Hugging Face's logo

AK-12
/
my_awesome_model

Audio Classification
Transformers
PyTorch
TensorBoard
hubert
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
AK-12 commited on
Commit
d617ef5
•
1 Parent(s): abf5e10

End of training

Browse files
Files changed (2) hide show
  1. README.md +29 -24
  2. pytorch_model.bin +1 -1
README.md CHANGED
@@ -8,7 +8,7 @@ datasets:
8
  metrics:
9
  - accuracy
10
  model-index:
11
- - name: DistilHuBERT-finetuned-gtzan
12
  results:
13
  - task:
14
  name: Audio Classification
@@ -22,18 +22,18 @@ model-index:
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
29
  should probably proofread and complete it, then remove this comment. -->
30
 
31
- # DistilHuBERT-finetuned-gtzan
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: 0.8372
36
- - Accuracy: 0.85
37
 
38
  ## Model description
39
 
@@ -52,34 +52,39 @@ More information needed
52
  ### Training hyperparameters
53
 
54
  The following hyperparameters were used during training:
55
- - learning_rate: 6e-05
56
- - train_batch_size: 7
57
- - eval_batch_size: 7
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
- | 1.9696 | 1.0 | 129 | 1.8571 | 0.55 |
69
- | 1.4269 | 2.0 | 258 | 1.2394 | 0.61 |
70
- | 1.0166 | 3.0 | 387 | 1.0173 | 0.74 |
71
- | 0.7446 | 4.0 | 516 | 0.8103 | 0.75 |
72
- | 0.4953 | 5.0 | 645 | 0.7800 | 0.77 |
73
- | 0.3973 | 6.0 | 774 | 0.7359 | 0.81 |
74
- | 0.2831 | 7.0 | 903 | 0.6434 | 0.84 |
75
- | 0.2147 | 8.0 | 1032 | 0.6592 | 0.84 |
76
- | 0.1287 | 9.0 | 1161 | 0.6988 | 0.85 |
77
- | 0.014 | 10.0 | 1290 | 0.7569 | 0.83 |
78
- | 0.0073 | 11.0 | 1419 | 0.8282 | 0.84 |
79
- | 0.0049 | 12.0 | 1548 | 0.8531 | 0.84 |
80
- | 0.0053 | 13.0 | 1677 | 0.8584 | 0.84 |
81
- | 0.0044 | 14.0 | 1806 | 0.8707 | 0.84 |
82
- | 0.0038 | 15.0 | 1935 | 0.8372 | 0.85 |
 
 
 
83
 
84
 
85
  ### Framework versions
 
8
  metrics:
9
  - accuracy
10
  model-index:
11
+ - name: distilhubert-finetuned-gtzan
12
  results:
13
  - task:
14
  name: Audio Classification
 
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
+ value: 0.82
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
29
  should probably proofread and complete it, then remove this comment. -->
30
 
31
+ # distilhubert-finetuned-gtzan
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: 1.0646
36
+ - Accuracy: 0.82
37
 
38
  ## Model description
39
 
 
52
  ### Training hyperparameters
53
 
54
  The following hyperparameters were used during training:
55
+ - learning_rate: 5e-05
56
+ - train_batch_size: 2
57
+ - eval_batch_size: 2
58
  - seed: 42
59
+ - gradient_accumulation_steps: 2
60
+ - total_train_batch_size: 4
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: 18
65
 
66
  ### Training results
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
+ | 2.0114 | 1.0 | 225 | 1.8491 | 0.5 |
71
+ | 1.1983 | 2.0 | 450 | 1.1911 | 0.68 |
72
+ | 1.1408 | 3.0 | 675 | 0.9290 | 0.72 |
73
+ | 0.7166 | 4.0 | 900 | 0.7200 | 0.78 |
74
+ | 0.5334 | 5.0 | 1125 | 0.7233 | 0.79 |
75
+ | 0.3294 | 6.0 | 1350 | 0.4989 | 0.83 |
76
+ | 0.2949 | 7.0 | 1575 | 0.5294 | 0.85 |
77
+ | 0.0067 | 8.0 | 1800 | 0.7724 | 0.83 |
78
+ | 0.0041 | 9.0 | 2025 | 0.8986 | 0.8 |
79
+ | 0.0049 | 10.0 | 2250 | 0.9146 | 0.83 |
80
+ | 0.0016 | 11.0 | 2475 | 0.8999 | 0.85 |
81
+ | 0.0013 | 12.0 | 2700 | 0.8947 | 0.86 |
82
+ | 0.0015 | 13.0 | 2925 | 0.9257 | 0.85 |
83
+ | 0.0009 | 14.0 | 3150 | 1.0211 | 0.82 |
84
+ | 0.0009 | 15.0 | 3375 | 0.9288 | 0.84 |
85
+ | 0.0008 | 16.0 | 3600 | 0.9672 | 0.82 |
86
+ | 0.0009 | 17.0 | 3825 | 1.0717 | 0.82 |
87
+ | 0.0756 | 18.0 | 4050 | 1.0646 | 0.82 |
88
 
89
 
90
  ### Framework versions
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ee6e19fb5eab6eafc95dd5c57e519816fa3f678c9b065238466e3972f6b94034
3
  size 94783376
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:863f8185ac6054ec342cd29c665c50117e1c0bd0011a8f46f363575175beb329
3
  size 94783376