diff --git a/training.md b/models/README.md
similarity index 53%
rename from training.md
rename to models/README.md
index a1a8cb2..3120b4b 100644
--- a/training.md
+++ b/models/README.md
@@ -1,6 +1,16 @@
 # Meta information about training
+
+The trained models that are saved here follow the following naming convention:
+
+* Optuna intermediate model: `[model]-[dataset]-[context].pt`
+* Fully trained model: `[model]-[dataset]-full-[context].pt`
+
+The following parameters were used:
+
 * training size: 2048 for optuna, 209715 for full training
-* context sizes used: 128, 256
+* context sizes: {128, 256}
+
+The models were trained with the following command:
 
 ```bash
 uv run python ./results/[cnn,autoencoder] train --method [full,optuna] \