_GEN 8, LoRA MLP, beta=0.04, LR=5e-6, per-task reward multipliers
0f78f77
verified
3 months ago
__init__.py
Safe
176 Bytes
Round 2 Implementation: Multi-period campaign, regulatory shocks, adversarial grading, and GRPO training infrastructure
7 months ago
evaluator.py
Safe
4.51 kB
Sanitize empty finding descriptions
7 months ago
reward.py
Safe
5.97 kB
Harden reward parsing for truncated JSON
7 months ago
train_grpo.py
15.3 kB
fix: GRPO training - 5 critical fixes: NUM_GEN 8, LoRA MLP, beta=0.04, LR=5e-6, per-task reward multipliers
3 months ago