Hugging Face's logo

semaj83
/
distilhubert-finetuned-gtzan

Audio Classification
Transformers
PyTorch
hubert
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
1
semaj83 commited on
Commit
0818981
•
1 Parent(s): ada0cef

End of training

Browse files
Files changed (2) hide show
  1. README.md +29 -24
  2. pytorch_model.bin +1 -1
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 [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: 0.6232
36
- - Accuracy: 0.85
37
 
38
  ## Model description
39
 
@@ -59,32 +59,37 @@ 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: 20
63
 
64
  ### Training results
65
 
66
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
67
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
68
- | 2.2706 | 1.0 | 57 | 2.2603 | 0.25 |
69
- | 2.0729 | 2.0 | 114 | 2.0172 | 0.38 |
70
- | 1.7159 | 3.0 | 171 | 1.6766 | 0.62 |
71
- | 1.5972 | 4.0 | 228 | 1.4569 | 0.65 |
72
- | 1.2733 | 5.0 | 285 | 1.2656 | 0.71 |
73
- | 1.2068 | 6.0 | 342 | 1.1271 | 0.77 |
74
- | 1.1018 | 7.0 | 399 | 1.0385 | 0.77 |
75
- | 1.0269 | 8.0 | 456 | 0.9562 | 0.76 |
76
- | 0.9285 | 9.0 | 513 | 0.9170 | 0.73 |
77
- | 0.8465 | 10.0 | 570 | 0.8357 | 0.8 |
78
- | 0.6841 | 11.0 | 627 | 0.8469 | 0.78 |
79
- | 0.6767 | 12.0 | 684 | 0.7362 | 0.84 |
80
- | 0.6276 | 13.0 | 741 | 0.7254 | 0.83 |
81
- | 0.5224 | 14.0 | 798 | 0.7046 | 0.82 |
82
- | 0.5469 | 15.0 | 855 | 0.6684 | 0.85 |
83
- | 0.5789 | 16.0 | 912 | 0.6343 | 0.85 |
84
- | 0.4983 | 17.0 | 969 | 0.6367 | 0.83 |
85
- | 0.4746 | 18.0 | 1026 | 0.6301 | 0.83 |
86
- | 0.4469 | 19.0 | 1083 | 0.6157 | 0.85 |
87
- | 0.4484 | 20.0 | 1140 | 0.6232 | 0.85 |
 
 
 
 
 
88
 
89
 
90
  ### Framework versions
 
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
+ value: 0.87
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: 0.5690
36
+ - Accuracy: 0.87
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: 25
63
 
64
  ### Training results
65
 
66
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
67
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
68
+ | 1.2968 | 1.0 | 57 | 1.2136 | 0.7 |
69
+ | 1.0931 | 2.0 | 114 | 1.1346 | 0.7 |
70
+ | 0.9362 | 3.0 | 171 | 0.9992 | 0.76 |
71
+ | 0.948 | 4.0 | 228 | 0.9344 | 0.76 |
72
+ | 0.7033 | 5.0 | 285 | 0.7802 | 0.81 |
73
+ | 0.6625 | 6.0 | 342 | 0.7777 | 0.79 |
74
+ | 0.5627 | 7.0 | 399 | 0.7143 | 0.81 |
75
+ | 0.5081 | 8.0 | 456 | 0.6232 | 0.86 |
76
+ | 0.4635 | 9.0 | 513 | 0.6564 | 0.85 |
77
+ | 0.3347 | 10.0 | 570 | 0.6108 | 0.85 |
78
+ | 0.2895 | 11.0 | 627 | 0.7139 | 0.8 |
79
+ | 0.2493 | 12.0 | 684 | 0.5887 | 0.84 |
80
+ | 0.2673 | 13.0 | 741 | 0.5907 | 0.86 |
81
+ | 0.1949 | 14.0 | 798 | 0.5798 | 0.83 |
82
+ | 0.1541 | 15.0 | 855 | 0.5532 | 0.87 |
83
+ | 0.1913 | 16.0 | 912 | 0.5314 | 0.87 |
84
+ | 0.1339 | 17.0 | 969 | 0.5337 | 0.88 |
85
+ | 0.0876 | 18.0 | 1026 | 0.5815 | 0.87 |
86
+ | 0.0713 | 19.0 | 1083 | 0.5847 | 0.85 |
87
+ | 0.0869 | 20.0 | 1140 | 0.5456 | 0.86 |
88
+ | 0.0587 | 21.0 | 1197 | 0.5480 | 0.86 |
89
+ | 0.0524 | 22.0 | 1254 | 0.5534 | 0.87 |
90
+ | 0.0621 | 23.0 | 1311 | 0.5707 | 0.87 |
91
+ | 0.0452 | 24.0 | 1368 | 0.5748 | 0.87 |
92
+ | 0.0464 | 25.0 | 1425 | 0.5690 | 0.87 |
93
 
94
 
95
  ### Framework versions
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bcd1ba9a1199e74d1f763371545001cbda205e98448c679127e9b673462d56cb
3
  size 94783376
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25bf1024b87e6356c613c999aee816fc2e3dd5df9ba8ed2d56711ebb2689c584
3
  size 94783376