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:
yashash045
/
schemashift
like
0
Sleeping
App
Files
Files
Community
Fetching metadata from the HF Docker repository...
main
schemashift
/
training
34.3 kB
Ctrl+K
Ctrl+K
2 contributors
History:
8 commits
yashash04
Phase 13 Stage 1 v2: fix termination signal - reward penalties for non-termination, reduced max_tokens, stop_strings
5a432bb
about 1 month ago
STAGE_1_KAGGLE_RUNBOOK.md
Safe
11.6 kB
Phase 13 Stage 1: pivot to winner's pattern - TRL 0.29.0 + fast_inference=False + DAPO loss
about 1 month ago
__init__.py
Safe
0 Bytes
first commit
about 1 month ago
grpo_kaggle.ipynb
Safe
17.8 kB
Phase 13 Stage 1 v2: fix termination signal - reward penalties for non-termination, reduced max_tokens, stop_strings
about 1 month ago
grpo_smoke.py
Safe
4.74 kB
Phase 8: Env client + GRPO training skeleton (Kaggle notebook)
about 1 month ago
train.py
Safe
111 Bytes
first commit
about 1 month ago
