End of training

README.md

@@ -22,7 +22,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.82
+      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: 0.6017
-- Accuracy: 0.82
+- Loss: 0.6551
+- Accuracy: 0.83
 
 ## Model description
 
@@ -60,26 +60,27 @@ The following hyperparameters were used during training:
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.1
 - num_epochs: 10
+- mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 2.0266        | 1.0   | 113  | 1.7851          | 0.59     |
-| 1.3016        | 2.0   | 226  | 1.1678          | 0.71     |
-| 1.0307        | 3.0   | 339  | 0.9306          | 0.75     |
-| 0.882         | 4.0   | 452  | 0.8685          | 0.74     |
-| 0.5489        | 5.0   | 565  | 0.7226          | 0.76     |
-| 0.3585        | 6.0   | 678  | 0.6712          | 0.79     |
-| 0.4149        | 7.0   | 791  | 0.6003          | 0.82     |
-| 0.119         | 8.0   | 904  | 0.5951          | 0.83     |
-| 0.2617        | 9.0   | 1017 | 0.5830          | 0.83     |
-| 0.0992        | 10.0  | 1130 | 0.6017          | 0.82     |
+| 1.9627        | 1.0   | 113  | 1.9008          | 0.51     |
+| 1.2185        | 2.0   | 226  | 1.2541          | 0.68     |
+| 0.8868        | 3.0   | 339  | 1.0025          | 0.7      |
+| 0.6438        | 4.0   | 452  | 0.8160          | 0.77     |
+| 0.4255        | 5.0   | 565  | 0.7545          | 0.79     |
+| 0.3223        | 6.0   | 678  | 0.6584          | 0.82     |
+| 0.2756        | 7.0   | 791  | 0.7826          | 0.76     |
+| 0.186         | 8.0   | 904  | 0.6439          | 0.82     |
+| 0.1233        | 9.0   | 1017 | 0.6260          | 0.85     |
+| 0.0971        | 10.0  | 1130 | 0.6551          | 0.83     |
 
 
 ### Framework versions
 
-- Transformers 4.31.0
-- Pytorch 2.0.1+cu118
-- Datasets 2.14.4
-- Tokenizers 0.13.3
+- Transformers 4.35.2
+- Pytorch 2.1.0+cu121
+- Datasets 2.16.0
+- Tokenizers 0.15.0

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f84634253ed7b2ae5dcfa38e289eb457039e13d9a077f15103ad83f68841b10
+oid sha256:dde1cb653a318506afff0f1e40fcdfd56b45cd94742f3cef1c59fe735941baf2
 size 94771728