Update README.md

README.md

@@ -36,42 +36,40 @@ This model is a fine-tuned version of [silma-ai/SILMA-9B-Instruct-v1.0](https://
 - Efficient inference with 4-bit quantization
 - Fine-tuned using PEFT with LoraConfig for parameter-efficient training
 
-Step	|Training Loss	|Validation Loss
-10	2.207200	1.487218
-20	1.021200	0.331835
-30	0.205000	0.138645
-40	0.112900	0.111273
-50	0.113500	0.105615
-60	0.100400	0.104426
-70	0.104500	0.101215
-80	0.099500	0.098990
-90	0.098300	0.098076
-100	0.093900	0.099338
-110	0.100200	0.095021
-120	0.094700	0.093543
-130	0.089800	0.090921
-140	0.087000	0.088527
-150	0.085700	0.085943
-160	0.095600	0.082870
-170	0.079100	0.080233
-180	0.079200	0.077066
-190	0.083400	0.074134
-200	0.087500	0.074748
-210	0.076200	0.069750
-220	0.069400	0.067776
-230	0.075400	0.065210
-240	0.069600	0.063573
-250	0.068100	0.061195
-260	0.067900	0.059264
-270	0.061500	0.057951
-280	0.059900	0.056350
-290	0.056100	0.054536
-300	0.052200	0.052772
-310	0.053400	0.052114
-320	0.049700	0.050167
-330	0.045900	0.048726
-340	0.061800	0.047798
-350	0.047500	0.045877
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 2.1356        | 0.04  | 10   | 1.4071          |
+| 0.8079        | 0.08  | 20   | 0.2825          |
+| 0.1592        | 0.12  | 30   | 0.1427          |
+| 0.1202        | 0.16  | 40   | 0.1121          |
+| 0.1095        | 0.2   | 50   | 0.1071          |
+| 0.1024        | 0.24  | 60   | 0.1036          |
+| 0.0993        | 0.28  | 70   | 0.1002          |
+| 0.091         | 0.32  | 80   | 0.0992          |
+| 0.1096        | 0.36  | 90   | 0.0965          |
+| 0.0943        | 0.4   | 100  | 0.0916          |
+| 0.0882        | 0.44  | 110  | 0.0896          |
+| 0.0853        | 0.48  | 120  | 0.0848          |
+| 0.0767        | 0.52  | 130  | 0.0808          |
+| 0.0778        | 0.56  | 140  | 0.0765          |
+| 0.0698        | 0.6   | 150  | 0.0734          |
+| 0.0784        | 0.64  | 160  | 0.0694          |
+| 0.0648        | 0.68  | 170  | 0.0658          |
+| 0.0797        | 0.72  | 180  | 0.0630          |
+| 0.0591        | 0.76  | 190  | 0.0604          |
+| 0.0557        | 0.8   | 200  | 0.0582          |
+| 0.0567        | 0.84  | 210  | 0.0561          |
+| 0.057         | 0.88  | 220  | 0.0534          |
+| 0.0505        | 0.92  | 230  | 0.0515          |
+| 0.0483        | 0.96  | 240  | 0.0482          |
+| 0.0463        | 1.0   | 250  | 0.0463          |
+
+
+### Training Metrics
+[Training Loss on wandb 🔗](https://wandb.ai/mohnasgbr/huggingface/reports/train-loss-24-09-07-03-41-58---Vmlldzo5MjgxMTY4)
+
 
 ## Usage
 
@@ -104,7 +102,7 @@ qa_pipeline = pipeline(
 )
 
 # Example usage
-question = "كم عدد الكواكب في المجموعة الشمسية؟"
+question = "إذا كان لديك ثلاث سيارات، وبعت واحدة منها، كم سيارة ستبقى لديك؟"
 prompt = f"Question: {question}\nAnswer:"
 response = qa_pipeline(prompt)[0]['generated_text']
 
@@ -116,12 +114,7 @@ print(f"Answer: {response}")
 
 Our model demonstrates strong performance on Arabic QA tasks, particularly for questions requiring numerical answers. Here are some key metrics:
 
-- **Eval Loss**: 0.045
-- **Eval Loss**: 92% on our test set
-- **F1 Score**: 0.89
-- **Average Response Time**: 150ms
-
-(Note: Replace these placeholder metrics with your actual performance data)
+- **Eval Loss**: 0.046
 
 ## Limitations
 
@@ -147,25 +140,10 @@ The model was fine-tuned using the following configuration:
 
 While this model has been trained on a diverse dataset, it may still exhibit biases present in the training data. Users should be aware of potential biases and use the model responsibly.
 
-## Citation
-
-If you use this model in your research, please cite:
-
-```bibtex
-@misc{silma9b_arabic_qa,
-  author = {Mohammed Nasser},
-  title = {SILMA-9B-Instruct Fine-Tuned for Arabic QA},
-  year = {2024},
-  publisher = {GitHub},
-  journal = {GitHub repository},
-  howpublished = {\url{https://huggingface.co/MohammedNasser/silma_9b_instruct_ft}}
-}
-```
-
 ## Contact
 
 For any questions or feedback, please open an issue on the [GitHub repository](https://github.com/your-github-username/silma-9b-arabic-qa) or contact us at your.email@example.com.
 
 ---
 
-Made with ❤️ by [Your Name/Organization]
+Made with ❤️ by [M. N. Gaer/aiNarabic]