End of training

README.md

@@ -23,7 +23,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.84
+      value: 0.79
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -33,8 +33,8 @@ 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: 0.6275
-- Accuracy: 0.84
+- Loss: 0.7147
+- Accuracy: 0.79
 
 ## Model description
 
@@ -60,23 +60,20 @@ The following hyperparameters were used during training:
 - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.1
-- num_epochs: 10
+- num_epochs: 7
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 1.8861        | 1.0   | 113  | 1.8271          | 0.54     |
-| 1.2032        | 2.0   | 226  | 1.2458          | 0.68     |
-| 1.1038        | 3.0   | 339  | 1.0419          | 0.72     |
-| 0.692         | 4.0   | 452  | 0.8506          | 0.73     |
-| 0.5745        | 5.0   | 565  | 0.6885          | 0.82     |
-| 0.34          | 6.0   | 678  | 0.6142          | 0.8      |
-| 0.2653        | 7.0   | 791  | 0.6198          | 0.84     |
-| 0.1366        | 8.0   | 904  | 0.6278          | 0.83     |
-| 0.1925        | 9.0   | 1017 | 0.6213          | 0.84     |
-| 0.1025        | 10.0  | 1130 | 0.6275          | 0.84     |
+| 1.7687        | 1.0   | 113  | 1.8225          | 0.41     |
+| 1.1357        | 2.0   | 226  | 1.2043          | 0.64     |
+| 1.0921        | 3.0   | 339  | 0.9574          | 0.7      |
+| 0.7526        | 4.0   | 452  | 0.8872          | 0.73     |
+| 0.6312        | 5.0   | 565  | 0.7200          | 0.78     |
+| 0.4752        | 6.0   | 678  | 0.6838          | 0.79     |
+| 0.4123        | 7.0   | 791  | 0.7147          | 0.79     |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22060d047b3620d67500f9e1e324a1e9879c9494b98a5af5af477990aa043d19
+oid sha256:6afae9109570f5a457f2735eddcf529d23e2923fdabf250db52e2850af9df110
 size 94771728

runs/Dec28_12-46-36_33e29a4260d1/events.out.tfevents.1735390045.33e29a4260d1.1472.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76cc868c1e9a91116cc48d435428ab69a145b2837f4cfa7c026feaae90ff1d39
-size 41446
+oid sha256:018e2782db4825f90e3600ec841e542e4c697d88ebf108fd60f0bbde8390c0e2
+size 42123