Fix dates to 2026 and training duration to reflect actual 10h + 12h trial/error

README.md

@@ -53,7 +53,7 @@ In machine learning, **Ground Truth** is the "correct answer" we teach the model
 ```json
 {
   "merchant": "Starbucks Coffee",
-  "date": "2024-03-15",
+  "date": "2026-03-15",
   "subtotal": "$12.50",
   "tax": "$1.13",
   "total": "$13.63",
@@ -215,7 +215,7 @@ The model converged around **Epoch 9**. Training was stopped early because:
 | Peak learning rate | 8.0e-5 |
 | Training precision | bf16 |
 | GPU | NVIDIA L4 (24 GB VRAM) |
-| Training duration | ~4 hours |
+| Training duration | ~10 hours actual (+ ~12 hours trial/error) |
 | Early stopping epoch | 9 / 20 |
 
 ### Sample Visual Results
@@ -401,10 +401,10 @@ JSON Text Tokens
 If you use this model in research, please cite:
 
 ```bibtex
-@misc{receipt_donut_2024,
+@misc{receipt_donut_2026,
   title={Receipt Donut: Fine-tuned Document Understanding for Receipt Extraction},
   author={Awarebeyond},
-  year={2024},
+  year={2026},
   howpublished={\url{https://huggingface.co/Awarebeyond/receipt-donut}}
 }
 ```