Update README.md

README.md

@@ -9,23 +9,89 @@ This is a German to English translation model, fine-tuned over multiple stages s
 3. **Stage 2 Dataset**: Filtered `wmt16` with better train/val split
 4. **Stage 3 Dataset**: `iwslt2017` (clean conversational corpus)
 
-### 📊 Final Evaluation
+---
+license: apache-2.0
+tags:
+- translation
+- german
+- english
+- seq2seq
+- transformers
+- evaluation
+datasets:
+- iwslt2017
+language:
+- de
+- en
+metrics:
+- sacrebleu
+- rouge
+- bertscore
+---
 
-Evaluated on the **iwslt2017** test set:
+# 🇩🇪➡️🇬🇧 de-en-translator-3
 
-- 🔵 **BLEU Score**: 39.23
-- 🟢 **ROUGE-L**: 0.67
-- 🟣 **BERTScore (F1)**: 0.9535
+A transformer-based German → English translation model fine-tuned on the **IWSLT2017** dataset using Hugging Face's `Seq2SeqTrainer`.
 
-### 📦 Usage
+---
+
+## 🚀 Model Overview
+
+- ✅ Architecture: Seq2Seq (e.g., mBART / BART-style)
+- 🔤 Direction: German → English
+- 🧠 Trained using Hugging Face Transformers
+- 🎯 Optimized with early stopping and BLEU-based evaluation
+- 📦 Available on Hugging Face Hub for direct loading
+
+---
+
+## 📊 Evaluation Results
+
+Tested on the **IWSLT2017 `test` split**:
+
+| Metric       | Score     |
+|--------------|-----------|
+| 🔵 BLEU       | **39.23** |
+| 🟢 ROUGE-L    | **0.67**  |
+| 🟣 BERTScore (F1) | **0.9535** |
+
+---
+
+## ⚙️ Training Hyperparameters
+
+| Parameter                     | Value                           |
+|-------------------------------|----------------------------------|
+| **Model Checkpoint**          | `Aparna852/de-en-translator`     |
+| **Dataset**                   | `iwslt2017` (German-English)     |
+| **Epochs**                    | `3`                              |
+| **Train Batch Size**          | `4`                              |
+| **Eval Batch Size**           | `4`                              |
+| **Gradient Accumulation**     | `8`                              |
+| **Learning Rate**             | `2e-5`                           |
+| **Weight Decay**              | `0.01`                           |
+| **Warmup Steps**              | `500`                            |
+| **Max Sequence Length**       | `128`                            |
+| **FP16 (Mixed Precision)**    | `True` *(if CUDA available)*     |
+| **Evaluation Strategy**       | `epoch`                          |
+| **Save Strategy**             | `epoch`                          |
+| **Logging Strategy**          | `steps` (every 10 steps)         |
+| **Scheduler**                 | `linear`                         |
+| **Metric for Best Model**     | `eval_loss`                     |
+| **Early Stopping**            | `patience=2`                     |
+| **Load Best Model at End**    | `True`                           |
+| **Trainer API**               | `Seq2SeqTrainer` from 🤗 Transformers |
+
+---
+
+## 📥 Usage Example (Python)
 
 ```python
 from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
 
-tokenizer = AutoTokenizer.from_pretrained("Aparna852/final-de-en-iwslt-model")
-model = AutoModelForSeq2SeqLM.from_pretrained("Aparna852/final-de-en-iwslt-model")
+model = AutoModelForSeq2SeqLM.from_pretrained("Aparna852/de-en-translator-3")
+tokenizer = AutoTokenizer.from_pretrained("Aparna852/de-en-translator-3")
 
-text = "Guten Morgen!"
-inputs = tokenizer(text, return_tensors="pt")
-outputs = model.generate(**inputs)
-print(tokenizer.decode(outputs[0], skip_special_tokens=True))
+input_text = "Guten Morgen, wie geht es dir?"
+inputs = tokenizer(input_text, return_tensors="pt")
+output = model.generate(**inputs, max_length=128)
+print(tokenizer.decode(output[0], skip_special_tokens=True))