Hugging Face's logo

timjwhite
/
distilhubert-finetuned-gtzan

Audio Classification
Transformers
PyTorch
TensorBoard
hubert
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
timjwhite commited on
Commit
d3186b8
•
1 Parent(s): 03beab6

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +46 -16
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
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
@@ -32,8 +32,8 @@ should probably proofread and complete it, then remove this comment. -->
32
 
33
  This model is a fine-tuned version of [Sandiago21/distilhubert-finetuned-gtzan](https://huggingface.co/Sandiago21/distilhubert-finetuned-gtzan) on the GTZAN dataset.
34
  It achieves the following results on the evaluation set:
35
- - Loss: 0.9021
36
- - Accuracy: 0.85
37
 
38
  ## Model description
39
 
@@ -59,27 +59,57 @@ 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 | Validation Loss | Accuracy |
67
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
68
- | 0.2617 | 1.0 | 57 | 0.8101 | 0.76 |
69
- | 0.3005 | 2.0 | 114 | 0.8589 | 0.82 |
70
- | 0.0123 | 3.0 | 171 | 1.0596 | 0.8 |
71
- | 0.0141 | 4.0 | 228 | 1.0238 | 0.81 |
72
- | 0.0047 | 5.0 | 285 | 0.8953 | 0.83 |
73
- | 0.0889 | 6.0 | 342 | 0.8765 | 0.86 |
74
- | 0.0482 | 7.0 | 399 | 1.1115 | 0.83 |
75
- | 0.0013 | 8.0 | 456 | 1.0884 | 0.84 |
76
- | 0.0009 | 9.0 | 513 | 1.0055 | 0.85 |
77
- | 0.0008 | 10.0 | 570 | 0.9021 | 0.85 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
78
 
79
 
80
  ### Framework versions
81
 
82
  - Transformers 4.31.0
83
- - Pytorch 2.0.1+cu118
84
- - Datasets 2.14.3
85
  - Tokenizers 0.13.3
 
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
+ value: 0.88
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 [Sandiago21/distilhubert-finetuned-gtzan](https://huggingface.co/Sandiago21/distilhubert-finetuned-gtzan) on the GTZAN dataset.
34
  It achieves the following results on the evaluation set:
35
+ - Loss: 0.9951
36
+ - Accuracy: 0.88
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: 40
63
 
64
  ### Training results
65
 
66
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
67
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
68
+ | 0.0951 | 1.0 | 57 | 0.5566 | 0.87 |
69
+ | 0.0629 | 2.0 | 114 | 0.6819 | 0.83 |
70
+ | 0.0231 | 3.0 | 171 | 0.6118 | 0.86 |
71
+ | 0.0159 | 4.0 | 228 | 0.9208 | 0.83 |
72
+ | 0.0374 | 5.0 | 285 | 0.8746 | 0.85 |
73
+ | 0.1714 | 6.0 | 342 | 0.6671 | 0.87 |
74
+ | 0.2148 | 7.0 | 399 | 1.1850 | 0.79 |
75
+ | 0.0147 | 8.0 | 456 | 1.0551 | 0.79 |
76
+ | 0.0788 | 9.0 | 513 | 1.5179 | 0.79 |
77
+ | 0.0015 | 10.0 | 570 | 1.3290 | 0.8 |
78
+ | 0.0049 | 11.0 | 627 | 1.0943 | 0.85 |
79
+ | 0.0012 | 12.0 | 684 | 1.0667 | 0.85 |
80
+ | 0.0043 | 13.0 | 741 | 1.1816 | 0.82 |
81
+ | 0.0015 | 14.0 | 798 | 0.9108 | 0.88 |
82
+ | 0.0011 | 15.0 | 855 | 1.0289 | 0.87 |
83
+ | 0.001 | 16.0 | 912 | 0.7696 | 0.87 |
84
+ | 0.0006 | 17.0 | 969 | 0.8539 | 0.87 |
85
+ | 0.1001 | 18.0 | 1026 | 1.1917 | 0.78 |
86
+ | 0.0017 | 19.0 | 1083 | 1.0016 | 0.83 |
87
+ | 0.0525 | 20.0 | 1140 | 0.9513 | 0.88 |
88
+ | 0.0004 | 21.0 | 1197 | 0.9268 | 0.86 |
89
+ | 0.0003 | 22.0 | 1254 | 1.1209 | 0.82 |
90
+ | 0.0003 | 23.0 | 1311 | 0.9270 | 0.87 |
91
+ | 0.0003 | 24.0 | 1368 | 1.1148 | 0.84 |
92
+ | 0.0003 | 25.0 | 1425 | 1.0507 | 0.85 |
93
+ | 0.0002 | 26.0 | 1482 | 1.0156 | 0.86 |
94
+ | 0.0002 | 27.0 | 1539 | 1.0062 | 0.87 |
95
+ | 0.0002 | 28.0 | 1596 | 1.0124 | 0.87 |
96
+ | 0.0002 | 29.0 | 1653 | 1.0154 | 0.87 |
97
+ | 0.0002 | 30.0 | 1710 | 1.0092 | 0.88 |
98
+ | 0.0002 | 31.0 | 1767 | 1.0123 | 0.88 |
99
+ | 0.0175 | 32.0 | 1824 | 0.9928 | 0.88 |
100
+ | 0.0002 | 33.0 | 1881 | 1.0014 | 0.88 |
101
+ | 0.0115 | 34.0 | 1938 | 0.9989 | 0.88 |
102
+ | 0.0001 | 35.0 | 1995 | 0.9871 | 0.88 |
103
+ | 0.0001 | 36.0 | 2052 | 0.9920 | 0.88 |
104
+ | 0.0002 | 37.0 | 2109 | 0.9974 | 0.88 |
105
+ | 0.0002 | 38.0 | 2166 | 0.9950 | 0.88 |
106
+ | 0.0001 | 39.0 | 2223 | 0.9997 | 0.88 |
107
+ | 0.0001 | 40.0 | 2280 | 0.9951 | 0.88 |
108
 
109
 
110
  ### Framework versions
111
 
112
  - Transformers 4.31.0
113
+ - Pytorch 2.0.1+cu117
114
+ - Datasets 2.13.1
115
  - Tokenizers 0.13.3