Hugging Face's logo

Joserzapata
/
distilhubert-finetuned-gtzan

Audio Classification
Transformers
PyTorch
TensorBoard
hubert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
Joserzapata commited on
Commit
68244cb
•
1 Parent(s): b3738e5

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +20 -13
README.md CHANGED
@@ -18,8 +18,8 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  This model is a fine-tuned version of [ntu-spml/distilhubert](https://huggingface.co/ntu-spml/distilhubert) on the GTZAN dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 0.6869
22
- - Accuracy: 0.7889
23
 
24
  ## Model description
25
 
@@ -45,22 +45,29 @@ The following hyperparameters were used during training:
45
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
  - lr_scheduler_type: linear
47
  - lr_scheduler_warmup_ratio: 0.1
48
- - num_epochs: 10
49
 
50
  ### Training results
51
 
52
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
53
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
54
- | 1.9903 | 1.0 | 102 | 1.9462 | 0.5333 |
55
- | 1.4477 | 2.0 | 204 | 1.3659 | 0.5111 |
56
- | 1.082 | 3.0 | 306 | 1.1169 | 0.6444 |
57
- | 0.967 | 4.0 | 408 | 0.8758 | 0.8111 |
58
- | 0.4794 | 5.0 | 510 | 0.7574 | 0.8 |
59
- | 0.4756 | 6.0 | 612 | 0.7637 | 0.7667 |
60
- | 0.2381 | 7.0 | 714 | 0.7337 | 0.7889 |
61
- | 0.2841 | 8.0 | 816 | 0.6546 | 0.8111 |
62
- | 0.098 | 9.0 | 918 | 0.6680 | 0.8111 |
63
- | 0.1294 | 10.0 | 1020 | 0.6869 | 0.7889 |
 
 
 
 
 
 
 
64
 
65
 
66
  ### Framework versions
 
18
 
19
  This model is a fine-tuned version of [ntu-spml/distilhubert](https://huggingface.co/ntu-spml/distilhubert) on the GTZAN dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.8818
22
+ - Accuracy: 0.85
23
 
24
  ## Model description
25
 
 
45
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
  - lr_scheduler_type: linear
47
  - lr_scheduler_warmup_ratio: 0.1
48
+ - num_epochs: 17
49
 
50
  ### Training results
51
 
52
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
53
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
54
+ | 1.5851 | 1.0 | 113 | 1.7243 | 0.5 |
55
+ | 1.2937 | 2.0 | 226 | 1.2310 | 0.68 |
56
+ | 0.9718 | 3.0 | 339 | 0.8918 | 0.76 |
57
+ | 0.6613 | 4.0 | 452 | 0.6837 | 0.81 |
58
+ | 0.3693 | 5.0 | 565 | 0.6250 | 0.82 |
59
+ | 0.2991 | 6.0 | 678 | 0.5740 | 0.82 |
60
+ | 0.1381 | 7.0 | 791 | 0.5874 | 0.83 |
61
+ | 0.2047 | 8.0 | 904 | 0.5824 | 0.86 |
62
+ | 0.1192 | 9.0 | 1017 | 0.7106 | 0.83 |
63
+ | 0.0652 | 10.0 | 1130 | 0.6576 | 0.87 |
64
+ | 0.0105 | 11.0 | 1243 | 0.8236 | 0.84 |
65
+ | 0.0074 | 12.0 | 1356 | 0.7874 | 0.85 |
66
+ | 0.0064 | 13.0 | 1469 | 0.9066 | 0.84 |
67
+ | 0.0041 | 14.0 | 1582 | 0.8426 | 0.85 |
68
+ | 0.0038 | 15.0 | 1695 | 0.8676 | 0.84 |
69
+ | 0.0039 | 16.0 | 1808 | 0.8820 | 0.85 |
70
+ | 0.0036 | 17.0 | 1921 | 0.8818 | 0.85 |
71
 
72
 
73
  ### Framework versions