Hugging Face's logo

bxleigh
/
distilhubert-finetuned-gtzan_v3

Audio Classification
Transformers
PyTorch
hubert
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
bxleigh commited on
Commit
ffde411
•
1 Parent(s): 5ed8d32

End of training

Browse files
Files changed (2) hide show
  1. README.md +59 -33
  2. pytorch_model.bin +1 -1
README.md CHANGED
@@ -8,7 +8,7 @@ datasets:
8
  metrics:
9
  - accuracy
10
  model-index:
11
- - name: distilhubert-finetuned-gtzan4
12
  results:
13
  - task:
14
  name: Audio Classification
@@ -22,18 +22,18 @@ 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
29
  should probably proofread and complete it, then remove this comment. -->
30
 
31
- # distilhubert-finetuned-gtzan4
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: 1.0945
36
- - Accuracy: 0.78
37
 
38
  ## Model description
39
 
@@ -52,7 +52,7 @@ More information needed
52
  ### Training hyperparameters
53
 
54
  The following hyperparameters were used during training:
55
- - learning_rate: 5e-05
56
  - train_batch_size: 6
57
  - eval_batch_size: 6
58
  - seed: 42
@@ -61,38 +61,64 @@ 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: 30
65
 
66
  ### Training results
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
- | No log | 0.85 | 4 | 2.2991 | 0.06 |
71
- | 2.2997 | 1.92 | 9 | 2.2668 | 0.28 |
72
- | 2.2819 | 2.99 | 14 | 2.1877 | 0.33 |
73
- | 2.2336 | 3.84 | 18 | 2.1023 | 0.47 |
74
- | 2.1493 | 4.91 | 23 | 1.9895 | 0.52 |
75
- | 2.0571 | 5.97 | 28 | 1.8745 | 0.51 |
76
- | 1.9341 | 6.83 | 32 | 1.7838 | 0.57 |
77
- | 1.8274 | 7.89 | 37 | 1.6784 | 0.64 |
78
- | 1.724 | 8.96 | 42 | 1.5859 | 0.66 |
79
- | 1.6407 | 9.81 | 46 | 1.5234 | 0.66 |
80
- | 1.5593 | 10.88 | 51 | 1.4508 | 0.7 |
81
- | 1.4735 | 11.95 | 56 | 1.3982 | 0.69 |
82
- | 1.4185 | 12.8 | 60 | 1.3501 | 0.72 |
83
- | 1.3613 | 13.87 | 65 | 1.3131 | 0.74 |
84
- | 1.3099 | 14.93 | 70 | 1.2742 | 0.72 |
85
- | 1.2762 | 16.0 | 75 | 1.2485 | 0.73 |
86
- | 1.2762 | 16.85 | 79 | 1.2102 | 0.74 |
87
- | 1.2379 | 17.92 | 84 | 1.1931 | 0.75 |
88
- | 1.193 | 18.99 | 89 | 1.1647 | 0.75 |
89
- | 1.1863 | 19.84 | 93 | 1.1488 | 0.77 |
90
- | 1.1435 | 20.91 | 98 | 1.1349 | 0.78 |
91
- | 1.1424 | 21.97 | 103 | 1.1166 | 0.79 |
92
- | 1.0961 | 22.83 | 107 | 1.1025 | 0.78 |
93
- | 1.0887 | 23.89 | 112 | 1.0993 | 0.78 |
94
- | 1.0977 | 24.96 | 117 | 1.0952 | 0.78 |
95
- | 1.0661 | 25.6 | 120 | 1.0945 | 0.78 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
96
 
97
 
98
  ### Framework versions
 
8
  metrics:
9
  - accuracy
10
  model-index:
11
+ - name: distilhubert-finetuned-gtzan7
12
  results:
13
  - task:
14
  name: Audio Classification
 
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
+ value: 0.85
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-gtzan7
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: 0.5569
36
+ - Accuracy: 0.85
37
 
38
  ## Model description
39
 
 
52
  ### Training hyperparameters
53
 
54
  The following hyperparameters were used during training:
55
+ - learning_rate: 8e-05
56
  - train_batch_size: 6
57
  - eval_batch_size: 6
58
  - seed: 42
 
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: 60
65
 
66
  ### Training results
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
+ | No log | 0.85 | 4 | 2.2836 | 0.14 |
71
+ | 2.2984 | 1.92 | 9 | 2.2574 | 0.18 |
72
+ | 2.2856 | 2.99 | 14 | 2.2060 | 0.32 |
73
+ | 2.2478 | 3.84 | 18 | 2.1331 | 0.37 |
74
+ | 2.1775 | 4.91 | 23 | 1.9859 | 0.47 |
75
+ | 2.0557 | 5.97 | 28 | 1.8086 | 0.52 |
76
+ | 1.8764 | 6.83 | 32 | 1.6783 | 0.53 |
77
+ | 1.7133 | 7.89 | 37 | 1.5235 | 0.54 |
78
+ | 1.5661 | 8.96 | 42 | 1.4048 | 0.58 |
79
+ | 1.4544 | 9.81 | 46 | 1.3279 | 0.6 |
80
+ | 1.3365 | 10.88 | 51 | 1.2591 | 0.67 |
81
+ | 1.2228 | 11.95 | 56 | 1.1587 | 0.7 |
82
+ | 1.1298 | 12.8 | 60 | 1.1476 | 0.68 |
83
+ | 1.0601 | 13.87 | 65 | 1.0066 | 0.77 |
84
+ | 0.9886 | 14.93 | 70 | 0.9855 | 0.76 |
85
+ | 0.923 | 16.0 | 75 | 0.9767 | 0.73 |
86
+ | 0.923 | 16.85 | 79 | 0.8896 | 0.79 |
87
+ | 0.8539 | 17.92 | 84 | 0.8421 | 0.78 |
88
+ | 0.788 | 18.99 | 89 | 0.8270 | 0.8 |
89
+ | 0.7253 | 19.84 | 93 | 0.7764 | 0.82 |
90
+ | 0.6523 | 20.91 | 98 | 0.6998 | 0.85 |
91
+ | 0.5853 | 21.97 | 103 | 0.6891 | 0.87 |
92
+ | 0.5372 | 22.83 | 107 | 0.7106 | 0.8 |
93
+ | 0.4815 | 23.89 | 112 | 0.6542 | 0.82 |
94
+ | 0.4461 | 24.96 | 117 | 0.6136 | 0.87 |
95
+ | 0.3841 | 25.81 | 121 | 0.6338 | 0.81 |
96
+ | 0.3505 | 26.88 | 126 | 0.6082 | 0.87 |
97
+ | 0.3143 | 27.95 | 131 | 0.5776 | 0.88 |
98
+ | 0.2913 | 28.8 | 135 | 0.5833 | 0.86 |
99
+ | 0.2519 | 29.87 | 140 | 0.5543 | 0.89 |
100
+ | 0.2234 | 30.93 | 145 | 0.5606 | 0.84 |
101
+ | 0.1994 | 32.0 | 150 | 0.5726 | 0.86 |
102
+ | 0.1994 | 32.85 | 154 | 0.5391 | 0.86 |
103
+ | 0.1789 | 33.92 | 159 | 0.5908 | 0.83 |
104
+ | 0.1615 | 34.99 | 164 | 0.5498 | 0.85 |
105
+ | 0.1444 | 35.84 | 168 | 0.5389 | 0.85 |
106
+ | 0.1303 | 36.91 | 173 | 0.5829 | 0.84 |
107
+ | 0.1192 | 37.97 | 178 | 0.5278 | 0.87 |
108
+ | 0.1074 | 38.83 | 182 | 0.6011 | 0.83 |
109
+ | 0.1001 | 39.89 | 187 | 0.5260 | 0.87 |
110
+ | 0.0935 | 40.96 | 192 | 0.5778 | 0.84 |
111
+ | 0.0885 | 41.81 | 196 | 0.5563 | 0.86 |
112
+ | 0.0827 | 42.88 | 201 | 0.5556 | 0.86 |
113
+ | 0.0785 | 43.95 | 206 | 0.5807 | 0.84 |
114
+ | 0.0767 | 44.8 | 210 | 0.5649 | 0.85 |
115
+ | 0.0722 | 45.87 | 215 | 0.5551 | 0.85 |
116
+ | 0.0718 | 46.93 | 220 | 0.5432 | 0.86 |
117
+ | 0.0701 | 48.0 | 225 | 0.5720 | 0.85 |
118
+ | 0.0701 | 48.85 | 229 | 0.5695 | 0.85 |
119
+ | 0.068 | 49.92 | 234 | 0.5642 | 0.85 |
120
+ | 0.0673 | 50.99 | 239 | 0.5571 | 0.85 |
121
+ | 0.0672 | 51.2 | 240 | 0.5569 | 0.85 |
122
 
123
 
124
  ### Framework versions
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4b730ae9d5b6c282eab1e2c42676e82f9352cb5adc9a17daec206d8fe58aa2ec
3
  size 94783376
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e32287ea0819fe56ee2533aa97ac50c193924e5d8bf050ffe8aa96d9e394780d
3
  size 94783376