Hugging Face's logo

allispaul
/
hubert-base-ls960-finetuned-gtzan

Audio Classification
Transformers
PyTorch
TensorBoard
hubert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
allispaul commited on
Commit
e963ff8
•
1 Parent(s): 2adf5d4

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +97 -0
README.md ADDED
@@ -0,0 +1,97 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: facebook/hubert-base-ls960
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - accuracy
8
+ model-index:
9
+ - name: hubert-base-ls960-finetuned-gtzan
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ # hubert-base-ls960-finetuned-gtzan
17
+
18
+ This model is a fine-tuned version of [facebook/hubert-base-ls960](https://huggingface.co/facebook/hubert-base-ls960) on the None dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 1.1107
21
+ - Accuracy: 0.85
22
+
23
+ ## Model description
24
+
25
+ More information needed
26
+
27
+ ## Intended uses & limitations
28
+
29
+ More information needed
30
+
31
+ ## Training and evaluation data
32
+
33
+ More information needed
34
+
35
+ ## Training procedure
36
+
37
+ ### Training hyperparameters
38
+
39
+ The following hyperparameters were used during training:
40
+ - learning_rate: 5e-05
41
+ - train_batch_size: 4
42
+ - eval_batch_size: 4
43
+ - seed: 42
44
+ - gradient_accumulation_steps: 2
45
+ - total_train_batch_size: 8
46
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
+ - lr_scheduler_type: cosine
48
+ - lr_scheduler_warmup_ratio: 0.1
49
+ - num_epochs: 50
50
+
51
+ ### Training results
52
+
53
+ | Training Loss | Epoch | Step | Accuracy | Validation Loss |
54
+ |:-------------:|:-----:|:----:|:--------:|:---------------:|
55
+ | 1.9975 | 1.0 | 225 | 0.47 | 1.8130 |
56
+ | 1.2415 | 2.0 | 450 | 0.57 | 1.3022 |
57
+ | 1.0225 | 3.0 | 675 | 0.645 | 1.1478 |
58
+ | 1.1012 | 4.0 | 900 | 0.755 | 0.8725 |
59
+ | 1.0753 | 5.0 | 1125 | 0.67 | 1.1645 |
60
+ | 0.5354 | 6.0 | 1350 | 0.66 | 1.3094 |
61
+ | 0.7805 | 7.0 | 1575 | 0.795 | 0.8406 |
62
+ | 0.3307 | 8.0 | 1800 | 0.795 | 0.9782 |
63
+ | 0.1861 | 9.0 | 2025 | 0.79 | 0.9140 |
64
+ | 0.2776 | 10.0 | 2250 | 0.795 | 1.1711 |
65
+ | 0.314 | 11.0 | 2475 | 0.825 | 0.9193 |
66
+ | 0.1785 | 12.0 | 2700 | 0.82 | 1.0272 |
67
+ | 0.1444 | 13.0 | 2925 | 0.845 | 0.9903 |
68
+ | 0.0122 | 14.0 | 3150 | 0.835 | 0.9974 |
69
+ | 0.0116 | 15.0 | 3375 | 0.85 | 0.9670 |
70
+ | 0.3403 | 31.0 | 3472 | 1.0085 | 0.85 |
71
+ | 0.3596 | 32.0 | 3585 | 1.3101 | 0.81 |
72
+ | 0.0242 | 33.0 | 3697 | 0.9612 | 0.86 |
73
+ | 0.1006 | 34.0 | 3810 | 1.1904 | 0.82 |
74
+ | 0.1034 | 35.0 | 3922 | 0.9582 | 0.86 |
75
+ | 0.195 | 36.0 | 4035 | 1.0223 | 0.84 |
76
+ | 0.0081 | 37.0 | 4147 | 1.2461 | 0.8 |
77
+ | 0.006 | 38.0 | 4260 | 0.9541 | 0.87 |
78
+ | 0.281 | 39.0 | 4372 | 0.9340 | 0.87 |
79
+ | 0.0491 | 40.0 | 4485 | 1.0942 | 0.85 |
80
+ | 0.0537 | 41.0 | 4597 | 1.1521 | 0.85 |
81
+ | 0.0017 | 42.0 | 4710 | 1.1738 | 0.85 |
82
+ | 0.0031 | 43.0 | 4822 | 1.1584 | 0.85 |
83
+ | 0.1107 | 44.0 | 4935 | 1.1503 | 0.86 |
84
+ | 0.0032 | 45.0 | 5047 | 1.0710 | 0.87 |
85
+ | 0.0027 | 46.0 | 5160 | 1.1310 | 0.86 |
86
+ | 0.0013 | 47.0 | 5272 | 1.1194 | 0.86 |
87
+ | 0.0023 | 48.0 | 5385 | 1.1173 | 0.85 |
88
+ | 0.0286 | 49.0 | 5497 | 1.1087 | 0.85 |
89
+ | 0.0133 | 49.91 | 5600 | 1.1107 | 0.85 |
90
+
91
+
92
+ ### Framework versions
93
+
94
+ - Transformers 4.31.0
95
+ - Pytorch 2.0.1
96
+ - Datasets 2.15.0
97
+ - Tokenizers 0.13.2