Hugging Face's logo

jackoyoungblood
/
distilhubert-finetuned-gtzan

Audio Classification
Transformers
PyTorch
hubert
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
jackoyoungblood commited on
Commit
cded3c0
·
1 Parent(s): 3e3dce0

End of training

Browse files
Files changed (2) hide show
  1. README.md +25 -7
  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: 0.71
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: 1.0568
36
- - Accuracy: 0.71
37
 
38
  ## Model description
39
 
@@ -52,21 +52,39 @@ More information needed
52
  ### Training hyperparameters
53
 
54
  The following hyperparameters were used during training:
55
- - learning_rate: 9.46143018764732e-05
56
  - train_batch_size: 8
57
  - eval_batch_size: 8
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: 2
63
 
64
  ### Training results
65
 
66
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
67
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
68
- | 1.6451 | 1.0 | 113 | 1.3168 | 0.59 |
69
- | 1.1583 | 2.0 | 226 | 1.0568 | 0.71 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
70
 
71
 
72
  ### Framework versions
 
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
+ value: 0.78
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: 1.1493
36
+ - Accuracy: 0.78
37
 
38
  ## Model description
39
 
 
52
  ### Training hyperparameters
53
 
54
  The following hyperparameters were used during training:
55
+ - learning_rate: 0.00018
56
  - train_batch_size: 8
57
  - eval_batch_size: 8
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: 20
63
 
64
  ### Training results
65
 
66
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
67
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
68
+ | 1.7553 | 1.0 | 113 | 1.5918 | 0.47 |
69
+ | 1.0465 | 2.0 | 226 | 0.9806 | 0.68 |
70
+ | 1.2995 | 3.0 | 339 | 0.9627 | 0.72 |
71
+ | 1.1928 | 4.0 | 452 | 0.9208 | 0.71 |
72
+ | 0.3715 | 5.0 | 565 | 0.5924 | 0.81 |
73
+ | 0.4474 | 6.0 | 678 | 1.0245 | 0.71 |
74
+ | 0.4553 | 7.0 | 791 | 0.8025 | 0.79 |
75
+ | 0.029 | 8.0 | 904 | 1.3956 | 0.71 |
76
+ | 0.2059 | 9.0 | 1017 | 1.1544 | 0.79 |
77
+ | 0.1797 | 10.0 | 1130 | 1.6616 | 0.74 |
78
+ | 0.0009 | 11.0 | 1243 | 0.9263 | 0.86 |
79
+ | 0.1761 | 12.0 | 1356 | 0.9989 | 0.85 |
80
+ | 0.0006 | 13.0 | 1469 | 1.2108 | 0.8 |
81
+ | 0.0006 | 14.0 | 1582 | 0.9643 | 0.83 |
82
+ | 0.0005 | 15.0 | 1695 | 1.1004 | 0.8 |
83
+ | 0.0004 | 16.0 | 1808 | 1.0556 | 0.82 |
84
+ | 0.1084 | 17.0 | 1921 | 1.1447 | 0.81 |
85
+ | 0.0003 | 18.0 | 2034 | 1.1467 | 0.82 |
86
+ | 0.0003 | 19.0 | 2147 | 1.1723 | 0.8 |
87
+ | 0.0003 | 20.0 | 2260 | 1.1493 | 0.78 |
88
 
89
 
90
  ### Framework versions
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7e5ac06a1fa20160f180d4ac8939db5a1c7920ea6031366a615056345f9aa219
3
  size 94783376
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b754f34eba2e053d807ce0d09ecdd6c0a06757b1ba0cd1a04d96150ba23e250a
3
  size 94783376