artyomboyko commited on
Commit
f07fac4
1 Parent(s): 73a8aea

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +53 -8
README.md CHANGED
@@ -18,8 +18,8 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  This model is a fine-tuned version of [ntu-spml/distilhubert](https://huggingface.co/ntu-spml/distilhubert) on the GTZAN dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 0.4738
22
- - Accuracy: 0.88
23
 
24
  ## Model description
25
 
@@ -47,17 +47,62 @@ The following hyperparameters were used during training:
47
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
48
  - lr_scheduler_type: linear
49
  - lr_scheduler_warmup_ratio: 0.1
50
- - num_epochs: 5
51
 
52
  ### Training results
53
 
54
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
55
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
56
- | 0.2468 | 1.0 | 112 | 0.4818 | 0.86 |
57
- | 0.1157 | 2.0 | 225 | 0.4982 | 0.85 |
58
- | 0.1855 | 3.0 | 337 | 0.4842 | 0.86 |
59
- | 0.169 | 4.0 | 450 | 0.4762 | 0.88 |
60
- | 0.1003 | 4.98 | 560 | 0.4738 | 0.88 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
61
 
62
 
63
  ### Framework versions
 
18
 
19
  This model is a fine-tuned version of [ntu-spml/distilhubert](https://huggingface.co/ntu-spml/distilhubert) on the GTZAN dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.5759
22
+ - Accuracy: 0.87
23
 
24
  ## Model description
25
 
 
47
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
48
  - lr_scheduler_type: linear
49
  - lr_scheduler_warmup_ratio: 0.1
50
+ - num_epochs: 50
51
 
52
  ### Training results
53
 
54
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
55
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
56
+ | 0.2359 | 1.0 | 112 | 0.4776 | 0.87 |
57
+ | 0.1235 | 2.0 | 225 | 0.4872 | 0.84 |
58
+ | 0.2083 | 3.0 | 337 | 0.4910 | 0.85 |
59
+ | 0.19 | 4.0 | 450 | 0.4953 | 0.87 |
60
+ | 0.1128 | 5.0 | 562 | 0.4801 | 0.87 |
61
+ | 0.1644 | 6.0 | 675 | 0.4703 | 0.87 |
62
+ | 0.0699 | 7.0 | 787 | 0.4692 | 0.85 |
63
+ | 0.1082 | 8.0 | 900 | 0.4708 | 0.87 |
64
+ | 0.0898 | 9.0 | 1012 | 0.4347 | 0.89 |
65
+ | 0.1071 | 10.0 | 1125 | 0.5310 | 0.85 |
66
+ | 0.0727 | 11.0 | 1237 | 0.4765 | 0.87 |
67
+ | 0.0338 | 12.0 | 1350 | 0.4859 | 0.87 |
68
+ | 0.0233 | 13.0 | 1462 | 0.4713 | 0.87 |
69
+ | 0.0248 | 14.0 | 1575 | 0.5068 | 0.88 |
70
+ | 0.0263 | 15.0 | 1687 | 0.4874 | 0.88 |
71
+ | 0.0185 | 16.0 | 1800 | 0.4925 | 0.88 |
72
+ | 0.0142 | 17.0 | 1912 | 0.4766 | 0.89 |
73
+ | 0.0178 | 18.0 | 2025 | 0.4850 | 0.89 |
74
+ | 0.0153 | 19.0 | 2137 | 0.4660 | 0.88 |
75
+ | 0.012 | 20.0 | 2250 | 0.4831 | 0.88 |
76
+ | 0.0113 | 21.0 | 2362 | 0.4965 | 0.89 |
77
+ | 0.0106 | 22.0 | 2475 | 0.5098 | 0.89 |
78
+ | 0.011 | 23.0 | 2587 | 0.5093 | 0.89 |
79
+ | 0.009 | 24.0 | 2700 | 0.4989 | 0.91 |
80
+ | 0.0094 | 25.0 | 2812 | 0.4999 | 0.89 |
81
+ | 0.0441 | 26.0 | 2925 | 0.5197 | 0.88 |
82
+ | 0.0079 | 27.0 | 3037 | 0.5115 | 0.89 |
83
+ | 0.0072 | 28.0 | 3150 | 0.5136 | 0.88 |
84
+ | 0.007 | 29.0 | 3262 | 0.5394 | 0.88 |
85
+ | 0.0068 | 30.0 | 3375 | 0.5374 | 0.88 |
86
+ | 0.0061 | 31.0 | 3487 | 0.5221 | 0.88 |
87
+ | 0.0533 | 32.0 | 3600 | 0.5775 | 0.87 |
88
+ | 0.0055 | 33.0 | 3712 | 0.5632 | 0.88 |
89
+ | 0.0059 | 34.0 | 3825 | 0.5584 | 0.87 |
90
+ | 0.0051 | 35.0 | 3937 | 0.5444 | 0.88 |
91
+ | 0.0051 | 36.0 | 4050 | 0.5373 | 0.88 |
92
+ | 0.0045 | 37.0 | 4162 | 0.5723 | 0.87 |
93
+ | 0.0058 | 38.0 | 4275 | 0.5773 | 0.87 |
94
+ | 0.0043 | 39.0 | 4387 | 0.5455 | 0.88 |
95
+ | 0.0044 | 40.0 | 4500 | 0.5686 | 0.88 |
96
+ | 0.004 | 41.0 | 4612 | 0.5622 | 0.87 |
97
+ | 0.004 | 42.0 | 4725 | 0.5797 | 0.88 |
98
+ | 0.0042 | 43.0 | 4837 | 0.5621 | 0.88 |
99
+ | 0.0037 | 44.0 | 4950 | 0.5734 | 0.87 |
100
+ | 0.0048 | 45.0 | 5062 | 0.5774 | 0.88 |
101
+ | 0.0039 | 46.0 | 5175 | 0.5901 | 0.87 |
102
+ | 0.0043 | 47.0 | 5287 | 0.5743 | 0.88 |
103
+ | 0.0043 | 48.0 | 5400 | 0.5757 | 0.87 |
104
+ | 0.0037 | 49.0 | 5512 | 0.5710 | 0.88 |
105
+ | 0.0036 | 49.78 | 5600 | 0.5759 | 0.87 |
106
 
107
 
108
  ### Framework versions