Hugging Face's logo

on1onmangoes
/
ast-finetuned-audioset-10-10-0.450-finetuned-gtzan

Audio Classification
Transformers
TensorBoard
Safetensors
audio-spectrogram-transformer
Generated from Trainer
Eval Results
Model card Files
xet
Metrics Community
on1onmangoes commited on
Commit
ec91456
·
1 Parent(s): 2a9d42d

End of training

Browse files
Files changed (2) hide show
  1. README.md +24 -6
  2. model.safetensors +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 [MIT/ast-finetuned-audioset-10-10-0.450](https://huggingface.co/MIT/ast-finetuned-audioset-10-10-0.450) on the GTZAN dataset.
34
  It achieves the following results on the evaluation set:
35
- - Loss: 0.3564
36
  - Accuracy: 0.88
37
 
38
  ## Model description
@@ -53,21 +53,39 @@ More information needed
53
 
54
  The following hyperparameters were used during training:
55
  - learning_rate: 5e-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
  - mixed_precision_training: Native AMP
64
 
65
  ### Training results
66
 
67
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
68
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
69
- | 0.7046 | 1.0 | 113 | 0.5407 | 0.81 |
70
- | 0.1355 | 2.0 | 226 | 0.3564 | 0.88 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
71
 
72
 
73
  ### Framework versions
 
32
 
33
  This model is a fine-tuned version of [MIT/ast-finetuned-audioset-10-10-0.450](https://huggingface.co/MIT/ast-finetuned-audioset-10-10-0.450) on the GTZAN dataset.
34
  It achieves the following results on the evaluation set:
35
+ - Loss: 0.4457
36
  - Accuracy: 0.88
37
 
38
  ## Model description
 
53
 
54
  The following hyperparameters were used during training:
55
  - learning_rate: 5e-05
56
+ - train_batch_size: 16
57
+ - eval_batch_size: 16
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
  - mixed_precision_training: Native AMP
64
 
65
  ### Training results
66
 
67
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
68
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
69
+ | 0.5804 | 1.0 | 57 | 0.5356 | 0.84 |
70
+ | 0.2655 | 2.0 | 114 | 0.5664 | 0.76 |
71
+ | 0.1767 | 3.0 | 171 | 0.3925 | 0.88 |
72
+ | 0.4169 | 4.0 | 228 | 0.8874 | 0.78 |
73
+ | 0.0685 | 5.0 | 285 | 0.6067 | 0.83 |
74
+ | 0.0725 | 6.0 | 342 | 0.5612 | 0.81 |
75
+ | 0.1003 | 7.0 | 399 | 0.6928 | 0.82 |
76
+ | 0.004 | 8.0 | 456 | 0.4814 | 0.86 |
77
+ | 0.0122 | 9.0 | 513 | 0.6141 | 0.86 |
78
+ | 0.0009 | 10.0 | 570 | 0.4017 | 0.91 |
79
+ | 0.0828 | 11.0 | 627 | 0.4937 | 0.88 |
80
+ | 0.0025 | 12.0 | 684 | 0.8455 | 0.82 |
81
+ | 0.0005 | 13.0 | 741 | 0.4439 | 0.89 |
82
+ | 0.0001 | 14.0 | 798 | 0.4956 | 0.87 |
83
+ | 0.0001 | 15.0 | 855 | 0.4362 | 0.88 |
84
+ | 0.0001 | 16.0 | 912 | 0.4146 | 0.89 |
85
+ | 0.0299 | 17.0 | 969 | 0.4241 | 0.9 |
86
+ | 0.0001 | 18.0 | 1026 | 0.4375 | 0.87 |
87
+ | 0.0001 | 19.0 | 1083 | 0.4502 | 0.88 |
88
+ | 0.0001 | 20.0 | 1140 | 0.4457 | 0.88 |
89
 
90
 
91
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cb06ee450058f063942b4272c82494f00dcece8c212bae4da1dfb66db03b77d2
3
  size 344814656
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6537b4f59d7a276398e28fab820348e0bfde0e36f86e54ac6abcdd13efe44fd
3
  size 344814656