Hugging Face's logo

Nebyx
/
distilhubert-finetuned-gtzan

Audio Classification
Transformers
PyTorch
hubert
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
Nebyx commited on
Commit
d9ef05d
•
1 Parent(s): d6ede01

End of training

Browse files
Files changed (2) hide show
  1. README.md +20 -21
  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: 0.79
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: 1.0416
36
- - Accuracy: 0.79
37
 
38
  ## Model description
39
 
@@ -52,35 +52,34 @@ More information needed
52
  ### Training hyperparameters
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: 16
63
 
64
  ### Training results
65
 
66
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
67
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
68
- | 2.1363 | 1.0 | 113 | 2.0422 | 0.35 |
69
- | 1.4702 | 2.0 | 226 | 1.3950 | 0.58 |
70
- | 1.0964 | 3.0 | 339 | 1.0145 | 0.69 |
71
- | 1.0044 | 4.0 | 452 | 0.9337 | 0.7 |
72
- | 0.5048 | 5.0 | 565 | 0.8660 | 0.74 |
73
- | 0.404 | 6.0 | 678 | 0.7419 | 0.78 |
74
- | 0.3646 | 7.0 | 791 | 0.7474 | 0.76 |
75
- | 0.115 | 8.0 | 904 | 0.7273 | 0.8 |
76
- | 0.1827 | 9.0 | 1017 | 0.8134 | 0.8 |
77
- | 0.0188 | 10.0 | 1130 | 0.8383 | 0.83 |
78
- | 0.0129 | 11.0 | 1243 | 0.9425 | 0.8 |
79
- | 0.0342 | 12.0 | 1356 | 0.9965 | 0.8 |
80
- | 0.0075 | 13.0 | 1469 | 0.9938 | 0.8 |
81
- | 0.0069 | 14.0 | 1582 | 1.0191 | 0.8 |
82
- | 0.0063 | 15.0 | 1695 | 1.0215 | 0.79 |
83
- | 0.0056 | 16.0 | 1808 | 1.0416 | 0.79 |
84
 
85
 
86
  ### Framework versions
 
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
+ value: 0.84
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: 0.5831
36
+ - Accuracy: 0.84
37
 
38
  ## Model description
39
 
 
52
  ### Training hyperparameters
53
 
54
  The following hyperparameters were used during training:
55
+ - learning_rate: 3e-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: 15
63
 
64
  ### Training results
65
 
66
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
67
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
68
+ | 2.2116 | 1.0 | 113 | 2.1189 | 0.49 |
69
+ | 1.7203 | 2.0 | 226 | 1.6281 | 0.61 |
70
+ | 1.4375 | 3.0 | 339 | 1.2843 | 0.72 |
71
+ | 1.2632 | 4.0 | 452 | 1.1043 | 0.73 |
72
+ | 0.9465 | 5.0 | 565 | 0.9805 | 0.75 |
73
+ | 0.7118 | 6.0 | 678 | 0.8934 | 0.77 |
74
+ | 0.7515 | 7.0 | 791 | 0.7767 | 0.78 |
75
+ | 0.5352 | 8.0 | 904 | 0.7248 | 0.77 |
76
+ | 0.5492 | 9.0 | 1017 | 0.6303 | 0.85 |
77
+ | 0.3034 | 10.0 | 1130 | 0.6507 | 0.83 |
78
+ | 0.2219 | 11.0 | 1243 | 0.6366 | 0.82 |
79
+ | 0.1875 | 12.0 | 1356 | 0.6009 | 0.8 |
80
+ | 0.1476 | 13.0 | 1469 | 0.5826 | 0.84 |
81
+ | 0.258 | 14.0 | 1582 | 0.5855 | 0.84 |
82
+ | 0.4265 | 15.0 | 1695 | 0.5831 | 0.84 |
 
83
 
84
 
85
  ### Framework versions
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:01b7752be2e5aaaf8d6296b987c97d297003f8885faef2c1460c3ff07e74c4ad
3
  size 94783376
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55444da9fd3d22a268da84d15fcac3f29ece3a695bcc32403300a86f4dc85f74
3
  size 94783376