Hugging Face's logo

sophiaaez
/
distilhubert-finetuned-gtzan

Audio Classification
Transformers
PyTorch
hubert
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
sophiaaez commited on
Commit
186f768
•
1 Parent(s): 6055472

End of training

Browse files
Files changed (2) hide show
  1. README.md +16 -16
  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: 0.86
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: 0.4935
36
- - Accuracy: 0.86
37
 
38
  ## Model description
39
 
@@ -53,8 +53,8 @@ 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
@@ -65,16 +65,16 @@ The following hyperparameters were used during training:
65
 
66
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
67
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
68
- | 1.9946 | 1.0 | 113 | 1.8240 | 0.34 |
69
- | 1.3654 | 2.0 | 226 | 1.2118 | 0.64 |
70
- | 1.0678 | 3.0 | 339 | 0.9148 | 0.76 |
71
- | 0.8561 | 4.0 | 452 | 0.8637 | 0.73 |
72
- | 0.6218 | 5.0 | 565 | 0.7036 | 0.82 |
73
- | 0.4345 | 6.0 | 678 | 0.6201 | 0.85 |
74
- | 0.3861 | 7.0 | 791 | 0.5078 | 0.84 |
75
- | 0.1951 | 8.0 | 904 | 0.5180 | 0.86 |
76
- | 0.1886 | 9.0 | 1017 | 0.4792 | 0.86 |
77
- | 0.1548 | 10.0 | 1130 | 0.4935 | 0.86 |
78
 
79
 
80
  ### Framework versions
@@ -82,4 +82,4 @@ The following hyperparameters were used during training:
82
  - Transformers 4.34.0.dev0
83
  - Pytorch 2.0.1+cu118
84
  - Datasets 2.14.5
85
- - Tokenizers 0.13.3
 
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
 
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: 0.7146
36
+ - Accuracy: 0.79
37
 
38
  ## Model description
39
 
 
53
 
54
  The following hyperparameters were used during training:
55
  - learning_rate: 5e-05
56
+ - train_batch_size: 12
57
+ - eval_batch_size: 12
58
  - seed: 42
59
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
60
  - lr_scheduler_type: linear
 
65
 
66
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
67
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
68
+ | 2.0711 | 1.0 | 75 | 1.9438 | 0.49 |
69
+ | 1.4944 | 2.0 | 150 | 1.4307 | 0.53 |
70
+ | 1.2562 | 3.0 | 225 | 1.2180 | 0.65 |
71
+ | 0.9436 | 4.0 | 300 | 1.0209 | 0.71 |
72
+ | 0.7543 | 5.0 | 375 | 0.9073 | 0.73 |
73
+ | 0.5742 | 6.0 | 450 | 0.8047 | 0.75 |
74
+ | 0.4728 | 7.0 | 525 | 0.7736 | 0.78 |
75
+ | 0.3622 | 8.0 | 600 | 0.7412 | 0.78 |
76
+ | 0.2447 | 9.0 | 675 | 0.7117 | 0.79 |
77
+ | 0.2692 | 10.0 | 750 | 0.7146 | 0.79 |
78
 
79
 
80
  ### Framework versions
 
82
  - Transformers 4.34.0.dev0
83
  - Pytorch 2.0.1+cu118
84
  - Datasets 2.14.5
85
+ - Tokenizers 0.14.0
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b11476b6ddcd59cf7b9d86f1209d82e473cc604f6c068ba1d20fdea7c0311e8b
3
  size 94783376
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b1c2b9254a45f1d3346b94d229a6a4d8d0124cf1f35438e6018e4ce15e16ad0
3
  size 94783376