Added Checkpoint Metrics

README-huggingface.md

@@ -25,9 +25,15 @@ model-index:
           type: fka/awesome-chatgpt-prompts
           name: Awesome ChatGPT Prompts
         metrics:
-          - name: perplexity
-            type: perplexity
-            value: 15.3
+          - name: epoch
+            type: number
+            value: 2
+          - name: model_size
+            type: text
+            value: "1.82 GB"
+          - name: run_time
+            type: text
+            value: "2.5 minutes on Intel UHD Graphics 630"
           - name: accuracy
             type: accuracy
             value: 78.5
@@ -97,7 +103,10 @@ The model is trained on the [awesome-chatgpt-prompts](https://huggingface.co/dat
 ## Evaluation Results
 
 The model shows strong performance across key metrics:
-- **Perplexity:** 15.3
+- **Final Epoch:** 2
+- **Model Size:** 1.82 GB
+- **Total Run Time:** 2.5 minutes on Intel UHD Graphics 630
+- **Loss:** 7.11
 - **Accuracy:** 78.5%
 - **Response Coherence:** 82.1%
 - **Peer Network Efficiency:** 91.2%

README.md

@@ -24,12 +24,18 @@ model-index:
           name: Custom Text Dataset
           type: text
         metrics:
-          - name: Perplexity
-            type: perplexity
-            value: to be updated after training
+          - name: Epoch
+            type: number
+            value: 2
+          - name: Model Size
+            type: text
+            value: "1.82 GB"
+          - name: Run Time
+            type: text
+            value: "2.5 minutes on Intel UHD Graphics 630"
           - name: Loss
             type: cross-entropy
-            value: to be updated after training
+            value: 7.11
 ---
 
 # OpenPeerLLM: A Decentralized Large Language Model
@@ -89,7 +95,10 @@ The model is trained on the [awesome-chatgpt-prompts](https://huggingface.co/dat
 ## Evaluation Results
 
 Initial testing shows promising results:
-- **Perplexity:** 15.3
+- **Final Epoch:** 2
+- **Model Size:** 1.82 GB
+- **Total Run Time:** 2.5 minutes on Intel UHD Graphics 630
+- **Loss:** 7.11
 - **Accuracy:** 78.5%
 - **Response Coherence:** 82.1%
 - **Peer Network Efficiency:** 91.2%