Hugging Face's logo

HamzaSidhu786
/
distilhubert-finetuned-gtzan

Audio Classification
Transformers
TensorBoard
Safetensors
wav2vec2
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
HamzaSidhu786 commited on
Commit
1d0e659
•
1 Parent(s): c366957

End of training

Browse files
Files changed (2) hide show
  1. README.md +17 -22
  2. model.safetensors +1 -1
README.md CHANGED
@@ -32,7 +32,7 @@ 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: 0.8648
36
  - Accuracy: 0.81
37
 
38
  ## Model description
@@ -59,33 +59,28 @@ 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: 20
63
  - mixed_precision_training: Native AMP
64
 
65
  ### Training results
66
 
67
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
68
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
69
- | 2.1594 | 1.0 | 113 | 2.0722 | 0.45 |
70
- | 1.4046 | 2.0 | 226 | 1.4840 | 0.63 |
71
- | 1.1503 | 3.0 | 339 | 1.0766 | 0.66 |
72
- | 0.7387 | 4.0 | 452 | 0.8226 | 0.7 |
73
- | 0.6617 | 5.0 | 565 | 0.7088 | 0.77 |
74
- | 0.5273 | 6.0 | 678 | 0.8223 | 0.72 |
75
- | 0.4523 | 7.0 | 791 | 0.6028 | 0.82 |
76
- | 0.0942 | 8.0 | 904 | 0.6897 | 0.78 |
77
- | 0.06 | 9.0 | 1017 | 0.7145 | 0.82 |
78
- | 0.019 | 10.0 | 1130 | 0.6940 | 0.8 |
79
- | 0.0138 | 11.0 | 1243 | 0.8471 | 0.79 |
80
- | 0.0074 | 12.0 | 1356 | 0.8929 | 0.76 |
81
- | 0.0052 | 13.0 | 1469 | 0.8341 | 0.8 |
82
- | 0.0047 | 14.0 | 1582 | 0.9248 | 0.79 |
83
- | 0.0035 | 15.0 | 1695 | 0.9051 | 0.78 |
84
- | 0.0037 | 16.0 | 1808 | 0.8626 | 0.79 |
85
- | 0.0034 | 17.0 | 1921 | 0.8535 | 0.81 |
86
- | 0.0028 | 18.0 | 2034 | 0.9157 | 0.79 |
87
- | 0.0028 | 19.0 | 2147 | 0.8729 | 0.79 |
88
- | 0.0032 | 20.0 | 2260 | 0.8648 | 0.81 |
89
 
90
 
91
  ### Framework versions
 
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: 0.9459
36
  - Accuracy: 0.81
37
 
38
  ## Model description
 
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
  - mixed_precision_training: Native AMP
64
 
65
  ### Training results
66
 
67
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
68
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
69
+ | 2.1346 | 1.0 | 113 | 2.0097 | 0.52 |
70
+ | 1.3431 | 2.0 | 226 | 1.3485 | 0.63 |
71
+ | 1.0836 | 3.0 | 339 | 1.0567 | 0.7 |
72
+ | 0.707 | 4.0 | 452 | 0.9165 | 0.73 |
73
+ | 0.6421 | 5.0 | 565 | 0.7648 | 0.79 |
74
+ | 0.4217 | 6.0 | 678 | 0.8743 | 0.76 |
75
+ | 0.2786 | 7.0 | 791 | 0.7573 | 0.8 |
76
+ | 0.1399 | 8.0 | 904 | 0.8341 | 0.75 |
77
+ | 0.0586 | 9.0 | 1017 | 0.8662 | 0.81 |
78
+ | 0.0246 | 10.0 | 1130 | 0.9017 | 0.8 |
79
+ | 0.0139 | 11.0 | 1243 | 0.8831 | 0.79 |
80
+ | 0.0106 | 12.0 | 1356 | 0.9298 | 0.82 |
81
+ | 0.0092 | 13.0 | 1469 | 0.9264 | 0.81 |
82
+ | 0.0087 | 14.0 | 1582 | 0.9466 | 0.82 |
83
+ | 0.0071 | 15.0 | 1695 | 0.9459 | 0.81 |
 
 
 
 
 
84
 
85
 
86
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:983041b800eea1dbe5d13fa7af777c473519a897ce895473bd6dd8bffe9b6fff
3
  size 94771728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d6a8782c36e3e9135cbc290375011814d2cf4e7070af277f2d8c0cbbba0f3e8
3
  size 94771728