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: 0.82
+---
+
+<!-- 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: 1.0171
+- Accuracy: 0.82
+
+## 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: 15
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 2.1164        | 1.0   | 113  | 2.0148          | 0.45     |
+| 1.3653        | 2.0   | 226  | 1.3290          | 0.64     |
+| 1.1139        | 3.0   | 339  | 1.0579          | 0.71     |
+| 1.0451        | 4.0   | 452  | 1.0425          | 0.72     |
+| 0.5678        | 5.0   | 565  | 0.8254          | 0.76     |
+| 0.3324        | 6.0   | 678  | 0.7542          | 0.81     |
+| 0.4072        | 7.0   | 791  | 0.6650          | 0.81     |
+| 0.0858        | 8.0   | 904  | 0.8092          | 0.79     |
+| 0.2328        | 9.0   | 1017 | 0.8203          | 0.8      |
+| 0.0331        | 10.0  | 1130 | 0.9223          | 0.83     |
+| 0.0129        | 11.0  | 1243 | 0.9507          | 0.84     |
+| 0.1248        | 12.0  | 1356 | 0.9733          | 0.83     |
+| 0.0087        | 13.0  | 1469 | 1.0091          | 0.82     |
+| 0.0677        | 14.0  | 1582 | 1.0063          | 0.82     |
+| 0.008         | 15.0  | 1695 | 1.0171          | 0.82     |
+
+
+### Framework versions
+
+- Transformers 4.32.0
+- Pytorch 2.0.1+cu118
+- Datasets 2.14.4
+- Tokenizers 0.13.3

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d16e65f2137b63fb96fe34bdcc68475a02887bb7724e485ebb0ccddbb571407
+oid sha256:3c52b028272d19b60aafd8fa85c5589e33d37c38775bd507ca9f9653a59a1ad2
 size 94783376