Hugging Face's logo

adavirro
/
distilhubert-finetuned-gtzan

Audio Classification
Transformers
PyTorch
TensorBoard
hubert
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
adavirro commited on
Commit
0f76d08
•
1 Parent(s): a70f28a

End of training

Browse files
Files changed (2) hide show
  1. README.md +93 -2
  2. pytorch_model.bin +1 -1
README.md CHANGED
@@ -1,4 +1,95 @@
1
- DistilHubert fine-tuned on gtzan dataset as part of HF Audio Course:
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2
 
3
- https://huggingface.co/learn/audio-course/chapter4/fine-tuning
 
4
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: ntu-spml/distilhubert
4
+ tags:
5
+ - generated_from_trainer
6
+ datasets:
7
+ - marsyas/gtzan
8
+ metrics:
9
+ - accuracy
10
+ model-index:
11
+ - name: distilhubert-finetuned-gtzan
12
+ results:
13
+ - task:
14
+ name: Audio Classification
15
+ type: audio-classification
16
+ dataset:
17
+ name: GTZAN
18
+ type: marsyas/gtzan
19
+ config: all
20
+ split: train
21
+ args: all
22
+ metrics:
23
+ - name: Accuracy
24
+ type: accuracy
25
+ value: 0.83
26
+ ---
27
 
28
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
29
+ should probably proofread and complete it, then remove this comment. -->
30
 
31
+ # distilhubert-finetuned-gtzan
32
+
33
+ This model is a fine-tuned version of [ntu-spml/distilhubert](https://huggingface.co/ntu-spml/distilhubert) on the GTZAN dataset.
34
+ It achieves the following results on the evaluation set:
35
+ - Loss: 1.1893
36
+ - Accuracy: 0.83
37
+
38
+ ## Model description
39
+
40
+ More information needed
41
+
42
+ ## Intended uses & limitations
43
+
44
+ More information needed
45
+
46
+ ## Training and evaluation data
47
+
48
+ More information needed
49
+
50
+ ## Training procedure
51
+
52
+ ### Training hyperparameters
53
+
54
+ The following hyperparameters were used during training:
55
+ - learning_rate: 5e-05
56
+ - train_batch_size: 4
57
+ - eval_batch_size: 4
58
+ - seed: 42
59
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
60
+ - lr_scheduler_type: linear
61
+ - lr_scheduler_warmup_ratio: 0.1
62
+ - num_epochs: 20
63
+
64
+ ### Training results
65
+
66
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
67
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
68
+ | 1.9486 | 1.0 | 225 | 1.8744 | 0.54 |
69
+ | 1.0616 | 2.0 | 450 | 1.2196 | 0.66 |
70
+ | 1.0193 | 3.0 | 675 | 0.7841 | 0.78 |
71
+ | 0.81 | 4.0 | 900 | 0.7212 | 0.8 |
72
+ | 0.2171 | 5.0 | 1125 | 0.7194 | 0.77 |
73
+ | 0.0458 | 6.0 | 1350 | 0.8966 | 0.81 |
74
+ | 0.3485 | 7.0 | 1575 | 0.7960 | 0.81 |
75
+ | 0.09 | 8.0 | 1800 | 1.0860 | 0.82 |
76
+ | 0.0031 | 9.0 | 2025 | 0.7744 | 0.84 |
77
+ | 0.0026 | 10.0 | 2250 | 0.8249 | 0.87 |
78
+ | 0.0032 | 11.0 | 2475 | 1.0680 | 0.84 |
79
+ | 0.0012 | 12.0 | 2700 | 1.0724 | 0.83 |
80
+ | 0.0011 | 13.0 | 2925 | 1.1407 | 0.83 |
81
+ | 0.0009 | 14.0 | 3150 | 1.0395 | 0.85 |
82
+ | 0.0007 | 15.0 | 3375 | 1.2991 | 0.83 |
83
+ | 0.0006 | 16.0 | 3600 | 1.1403 | 0.83 |
84
+ | 0.0007 | 17.0 | 3825 | 1.0837 | 0.83 |
85
+ | 0.0005 | 18.0 | 4050 | 1.1463 | 0.83 |
86
+ | 0.0005 | 19.0 | 4275 | 1.1987 | 0.83 |
87
+ | 0.0005 | 20.0 | 4500 | 1.1893 | 0.83 |
88
+
89
+
90
+ ### Framework versions
91
+
92
+ - Transformers 4.33.0.dev0
93
+ - Pytorch 2.0.1+cu118
94
+ - Datasets 2.14.4.dev0
95
+ - Tokenizers 0.13.3
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cb993185254e23ecdf49c694b8766ba64a1500dc043547a744b35ecaeb8e57eb
3
  size 94783376
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eca23a84ba6eaf03529ea1059b492fd0b24dccb58cf99b0b34fc445aabb852e7
3
  size 94783376