End of training

README.md

@@ -22,7 +22,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.82
+      value: 0.86
 ---
 
 <!-- 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: 1.3274
-- Accuracy: 0.82
+- Loss: 0.5678
+- Accuracy: 0.86
 
 ## Model description
 
@@ -53,29 +53,34 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 5e-05
-- train_batch_size: 1
-- eval_batch_size: 1
+- 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: 10
+- num_epochs: 15
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 1.3436        | 1.0   | 899  | 1.3559          | 0.57     |
-| 1.1232        | 2.0   | 1798 | 1.3862          | 0.65     |
-| 0.0315        | 3.0   | 2697 | 0.8953          | 0.76     |
-| 0.0174        | 4.0   | 3596 | 0.9777          | 0.81     |
-| 0.9155        | 5.0   | 4495 | 1.0478          | 0.81     |
-| 0.4285        | 6.0   | 5394 | 1.6165          | 0.78     |
-| 0.0003        | 7.0   | 6293 | 0.9844          | 0.86     |
-| 0.0001        | 8.0   | 7192 | 1.3545          | 0.82     |
-| 0.0001        | 9.0   | 8091 | 1.3581          | 0.82     |
-| 0.0001        | 10.0  | 8990 | 1.3274          | 0.82     |
+| 2.2153        | 1.0   | 57   | 2.1306          | 0.37     |
+| 1.5998        | 2.0   | 114  | 1.5355          | 0.59     |
+| 1.2268        | 3.0   | 171  | 1.1801          | 0.7      |
+| 0.8839        | 4.0   | 228  | 1.0267          | 0.68     |
+| 0.8058        | 5.0   | 285  | 0.8348          | 0.77     |
+| 0.6722        | 6.0   | 342  | 0.7497          | 0.78     |
+| 0.6603        | 7.0   | 399  | 0.6921          | 0.78     |
+| 0.4026        | 8.0   | 456  | 0.6814          | 0.8      |
+| 0.3244        | 9.0   | 513  | 0.6138          | 0.81     |
+| 0.2639        | 10.0  | 570  | 0.5887          | 0.85     |
+| 0.1619        | 11.0  | 627  | 0.6005          | 0.83     |
+| 0.1652        | 12.0  | 684  | 0.5589          | 0.83     |
+| 0.1354        | 13.0  | 741  | 0.6157          | 0.8      |
+| 0.0821        | 14.0  | 798  | 0.6221          | 0.83     |
+| 0.1009        | 15.0  | 855  | 0.5678          | 0.86     |
 
 
 ### Framework versions

runs/Sep04_14-21-42_5ee459a6381b/events.out.tfevents.1725459716.5ee459a6381b.1361.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9fc2ec8df0f9eb562af0de4e478431f4007eaebf28331164cbe6a72382c7d024
-size 46548
+oid sha256:bd8f35da9d807082b60c90c04022a5de310d65ea15604fc70f370eb3e98f606c
+size 47225