Hugging Face's logo

NicolasDenier
/
distilhubert-finetuned-gtzan

Audio Classification
Transformers
PyTorch
TensorBoard
hubert
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
1
NicolasDenier commited on
Commit
5538812
•
1 Parent(s): 4e9b182

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +22 -19
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
- value: 0.78
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
- - Loss: 0.7136
36
- - Accuracy: 0.78
37
 
38
  ## Model description
39
 
@@ -61,27 +61,30 @@ The following hyperparameters were used during training:
61
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
62
  - lr_scheduler_type: linear
63
  - lr_scheduler_warmup_ratio: 0.1
64
- - num_epochs: 15
65
 
66
  ### Training results
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
- | 2.1794 | 1.0 | 112 | 2.1111 | 0.29 |
71
- | 1.8527 | 2.0 | 225 | 1.7586 | 0.33 |
72
- | 1.4409 | 3.0 | 337 | 1.4728 | 0.48 |
73
- | 1.4484 | 4.0 | 450 | 1.3092 | 0.59 |
74
- | 1.409 | 5.0 | 562 | 1.1073 | 0.68 |
75
- | 1.0274 | 6.0 | 675 | 1.1107 | 0.67 |
76
- | 1.0141 | 7.0 | 787 | 0.9898 | 0.7 |
77
- | 0.8946 | 8.0 | 900 | 0.9540 | 0.68 |
78
- | 1.0337 | 9.0 | 1012 | 0.8722 | 0.72 |
79
- | 0.8065 | 10.0 | 1125 | 0.8196 | 0.74 |
80
- | 1.0335 | 11.0 | 1237 | 0.7891 | 0.75 |
81
- | 0.7712 | 12.0 | 1350 | 0.7298 | 0.78 |
82
- | 0.7041 | 13.0 | 1462 | 0.7240 | 0.8 |
83
- | 0.7287 | 14.0 | 1575 | 0.7206 | 0.78 |
84
- | 0.9821 | 14.93 | 1680 | 0.7136 | 0.78 |
 
 
 
85
 
86
 
87
  ### Framework versions
 
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
+ value: 0.91
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
+ - Loss: 0.3539
36
+ - Accuracy: 0.91
37
 
38
  ## Model description
39
 
 
61
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
62
  - lr_scheduler_type: linear
63
  - lr_scheduler_warmup_ratio: 0.1
64
+ - num_epochs: 18
65
 
66
  ### Training results
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
+ | 2.2281 | 1.0 | 112 | 2.1128 | 0.26 |
71
+ | 1.7082 | 2.0 | 225 | 1.6252 | 0.52 |
72
+ | 1.267 | 3.0 | 337 | 1.3100 | 0.54 |
73
+ | 1.1791 | 4.0 | 450 | 1.0496 | 0.71 |
74
+ | 1.1765 | 5.0 | 562 | 0.8928 | 0.74 |
75
+ | 0.5714 | 6.0 | 675 | 0.8298 | 0.77 |
76
+ | 0.4869 | 7.0 | 787 | 0.7145 | 0.79 |
77
+ | 0.4967 | 8.0 | 900 | 0.6990 | 0.82 |
78
+ | 0.8314 | 9.0 | 1012 | 0.5657 | 0.83 |
79
+ | 0.4633 | 10.0 | 1125 | 0.4589 | 0.89 |
80
+ | 0.5547 | 11.0 | 1237 | 0.4919 | 0.86 |
81
+ | 0.4827 | 12.0 | 1350 | 0.4069 | 0.92 |
82
+ | 0.324 | 13.0 | 1462 | 0.4634 | 0.87 |
83
+ | 0.5224 | 14.0 | 1575 | 0.4419 | 0.86 |
84
+ | 0.1873 | 15.0 | 1687 | 0.3988 | 0.89 |
85
+ | 0.2852 | 16.0 | 1800 | 0.3788 | 0.9 |
86
+ | 0.3169 | 17.0 | 1912 | 0.3526 | 0.89 |
87
+ | 0.4491 | 17.92 | 2016 | 0.3539 | 0.91 |
88
 
89
 
90
  ### Framework versions