End of training, # of epochs increased to 15

README.md

@@ -33,7 +33,7 @@ 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: 0.5223
+- Loss: 0.8346
 - Accuracy: 0.86
 
 ## Model description
@@ -60,23 +60,28 @@ 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: 10
+- num_epochs: 15
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 1.9168        | 1.0   | 113  | 1.8623          | 0.57     |
-| 1.2498        | 2.0   | 226  | 1.2677          | 0.63     |
-| 0.9741        | 3.0   | 339  | 1.1579          | 0.63     |
-| 0.6373        | 4.0   | 452  | 0.6921          | 0.79     |
-| 0.5008        | 5.0   | 565  | 0.6113          | 0.81     |
-| 0.3696        | 6.0   | 678  | 0.5258          | 0.85     |
-| 0.2516        | 7.0   | 791  | 0.4998          | 0.88     |
-| 0.1192        | 8.0   | 904  | 0.4894          | 0.87     |
-| 0.0982        | 9.0   | 1017 | 0.4799          | 0.86     |
-| 0.0743        | 10.0  | 1130 | 0.5223          | 0.86     |
+| 0.1361        | 1.0   | 113  | 0.5399          | 0.85     |
+| 0.3632        | 2.0   | 226  | 0.5833          | 0.86     |
+| 0.0152        | 3.0   | 339  | 0.5908          | 0.86     |
+| 0.1117        | 4.0   | 452  | 0.6009          | 0.86     |
+| 0.0171        | 5.0   | 565  | 0.7137          | 0.84     |
+| 0.0021        | 6.0   | 678  | 0.8152          | 0.85     |
+| 0.0032        | 7.0   | 791  | 0.9775          | 0.85     |
+| 0.0012        | 8.0   | 904  | 0.9153          | 0.84     |
+| 0.001         | 9.0   | 1017 | 0.8607          | 0.86     |
+| 0.0091        | 10.0  | 1130 | 0.8902          | 0.85     |
+| 0.0007        | 11.0  | 1243 | 0.8366          | 0.85     |
+| 0.0007        | 12.0  | 1356 | 0.8321          | 0.86     |
+| 0.0007        | 13.0  | 1469 | 0.8330          | 0.86     |
+| 0.0007        | 14.0  | 1582 | 0.8421          | 0.86     |
+| 0.0006        | 15.0  | 1695 | 0.8346          | 0.86     |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df4c0ff313eaedfe834584556ff70a2b08d06d63d4c00c86525312fbfe844abf
+oid sha256:bcede37f4498df05ce09b4805038f97d25a6333b0585b95e0b27bbca7c465bd2
 size 94771728

runs/Sep04_19-09-03_a83f59f8c6fe/events.out.tfevents.1725476957.a83f59f8c6fe.1835.1

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3bd00dda9ad736a18c8441398bd633610c69c73bda2d4eddda7a541d4b5a6e81
-size 82087
+oid sha256:5fde3ff473298d2e5f6a61c6486ea3facca7c7dec5c47a6631538a7b08fc165f
+size 82764