update model card README.md

README.md

@@ -5,9 +5,24 @@ tags:
 - generated_from_trainer
 datasets:
 - marsyas/gtzan
+metrics:
+- accuracy
 model-index:
 - name: distilhubert-finetuned-gtzan
-  results: []
+  results:
+  - task:
+      name: Audio Classification
+      type: audio-classification
+    dataset:
+      name: GTZAN
+      type: marsyas/gtzan
+      config: all
+      split: train
+      args: all
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.88
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -16,6 +31,9 @@ should probably proofread and complete it, then remove this comment. -->
 # distilhubert-finetuned-gtzan
 
 This model is a fine-tuned version of [ntu-spml/distilhubert](https://huggingface.co/ntu-spml/distilhubert) on the GTZAN dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.5117
+- Accuracy: 0.88
 
 ## Model description
 
@@ -45,6 +63,19 @@ The following hyperparameters were used during training:
 - lr_scheduler_warmup_ratio: 0.1
 - num_epochs: 7
 
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 1.8388        | 1.0   | 112  | 1.7222          | 0.53     |
+| 1.3269        | 2.0   | 225  | 1.1259          | 0.73     |
+| 0.8797        | 3.0   | 337  | 0.8566          | 0.78     |
+| 0.6708        | 4.0   | 450  | 0.7945          | 0.8      |
+| 0.6879        | 5.0   | 562  | 0.6607          | 0.85     |
+| 0.5266        | 6.0   | 675  | 0.5240          | 0.88     |
+| 0.3709        | 6.97  | 784  | 0.5117          | 0.88     |
+
+
 ### Framework versions
 
 - Transformers 4.31.0