End of training

README.md

@@ -22,7 +22,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.81
+      value: 0.84
 ---
 
 <!-- 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: 0.6734
-- Accuracy: 0.81
+- Loss: 1.0184
+- Accuracy: 0.84
 
 ## Model description
 
@@ -52,35 +52,30 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 3e-05
-- train_batch_size: 8
-- eval_batch_size: 8
+- learning_rate: 5e-05
+- train_batch_size: 2
+- eval_batch_size: 2
 - 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: 15
+- num_epochs: 10
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 2.1966        | 1.0   | 113  | 2.1508          | 0.49     |
-| 1.6173        | 2.0   | 226  | 1.6236          | 0.57     |
-| 1.4483        | 3.0   | 339  | 1.3165          | 0.69     |
-| 1.1295        | 4.0   | 452  | 1.1380          | 0.7      |
-| 0.9444        | 5.0   | 565  | 0.9592          | 0.76     |
-| 0.8205        | 6.0   | 678  | 0.9024          | 0.74     |
-| 0.6711        | 7.0   | 791  | 0.8497          | 0.78     |
-| 0.4759        | 8.0   | 904  | 0.8240          | 0.78     |
-| 0.4657        | 9.0   | 1017 | 0.7534          | 0.79     |
-| 0.3651        | 10.0  | 1130 | 0.7403          | 0.8      |
-| 0.3154        | 11.0  | 1243 | 0.7082          | 0.82     |
-| 0.252         | 12.0  | 1356 | 0.7222          | 0.81     |
-| 0.2265        | 13.0  | 1469 | 0.7063          | 0.82     |
-| 0.2478        | 14.0  | 1582 | 0.6898          | 0.81     |
-| 0.1386        | 15.0  | 1695 | 0.6734          | 0.81     |
+| 1.6293        | 1.0   | 450  | 1.4785          | 0.51     |
+| 1.4503        | 2.0   | 900  | 1.0904          | 0.68     |
+| 0.1918        | 3.0   | 1350 | 0.6702          | 0.75     |
+| 0.0857        | 4.0   | 1800 | 0.7173          | 0.79     |
+| 0.0601        | 5.0   | 2250 | 0.9274          | 0.77     |
+| 0.0047        | 6.0   | 2700 | 0.9787          | 0.81     |
+| 0.6662        | 7.0   | 3150 | 1.0511          | 0.81     |
+| 0.0012        | 8.0   | 3600 | 1.0870          | 0.84     |
+| 0.0015        | 9.0   | 4050 | 0.9564          | 0.87     |
+| 0.0012        | 10.0  | 4500 | 1.0184          | 0.84     |
 
 
 ### Framework versions

runs/Mar07_20-18-02_3009a6145419/events.out.tfevents.1709842683.3009a6145419.440.1

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae77da3bb877e0b05f47159a975f21e245e403c2e69a1c0af6034b60a9920a99
-size 179500
+oid sha256:04fcc6f232de00e8a2de67e01b7a1b81a6914ad42ddc52796bbe27b1fbf2b8fc
+size 199167