Hugging Face's logo

steimel64
/
distilhubert-finetuned-gtzan

Audio Classification
Transformers
Safetensors
hubert
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
steimel64 commited on
Commit
612ed60
•
1 Parent(s): 37dcc86

End of training

Browse files
Files changed (2) hide show
  1. README.md +55 -55
  2. model.safetensors +1 -1
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
- value: 0.775
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: 1.2754
36
- - Accuracy: 0.775
37
 
38
  ## Model description
39
 
@@ -57,8 +57,8 @@ The following hyperparameters were used during training:
57
  - eval_batch_size: 12
58
  - seed: 42
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: 50
63
  - mixed_precision_training: Native AMP
64
 
@@ -66,56 +66,56 @@ The following hyperparameters were used during training:
66
 
67
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
68
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
69
- | 2.2856 | 1.0 | 67 | 2.2801 | 0.19 |
70
- | 2.1936 | 2.0 | 134 | 2.1829 | 0.335 |
71
- | 1.9496 | 3.0 | 201 | 1.9189 | 0.5 |
72
- | 1.6727 | 4.0 | 268 | 1.6280 | 0.595 |
73
- | 1.5444 | 5.0 | 335 | 1.4530 | 0.635 |
74
- | 1.0974 | 6.0 | 402 | 1.2269 | 0.67 |
75
- | 1.0647 | 7.0 | 469 | 1.0802 | 0.72 |
76
- | 0.8521 | 8.0 | 536 | 0.9819 | 0.72 |
77
- | 0.7618 | 9.0 | 603 | 0.9660 | 0.74 |
78
- | 0.5022 | 10.0 | 670 | 0.8664 | 0.75 |
79
- | 0.4576 | 11.0 | 737 | 0.8972 | 0.7 |
80
- | 0.2801 | 12.0 | 804 | 0.8073 | 0.76 |
81
- | 0.2404 | 13.0 | 871 | 0.7892 | 0.765 |
82
- | 0.1493 | 14.0 | 938 | 0.8512 | 0.74 |
83
- | 0.0945 | 15.0 | 1005 | 0.8876 | 0.74 |
84
- | 0.049 | 16.0 | 1072 | 0.9735 | 0.72 |
85
- | 0.0311 | 17.0 | 1139 | 0.9881 | 0.76 |
86
- | 0.0225 | 18.0 | 1206 | 1.0965 | 0.735 |
87
- | 0.0164 | 19.0 | 1273 | 1.0578 | 0.76 |
88
- | 0.0124 | 20.0 | 1340 | 1.0298 | 0.75 |
89
- | 0.0109 | 21.0 | 1407 | 1.0762 | 0.745 |
90
- | 0.0085 | 22.0 | 1474 | 1.1168 | 0.75 |
91
- | 0.0071 | 23.0 | 1541 | 1.1697 | 0.73 |
92
- | 0.0063 | 24.0 | 1608 | 1.1204 | 0.765 |
93
- | 0.0054 | 25.0 | 1675 | 1.1270 | 0.765 |
94
- | 0.005 | 26.0 | 1742 | 1.1315 | 0.76 |
95
- | 0.0521 | 27.0 | 1809 | 1.1868 | 0.755 |
96
- | 0.004 | 28.0 | 1876 | 1.1645 | 0.77 |
97
- | 0.0468 | 29.0 | 1943 | 1.1515 | 0.775 |
98
- | 0.0036 | 30.0 | 2010 | 1.1655 | 0.775 |
99
- | 0.0595 | 31.0 | 2077 | 1.2069 | 0.76 |
100
- | 0.003 | 32.0 | 2144 | 1.2012 | 0.77 |
101
- | 0.0029 | 33.0 | 2211 | 1.2369 | 0.755 |
102
- | 0.0027 | 34.0 | 2278 | 1.2397 | 0.765 |
103
- | 0.0026 | 35.0 | 2345 | 1.2581 | 0.765 |
104
- | 0.029 | 36.0 | 2412 | 1.2226 | 0.76 |
105
- | 0.0024 | 37.0 | 2479 | 1.1833 | 0.775 |
106
- | 0.0023 | 38.0 | 2546 | 1.2723 | 0.765 |
107
- | 0.0023 | 39.0 | 2613 | 1.2575 | 0.77 |
108
- | 0.0284 | 40.0 | 2680 | 1.2945 | 0.76 |
109
- | 0.002 | 41.0 | 2747 | 1.2345 | 0.765 |
110
- | 0.0203 | 42.0 | 2814 | 1.2607 | 0.77 |
111
- | 0.002 | 43.0 | 2881 | 1.2945 | 0.765 |
112
- | 0.0019 | 44.0 | 2948 | 1.2487 | 0.77 |
113
- | 0.0018 | 45.0 | 3015 | 1.2626 | 0.78 |
114
- | 0.0018 | 46.0 | 3082 | 1.2692 | 0.77 |
115
- | 0.0017 | 47.0 | 3149 | 1.2783 | 0.77 |
116
- | 0.0018 | 48.0 | 3216 | 1.2813 | 0.775 |
117
- | 0.0017 | 49.0 | 3283 | 1.2861 | 0.775 |
118
- | 0.0275 | 50.0 | 3350 | 1.2754 | 0.775 |
119
 
120
 
121
  ### Framework versions
 
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
+ value: 0.815
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: 1.2091
36
+ - Accuracy: 0.815
37
 
38
  ## Model description
39
 
 
57
  - eval_batch_size: 12
58
  - seed: 42
59
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
60
+ - lr_scheduler_type: cosine
61
+ - lr_scheduler_warmup_ratio: 0.03
62
  - num_epochs: 50
63
  - mixed_precision_training: Native AMP
64
 
 
66
 
67
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
68
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
69
+ | 2.2632 | 1.0 | 67 | 2.2116 | 0.335 |
70
+ | 1.8978 | 2.0 | 134 | 1.8129 | 0.5 |
71
+ | 1.5811 | 3.0 | 201 | 1.4946 | 0.66 |
72
+ | 1.1795 | 4.0 | 268 | 1.2851 | 0.65 |
73
+ | 1.0256 | 5.0 | 335 | 1.1538 | 0.66 |
74
+ | 0.9168 | 6.0 | 402 | 1.0270 | 0.69 |
75
+ | 0.9383 | 7.0 | 469 | 0.9349 | 0.73 |
76
+ | 0.5988 | 8.0 | 536 | 0.8443 | 0.795 |
77
+ | 0.4844 | 9.0 | 603 | 0.8053 | 0.775 |
78
+ | 0.422 | 10.0 | 670 | 0.7710 | 0.785 |
79
+ | 0.2138 | 11.0 | 737 | 0.7353 | 0.8 |
80
+ | 0.1834 | 12.0 | 804 | 0.8303 | 0.78 |
81
+ | 0.1789 | 13.0 | 871 | 0.7801 | 0.805 |
82
+ | 0.1649 | 14.0 | 938 | 0.8433 | 0.775 |
83
+ | 0.0259 | 15.0 | 1005 | 0.7846 | 0.8 |
84
+ | 0.0825 | 16.0 | 1072 | 0.9268 | 0.795 |
85
+ | 0.0091 | 17.0 | 1139 | 1.0432 | 0.795 |
86
+ | 0.0053 | 18.0 | 1206 | 0.9703 | 0.8 |
87
+ | 0.0038 | 19.0 | 1273 | 0.9689 | 0.82 |
88
+ | 0.0246 | 20.0 | 1340 | 1.0611 | 0.81 |
89
+ | 0.0023 | 21.0 | 1407 | 1.0502 | 0.82 |
90
+ | 0.0023 | 22.0 | 1474 | 1.0703 | 0.815 |
91
+ | 0.0016 | 23.0 | 1541 | 1.0911 | 0.825 |
92
+ | 0.0015 | 24.0 | 1608 | 1.1375 | 0.795 |
93
+ | 0.0013 | 25.0 | 1675 | 1.1529 | 0.815 |
94
+ | 0.0172 | 26.0 | 1742 | 1.1258 | 0.815 |
95
+ | 0.0011 | 27.0 | 1809 | 1.1206 | 0.82 |
96
+ | 0.001 | 28.0 | 1876 | 1.1492 | 0.82 |
97
+ | 0.0009 | 29.0 | 1943 | 1.1490 | 0.815 |
98
+ | 0.0008 | 30.0 | 2010 | 1.1527 | 0.815 |
99
+ | 0.0008 | 31.0 | 2077 | 1.2008 | 0.815 |
100
+ | 0.0638 | 32.0 | 2144 | 1.1685 | 0.815 |
101
+ | 0.0007 | 33.0 | 2211 | 1.1749 | 0.815 |
102
+ | 0.0858 | 34.0 | 2278 | 1.1683 | 0.815 |
103
+ | 0.0006 | 35.0 | 2345 | 1.1772 | 0.815 |
104
+ | 0.0007 | 36.0 | 2412 | 1.1801 | 0.815 |
105
+ | 0.0006 | 37.0 | 2479 | 1.1956 | 0.815 |
106
+ | 0.0006 | 38.0 | 2546 | 1.1937 | 0.815 |
107
+ | 0.0055 | 39.0 | 2613 | 1.2110 | 0.82 |
108
+ | 0.0006 | 40.0 | 2680 | 1.2023 | 0.815 |
109
+ | 0.0006 | 41.0 | 2747 | 1.2093 | 0.815 |
110
+ | 0.001 | 42.0 | 2814 | 1.2075 | 0.815 |
111
+ | 0.0006 | 43.0 | 2881 | 1.2079 | 0.815 |
112
+ | 0.0662 | 44.0 | 2948 | 1.2054 | 0.815 |
113
+ | 0.0006 | 45.0 | 3015 | 1.2066 | 0.815 |
114
+ | 0.0006 | 46.0 | 3082 | 1.2089 | 0.815 |
115
+ | 0.0006 | 47.0 | 3149 | 1.2093 | 0.815 |
116
+ | 0.0005 | 48.0 | 3216 | 1.2096 | 0.815 |
117
+ | 0.0005 | 49.0 | 3283 | 1.2094 | 0.815 |
118
+ | 0.0006 | 50.0 | 3350 | 1.2091 | 0.815 |
119
 
120
 
121
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4234c8bb4cbd7da6e3ee90dccc506a237c51a25a3361d8e2554e9e8bb1777c4d
3
  size 94771728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc3dfb110c0c6dae87ca7a5daa5f629bbf5ee71980ce9754e21bf271268cfbce
3
  size 94771728