End of training

README.md

@@ -22,7 +22,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.84
+      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: 0.9085
-- Accuracy: 0.84
+- Loss: 0.9791
+- Accuracy: 0.83
 
 ## Model description
 
@@ -59,7 +59,7 @@ 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
-- training_steps: 3000
+- training_steps: 4000
 
 ### Training results
 
@@ -90,8 +90,18 @@ The following hyperparameters were used during training:
 | 0.0161        | 20.35 | 2300 | 0.85     | 0.8464          |
 | 0.0157        | 21.24 | 2400 | 0.86     | 0.8459          |
 | 0.0039        | 22.12 | 2500 | 0.8      | 1.0282          |
-| 0.0145        | 23.01 | 2600 | 0.9218   | 0.84            |
-| 0.0149        | 23.89 | 2700 | 0.9085   | 0.84            |
+| 0.0157        | 23.01 | 2600 | 0.86     | 0.8649          |
+| 0.0119        | 23.89 | 2700 | 0.85     | 0.8894          |
+| 0.0129        | 24.78 | 2800 | 0.87     | 0.8624          |
+| 0.0124        | 25.66 | 2900 | 0.85     | 0.8862          |
+| 0.0025        | 26.55 | 3000 | 0.84     | 0.9097          |
+| 0.0197        | 27.43 | 3100 | 0.9150   | 0.85            |
+| 0.0193        | 28.32 | 3200 | 0.9986   | 0.83            |
+| 0.0119        | 29.2  | 3300 | 0.9001   | 0.87            |
+| 0.0017        | 30.09 | 3400 | 0.9599   | 0.83            |
+| 0.015         | 30.97 | 3500 | 0.9442   | 0.84            |
+| 0.0015        | 31.86 | 3600 | 0.9813   | 0.83            |
+| 0.0056        | 32.74 | 3700 | 0.9791   | 0.83            |
 
 
 ### Framework versions

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb24f1cce10a942e6b097315285b64c8dd735d3b81676eef1f9ea68e33fd7642
+oid sha256:8ffe6aa149d2250d28f5c513c2b303c1053ce95f219a9cee4d784b7d7d50e250
 size 94782534