Update README.md

README.md

@@ -13,6 +13,10 @@ tags:
 
 Midi event transformer for music generation
 
+### Model updates
+
+v1.2: Optmise the tokenizer and dataset. The dataset was filtered by `MIDITokenizer.check_quality`
+
 ## Model Details
 
 ### Model Description
@@ -35,16 +39,17 @@ Midi event transformer for music generation
 
 #### Training Hyperparameters
 
-- lr: 2e-5
+- basemodel: v1.1
+- lr: 1e-4
 - weight-decay: 0.01
-- batch: 4x2x4
+- batch: 2x2x2
 - fp16 mixed precision
 
 ####  Loss
- - val loss: 0.17
+ - val loss: 0.238
 
 ## Files
 
 - model.ckpt: latest model checkpoint
 - soundfont.sf2: soundfont file, i put it here for convenient downloading , [source](https://musical-artifacts.com/artifacts/433)
-
+- onnx/*.onnx: onnx format model