End of training

README.md

@@ -23,7 +23,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.83
+      value: 0.8
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -33,8 +33,8 @@ 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: 0.5416
-- Accuracy: 0.83
+- Loss: 0.7223
+- Accuracy: 0.8
 
 ## Model description
 
@@ -58,8 +58,8 @@ The following hyperparameters were used during training:
 - eval_batch_size: 8
 - seed: 42
 - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
-- lr_scheduler_type: cosine
-- lr_scheduler_warmup_ratio: 0.3
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.1
 - num_epochs: 10
 - mixed_precision_training: Native AMP
 
@@ -67,16 +67,16 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 2.217         | 1.0   | 113  | 2.1703          | 0.41     |
-| 1.6344        | 2.0   | 226  | 1.6105          | 0.65     |
-| 1.2861        | 3.0   | 339  | 1.1849          | 0.71     |
-| 0.8584        | 4.0   | 452  | 0.8745          | 0.71     |
-| 0.6935        | 5.0   | 565  | 0.7215          | 0.84     |
-| 0.4175        | 6.0   | 678  | 0.6174          | 0.8      |
-| 0.3046        | 7.0   | 791  | 0.5329          | 0.85     |
-| 0.121         | 8.0   | 904  | 0.5489          | 0.82     |
-| 0.1203        | 9.0   | 1017 | 0.5513          | 0.83     |
-| 0.0848        | 10.0  | 1130 | 0.5416          | 0.83     |
+| 1.9299        | 1.0   | 113  | 1.8406          | 0.51     |
+| 1.2175        | 2.0   | 226  | 1.2275          | 0.69     |
+| 1.025         | 3.0   | 339  | 0.9661          | 0.74     |
+| 0.7036        | 4.0   | 452  | 0.8200          | 0.77     |
+| 0.4876        | 5.0   | 565  | 0.7143          | 0.78     |
+| 0.4354        | 6.0   | 678  | 0.6871          | 0.79     |
+| 0.3558        | 7.0   | 791  | 0.7239          | 0.78     |
+| 0.1509        | 8.0   | 904  | 0.6783          | 0.8      |
+| 0.1775        | 9.0   | 1017 | 0.6948          | 0.83     |
+| 0.1069        | 10.0  | 1130 | 0.7223          | 0.8      |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74441050ec69fdab78457bfaa3baabb158b5305fff9deaf31e60125c3048d2fc
+oid sha256:628fc83d7b9139d4488ff222b54867b4325980001b9e0a9b406b1df1df666585
 size 94771728