Update README.md

README.md

@@ -3,62 +3,112 @@ library_name: transformers
 license: cc-by-nc-sa-4.0
 base_model: microsoft/layoutlmv3-base
 tags:
-- generated_from_trainer
+- layoutlmv3
+- document-ai
+- invoices
+- token-classification
+- pytorch
 metrics:
 - accuracy
 - precision
 - recall
 - f1
 model-index:
-- name: layoutlmv3-finetuned
-  results: []
+- name: layoutlmv3-finetuned-invoices
+  results:
+  - task:
+      type: token-classification
+      name: Named Entity Recognition (Invoices)
+    dataset:
+      name: Custom Invoice Dataset
+      type: invoices
+      split: test
+    metrics:
+      - name: Precision
+        type: precision
+        value: 0.9037
+      - name: Recall
+        type: recall
+        value: 0.8871
+      - name: F1
+        type: f1
+        value: 0.8954
 ---
 
-<!-- This model card has been generated automatically according to the information the Trainer had access to. You
-should probably proofread and complete it, then remove this comment. -->
+# layoutlmv3-finetuned-invoices
 
-# layoutlmv3-finetuned
+This model is a fine-tuned version of [microsoft/layoutlmv3-base](https://huggingface.co/microsoft/layoutlmv3-base) on a **custom invoice dataset** for document understanding tasks.  
+It was trained using the Hugging Face `Trainer` API with early stopping and mixed precision.
 
-This model is a fine-tuned version of [microsoft/layoutlmv3-base](https://huggingface.co/microsoft/layoutlmv3-base) on the None dataset.
-It achieves the following results on the evaluation set:
-- Loss: 0.1696
-- Accuracy: 0.9559
-- Precision: 0.9572
-- Recall: 0.9559
-- F1: 0.9562
+## Results
+
+The model achieves the following results on the held-out validation set after 10 epochs:
+
+| Epoch | Train Loss | Val Loss | Precision | Recall | F1     |
+|-------|------------|----------|-----------|--------|--------|
+| 1     | 0.8329     | 0.7094   | 0.7184    | 0.6524 | 0.6838 |
+| 5     | 0.3815     | 0.3104   | 0.8625    | 0.8559 | 0.8592 |
+| 8     | 0.2988     | 0.2350   | 0.8999    | 0.8803 | 0.8900 |
+| 10    | 0.2499     | 0.2254   | **0.9037**| 0.8872 | **0.8954** |
+
+---
 
 ## Model description
 
-More information needed
+- **Architecture**: LayoutLMv3  
+- **Base model**: microsoft/layoutlmv3-base  
+- **Task**: Token classification for invoice understanding (e.g., extracting key fields).  
+- **Input**: Scanned invoices (images + text tokens + bounding boxes).  
+- **Output**: Predicted entity labels (e.g., Invoice Number, Date, Vendor, Total).  
+
+---
 
 ## Intended uses & limitations
 
-More information needed
+- **Use cases**:  
+  - Automatic information extraction from invoices, receipts, and financial documents.  
+  - Document AI pipelines for expense management and automation.  
 
-## Training and evaluation data
+- **Limitations**:  
+  - Fine-tuned only on a limited invoice dataset.  
+  - May not generalize well to other document types (contracts, ID cards, etc.).  
+  - Sensitive to OCR quality — better input text = better results.  
 
-More information needed
+---
+
+## Training details
+
+### Hyperparameters
+- Learning rate: `3e-5`  
+- Train batch size: `4`  
+- Eval batch size: `4`  
+- Epochs: `10` (with early stopping)  
+- Optimizer: AdamW  
+- Weight decay: `0.01`  
+- Mixed precision (fp16): ✅  
+- Workers: `2`  
 
-## Training procedure
+### Framework versions
+- Transformers 4.56.0  
+- PyTorch 2.8.0+cu126  
+- Datasets 4.0.0  
+- Tokenizers 0.22.0  
 
-### Training hyperparameters
+---
 
-The following hyperparameters were used during training:
-- learning_rate: 5e-05
-- train_batch_size: 4
-- eval_batch_size: 8
-- seed: 42
-- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
-- lr_scheduler_type: linear
-- num_epochs: 3
+## How to use
 
-### Training results
+```python
+from transformers import AutoModelForTokenClassification, AutoProcessor
 
+repo_id = "your-username/layoutlmv3-finetuned-invoices"
 
+model = AutoModelForTokenClassification.from_pretrained(repo_id)
+processor = AutoProcessor.from_pretrained(repo_id)
 
-### Framework versions
+# Example inference
+from PIL import Image
+image = Image.open("sample_invoice.png")
 
-- Transformers 4.56.0
-- Pytorch 2.8.0+cu126
-- Datasets 4.0.0
-- Tokenizers 0.22.0
+encoding = processor(image, return_tensors="pt")
+outputs = model(**encoding)