End of training

README.md

@@ -23,7 +23,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.5
+      value: 0.83
 ---
 
 <!-- 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: 1.9885
-- Accuracy: 0.5
+- Loss: 0.5708
+- Accuracy: 0.83
 
 ## Model description
 
@@ -57,20 +57,26 @@ The following hyperparameters were used during training:
 - train_batch_size: 12
 - eval_batch_size: 12
 - seed: 42
-- gradient_accumulation_steps: 3
-- total_train_batch_size: 36
 - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.1
-- num_epochs: 2
+- num_epochs: 10
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 6.606         | 1.0   | 25   | 2.1162          | 0.41     |
-| 6.0846        | 2.0   | 50   | 1.9885          | 0.5      |
+| 2.0536        | 1.0   | 75   | 1.9482          | 0.35     |
+| 1.4103        | 2.0   | 150  | 1.4342          | 0.63     |
+| 1.1862        | 3.0   | 225  | 1.1184          | 0.7      |
+| 0.8092        | 4.0   | 300  | 0.9554          | 0.73     |
+| 0.5852        | 5.0   | 375  | 0.7298          | 0.84     |
+| 0.5186        | 6.0   | 450  | 0.6516          | 0.83     |
+| 0.4123        | 7.0   | 525  | 0.6696          | 0.79     |
+| 0.3285        | 8.0   | 600  | 0.5844          | 0.86     |
+| 0.328         | 9.0   | 675  | 0.6136          | 0.83     |
+| 0.2715        | 10.0  | 750  | 0.5708          | 0.83     |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:634927df7fe2bcea87b457507bf205828514a28cd3b616debdd7d0f57506f7bd
+oid sha256:66c54911ddfada5d59ba310263097ce3f5588d8ad3292c90c24971c349f2972d
 size 94771728