End of training

README.md

@@ -4,7 +4,7 @@ base_model: ntu-spml/distilhubert
 tags:
 - generated_from_trainer
 datasets:
-- marsyas/gtzan
+- gtzan
 metrics:
 - accuracy
 model-index:
@@ -14,15 +14,15 @@ model-index:
       name: Audio Classification
       type: audio-classification
     dataset:
-      name: GTZAN
-      type: marsyas/gtzan
+      name: gtzan
+      type: gtzan
       config: all
       split: train
       args: all
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.84
+      value: 0.85
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -30,10 +30,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # distilhubert-finetuned-gtzan
 
-This model is a fine-tuned version of [ntu-spml/distilhubert](https://huggingface.co/ntu-spml/distilhubert) on the GTZAN dataset.
+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: 0.5705
-- Accuracy: 0.84
+- Loss: 0.5801
+- Accuracy: 0.85
 
 ## Model description
 
@@ -52,30 +52,31 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 4.5e-05
+- learning_rate: 5e-05
 - train_batch_size: 8
 - eval_batch_size: 8
 - 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: 10
+- num_epochs: 11
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 2.0426        | 1.0   | 113  | 1.8813          | 0.46     |
-| 1.4432        | 2.0   | 226  | 1.2642          | 0.65     |
-| 1.0809        | 3.0   | 339  | 1.0160          | 0.71     |
-| 0.8867        | 4.0   | 452  | 0.9041          | 0.7      |
-| 0.614         | 5.0   | 565  | 0.7198          | 0.8      |
-| 0.4407        | 6.0   | 678  | 0.7244          | 0.78     |
-| 0.5076        | 7.0   | 791  | 0.6025          | 0.83     |
-| 0.2599        | 8.0   | 904  | 0.5808          | 0.86     |
-| 0.2674        | 9.0   | 1017 | 0.5695          | 0.84     |
-| 0.1853        | 10.0  | 1130 | 0.5705          | 0.84     |
+| 2.0115        | 1.0   | 113  | 1.8258          | 0.5      |
+| 1.3108        | 2.0   | 226  | 1.1814          | 0.64     |
+| 1.0318        | 3.0   | 339  | 0.9287          | 0.75     |
+| 0.8711        | 4.0   | 452  | 0.8692          | 0.74     |
+| 0.5744        | 5.0   | 565  | 0.6895          | 0.79     |
+| 0.3243        | 6.0   | 678  | 0.6500          | 0.78     |
+| 0.3846        | 7.0   | 791  | 0.5873          | 0.81     |
+| 0.1419        | 8.0   | 904  | 0.5719          | 0.83     |
+| 0.2204        | 9.0   | 1017 | 0.5105          | 0.83     |
+| 0.054         | 10.0  | 1130 | 0.6217          | 0.85     |
+| 0.035         | 11.0  | 1243 | 0.5801          | 0.85     |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe196014cf9ea7e9cb1aba2dc0abd573a95e47da44d89ff37fe40620a548b672
+oid sha256:bcaaf559293beff86534c8839018ceb263bd2583116a0cc7e1d5dea254ea8b99
 size 94771728