Update README.md

README.md

@@ -18,10 +18,10 @@ datasets:
 
 # LogicFlow-Llama-3B
 
-🚀 **Introducing LogicFlow-Llama-3B: Exploring Open Access to Chain-of-Thought Reasoning** 
-
 ![image/png](https://cdn-uploads.huggingface.co/production/uploads/664589a52d210101d1eac6ad/l_vPNI8K1AbiHHXUTo6aa.png)
 
+🚀 **Introducing LogicFlow-Llama-3B: Exploring Open Access to Chain-of-Thought Reasoning** 
+
 Ever wished your AI could not just *tell* you the answer, but *show* you its thinking? **LogicFlow-Llama-3B** represents an exciting attempt to instill robust Chain-of-Thought (CoT) capabilities into models like `meta-llama/Llama-3.2-3B-Instruct`, which, in its base form, does not possess strong inherent CoT reasoning. This isn't just another fine-tune; it's a meticulously crafted model designed to explore the potential of CoT on accessible hardware.
 
 Leveraging the insightful `open-thoughts/OpenThoughts-114k` dataset and the versatile [LLaMA-Factory](https://github.com/hiyouga/LLaMA-Factory) training library, LogicFlow-Llama-3B has been trained to dissect intricate problems and articulate its reasoning process step-by-step. Remarkably, this entire fine-tuning process was accomplished **on a single GPU**, demonstrating a pathway to more accessible CoT model development. Get ready to explore the frontiers of logical AI and unlock a new era of AI-powered deep thinking, even with limited resources!
@@ -34,7 +34,7 @@ Leveraging the insightful `open-thoughts/OpenThoughts-114k` dataset and the vers
 - **Fine-tuning Method:** LoRA (Low-Rank Adaptation)
 - **Fine-tuning Library:** LLaMA-Factory
 - **Dataset:** `open-thoughts/OpenThoughts-114k` (for Chain-of-Thought enhancement)
-- **Training Hardware:** Single GPU
+- **Training Hardware:** Single GPU-A6000  
 - **LoRA Rank:** 8
 - **LoRA Alpha:** 16
 - **LoRA Dropout:** 0
@@ -80,7 +80,8 @@ print(tokenizer.decode(outputs[0], skip_special_tokens=True))
 
 ## Training Process
 
-The model was fine-tuned for 3.0 epochs over a total of 18750 steps on a single GPU. The training was conducted using a linear learning rate scheduler, starting from an initial learning rate of 5e-5.
+The model was fine-tuned for **3.0 epochs** over a total of **18,750 steps** on a single **A6000 GPU**. Training employed a **linear learning rate scheduler**, starting from an initial rate of **5e-5**, with gradual decay toward zero. The process leveraged **LoRA** with `bf16` precision and **FlashAttention2** for efficient memory use and speed.
+
 
 Here's a glimpse into the training progression:
 
@@ -94,6 +95,18 @@ Below is a visualization of the training loss curve:
 
 ![Training Loss](training_loss.png)
 
+### 📊 Final Training Metrics
+
+| Metric                      | Value                       |
+|----------------------------|-----------------------------|
+| **Epochs**                 | 3.0                         |
+| **Input Tokens Seen**      | 613,609,008                 |
+| **Total FLOPs**            | 9,706,625,883 GFLOPs        |
+| **Final Train Loss**       | 0.435                       |
+| **Total Runtime**          | 1 day, 22 hours, 12 minutes |
+| **Samples per Second**     | 1.803                       |
+| **Steps per Second**       | 0.113                       |
+
 ### Training Configuration (from `llamaboard_config.yaml`):
 
 ```yaml