End of training

README.md

@@ -0,0 +1,88 @@
+---
+license: apache-2.0
+base_model: ntu-spml/distilhubert
+tags:
+- generated_from_trainer
+datasets:
+- marsyas/gtzan
+metrics:
+- accuracy
+model-index:
+- name: distilhubert-finetuned-gtzan
+  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: 0.88
+---
+
+<!-- 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: 0.5008
+- Accuracy: 0.88
+
+## 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: 3e-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: 12
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 2.1457        | 1.0   | 113  | 2.0729          | 0.51     |
+| 1.5675        | 2.0   | 226  | 1.5158          | 0.59     |
+| 1.2498        | 3.0   | 339  | 1.2242          | 0.67     |
+| 1.1526        | 4.0   | 452  | 1.0223          | 0.72     |
+| 0.8489        | 5.0   | 565  | 0.8472          | 0.77     |
+| 0.8115        | 6.0   | 678  | 0.7177          | 0.82     |
+| 0.6554        | 7.0   | 791  | 0.6736          | 0.83     |
+| 0.45          | 8.0   | 904  | 0.5767          | 0.88     |
+| 0.4059        | 9.0   | 1017 | 0.5429          | 0.88     |
+| 0.3081        | 10.0  | 1130 | 0.5187          | 0.88     |
+| 0.3331        | 11.0  | 1243 | 0.5111          | 0.86     |
+| 0.2877        | 12.0  | 1356 | 0.5008          | 0.88     |
+
+
+### Framework versions
+
+- Transformers 4.36.2
+- Pytorch 2.1.0+cu121
+- Datasets 2.15.0
+- Tokenizers 0.15.0

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7246ea0e8e3d3a91a1405568b07070230f18a344d74d4ca43f0dd294fe2b44a1
+oid sha256:b3c8be56214377969819edc69c87efd6673f2bc78ce10ebf9b56fc45a5d74071
 size 94771728