End of training

README.md

@@ -22,7 +22,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.81
+      value: 0.72
 ---
 
 <!-- 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: 0.6504
-- Accuracy: 0.81
+- Loss: 1.3187
+- Accuracy: 0.72
 
 ## Model description
 
@@ -56,31 +56,29 @@ The following hyperparameters were used during training:
 - train_batch_size: 8
 - eval_batch_size: 8
 - seed: 42
+- gradient_accumulation_steps: 4
+- 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
-- num_epochs: 15
+- num_epochs: 11
 - mixed_precision_training: Native AMP
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Accuracy |
-|:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 2.2428        | 1.0   | 113  | 2.1981          | 0.35     |
-| 1.7527        | 2.0   | 226  | 1.7611          | 0.55     |
-| 1.6002        | 3.0   | 339  | 1.4516          | 0.65     |
-| 1.2101        | 4.0   | 452  | 1.2245          | 0.7      |
-| 1.1006        | 5.0   | 565  | 1.0758          | 0.73     |
-| 0.9583        | 6.0   | 678  | 0.9477          | 0.76     |
-| 0.8705        | 7.0   | 791  | 0.8907          | 0.77     |
-| 0.6892        | 8.0   | 904  | 0.8438          | 0.75     |
-| 0.6141        | 9.0   | 1017 | 0.7574          | 0.79     |
-| 0.5614        | 10.0  | 1130 | 0.7300          | 0.81     |
-| 0.5347        | 11.0  | 1243 | 0.6830          | 0.8      |
-| 0.5106        | 12.0  | 1356 | 0.7286          | 0.81     |
-| 0.4662        | 13.0  | 1469 | 0.6701          | 0.8      |
-| 0.6223        | 14.0  | 1582 | 0.6728          | 0.8      |
-| 0.3604        | 15.0  | 1695 | 0.6504          | 0.81     |
+| Training Loss | Epoch   | Step | Validation Loss | Accuracy |
+|:-------------:|:-------:|:----:|:---------------:|:--------:|
+| 2.2889        | 0.9912  | 28   | 2.2613          | 0.38     |
+| 2.1553        | 1.9823  | 56   | 2.0953          | 0.56     |
+| 1.9626        | 2.9735  | 84   | 1.8820          | 0.54     |
+| 1.7839        | 4.0     | 113  | 1.7308          | 0.61     |
+| 1.6749        | 4.9912  | 141  | 1.5920          | 0.64     |
+| 1.5595        | 5.9823  | 169  | 1.5004          | 0.68     |
+| 1.5266        | 6.9735  | 197  | 1.4368          | 0.68     |
+| 1.4459        | 8.0     | 226  | 1.3776          | 0.71     |
+| 1.4152        | 8.9912  | 254  | 1.3481          | 0.71     |
+| 1.3766        | 9.9823  | 282  | 1.3242          | 0.72     |
+| 1.3682        | 10.9027 | 308  | 1.3187          | 0.72     |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37c0b31df85f133f6f7b0f7be7d0da69faa66b56f693a92ddb076fe24656138f
+oid sha256:2df4cf3bfd649bedab647add4d1961e2a18362ca156226f0259413ff18c44cda
 size 94771728