Hugging Face's logo

Sandiago21
/
hubert-large-ls960-ft-finetuned-gtzan

Audio Classification
Transformers
PyTorch
TensorBoard
Safetensors
hubert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
2
Sandiago21 commited on
Commit
1d15b75
•
1 Parent(s): 464a7bb

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +22 -24
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 [facebook/hubert-large-ls960-ft](https://huggingface.co/facebook/hubert-large-ls960-ft) on the GTZAN dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: nan
22
- - Accuracy: 0.86
23
 
24
  ## Model description
25
 
@@ -38,7 +38,7 @@ More information needed
38
  ### Training hyperparameters
39
 
40
  The following hyperparameters were used during training:
41
- - learning_rate: 0.0001
42
  - train_batch_size: 2
43
  - eval_batch_size: 2
44
  - seed: 42
@@ -47,32 +47,30 @@ The following hyperparameters were used during training:
47
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
48
  - lr_scheduler_type: linear
49
  - lr_scheduler_warmup_ratio: 0.1
50
- - num_epochs: 20
51
 
52
  ### Training results
53
 
54
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
55
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
56
- | 2.2625 | 1.0 | 56 | 2.2399 | 0.23 |
57
- | 1.7887 | 1.99 | 112 | 1.7278 | 0.4 |
58
- | 1.4728 | 2.99 | 168 | 1.4387 | 0.48 |
59
- | 1.1536 | 4.0 | 225 | 1.3178 | 0.54 |
60
- | 1.0758 | 5.0 | 281 | 1.1903 | 0.6 |
61
- | 0.9742 | 5.99 | 337 | 0.8416 | 0.72 |
62
- | 0.8285 | 6.99 | 393 | 0.5875 | 0.78 |
63
- | 0.7953 | 8.0 | 450 | 0.7786 | 0.75 |
64
- | 0.6224 | 9.0 | 506 | 0.6753 | 0.8 |
65
- | 0.3806 | 9.99 | 562 | 0.5826 | 0.84 |
66
- | 0.3121 | 10.99 | 618 | 0.7312 | 0.78 |
67
- | 0.1729 | 12.0 | 675 | 0.6526 | 0.85 |
68
- | 0.2958 | 13.0 | 731 | 0.7831 | 0.83 |
69
- | 0.1496 | 13.99 | 787 | 0.8518 | 0.79 |
70
- | 0.0659 | 14.99 | 843 | 0.8194 | 0.82 |
71
- | 0.1208 | 16.0 | 900 | 0.8555 | 0.82 |
72
- | 0.147 | 17.0 | 956 | 0.6768 | 0.86 |
73
- | 0.0284 | 17.99 | 1012 | 0.7065 | 0.86 |
74
- | 0.0295 | 18.99 | 1068 | 0.6942 | 0.87 |
75
- | 0.0524 | 19.91 | 1120 | nan | 0.86 |
76
 
77
 
78
  ### Framework versions
 
18
 
19
  This model is a fine-tuned version of [facebook/hubert-large-ls960-ft](https://huggingface.co/facebook/hubert-large-ls960-ft) on the GTZAN dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.7096
22
+ - Accuracy: 0.85
23
 
24
  ## Model description
25
 
 
38
  ### Training hyperparameters
39
 
40
  The following hyperparameters were used during training:
41
+ - learning_rate: 8e-05
42
  - train_batch_size: 2
43
  - eval_batch_size: 2
44
  - seed: 42
 
47
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
48
  - lr_scheduler_type: linear
49
  - lr_scheduler_warmup_ratio: 0.1
50
+ - num_epochs: 18
51
 
52
  ### Training results
53
 
54
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
55
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
56
+ | 2.2623 | 1.0 | 56 | 2.2399 | 0.21 |
57
+ | 1.881 | 1.99 | 112 | 1.7105 | 0.41 |
58
+ | 1.5793 | 2.99 | 168 | 1.6203 | 0.46 |
59
+ | 1.3018 | 4.0 | 225 | 1.3824 | 0.52 |
60
+ | 1.0219 | 5.0 | 281 | 0.9899 | 0.66 |
61
+ | 0.9047 | 5.99 | 337 | 0.8812 | 0.74 |
62
+ | 0.8353 | 6.99 | 393 | 0.7629 | 0.78 |
63
+ | 0.659 | 8.0 | 450 | 0.9674 | 0.71 |
64
+ | 0.645 | 9.0 | 506 | 0.8953 | 0.74 |
65
+ | 0.6233 | 9.99 | 562 | 0.6638 | 0.8 |
66
+ | 0.4155 | 10.99 | 618 | 0.6323 | 0.81 |
67
+ | 0.2689 | 12.0 | 675 | 0.5423 | 0.83 |
68
+ | 0.3714 | 13.0 | 731 | 0.6770 | 0.83 |
69
+ | 0.0692 | 13.99 | 787 | 0.6260 | 0.83 |
70
+ | 0.0778 | 14.99 | 843 | 0.5801 | 0.85 |
71
+ | 0.187 | 16.0 | 900 | 0.6722 | 0.83 |
72
+ | 0.1469 | 17.0 | 956 | 0.7473 | 0.85 |
73
+ | 0.1052 | 17.92 | 1008 | 0.7096 | 0.85 |
 
 
74
 
75
 
76
  ### Framework versions