Hugging Face's logo

Terps
/
distilhubert-finetuned-gtzan

Audio Classification
Transformers
PyTorch
hubert
Generated from Trainer
Inference Endpoints
Model card Files Community
Terps commited on
Commit
0c551ce
•
1 Parent(s): f2003f9

End of training

Browse files
Files changed (2) hide show
  1. README.md +28 -25
  2. pytorch_model.bin +1 -1
README.md CHANGED
@@ -32,7 +32,7 @@ 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: 0.8249
36
  - Accuracy: 0.82
37
 
38
  ## Model description
@@ -58,35 +58,38 @@ The following hyperparameters were used during training:
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: 0.2
62
- - num_epochs: 22
63
 
64
  ### Training results
65
 
66
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
67
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
68
- | 2.2842 | 1.0 | 113 | 2.2543 | 0.3 |
69
- | 2.0773 | 2.0 | 226 | 1.9873 | 0.48 |
70
- | 1.7159 | 3.0 | 339 | 1.5782 | 0.62 |
71
- | 1.387 | 4.0 | 452 | 1.2804 | 0.66 |
72
- | 1.1222 | 5.0 | 565 | 1.0393 | 0.73 |
73
- | 0.7876 | 6.0 | 678 | 0.9051 | 0.74 |
74
- | 0.9007 | 7.0 | 791 | 0.8055 | 0.76 |
75
- | 0.5017 | 8.0 | 904 | 0.7151 | 0.75 |
76
- | 0.5264 | 9.0 | 1017 | 0.6879 | 0.77 |
77
- | 0.3012 | 10.0 | 1130 | 0.6588 | 0.82 |
78
- | 0.1607 | 11.0 | 1243 | 0.7615 | 0.77 |
79
- | 0.127 | 12.0 | 1356 | 0.7563 | 0.81 |
80
- | 0.0604 | 13.0 | 1469 | 0.6578 | 0.82 |
81
- | 0.0634 | 14.0 | 1582 | 0.7324 | 0.82 |
82
- | 0.0316 | 15.0 | 1695 | 0.7794 | 0.8 |
83
- | 0.0249 | 16.0 | 1808 | 0.7383 | 0.83 |
84
- | 0.0605 | 17.0 | 1921 | 0.8103 | 0.81 |
85
- | 0.0128 | 18.0 | 2034 | 0.7825 | 0.83 |
86
- | 0.0114 | 19.0 | 2147 | 0.7690 | 0.81 |
87
- | 0.0111 | 20.0 | 2260 | 0.7878 | 0.82 |
88
- | 0.01 | 21.0 | 2373 | 0.8346 | 0.82 |
89
- | 0.0088 | 22.0 | 2486 | 0.8249 | 0.82 |
 
 
 
90
 
91
 
92
  ### Framework versions
 
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: 0.7819
36
  - Accuracy: 0.82
37
 
38
  ## Model description
 
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: 0.3
62
+ - num_epochs: 25
63
 
64
  ### Training results
65
 
66
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
67
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
68
+ | 2.286 | 1.0 | 113 | 2.2792 | 0.26 |
69
+ | 2.1863 | 2.0 | 226 | 2.1408 | 0.34 |
70
+ | 1.9386 | 3.0 | 339 | 1.8744 | 0.48 |
71
+ | 1.6908 | 4.0 | 452 | 1.6502 | 0.57 |
72
+ | 1.5259 | 5.0 | 565 | 1.4149 | 0.72 |
73
+ | 1.1279 | 6.0 | 678 | 1.2700 | 0.62 |
74
+ | 1.2204 | 7.0 | 791 | 0.9902 | 0.75 |
75
+ | 0.861 | 8.0 | 904 | 0.8020 | 0.8 |
76
+ | 0.8153 | 9.0 | 1017 | 0.7291 | 0.8 |
77
+ | 0.3983 | 10.0 | 1130 | 0.7304 | 0.8 |
78
+ | 0.2209 | 11.0 | 1243 | 0.6960 | 0.79 |
79
+ | 0.2523 | 12.0 | 1356 | 0.5783 | 0.83 |
80
+ | 0.1267 | 13.0 | 1469 | 0.5613 | 0.83 |
81
+ | 0.0468 | 14.0 | 1582 | 0.7976 | 0.8 |
82
+ | 0.025 | 15.0 | 1695 | 0.8478 | 0.81 |
83
+ | 0.0158 | 16.0 | 1808 | 0.7448 | 0.8 |
84
+ | 0.0706 | 17.0 | 1921 | 0.7183 | 0.83 |
85
+ | 0.0096 | 18.0 | 2034 | 0.7532 | 0.82 |
86
+ | 0.0076 | 19.0 | 2147 | 0.7907 | 0.81 |
87
+ | 0.0354 | 20.0 | 2260 | 0.7120 | 0.83 |
88
+ | 0.0063 | 21.0 | 2373 | 0.7525 | 0.83 |
89
+ | 0.0055 | 22.0 | 2486 | 0.7647 | 0.82 |
90
+ | 0.0049 | 23.0 | 2599 | 0.7945 | 0.82 |
91
+ | 0.0048 | 24.0 | 2712 | 0.7982 | 0.82 |
92
+ | 0.0321 | 25.0 | 2825 | 0.7819 | 0.82 |
93
 
94
 
95
  ### Framework versions
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:84eb5209ab7d340f8eea5b8ac32539b92d0c8c3e4b34978a56f3528b4858682c
3
  size 94783376
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc1c05243ed113ade61d16bbf550fb5ec00256e03b2e429d1d20a1b766f04b81
3
  size 94783376