Update README.md

README.md

@@ -15,15 +15,31 @@ tags:
 - code
 ---
 
-# Model Card for ethicalabs/FlowerTune-Qwen2.5-Coder-0.5B-Instruct
+# Model Card for FlowerTune-Qwen2.5-Coder-0.5B-Instruct-PEFT
 
 This PEFT adapter has been trained by using [Flower](https://flower.ai/), a friendly federated AI framework.
 
 The adapter and benchmark results have been submitted to the [FlowerTune LLM Code Leaderboard](https://flower.ai/benchmarks/llm-leaderboard/code/).
 
+### Evaluation Results (Accuracy)
+
+- **MBPP**:  25.80 %
+- **HumanEval**: 37.81 %
+- **MultiPL-E (JS)**: 41.00 %
+- **MultiPL-E (C++)**: 32.92 %
+- **Average**: 34.38 %
+
+### Communication Budget
+
+8766.51 MB Megabytes
+
+### Training Loss Plot
+
+![Training Loss](./train_loss.png)
+
 ## Model Details
 
-Please check the following GitHub project for model details and evaluation results (Work in Progress!!!):
+Please check the following GitHub project for model details and evaluation results:
 
 [https://github.com/ethicalabs-ai/FlowerTune-Qwen2.5-Coder-0.5B-Instruct/](https://github.com/ethicalabs-ai/FlowerTune-Qwen2.5-Coder-0.5B-Instruct/)
 
@@ -39,18 +55,6 @@ base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-Coder-0.5B-Instr
 model = PeftModel.from_pretrained(base_model, "ethicalabs/FlowerTune-Qwen2.5-Coder-0.5B-Instruct")
 ```
 
-### Evaluation Results (Accuracy)
-
-- **MBPP**:  21.20 %
-- **HumanEval**: 36.59 %
-- **MultiPL-E (JS)**: 40.38 %
-- **MultiPL-E (C++)**: 33.55 %
-- **Average**: 33.00 %
-
-### Communication Budget
-
-8766.51 MB Megabytes
-
 ### Framework versions
 
 - PEFT 0.14.0