Update README.md

README.md

@@ -19,6 +19,14 @@ Following https://github.com/KellerJordan/modded-nanogpt for fun (learning).
 - 4 seconds per step, total 3200 steps
 - Checkpoint saved every 320 steps
 
+## Training loss
+
+To experimentally check the neural scaling law:
+
+![baseline/analysis/loss_plot2.png](baseline/analysis/loss_plot2.png)
+
+(Fitted line: `log y = -0.11 * log x + 0.9` where x is step (0 to 3200) and y is the training loss)
+
 ## Demo
 
 Available at https://huggingface.co/spaces/lemonteaa/nanogpt-speedrun-demo