Update README.md

README.md

@@ -10,12 +10,12 @@ base_model:
 - Qwen/Qwen2.5-Coder-3B-Instruct
 ---
 
-# Model Card for Model ID
+# Introduction
 
 <!-- Provide a quick summary of what the model is/does. -->
 This model is a prototype of a large language model specifically fine-tuned for Fortran90 code generation. It is based on the Qwen 2.5 Coder 3B Instruct model and has been refined using Supervised Fine-Tuning and Reinforcement Learning with Verifiable Rewards (via GRPO).
 
-This model was fine-tuned briefly, without any human-labeled data and using only a single consumer GPU. Despite these clear constraints, the training process led to a 400% boost in performance on tasks involving simple to moderately complex program generation (HumanEval). Compilation errors dropped as well, and the model now performs close to much larger, general-purpose models that weren’t specifically trained for this task.
+This model was fine-tuned briefly, without any human-labeled data and using only a single consumer GPU. Despite these clear constraints, the training process led to a 400% boost in performance on tasks involving simple to moderately complex fortran program generation (HumanEval-like). Compilation errors dropped as well, and the model now performs close to much larger general-purpose models that weren’t specifically trained for this task.
 
 ## Evaluation
 Due to the lack of existing benchmarks for Fortran code generation, a quick-and-dirty adaptation of the HumanEval benchmark was created for Fortran in order to evaluate the model. This benchmark is currently under review and will be released publicly at a later date.
@@ -25,6 +25,7 @@ According to the current demo version of the FortranHumanEval benchmark:
 | Model                | pass@1 | Compile Error Rate |
 |----------------------|--------|--------------------|
 | **FortranCodeGen 3B**     |    23.17%   |        17.68%           |
+|**FortranCodeGen 3B only sft**     |    19.51%   |        31.09%           |
 | Qwen 2.5 Coder 3B     |    5.48%   |        63.41%          |
 | GPT-4o mini           |    18.90%   |           43.90%        |
 | GPT-4o                |    32.31%   |        17.07%           |
@@ -100,3 +101,7 @@ By guiding generation through specific topics, I built a synthetic dataset of 30
 
 ### Training Procedure
 
+#### Supervised Fine-Tuning
+
+Ihttps://wandb.ai/giulioleonardi2001-universit-di-pisa/Fortran-Qwen2.5-Coder-3B_fine_tuning/runs/hjmptz72/panel/6kalharhb?
+