Hugging Face's logo

AltamashAhmed
/
distilHuBERT-finetuned-gtzan

Audio Classification
Transformers
PyTorch
hubert
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
AltamashAhmed commited on
Commit
ef4156d
•
1 Parent(s): 76e3609

End of training

Browse files
Files changed (2) hide show
  1. README.md +14 -19
  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: 0.84
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: 0.6265
36
- - Accuracy: 0.84
37
 
38
  ## Model description
39
 
@@ -59,30 +59,25 @@ The following hyperparameters were used during training:
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: 13
63
 
64
  ### Training results
65
 
66
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
67
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
68
- | 2.0988 | 1.0 | 113 | 1.9164 | 0.56 |
69
- | 1.3834 | 2.0 | 226 | 1.2485 | 0.7 |
70
- | 1.1343 | 3.0 | 339 | 0.9713 | 0.75 |
71
- | 0.897 | 4.0 | 452 | 0.7710 | 0.76 |
72
- | 0.5256 | 5.0 | 565 | 0.6420 | 0.84 |
73
- | 0.3336 | 6.0 | 678 | 0.5857 | 0.78 |
74
- | 0.3573 | 7.0 | 791 | 0.6032 | 0.82 |
75
- | 0.1263 | 8.0 | 904 | 0.5329 | 0.87 |
76
- | 0.1441 | 9.0 | 1017 | 0.5311 | 0.86 |
77
- | 0.0638 | 10.0 | 1130 | 0.6264 | 0.83 |
78
- | 0.0302 | 11.0 | 1243 | 0.6195 | 0.86 |
79
- | 0.033 | 12.0 | 1356 | 0.6380 | 0.85 |
80
- | 0.0181 | 13.0 | 1469 | 0.6265 | 0.84 |
81
 
82
 
83
  ### Framework versions
84
 
85
- - Transformers 4.32.1
86
  - Pytorch 2.0.1+cu118
87
- - Datasets 2.14.4
88
  - 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: 0.5657
36
+ - Accuracy: 0.85
37
 
38
  ## Model description
39
 
 
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: 8
63
 
64
  ### Training results
65
 
66
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
67
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
68
+ | 1.9277 | 1.0 | 113 | 1.7812 | 0.41 |
69
+ | 1.3526 | 2.0 | 226 | 1.1616 | 0.67 |
70
+ | 1.043 | 3.0 | 339 | 0.8962 | 0.78 |
71
+ | 0.8494 | 4.0 | 452 | 0.8234 | 0.76 |
72
+ | 0.5931 | 5.0 | 565 | 0.7085 | 0.78 |
73
+ | 0.3861 | 6.0 | 678 | 0.6669 | 0.8 |
74
+ | 0.4828 | 7.0 | 791 | 0.5674 | 0.86 |
75
+ | 0.2302 | 8.0 | 904 | 0.5657 | 0.85 |
 
 
 
 
 
76
 
77
 
78
  ### Framework versions
79
 
80
+ - Transformers 4.33.1
81
  - Pytorch 2.0.1+cu118
82
+ - Datasets 2.14.5
83
  - Tokenizers 0.13.3
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6df179eb41445adb1ce09d0bdbd1aee0cf57933acca2fbb44e8295c9bf30263f
3
  size 94783376
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9d404b3102baa385f586046a7b8ab945335b4b232dad48f6d6dfa29627be9dc
3
  size 94783376