Hugging Face's logo

WasuratS
/
distilhubert-finetuned-gtzan

Audio Classification
Transformers
PyTorch
TensorBoard
hubert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
WasuratS commited on
Commit
5cdba00
•
1 Parent(s): e86d0e3

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +38 -26
README.md CHANGED
@@ -18,8 +18,8 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  This model is a fine-tuned version of [ntu-spml/distilhubert](https://huggingface.co/ntu-spml/distilhubert) on the GTZAN dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 0.6711
22
- - Accuracy: 0.82
23
 
24
  ## Model description
25
 
@@ -38,41 +38,53 @@ More information needed
38
  ### Training hyperparameters
39
 
40
  The following hyperparameters were used during training:
41
- - learning_rate: 2e-05
42
- - train_batch_size: 8
43
- - eval_batch_size: 8
44
  - seed: 42
45
  - distributed_type: multi-GPU
 
 
46
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
  - lr_scheduler_type: linear
48
  - lr_scheduler_warmup_ratio: 0.1
49
- - num_epochs: 20
50
  - mixed_precision_training: Native AMP
51
 
52
  ### Training results
53
 
54
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
55
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
56
- | 2.1962 | 1.0 | 113 | 2.2220 | 0.29 |
57
- | 1.9431 | 2.0 | 226 | 1.8877 | 0.5 |
58
- | 1.634 | 3.0 | 339 | 1.5106 | 0.63 |
59
- | 1.3403 | 4.0 | 452 | 1.3191 | 0.66 |
60
- | 1.1067 | 5.0 | 565 | 1.1082 | 0.68 |
61
- | 1.0416 | 6.0 | 678 | 1.0664 | 0.72 |
62
- | 0.7723 | 7.0 | 791 | 0.9729 | 0.77 |
63
- | 0.8281 | 8.0 | 904 | 0.8799 | 0.78 |
64
- | 0.6344 | 9.0 | 1017 | 0.8142 | 0.77 |
65
- | 0.8819 | 10.0 | 1130 | 0.8719 | 0.73 |
66
- | 0.4279 | 11.0 | 1243 | 0.8150 | 0.78 |
67
- | 0.425 | 12.0 | 1356 | 0.7137 | 0.81 |
68
- | 0.2749 | 13.0 | 1469 | 0.6987 | 0.8 |
69
- | 0.2182 | 14.0 | 1582 | 0.6849 | 0.82 |
70
- | 0.2128 | 15.0 | 1695 | 0.6918 | 0.82 |
71
- | 0.1831 | 16.0 | 1808 | 0.6600 | 0.81 |
72
- | 0.1517 | 17.0 | 1921 | 0.6571 | 0.82 |
73
- | 0.2888 | 18.0 | 2034 | 0.6880 | 0.81 |
74
- | 0.1605 | 19.0 | 2147 | 0.6874 | 0.82 |
75
- | 0.1492 | 20.0 | 2260 | 0.6711 | 0.82 |
 
 
 
 
 
 
 
 
 
 
76
 
77
 
78
  ### Framework versions
 
18
 
19
  This model is a fine-tuned version of [ntu-spml/distilhubert](https://huggingface.co/ntu-spml/distilhubert) on the GTZAN dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 1.2658
22
+ - Accuracy: 0.8
23
 
24
  ## Model description
25
 
 
38
  ### Training hyperparameters
39
 
40
  The following hyperparameters were used during training:
41
+ - learning_rate: 5e-05
42
+ - train_batch_size: 4
43
+ - eval_batch_size: 4
44
  - seed: 42
45
  - distributed_type: multi-GPU
46
+ - gradient_accumulation_steps: 2
47
+ - total_train_batch_size: 8
48
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
49
  - lr_scheduler_type: linear
50
  - lr_scheduler_warmup_ratio: 0.1
51
+ - num_epochs: 30
52
  - mixed_precision_training: Native AMP
53
 
54
  ### Training results
55
 
56
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
57
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
58
+ | 2.1071 | 1.0 | 112 | 2.1453 | 0.33 |
59
+ | 1.6165 | 2.0 | 225 | 1.6129 | 0.59 |
60
+ | 1.2842 | 3.0 | 337 | 1.2084 | 0.68 |
61
+ | 0.9805 | 4.0 | 450 | 0.8842 | 0.74 |
62
+ | 0.5216 | 5.0 | 562 | 0.7350 | 0.78 |
63
+ | 0.5017 | 6.0 | 675 | 0.8196 | 0.77 |
64
+ | 0.1998 | 7.0 | 787 | 0.6709 | 0.8 |
65
+ | 0.3662 | 8.0 | 900 | 0.8483 | 0.78 |
66
+ | 0.2711 | 9.0 | 1012 | 0.8567 | 0.81 |
67
+ | 0.0183 | 10.0 | 1125 | 0.8994 | 0.82 |
68
+ | 0.0299 | 11.0 | 1237 | 1.2142 | 0.8 |
69
+ | 0.0064 | 12.0 | 1350 | 1.0208 | 0.81 |
70
+ | 0.004 | 13.0 | 1462 | 1.0619 | 0.81 |
71
+ | 0.0031 | 14.0 | 1575 | 1.1454 | 0.79 |
72
+ | 0.0028 | 15.0 | 1687 | 1.1010 | 0.81 |
73
+ | 0.0023 | 16.0 | 1800 | 1.0595 | 0.8 |
74
+ | 0.0017 | 17.0 | 1912 | 1.1340 | 0.8 |
75
+ | 0.0015 | 18.0 | 2025 | 1.1760 | 0.81 |
76
+ | 0.0014 | 19.0 | 2137 | 1.1361 | 0.81 |
77
+ | 0.0012 | 20.0 | 2250 | 1.2138 | 0.81 |
78
+ | 0.0011 | 21.0 | 2362 | 1.1366 | 0.81 |
79
+ | 0.0012 | 22.0 | 2475 | 1.1662 | 0.8 |
80
+ | 0.0011 | 23.0 | 2587 | 1.1491 | 0.8 |
81
+ | 0.0009 | 24.0 | 2700 | 1.1287 | 0.81 |
82
+ | 0.0009 | 25.0 | 2812 | 1.2027 | 0.81 |
83
+ | 0.0009 | 26.0 | 2925 | 1.1740 | 0.81 |
84
+ | 0.0009 | 27.0 | 3037 | 1.2011 | 0.81 |
85
+ | 0.0009 | 28.0 | 3150 | 1.2523 | 0.8 |
86
+ | 0.0008 | 29.0 | 3262 | 1.2494 | 0.81 |
87
+ | 0.0007 | 29.87 | 3360 | 1.2658 | 0.8 |
88
 
89
 
90
  ### Framework versions