Update README.md

README.md

@@ -12,7 +12,15 @@ library_name: adapter-transformers
 
 # Technoculture/MT7Bi-alpha-dpo-v-0.2
 
-## DPO Training Dataset Details
+## Training Details
+
+- **GPU:** Nvidia A100 Tensor Core GPU
+- **Total Batches:** 4266
+- **Epochs:** 3
+- **Duration:** 3 hours, 59 minutes, and 55 seconds
+
+
+## DPO Training Dataset Mixture
 | Dataset Name                                       | Original Size(Rows) | Ratio | Size After Ratio(Rows) |
 |----------------------------------------------------|---------------|-------|------------------|
 | argilla/distilabel-math-preference-dpo            | 2.4k | 1.0   | 2.4k           | 
@@ -21,4 +29,11 @@ library_name: adapter-transformers
 | argilla/distilabel-capybara-dpo-7k-binarized      | 7.5k | 0.2   | 1.5k           | 
 Total Size: 11.38k
 
-For full details of this dpo-training please read our notebook [MT7Bi-alpha-dpo-v0.2.ipynb](https://colab.research.google.com/drive/1nA0kHK8yGuz0IRlZD9pzsYYZnlL7LSeI?usp=sharing).
+## Training Loss Plot
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/658bed1c8ff537204fbd92a3/CKi7ArBnCyuidJPHo3M5T.png)
+
+## Training Loss Smoothed Plot
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/658bed1c8ff537204fbd92a3/tFyGJLw3Vj3m2jaaWk66E.png)
+
+### For full details of this dpo-training please read our notebook [MT7Bi-alpha-dpo-v0.2.ipynb](https://colab.research.google.com/drive/1nA0kHK8yGuz0IRlZD9pzsYYZnlL7LSeI?usp=sharing).
+