update model card README.md

README.md

@@ -17,15 +17,15 @@ model-index:
       name: audiofolder
       type: audiofolder
       config: Data_Train
-      split: train
+      split: train[:90%]
       args: Data_Train
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.8251533742331288
+      value: 0.838957055214724
     - name: F1
       type: f1
-      value: 0.8129155478522945
+      value: 0.8286657330565742
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -35,9 +35,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the audiofolder dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.8220
-- Accuracy: 0.8252
-- F1: 0.8129
+- Loss: 0.8341
+- Accuracy: 0.8390
+- F1: 0.8287
 
 ## Model description
 
@@ -71,11 +71,11 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
-| 1.8825        | 1.0   | 1449 | 2.1386          | 0.3735   | 0.2790 |
-| 1.2037        | 2.0   | 2898 | 1.2566          | 0.6557   | 0.5859 |
-| 1.1576        | 3.0   | 4347 | 0.9368          | 0.7722   | 0.7510 |
-| 0.7057        | 4.0   | 5796 | 0.8254          | 0.8044   | 0.7885 |
-| 0.5655        | 5.0   | 7245 | 0.8220          | 0.8252   | 0.8129 |
+| 1.6193        | 1.0   | 1304 | 1.6888          | 0.5061   | 0.3780 |
+| 1.0537        | 2.0   | 2608 | 1.2344          | 0.6794   | 0.6414 |
+| 0.8454        | 3.0   | 3912 | 0.9588          | 0.7653   | 0.7465 |
+| 0.7623        | 4.0   | 5216 | 0.8678          | 0.8198   | 0.8107 |
+| 0.4638        | 5.0   | 6520 | 0.8341          | 0.8390   | 0.8287 |
 
 
 ### Framework versions