End of training

README.md

@@ -0,0 +1,86 @@
+---
+license: apache-2.0
+base_model: ntu-spml/distilhubert
+tags:
+- generated_from_trainer
+datasets:
+- wangyuhao/gtzan
+metrics:
+- accuracy
+model-index:
+- name: distilhubert-finetuned-gtzan
+  results:
+  - task:
+      name: Audio Classification
+      type: audio-classification
+    dataset:
+      name: GTZAN
+      type: wangyuhao/gtzan
+      config: all
+      split: train
+      args: all
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.81
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# distilhubert-finetuned-gtzan
+
+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: 0.6267
+- Accuracy: 0.81
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- 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
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 1.9327        | 1.0   | 113  | 1.8862          | 0.54     |
+| 1.2718        | 2.0   | 226  | 1.3561          | 0.59     |
+| 1.0819        | 3.0   | 339  | 0.9499          | 0.75     |
+| 0.6249        | 4.0   | 452  | 0.9274          | 0.69     |
+| 0.5024        | 5.0   | 565  | 0.6737          | 0.8      |
+| 0.3257        | 6.0   | 678  | 0.5909          | 0.82     |
+| 0.3394        | 7.0   | 791  | 0.6002          | 0.82     |
+| 0.1471        | 8.0   | 904  | 0.6238          | 0.81     |
+| 0.1124        | 9.0   | 1017 | 0.6223          | 0.82     |
+| 0.0898        | 10.0  | 1130 | 0.6267          | 0.81     |
+
+
+### Framework versions
+
+- Transformers 4.38.2
+- Pytorch 2.2.1+cu121
+- Datasets 2.18.0
+- Tokenizers 0.15.2

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f7ceb9e4c674f552b04c20c19097fa4e1f4d0822360de6e3c2a205f7d4a7093
+oid sha256:7b2116952a3d83561ff3736ccaab4d73f522c27d6687c06e87812647fa9f70fc
 size 94771728

runs/Apr04_22-03-50_dd82ee5c072c/events.out.tfevents.1712268241.dd82ee5c072c.5461.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b93640b1469985946ab2f24463d53f9eabcb917e4bb88168e4ffb8a93f36f980
-size 56593
+oid sha256:7fb563ac8893c5076649ac65990566774bae5e29efa4feafae11ddac08bd836c
+size 56947