Hugging Face's logo

mmcgovern574
/
distilhubert-finetuned-gtzan

Audio Classification
Transformers
TensorBoard
Safetensors
hubert
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
mmcgovern574 commited on
Commit
cb3b8de
•
1 Parent(s): dc2c417

End of training

Browse files
Files changed (2) hide show
  1. README.md +16 -36
  2. model.safetensors +1 -1
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
- value: 0.81
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: 1.0178
36
- - Accuracy: 0.81
37
 
38
  ## Model description
39
 
@@ -52,55 +52,35 @@ More information needed
52
  ### Training hyperparameters
53
 
54
  The following hyperparameters were used during training:
55
- - learning_rate: 5e-05
56
  - train_batch_size: 16
57
  - eval_batch_size: 16
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: 30
63
  - mixed_precision_training: Native AMP
64
 
65
  ### Training results
66
 
67
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
68
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
69
- | 2.2598 | 1.0 | 57 | 2.2140 | 0.34 |
70
- | 1.8981 | 2.0 | 114 | 1.8262 | 0.56 |
71
- | 1.4487 | 3.0 | 171 | 1.4402 | 0.64 |
72
- | 1.1792 | 4.0 | 228 | 1.1520 | 0.69 |
73
- | 0.9231 | 5.0 | 285 | 0.9415 | 0.75 |
74
- | 0.7141 | 6.0 | 342 | 0.8904 | 0.73 |
75
- | 0.5477 | 7.0 | 399 | 0.7395 | 0.78 |
76
- | 0.3968 | 8.0 | 456 | 0.6359 | 0.81 |
77
- | 0.4259 | 9.0 | 513 | 0.6345 | 0.8 |
78
- | 0.2474 | 10.0 | 570 | 0.6333 | 0.8 |
79
- | 0.1379 | 11.0 | 627 | 0.5374 | 0.83 |
80
- | 0.0781 | 12.0 | 684 | 0.6484 | 0.84 |
81
- | 0.0337 | 13.0 | 741 | 0.7072 | 0.84 |
82
- | 0.0211 | 14.0 | 798 | 0.7023 | 0.83 |
83
- | 0.0135 | 15.0 | 855 | 0.8199 | 0.83 |
84
- | 0.0097 | 16.0 | 912 | 0.8009 | 0.83 |
85
- | 0.065 | 17.0 | 969 | 0.8992 | 0.81 |
86
- | 0.0067 | 18.0 | 1026 | 0.8628 | 0.82 |
87
- | 0.0118 | 19.0 | 1083 | 0.6922 | 0.85 |
88
- | 0.0052 | 20.0 | 1140 | 0.8001 | 0.84 |
89
- | 0.077 | 21.0 | 1197 | 0.8324 | 0.82 |
90
- | 0.0043 | 22.0 | 1254 | 0.9468 | 0.8 |
91
- | 0.0039 | 23.0 | 1311 | 0.8866 | 0.8 |
92
- | 0.0696 | 24.0 | 1368 | 0.9424 | 0.82 |
93
- | 0.0037 | 25.0 | 1425 | 0.7855 | 0.81 |
94
- | 0.0631 | 26.0 | 1482 | 0.7659 | 0.82 |
95
- | 0.0592 | 27.0 | 1539 | 0.8605 | 0.83 |
96
- | 0.0034 | 28.0 | 1596 | 0.9266 | 0.82 |
97
- | 0.0032 | 29.0 | 1653 | 0.9831 | 0.82 |
98
- | 0.0032 | 30.0 | 1710 | 1.0178 | 0.81 |
99
 
100
 
101
  ### Framework versions
102
 
103
  - Transformers 4.36.2
104
  - Pytorch 2.1.0+cu121
105
- - Datasets 2.15.0
106
  - Tokenizers 0.15.0
 
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: 0.8742
36
+ - Accuracy: 0.79
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: 16
57
  - eval_batch_size: 16
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: 10
63
  - mixed_precision_training: Native AMP
64
 
65
  ### Training results
66
 
67
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
68
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
69
+ | 2.2265 | 1.0 | 57 | 2.1424 | 0.41 |
70
+ | 1.7837 | 2.0 | 114 | 1.6990 | 0.54 |
71
+ | 1.4838 | 3.0 | 171 | 1.4898 | 0.63 |
72
+ | 1.3231 | 4.0 | 228 | 1.2616 | 0.7 |
73
+ | 1.1623 | 5.0 | 285 | 1.1048 | 0.75 |
74
+ | 1.043 | 6.0 | 342 | 1.0032 | 0.77 |
75
+ | 0.9029 | 7.0 | 399 | 0.9896 | 0.76 |
76
+ | 0.8869 | 8.0 | 456 | 0.8895 | 0.81 |
77
+ | 0.8797 | 9.0 | 513 | 0.8821 | 0.8 |
78
+ | 0.8542 | 10.0 | 570 | 0.8742 | 0.79 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
79
 
80
 
81
  ### Framework versions
82
 
83
  - Transformers 4.36.2
84
  - Pytorch 2.1.0+cu121
85
+ - Datasets 2.16.0
86
  - Tokenizers 0.15.0
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0b674ae7f8c6831e3e99ec1bf8eabc1197c502535a50b86e17773e15507d5e43
3
  size 94771728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d786989009ef96653a8e0ce50a951864dac4da0208603368b1b90a1cf5e28c60
3
  size 94771728