Update README.md

README.md

@@ -3,5 +3,20 @@ language:
 - it
 pipeline_tag: fill-mask
 ---
-This model (based on bert-tiny) has been trained from scratch on 5k italian Wikipedia articles and on a wide collection of italian words and dictionary definitions.
+
+This model (based on [bert-tiny](https://huggingface.co/google/bert_uncased_L-2_H-128_A-2)) has been trained from scratch on 5k italian Wikipedia articles and on a wide collection of italian words and dictionary definitions.
+
+The project is still a work in progress, new versions will come soon.
+
+# Training
+
+- epochs: 200
+- lr: 1e-5
+- optim: AdamW
+- weight_decay: 1e-3
+
+# Eval
+
+- perplexity: 50
+