Hugging Face's logo

wilson-wei
/
distilhubert-finetuned-gtzan

Audio Classification
Transformers
PyTorch
hubert
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
wilson-wei commited on
Commit
42e546b
•
1 Parent(s): 8e9e479

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +26 -19
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
- value: 0.86
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -32,8 +32,8 @@ should probably proofread and complete it, then remove this comment. -->
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
- - Accuracy: 0.86
36
- - Loss: 0.7644
37
 
38
  ## Model description
39
 
@@ -59,27 +59,34 @@ The following hyperparameters were used during training:
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: 10
63
 
64
  ### Training results
65
 
66
  | Training Loss | Epoch | Step | Accuracy | Validation Loss |
67
  |:-------------:|:-----:|:----:|:--------:|:---------------:|
68
- | 2.1622 | 1.0 | 113 | 0.36 | 2.0289 |
69
- | 1.6015 | 2.0 | 226 | 0.59 | 1.4290 |
70
- | 1.1929 | 3.0 | 339 | 0.7 | 1.1003 |
71
- | 0.9015 | 4.0 | 452 | 0.76 | 0.8761 |
72
- | 0.7038 | 5.0 | 565 | 0.76 | 0.7516 |
73
- | 0.3261 | 6.0 | 678 | 0.77 | 0.7753 |
74
- | 0.5327 | 7.0 | 791 | 0.79 | 0.6131 |
75
- | 0.1239 | 8.0 | 904 | 0.8 | 0.6283 |
76
- | 0.1193 | 9.0 | 1017 | 0.85 | 0.5770 |
77
- | 0.1405 | 10.0 | 1130 | 0.8 | 0.7979 |
78
- | 0.0113 | 11.0 | 1243 | 0.81 | 0.7830 |
79
- | 0.1392 | 12.0 | 1356 | 0.85 | 0.7350 |
80
- | 0.0065 | 13.0 | 1469 | 0.82 | 0.7935 |
81
- | 0.0049 | 14.0 | 1582 | 0.84 | 0.8323 |
82
- | 0.0041 | 15.0 | 1695 | 0.86 | 0.7644 |
 
 
 
 
 
 
 
83
 
84
 
85
  ### Framework versions
 
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
+ value: 0.82
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
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
+ - Accuracy: 0.82
36
+ - Loss: 1.0803
37
 
38
  ## Model description
39
 
 
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 | Accuracy | Validation Loss |
67
  |:-------------:|:-----:|:----:|:--------:|:---------------:|
68
+ | 2.2295 | 1.0 | 113 | 0.4 | 2.1501 |
69
+ | 1.7373 | 2.0 | 226 | 0.6 | 1.6194 |
70
+ | 1.3497 | 3.0 | 339 | 0.72 | 1.1717 |
71
+ | 1.0135 | 4.0 | 452 | 0.71 | 1.0361 |
72
+ | 0.6951 | 5.0 | 565 | 0.77 | 0.7724 |
73
+ | 0.4279 | 6.0 | 678 | 0.76 | 0.7731 |
74
+ | 0.5178 | 7.0 | 791 | 0.82 | 0.6048 |
75
+ | 0.141 | 8.0 | 904 | 0.79 | 0.7486 |
76
+ | 0.2459 | 9.0 | 1017 | 0.85 | 0.6326 |
77
+ | 0.0331 | 10.0 | 1130 | 0.82 | 0.8706 |
78
+ | 0.0214 | 11.0 | 1243 | 0.81 | 1.0099 |
79
+ | 0.0744 | 12.0 | 1356 | 0.8 | 1.0210 |
80
+ | 0.0043 | 13.0 | 1469 | 0.82 | 0.9894 |
81
+ | 0.0032 | 14.0 | 1582 | 0.82 | 0.9803 |
82
+ | 0.0025 | 15.0 | 1695 | 0.83 | 1.0476 |
83
+ | 0.0021 | 16.0 | 1808 | 0.82 | 1.0483 |
84
+ | 0.0183 | 17.0 | 1921 | 0.87 | 0.9175 |
85
+ | 0.0017 | 18.0 | 2034 | 0.83 | 1.0867 |
86
+ | 0.0015 | 19.0 | 2147 | 0.82 | 1.1854 |
87
+ | 0.0014 | 20.0 | 2260 | 0.84 | 0.9784 |
88
+ | 0.0012 | 21.0 | 2373 | 0.82 | 1.0518 |
89
+ | 0.0011 | 22.0 | 2486 | 0.82 | 1.0803 |
90
 
91
 
92
  ### Framework versions