docs(readme): link raw training logs + training scripts per organizer ask

Hackathon organizer reminded teams to share env, training logs, and
training scripts. Env Space + scripts already linked. Added two rows:

- "Raw training logs" -> Pratham-math/fathom-1.5b-grpo/logs/ which now
contains the SFT warmstart log, the v1 flat-curve run log, and the
v2 successful-run log (all UTF-8, grep-friendly).
- "Training scripts" -> direct links to train/grpo.py and
scripts/job_train.sh in the HF code repo.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

README.md

@@ -20,6 +20,8 @@ Submitted to the Meta × PyTorch × Hugging Face OpenEnv Hackathon Grand Finale
 | **Colab reproducer notebook** | [`notebooks/fathom_train.ipynb`](https://huggingface.co/Pratham-math/fathom-code/blob/main/notebooks/fathom_train.ipynb) (open via HF code repo) |
 | **Mini-blog** | <https://huggingface.co/spaces/Pratham-math/fathom-blog> |
 | **W&B training run (v2 — successful learning)** | <https://wandb.ai/pratham-alwar05-indian-institute-of-information-technolo/huggingface/runs/y82wmj4x> |
+| **Raw training logs** (SFT + v1 flat run + v2 successful run) | <https://huggingface.co/Pratham-math/fathom-1.5b-grpo/tree/main/logs> |
+| **Training scripts** | [`train/grpo.py`](https://huggingface.co/Pratham-math/fathom-code/blob/main/train/grpo.py), [`scripts/job_train.sh`](https://huggingface.co/Pratham-math/fathom-code/blob/main/scripts/job_train.sh) |
 
 > The HF Space `/healthz` endpoint cold-starts the first time it's hit; if you get a 503, refresh once and it returns 200.