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: 0.86
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -17,13 +32,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 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:
-- eval_loss: 1.8797
-- eval_accuracy: 0.53
-- eval_runtime: 82.589
-- eval_samples_per_second: 1.211
-- eval_steps_per_second: 0.303
-- epoch: 1.0
-- step: 56
+- Loss: 0.5690
+- Accuracy: 0.86
 
 ## Model description
 
@@ -51,7 +61,21 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.1
-- num_epochs: 3
+- num_epochs: 8
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 1.5369        | 1.0   | 56   | 1.4184          | 0.69     |
+| 1.1716        | 1.99  | 112  | 1.0323          | 0.75     |
+| 0.9106        | 2.99  | 168  | 0.8989          | 0.8      |
+| 0.9016        | 4.0   | 225  | 0.7206          | 0.82     |
+| 0.6024        | 5.0   | 281  | 0.7432          | 0.81     |
+| 0.5155        | 5.99  | 337  | 0.6442          | 0.83     |
+| 0.3924        | 6.99  | 393  | 0.5743          | 0.85     |
+| 0.3956        | 7.96  | 448  | 0.5690          | 0.86     |
+
 
 ### Framework versions