diff --git a/README.md b/README.md
index 3d5e894..631f277 100644
--- a/README.md
+++ b/README.md
@@ -15,6 +15,17 @@ Model was trained on wikiner-fr dataset (~170 634  sentences).
 Model was validated on emails/chat data and overperformed other models on this type of data specifically. 
 In particular the model seems to work better on entity that don't start with an upper case.
 
+## Training data
+Training data was classified as follow:
+
+Abbreviation|Description
+-|-
+O |Outside of a named entity
+MISC |Miscellaneous entity
+PER |Person’s name
+ORG |Organization
+LOC |Location
+
 
 ## How to use camembert-ner with HuggingFace
 
@@ -81,29 +92,23 @@ nlp("Apple est créée le 1er avril 1976 dans le garage de la maison d'enfance d
 
 ## Model performances (metric: seqeval)
 
-Global
-```
-'precision': 0.8859
-'recall': 0.8971
-'f1': 0.8914
-```
+Overall
+
+precision|recall|f1
+-|-|-
+0.8859|0.8971|0.8914
 
 By entity
-```
-'LOC': {'precision': 0.8905576596578294,
-		'recall': 0.900554675118859,
-		'f1': 0.8955282684352223},
-'MISC': {'precision': 0.8175627240143369,
-		 'recall': 0.8117437722419929,
-		 'f1': 0.8146428571428571},
-'ORG': {'precision': 0.8099480326651819,
-		'recall': 0.8265151515151515,
-		'f1': 0.8181477315335584},
-'PER': {'precision': 0.9372509960159362,
-		'recall': 0.959812321501428,
-		'f1': 0.9483975005039308}
 
- ```
+entity|precision|recall|f1
+-|-|-|-
+PER|0.9372|0.9598|0.9483 
+ORG|0.8099|0.8265|0.8181
+LOC|0.8905|0.9005|0.8955
+MISC|0.8175|0.8117|0.8146
+
+
+
 
 A short article on how I used the result of this model to train a LSTM model for signature detection in emails:  
 https://medium.com/@jean-baptiste.polle/lstm-model-for-email-signature-detection-8e990384fefa