End of training

README.md

@@ -22,7 +22,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.82
+      value: 0.7
 ---
 
 <!-- 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: 0.9471
-- Accuracy: 0.82
+- Loss: 1.6085
+- Accuracy: 0.7
 
 ## Model description
 
@@ -52,12 +52,10 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.0001
-- train_batch_size: 16
-- eval_batch_size: 16
+- learning_rate: 1e-05
+- train_batch_size: 20
+- eval_batch_size: 20
 - seed: 42
-- gradient_accumulation_steps: 2
-- total_train_batch_size: 32
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.1
@@ -67,16 +65,16 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 0.1739        | 0.98  | 28   | 0.7633          | 0.83     |
-| 0.097         | 2.0   | 57   | 0.6388          | 0.86     |
-| 0.0422        | 2.98  | 85   | 0.8436          | 0.82     |
-| 0.0192        | 4.0   | 114  | 0.7988          | 0.85     |
-| 0.0086        | 4.98  | 142  | 0.9796          | 0.82     |
-| 0.0258        | 6.0   | 171  | 0.8960          | 0.83     |
-| 0.0043        | 6.98  | 199  | 0.9304          | 0.83     |
-| 0.0108        | 8.0   | 228  | 0.9277          | 0.81     |
-| 0.003         | 8.98  | 256  | 0.9678          | 0.82     |
-| 0.0075        | 9.82  | 280  | 0.9471          | 0.82     |
+| 2.284         | 1.0   | 45   | 2.2715          | 0.28     |
+| 2.2235        | 2.0   | 90   | 2.1789          | 0.47     |
+| 2.0628        | 3.0   | 135  | 2.0368          | 0.63     |
+| 1.9314        | 4.0   | 180  | 1.9068          | 0.66     |
+| 1.8308        | 5.0   | 225  | 1.8077          | 0.66     |
+| 1.7901        | 6.0   | 270  | 1.7276          | 0.7      |
+| 1.7703        | 7.0   | 315  | 1.6747          | 0.69     |
+| 1.7163        | 8.0   | 360  | 1.6382          | 0.69     |
+| 1.6133        | 9.0   | 405  | 1.6154          | 0.7      |
+| 1.6876        | 10.0  | 450  | 1.6085          | 0.7      |
 
 
 ### Framework versions

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1652b73bd76900ca10d2c4e0cfeca5812d871e67496943555d861f08ff515b8f
+oid sha256:81544f9863653d2a9e9a040762b0abea4c02deaf7a23fb54717195d84e446f47
 size 94783376