End of training

README.md

@@ -0,0 +1,90 @@
+---
+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: 0.79
+---
+
+<!-- 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: 0.6681
+- Accuracy: 0.79
+
+## 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: 15
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 2.217         | 1.0   | 113  | 2.1052          | 0.56     |
+| 1.6052        | 2.0   | 226  | 1.5168          | 0.64     |
+| 1.3013        | 3.0   | 339  | 1.1829          | 0.72     |
+| 1.0992        | 4.0   | 452  | 1.0341          | 0.71     |
+| 0.8897        | 5.0   | 565  | 0.9080          | 0.72     |
+| 0.5886        | 6.0   | 678  | 0.8139          | 0.75     |
+| 0.6883        | 7.0   | 791  | 0.6996          | 0.8      |
+| 0.3935        | 8.0   | 904  | 0.6771          | 0.78     |
+| 0.4424        | 9.0   | 1017 | 0.6573          | 0.82     |
+| 0.2705        | 10.0  | 1130 | 0.6986          | 0.79     |
+| 0.1556        | 11.0  | 1243 | 0.6894          | 0.79     |
+| 0.136         | 12.0  | 1356 | 0.6990          | 0.81     |
+| 0.1151        | 13.0  | 1469 | 0.6639          | 0.81     |
+| 0.1337        | 14.0  | 1582 | 0.6649          | 0.81     |
+| 0.1949        | 15.0  | 1695 | 0.6681          | 0.79     |
+
+
+### Framework versions
+
+- Transformers 4.34.0
+- Pytorch 2.0.1+cu118
+- Datasets 2.14.5
+- Tokenizers 0.14.0

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:123262a32135aadd92a0c3bf8864c4eb758db3af0ce72a2f34d0dcd6a7a4db97
+oid sha256:b9e5af01678e43e2aac2f76cb5326b86fd31e1381c8f147f49c2203c8751832a
 size 94783376