Update README.md

README.md

@@ -27,6 +27,17 @@ This model is the ONNX version of [https://huggingface.co/SamLowe/roberta-base-g
 - is faster in inference than normal Transformers, particularly for smaller batch sizes
   - in my tests about 2x to 3x as fast for a batch size of 1 on a 8 core 11th gen i7 CPU using ONNXRuntime
 
+#### Metrics
+
+Using a fixed threshold of 0.5 to convert the scores to binary predictions for each label:
+
+- Accuracy: 0.474
+- Precision: 0.575
+- Recall: 0.396
+- F1: 0.450
+
+See more details in the SamLowe/roberta-base-go_emotions model card for the increases possible through selecting label-specific thresholds to maximise F1 scores, or another metric.
+
 ### Quantized (INT8) ONNX version
 
 `onnx/model_quantized.onnx` is the int8 quantized version 
@@ -36,6 +47,19 @@ This model is the ONNX version of [https://huggingface.co/SamLowe/roberta-base-g
 - is faster in inference than both the full precision ONNX above, and the normal Transformers model
   - about 2x as fast for a batch size of 1 on an 8 core 11th gen i7 CPU using ONNXRuntime vs the full precision model above
   - which makes it circa 5x as fast as the full precision normal Transformers model (on the above mentioned CPU, for a batch of 1)
+ 
+#### Metrics for Quantized (INT8) Model
+
+Using a fixed threshold of 0.5 to convert the scores to binary predictions for each label:
+
+- Accuracy: 0.475
+- Precision: 0.582
+- Recall: 0.398
+- F1: 0.447
+
+Note how the metrics are almost identical to the full precision metrics above.
+
+See more details in the SamLowe/roberta-base-go_emotions model card for the increases possible through selecting label-specific thresholds to maximise F1 scores, or another metric.
 
 ### How to use