update model card README.md

README.md

@@ -22,7 +22,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.86
+      value: 0.87
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -32,8 +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:
-- Loss: 0.8208
-- Accuracy: 0.86
+- Loss: 0.8403
+- Accuracy: 0.87
 
 ## Model description
 
@@ -53,38 +53,28 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 5e-05
-- train_batch_size: 8
-- eval_batch_size: 8
+- train_batch_size: 16
+- eval_batch_size: 16
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.1
-- num_epochs: 20
+- num_epochs: 10
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 2.1942        | 1.0   | 113  | 2.1009          | 0.34     |
-| 1.5746        | 2.0   | 226  | 1.4756          | 0.59     |
-| 1.176         | 3.0   | 339  | 1.1244          | 0.72     |
-| 0.9955        | 4.0   | 452  | 0.9900          | 0.74     |
-| 0.7129        | 5.0   | 565  | 0.7653          | 0.79     |
-| 0.3957        | 6.0   | 678  | 0.6458          | 0.83     |
-| 0.4143        | 7.0   | 791  | 0.5677          | 0.84     |
-| 0.0693        | 8.0   | 904  | 0.6466          | 0.83     |
-| 0.1543        | 9.0   | 1017 | 0.6063          | 0.87     |
-| 0.0141        | 10.0  | 1130 | 0.6661          | 0.86     |
-| 0.0105        | 11.0  | 1243 | 0.6862          | 0.87     |
-| 0.1235        | 12.0  | 1356 | 0.7561          | 0.86     |
-| 0.0053        | 13.0  | 1469 | 0.7607          | 0.87     |
-| 0.0044        | 14.0  | 1582 | 0.7905          | 0.86     |
-| 0.004         | 15.0  | 1695 | 0.7764          | 0.86     |
-| 0.0036        | 16.0  | 1808 | 0.8037          | 0.86     |
-| 0.0187        | 17.0  | 1921 | 0.8085          | 0.86     |
-| 0.0027        | 18.0  | 2034 | 0.8106          | 0.86     |
-| 0.0027        | 19.0  | 2147 | 0.8178          | 0.86     |
-| 0.0029        | 20.0  | 2260 | 0.8208          | 0.86     |
+| 0.0376        | 1.0   | 57   | 0.6132          | 0.88     |
+| 0.052         | 2.0   | 114  | 0.8688          | 0.84     |
+| 0.0047        | 3.0   | 171  | 0.7919          | 0.84     |
+| 0.0029        | 4.0   | 228  | 0.8666          | 0.85     |
+| 0.0021        | 5.0   | 285  | 0.8617          | 0.87     |
+| 0.0813        | 6.0   | 342  | 0.9202          | 0.86     |
+| 0.0461        | 7.0   | 399  | 0.8868          | 0.85     |
+| 0.0014        | 8.0   | 456  | 0.8567          | 0.86     |
+| 0.0012        | 9.0   | 513  | 0.8471          | 0.86     |
+| 0.0013        | 10.0  | 570  | 0.8403          | 0.87     |
 
 
 ### Framework versions