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: 0.85
 ---
 
 <!-- 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 [ntu-spml/distilhubert](https://huggingface.co/ntu-spml/distilhubert) on the GTZAN dataset.
 It achieves the following results on the evaluation set:
-- eval_loss: 0.7385
-- eval_accuracy: 0.88
-- eval_runtime: 52.8209
-- eval_samples_per_second: 1.893
-- eval_steps_per_second: 0.473
-- epoch: 7.0
-- step: 1575
+- Loss: 0.7283
+- Accuracy: 0.85
 
 ## Model description
 
@@ -46,11 +56,29 @@ The following hyperparameters were used during training:
 - train_batch_size: 4
 - eval_batch_size: 4
 - seed: 42
+- gradient_accumulation_steps: 2
+- 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: 10
 
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 1.8021        | 1.0   | 112  | 1.6488          | 0.43     |
+| 1.0861        | 2.0   | 225  | 1.0086          | 0.67     |
+| 0.6939        | 3.0   | 337  | 0.7443          | 0.74     |
+| 0.5646        | 4.0   | 450  | 0.8549          | 0.74     |
+| 0.3003        | 5.0   | 562  | 0.7615          | 0.78     |
+| 0.0586        | 6.0   | 675  | 0.7139          | 0.82     |
+| 0.1372        | 7.0   | 787  | 0.7026          | 0.81     |
+| 0.0961        | 8.0   | 900  | 0.8469          | 0.83     |
+| 0.0118        | 9.0   | 1012 | 0.6534          | 0.85     |
+| 0.0742        | 9.96  | 1120 | 0.7283          | 0.85     |
+
+
 ### Framework versions
 
 - Transformers 4.33.0.dev0

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d2dbc5a70f0807f53a465fe9543101bfd4861b2e63af2a91eec1c50761142c3
+oid sha256:4bba85f11bf8bfe866d1ae76bd634389e4b7206fc4ff475ec07df73fa1c947d0
 size 94783376