Update README.md

README.md

@@ -3,7 +3,25 @@ tags:
 - generated_from_trainer
 model-index:
 - name: gttbsc_phi-freezed-best
-  results: []
+  results: 
+    - task:
+        type: dialogue act classification
+      dataset:
+        name: asapp/slue-phase-2
+        type: hvb
+      metrics:
+        - name: F1 macro E2E
+          type: F1 macro
+          value: 65.66
+        - name: F1 macro GT
+          type: F1 macro
+          value: 69.97
+datasets:
+- asapp/slue-phase-2
+language:
+- en
+metrics:
+- f1-macro
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -11,21 +29,20 @@ should probably proofread and complete it, then remove this comment. -->
 
 # gttbsc_phi-freezed-best
 
-This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
+Ground truth text based multi-label DAC
 
 ## Model description
 
-More information needed
+Backbone: [Phi 3 mini](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct)  
+Pooling: Weighted mean pooling  
+Multi-label classification head: 2 dense layers with two dropouts 0.3 and Tanh activation inbetween  
 
-## Intended uses & limitations
-
-More information needed
 
 ## Training and evaluation data
 
-More information needed
+Trained on ground truth.  
+Evaluated on ground truth (GT) and normalized [Whisper small](https://huggingface.co/openai/whisper-small) transcripts (E2E).  
 
-## Training procedure
 
 ### Training hyperparameters
 
@@ -40,8 +57,6 @@ The following hyperparameters were used during training:
 - lr_scheduler_type: linear
 - num_epochs: 20
 
-### Training results
-
 
 
 ### Framework versions