Hugging Face's logo

mlubos
/
distilhubert-finetuned-gtzan

Audio Classification
Transformers
PyTorch
TensorBoard
Safetensors
hubert
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
mlubos commited on
Commit
79e9943
·
1 Parent(s): 2c7b6d7

End of training

Browse files
Files changed (2) hide show
  1. README.md +22 -27
  2. model.safetensors +1 -1
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
- value: 0.83
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: 0.9928
36
- - Accuracy: 0.83
37
 
38
  ## Model description
39
 
@@ -59,38 +59,33 @@ 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
  - mixed_precision_training: Native AMP
64
 
65
  ### Training results
66
 
67
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
68
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
69
- | 2.1503 | 1.0 | 113 | 2.0510 | 0.39 |
70
- | 1.5109 | 2.0 | 226 | 1.4380 | 0.52 |
71
- | 1.1899 | 3.0 | 339 | 1.0524 | 0.75 |
72
- | 1.0 | 4.0 | 452 | 0.8747 | 0.74 |
73
- | 0.6723 | 5.0 | 565 | 0.7782 | 0.75 |
74
- | 0.3818 | 6.0 | 678 | 0.6725 | 0.77 |
75
- | 0.4716 | 7.0 | 791 | 0.5217 | 0.86 |
76
- | 0.1227 | 8.0 | 904 | 0.5807 | 0.85 |
77
- | 0.13 | 9.0 | 1017 | 0.6363 | 0.86 |
78
- | 0.0273 | 10.0 | 1130 | 0.9141 | 0.79 |
79
- | 0.0102 | 11.0 | 1243 | 0.8920 | 0.82 |
80
- | 0.1046 | 12.0 | 1356 | 1.0016 | 0.83 |
81
- | 0.0053 | 13.0 | 1469 | 0.8576 | 0.83 |
82
- | 0.0045 | 14.0 | 1582 | 0.9312 | 0.84 |
83
- | 0.0038 | 15.0 | 1695 | 0.8768 | 0.83 |
84
- | 0.0033 | 16.0 | 1808 | 0.9150 | 0.83 |
85
- | 0.0301 | 17.0 | 1921 | 0.9653 | 0.84 |
86
- | 0.0027 | 18.0 | 2034 | 0.9828 | 0.84 |
87
- | 0.0025 | 19.0 | 2147 | 0.9913 | 0.83 |
88
- | 0.0029 | 20.0 | 2260 | 0.9928 | 0.83 |
89
 
90
 
91
  ### Framework versions
92
 
93
- - Transformers 4.35.0.dev0
94
  - Pytorch 2.1.0+cu118
95
- - Datasets 2.14.6
96
- - Tokenizers 0.14.1
 
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
 
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: 0.8380
36
+ - Accuracy: 0.85
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: 15
63
  - mixed_precision_training: Native AMP
64
 
65
  ### Training results
66
 
67
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
68
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
69
+ | 2.1361 | 1.0 | 113 | 1.9757 | 0.39 |
70
+ | 1.3989 | 2.0 | 226 | 1.3594 | 0.59 |
71
+ | 1.0771 | 3.0 | 339 | 0.9829 | 0.76 |
72
+ | 0.8901 | 4.0 | 452 | 0.8849 | 0.73 |
73
+ | 0.5455 | 5.0 | 565 | 0.7559 | 0.78 |
74
+ | 0.3767 | 6.0 | 678 | 0.7000 | 0.78 |
75
+ | 0.3712 | 7.0 | 791 | 0.6591 | 0.81 |
76
+ | 0.1638 | 8.0 | 904 | 0.6108 | 0.85 |
77
+ | 0.2128 | 9.0 | 1017 | 0.6600 | 0.84 |
78
+ | 0.1121 | 10.0 | 1130 | 0.8119 | 0.84 |
79
+ | 0.0144 | 11.0 | 1243 | 0.8470 | 0.85 |
80
+ | 0.1023 | 12.0 | 1356 | 0.7687 | 0.86 |
81
+ | 0.0096 | 13.0 | 1469 | 0.8509 | 0.85 |
82
+ | 0.0083 | 14.0 | 1582 | 0.8137 | 0.85 |
83
+ | 0.0088 | 15.0 | 1695 | 0.8380 | 0.85 |
 
 
 
 
 
84
 
85
 
86
  ### Framework versions
87
 
88
+ - Transformers 4.36.0.dev0
89
  - Pytorch 2.1.0+cu118
90
+ - Datasets 2.15.0
91
+ - Tokenizers 0.15.0
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fcb0be6588536dd21dedb62f7368f6ed445388d5f0ec776ebb145f4f32c6dd8e
3
  size 94771728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82ced5ec10aeaece0c864ed1f0bc86ef124d5a3bd950df610b6204b05325212e
3
  size 94771728