End of training

README.md

@@ -22,7 +22,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.85
+      value: 0.83
 ---
 
 <!-- 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: 0.9000
-- Accuracy: 0.85
+- Accuracy: 0.83
+- Loss: 0.6037
 
 ## Model description
 
@@ -52,40 +52,30 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 5e-05
+- learning_rate: 2e-05
 - train_batch_size: 8
 - eval_batch_size: 8
 - 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
 - mixed_precision_training: Native AMP
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Accuracy |
-|:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 2.1605        | 1.0   | 113  | 2.0687          | 0.43     |
-| 1.4882        | 2.0   | 226  | 1.4799          | 0.57     |
-| 1.153         | 3.0   | 339  | 1.0688          | 0.72     |
-| 0.7342        | 4.0   | 452  | 0.8125          | 0.77     |
-| 0.6006        | 5.0   | 565  | 0.6751          | 0.81     |
-| 0.3723        | 6.0   | 678  | 0.6401          | 0.8      |
-| 0.2502        | 7.0   | 791  | 0.6562          | 0.8      |
-| 0.1122        | 8.0   | 904  | 0.7022          | 0.81     |
-| 0.0708        | 9.0   | 1017 | 0.6970          | 0.85     |
-| 0.0181        | 10.0  | 1130 | 0.8265          | 0.84     |
-| 0.0129        | 11.0  | 1243 | 0.7396          | 0.85     |
-| 0.0061        | 12.0  | 1356 | 0.7550          | 0.87     |
-| 0.0047        | 13.0  | 1469 | 0.8028          | 0.85     |
-| 0.004         | 14.0  | 1582 | 0.8657          | 0.84     |
-| 0.0039        | 15.0  | 1695 | 0.8750          | 0.85     |
-| 0.0031        | 16.0  | 1808 | 0.8898          | 0.86     |
-| 0.0028        | 17.0  | 1921 | 0.8835          | 0.85     |
-| 0.0025        | 18.0  | 2034 | 0.9102          | 0.85     |
-| 0.0025        | 19.0  | 2147 | 0.9007          | 0.86     |
-| 0.0024        | 20.0  | 2260 | 0.9000          | 0.85     |
+| Training Loss | Epoch | Step | Accuracy | Validation Loss |
+|:-------------:|:-----:|:----:|:--------:|:---------------:|
+| 1.1965        | 1.0   | 113  | 0.72     | 1.0930          |
+| 0.8761        | 2.0   | 226  | 0.72     | 0.9204          |
+| 1.2037        | 3.0   | 339  | 0.78     | 0.8489          |
+| 0.7389        | 4.0   | 452  | 0.79     | 0.7939          |
+| 0.8392        | 5.0   | 565  | 0.84     | 0.6780          |
+| 0.8498        | 6.0   | 678  | 0.82     | 0.6483          |
+| 0.4516        | 7.0   | 791  | 0.82     | 0.6372          |
+| 0.32          | 8.0   | 904  | 0.81     | 0.6238          |
+| 0.5597        | 9.0   | 1017 | 0.81     | 0.6276          |
+| 0.3312        | 10.0  | 1130 | 0.83     | 0.6037          |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72ddaffc8c23f73abc8d48fc58f69d3fb66dde305abd6af884a448afdb0af428
+oid sha256:37a1b8c85ad6854708556accc9660379437ca66a0f2f5f8a4744268ab08adb54
 size 94771728

runs/Apr15_14-44-25_75a9e4ad7edb/events.out.tfevents.1713192289.75a9e4ad7edb.1955.2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03d25ac2820ebcb02c500befe455b86da77127a5aa1837378736a3134bfa553a
-size 56593
+oid sha256:9e1011940373b0a7d565cbd45cca12605677de7b54d25ba98f9d50e80e7c19f2
+size 56947

runs/Apr15_14-44-25_75a9e4ad7edb/events.out.tfevents.1713197348.75a9e4ad7edb.1955.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97eac1528f59517f8876aa940ad2cc3a2afc6d2f22cf93a75d94a29180dfec3b
+size 6157