Fetching metadata from the HF Docker repository... 
final training
0819987 - 30.9 kB Add SFT GRPO training pipeline
- 5.32 kB Refactor agent architecture, improve heuristics logic, enhance parser robustness, simplify config, and optimize Docker setup for HF deployment
- 2.49 kB Add SFT GRPO training pipeline
- 10.8 kB fix: GRPO crash (unsloth_num_chunks), seq_len truncation, --run_grpo alias, logs/ auto-create, difficulty fallback
- 2.58 kB Refactor agent architecture, improve heuristics logic, enhance parser robustness, simplify config, and optimize Docker setup for HF deployment
- 1.52 kB Refactor agent architecture, improve heuristics logic, enhance parser robustness, simplify config, and optimize Docker setup for HF deployment
- 1.82 kB Refactor agent architecture, improve heuristics logic, enhance parser robustness, simplify config, and optimize Docker setup for HF deployment
- 2.44 kB Refactor agent architecture, improve heuristics logic, enhance parser robustness, simplify config, and optimize Docker setup for HF deployment
- 1 kB Add SFT GRPO training pipeline
- 8.39 kB Add SFT GRPO training pipeline
- 9.17 kB Add SFT GRPO training pipeline
- 1.54 kB Refactor agent architecture, improve heuristics logic, enhance parser robustness, simplify config, and optimize Docker setup for HF deployment
- 3.62 kB Increasing the odds more
- 757 Bytes Increasing the odds more
- 5.16 kB Add SFT GRPO training pipeline
- 37.7 kB Increasing the odds more
- 10.2 kB final training
- 134 kB Upload witness-stand.ipynb
