End of training

README.md

@@ -22,7 +22,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.82
+      value: 0.78
 ---
 
 <!-- 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: 1.0646
-- Accuracy: 0.82
+- Loss: 0.7054
+- Accuracy: 0.78
 
 ## Model description
 
@@ -52,39 +52,31 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 5e-05
-- train_batch_size: 2
-- eval_batch_size: 2
+- learning_rate: 6e-05
+- train_batch_size: 6
+- eval_batch_size: 6
 - seed: 42
 - gradient_accumulation_steps: 2
-- total_train_batch_size: 4
+- total_train_batch_size: 12
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.1
-- num_epochs: 18
+- num_epochs: 10
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 2.0114        | 1.0   | 225  | 1.8491          | 0.5      |
-| 1.1983        | 2.0   | 450  | 1.1911          | 0.68     |
-| 1.1408        | 3.0   | 675  | 0.9290          | 0.72     |
-| 0.7166        | 4.0   | 900  | 0.7200          | 0.78     |
-| 0.5334        | 5.0   | 1125 | 0.7233          | 0.79     |
-| 0.3294        | 6.0   | 1350 | 0.4989          | 0.83     |
-| 0.2949        | 7.0   | 1575 | 0.5294          | 0.85     |
-| 0.0067        | 8.0   | 1800 | 0.7724          | 0.83     |
-| 0.0041        | 9.0   | 2025 | 0.8986          | 0.8      |
-| 0.0049        | 10.0  | 2250 | 0.9146          | 0.83     |
-| 0.0016        | 11.0  | 2475 | 0.8999          | 0.85     |
-| 0.0013        | 12.0  | 2700 | 0.8947          | 0.86     |
-| 0.0015        | 13.0  | 2925 | 0.9257          | 0.85     |
-| 0.0009        | 14.0  | 3150 | 1.0211          | 0.82     |
-| 0.0009        | 15.0  | 3375 | 0.9288          | 0.84     |
-| 0.0008        | 16.0  | 3600 | 0.9672          | 0.82     |
-| 0.0009        | 17.0  | 3825 | 1.0717          | 0.82     |
-| 0.0756        | 18.0  | 4050 | 1.0646          | 0.82     |
+| 2.0862        | 0.99  | 79   | 1.8937          | 0.42     |
+| 1.4131        | 2.0   | 159  | 1.3534          | 0.64     |
+| 1.0176        | 2.99  | 238  | 1.0980          | 0.66     |
+| 0.6508        | 4.0   | 318  | 0.7554          | 0.86     |
+| 0.5523        | 4.99  | 397  | 0.7662          | 0.76     |
+| 0.398         | 6.0   | 477  | 0.6944          | 0.8      |
+| 0.2008        | 6.99  | 556  | 0.6739          | 0.76     |
+| 0.1801        | 8.0   | 636  | 0.7623          | 0.78     |
+| 0.1044        | 8.99  | 715  | 0.7073          | 0.8      |
+| 0.0788        | 9.94  | 790  | 0.7054          | 0.78     |
 
 
 ### Framework versions

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57c129ea25cc7597aa41bdbb9bd3a37a25cdf3e4ab97cd64b570376ed90c5d7e
+oid sha256:8e9c2d02e681592d0039d506c8a6ba17c0378383e43c9bab1bedd6dfaa5094c4
 size 94783376