update model card README.md

README.md

@@ -18,8 +18,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [NemesisAlm/distilhubert-finetuned-gtzan](https://huggingface.co/NemesisAlm/distilhubert-finetuned-gtzan) on the GTZAN dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.8475
-- Accuracy: 0.74
+- Loss: 2.1781
+- Accuracy: 0.79
 
 ## Model description
 
@@ -42,19 +42,23 @@ The following hyperparameters were used during training:
 - train_batch_size: 2
 - eval_batch_size: 2
 - seed: 42
-- gradient_accumulation_steps: 2
-- total_train_batch_size: 4
+- 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: 1
+- num_epochs: 5
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 0.0012        | 1.0   | 225  | 1.8475          | 0.74     |
+| 0.132         | 1.0   | 112  | 2.0618          | 0.75     |
+| 0.0004        | 2.0   | 225  | 2.5336          | 0.73     |
+| 0.0001        | 3.0   | 337  | 2.0191          | 0.78     |
+| 0.0001        | 4.0   | 450  | 2.0529          | 0.79     |
+| 0.0           | 4.98  | 560  | 2.1781          | 0.79     |
 
 
 ### Framework versions