End of training

README.md

@@ -5,9 +5,24 @@ tags:
 - generated_from_trainer
 datasets:
 - marsyas/gtzan
+metrics:
+- accuracy
 model-index:
 - name: distilhubert-finetuned-gtzan
-  results: []
+  results:
+  - task:
+      name: Audio Classification
+      type: audio-classification
+    dataset:
+      name: GTZAN
+      type: marsyas/gtzan
+      config: all
+      split: train
+      args: all
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.84
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -17,13 +32,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [arshsin/distilhubert-finetuned-gtzan](https://huggingface.co/arshsin/distilhubert-finetuned-gtzan) on the GTZAN dataset.
 It achieves the following results on the evaluation set:
-- eval_loss: 1.3357
-- eval_accuracy: 0.84
-- eval_runtime: 72.1033
-- eval_samples_per_second: 1.387
-- eval_steps_per_second: 0.236
-- epoch: 3.97
-- step: 85
+- Loss: 1.6457
+- Accuracy: 0.84
 
 ## Model description
 
@@ -42,18 +52,39 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 4e-05
-- train_batch_size: 6
-- eval_batch_size: 6
+- learning_rate: 5e-06
+- train_batch_size: 8
+- eval_batch_size: 8
 - seed: 42
-- gradient_accumulation_steps: 7
-- total_train_batch_size: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 16
 - 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: 15
 - mixed_precision_training: Native AMP
 
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 0.0001        | 0.99  | 56   | 1.4113          | 0.84     |
+| 0.0001        | 2.0   | 113  | 1.4248          | 0.84     |
+| 0.0001        | 2.99  | 169  | 1.4818          | 0.83     |
+| 0.0001        | 4.0   | 226  | 1.5228          | 0.83     |
+| 0.0001        | 4.99  | 282  | 1.5067          | 0.84     |
+| 0.0032        | 6.0   | 339  | 1.5205          | 0.84     |
+| 0.0           | 6.99  | 395  | 1.5488          | 0.84     |
+| 0.0           | 8.0   | 452  | 1.5890          | 0.84     |
+| 0.0           | 8.99  | 508  | 1.6020          | 0.83     |
+| 0.0117        | 10.0  | 565  | 1.5945          | 0.84     |
+| 0.0           | 10.99 | 621  | 1.6145          | 0.84     |
+| 0.0           | 12.0  | 678  | 1.6370          | 0.83     |
+| 0.0           | 12.99 | 734  | 1.6396          | 0.84     |
+| 0.0           | 14.0  | 791  | 1.6458          | 0.83     |
+| 0.0           | 14.87 | 840  | 1.6457          | 0.84     |
+
+
 ### Framework versions
 
 - Transformers 4.35.2

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a5cd16d9add4799b6f19e8b925b13c633e83530b2858e40e771e29e5ab6a09d
+oid sha256:a50a5706584034bdba8fc9351590d325248fe96148f63159ff7737756df0df2d
 size 94771728