Hugging Face's logo

StatsGary
/
distilhubert-finetuned-gtzan

Audio Classification
Transformers
PyTorch
TensorBoard
hubert
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
1
StatsGary commited on
Commit
20d925c
•
1 Parent(s): 2a4c7fa

End of training

Browse files
Files changed (2) hide show
  1. README.md +15 -17
  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: 0.8656
36
- - Accuracy: 0.79
37
 
38
  ## Model description
39
 
@@ -61,29 +61,27 @@ The following hyperparameters were used during training:
61
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
62
  - lr_scheduler_type: linear
63
  - lr_scheduler_warmup_ratio: 0.1
64
- - num_epochs: 12
65
 
66
  ### Training results
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
- | 2.2551 | 0.99 | 28 | 2.1958 | 0.42 |
71
- | 1.9057 | 1.98 | 56 | 1.8188 | 0.48 |
72
- | 1.5675 | 2.97 | 84 | 1.5186 | 0.6 |
73
- | 1.3558 | 4.0 | 113 | 1.3338 | 0.62 |
74
- | 1.173 | 4.99 | 141 | 1.1868 | 0.67 |
75
- | 1.0698 | 5.98 | 169 | 1.0959 | 0.69 |
76
- | 0.9679 | 6.97 | 197 | 1.0034 | 0.71 |
77
- | 0.931 | 8.0 | 226 | 0.9618 | 0.77 |
78
- | 0.7555 | 8.99 | 254 | 0.9024 | 0.78 |
79
- | 0.7125 | 9.98 | 282 | 0.8882 | 0.8 |
80
- | 0.6674 | 10.97 | 310 | 0.8610 | 0.8 |
81
- | 0.6338 | 11.89 | 336 | 0.8656 | 0.79 |
82
 
83
 
84
  ### Framework versions
85
 
86
  - Transformers 4.32.0.dev0
87
  - Pytorch 2.0.1+cu118
88
- - Datasets 2.13.1
89
  - Tokenizers 0.13.3
 
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: 0.6339
36
+ - Accuracy: 0.85
37
 
38
  ## Model description
39
 
 
61
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
62
  - lr_scheduler_type: linear
63
  - lr_scheduler_warmup_ratio: 0.1
64
+ - num_epochs: 10
65
 
66
  ### Training results
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
+ | 0.3209 | 0.99 | 28 | 0.6060 | 0.79 |
71
+ | 0.2765 | 1.98 | 56 | 0.6062 | 0.8 |
72
+ | 0.1591 | 2.97 | 84 | 0.5890 | 0.82 |
73
+ | 0.1229 | 4.0 | 113 | 0.5589 | 0.85 |
74
+ | 0.1015 | 4.99 | 141 | 0.6551 | 0.87 |
75
+ | 0.0537 | 5.98 | 169 | 0.6066 | 0.84 |
76
+ | 0.0422 | 6.97 | 197 | 0.5947 | 0.84 |
77
+ | 0.0422 | 8.0 | 226 | 0.5898 | 0.85 |
78
+ | 0.0415 | 8.99 | 254 | 0.6020 | 0.85 |
79
+ | 0.0296 | 9.91 | 280 | 0.6339 | 0.85 |
 
 
80
 
81
 
82
  ### Framework versions
83
 
84
  - Transformers 4.32.0.dev0
85
  - Pytorch 2.0.1+cu118
86
+ - Datasets 2.14.3
87
  - Tokenizers 0.13.3
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f9fbe28cde5e6b22058985b64adc46a735e25e3cf741ac1ab9cc9421644bf013
3
  size 94783376
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f40f4da4ae1e89d9ff2d47d86abf2fa698f586c63ebc1d0c569b39f8e15406a
3
  size 94783376