End of training

README.md

@@ -0,0 +1,96 @@
+---
+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: 0.84
+---
+
+<!-- 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: 0.8931
+- Accuracy: 0.84
+
+## 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: cosine
+- lr_scheduler_warmup_ratio: 0.05
+- num_epochs: 20
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 1.9292        | 1.0   | 113  | 1.8783          | 0.49     |
+| 1.1771        | 2.0   | 226  | 1.2910          | 0.64     |
+| 0.9343        | 3.0   | 339  | 1.0554          | 0.67     |
+| 0.5929        | 4.0   | 452  | 0.8423          | 0.75     |
+| 0.5678        | 5.0   | 565  | 0.7333          | 0.78     |
+| 0.2351        | 6.0   | 678  | 0.6266          | 0.84     |
+| 0.2348        | 7.0   | 791  | 0.6047          | 0.81     |
+| 0.0834        | 8.0   | 904  | 0.7525          | 0.82     |
+| 0.0374        | 9.0   | 1017 | 0.8083          | 0.82     |
+| 0.0089        | 10.0  | 1130 | 0.7745          | 0.83     |
+| 0.0068        | 11.0  | 1243 | 0.7883          | 0.85     |
+| 0.0046        | 12.0  | 1356 | 0.8266          | 0.84     |
+| 0.004         | 13.0  | 1469 | 0.8557          | 0.84     |
+| 0.0038        | 14.0  | 1582 | 0.9485          | 0.83     |
+| 0.0031        | 15.0  | 1695 | 0.9042          | 0.84     |
+| 0.0031        | 16.0  | 1808 | 0.8945          | 0.84     |
+| 0.0031        | 17.0  | 1921 | 0.8780          | 0.84     |
+| 0.0026        | 18.0  | 2034 | 0.9071          | 0.84     |
+| 0.0027        | 19.0  | 2147 | 0.8932          | 0.84     |
+| 0.0027        | 20.0  | 2260 | 0.8931          | 0.84     |
+
+
+### Framework versions
+
+- Transformers 4.42.4
+- Pytorch 2.4.0+cu121
+- Datasets 2.21.0
+- Tokenizers 0.19.1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01a3519fd851db3179ff6d38803f486bf575e4a8fde5c98e58201af950f0dd1e
+oid sha256:b2701bda6c758816f16daccfb6a39b90ba252923d92ec9c93cfe9958c572f9bc
 size 94771728

runs/Sep04_09-03-47_de5ed1468100/events.out.tfevents.1725440865.de5ed1468100.480.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7645798b81b461d557c6f6fd098e252fa832c7ed283c8688f2286ff498144cd7
-size 107459
+oid sha256:dd810ecc34707bb4068c508324b1b77aed60015f3743b4921cb4a3a31b77bc75
+size 108136