End of training

README.md

@@ -1,6 +1,6 @@
 ---
 license: apache-2.0
-base_model: vpingale07/distilhubert-v2
+base_model: vpingale07/distilhubert-v2-v3
 tags:
 - generated_from_trainer
 datasets:
@@ -22,7 +22,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.76
+      value: 0.785
 ---
 
 <!-- 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. -->
 
 # vpingale07/distilhubert-v2-finetuned-gtzan
 
-This model is a fine-tuned version of [vpingale07/distilhubert-v2](https://huggingface.co/vpingale07/distilhubert-v2) on the GTZAN dataset.
+This model is a fine-tuned version of [vpingale07/distilhubert-v2-v3](https://huggingface.co/vpingale07/distilhubert-v2-v3) on the GTZAN dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.7594
-- Accuracy: 0.76
+- Loss: 1.0276
+- Accuracy: 0.785
 
 ## Model description
 
@@ -59,17 +59,21 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.1
-- num_epochs: 4
+- num_epochs: 8
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 0.844         | 1.0   | 100  | 1.0321          | 0.665    |
-| 0.577         | 2.0   | 200  | 0.9200          | 0.72     |
-| 0.3848        | 3.0   | 300  | 0.8345          | 0.74     |
-| 0.2614        | 4.0   | 400  | 0.7594          | 0.76     |
+| 0.4443        | 1.0   | 100  | 0.7764          | 0.745    |
+| 0.2265        | 2.0   | 200  | 0.8049          | 0.77     |
+| 0.0928        | 3.0   | 300  | 0.9190          | 0.74     |
+| 0.0661        | 4.0   | 400  | 0.9776          | 0.765    |
+| 0.0095        | 5.0   | 500  | 1.0018          | 0.76     |
+| 0.0069        | 6.0   | 600  | 0.9838          | 0.79     |
+| 0.0046        | 7.0   | 700  | 1.0447          | 0.78     |
+| 0.0041        | 8.0   | 800  | 1.0276          | 0.785    |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5d1a3a7bfeace4889c38cba9c11023a84dff70c0a1568b3001356e437e7cc11
+oid sha256:dd410c7dfe5356ecfdb5cdeba6e23602fa7aa831b6b4b74b2431bf538ecdc7fe
 size 94771728