End of training

README.md

@@ -22,7 +22,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.86
+      value: 0.9475
 ---
 
 <!-- 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: 0.8495
-- Accuracy: 0.86
+- Loss: 0.3616
+- Accuracy: 0.9475
 
 ## Model description
 
@@ -59,13 +59,17 @@ 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: 1
+- num_epochs: 5
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 0.1333        | 1.0   | 159  | 0.8495          | 0.86     |
+| 0.2804        | 1.0   | 100  | 0.3327          | 0.9475   |
+| 0.4089        | 2.0   | 200  | 0.3448          | 0.955    |
+| 0.0564        | 3.0   | 300  | 0.3446          | 0.95     |
+| 0.0           | 4.0   | 400  | 0.3417          | 0.9475   |
+| 0.0           | 5.0   | 500  | 0.3616          | 0.9475   |
 
 
 ### Framework versions

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a19e30adce278d06cfd53ad67146e1f4696345012b1b4f3666c11c5813c3e96f
+oid sha256:e3f02da665f1a6ed0b556cd76d0afa89f42baed967d223c8ef1ca7b9c5a1270d
 size 94783376