update model card README.md

README.md

@@ -1,6 +1,6 @@
 ---
 license: apache-2.0
-base_model: ntu-spml/distilhubert
+base_model: NicolasDenier/distilhubert-finetuned-gtzan
 tags:
 - generated_from_trainer
 datasets:
@@ -30,9 +30,9 @@ 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 [NicolasDenier/distilhubert-finetuned-gtzan](https://huggingface.co/NicolasDenier/distilhubert-finetuned-gtzan) on the GTZAN dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.5415
+- Loss: 0.6529
 - Accuracy: 0.85
 
 ## Model description
@@ -53,28 +53,25 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 5e-05
-- train_batch_size: 8
-- eval_batch_size: 8
+- train_batch_size: 2
+- eval_batch_size: 2
 - seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 8
 - 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: 5
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 2.0328        | 1.0   | 113  | 1.8396          | 0.43     |
-| 1.2922        | 2.0   | 226  | 1.1828          | 0.65     |
-| 1.0338        | 3.0   | 339  | 0.8719          | 0.8      |
-| 0.8669        | 4.0   | 452  | 0.8398          | 0.71     |
-| 0.4825        | 5.0   | 565  | 0.6409          | 0.83     |
-| 0.3995        | 6.0   | 678  | 0.6009          | 0.82     |
-| 0.4146        | 7.0   | 791  | 0.5531          | 0.81     |
-| 0.1697        | 8.0   | 904  | 0.5346          | 0.84     |
-| 0.2216        | 9.0   | 1017 | 0.5411          | 0.85     |
-| 0.1152        | 10.0  | 1130 | 0.5415          | 0.85     |
+| 0.6294        | 1.0   | 224  | 0.6803          | 0.85     |
+| 0.4995        | 2.0   | 449  | 0.6409          | 0.87     |
+| 0.3727        | 3.0   | 674  | 0.5873          | 0.87     |
+| 0.1291        | 4.0   | 899  | 0.6303          | 0.86     |
+| 0.0569        | 4.98  | 1120 | 0.6529          | 0.85     |
 
 
 ### Framework versions