DanGalt commited on
Commit
dc457a7
1 Parent(s): fdbee29

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +12 -16
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: 0.7186
22
- - Accuracy: 0.86
23
 
24
  ## Model description
25
 
@@ -43,27 +43,23 @@ The following hyperparameters were used during training:
43
  - eval_batch_size: 16
44
  - seed: 42
45
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-05
46
- - lr_scheduler_type: linear
47
  - lr_scheduler_warmup_ratio: 0.1
48
- - num_epochs: 12
49
  - label_smoothing_factor: 0.05
50
 
51
  ### Training results
52
 
53
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
54
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
55
- | 1.7045 | 1.0 | 113 | 1.7952 | 0.44 |
56
- | 1.1808 | 2.0 | 226 | 1.1510 | 0.66 |
57
- | 1.0978 | 3.0 | 339 | 0.9947 | 0.74 |
58
- | 0.837 | 4.0 | 452 | 0.8767 | 0.81 |
59
- | 0.5078 | 5.0 | 565 | 0.7830 | 0.86 |
60
- | 0.3832 | 6.0 | 678 | 0.7838 | 0.84 |
61
- | 0.3902 | 7.0 | 791 | 0.8064 | 0.83 |
62
- | 0.3322 | 8.0 | 904 | 0.7964 | 0.82 |
63
- | 0.3455 | 9.0 | 1017 | 0.7507 | 0.87 |
64
- | 0.2924 | 10.0 | 1130 | 0.8073 | 0.86 |
65
- | 0.2925 | 11.0 | 1243 | 0.7269 | 0.86 |
66
- | 0.2853 | 12.0 | 1356 | 0.7186 | 0.86 |
67
 
68
 
69
  ### 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: 0.7162
22
+ - Accuracy: 0.88
23
 
24
  ## Model description
25
 
 
43
  - eval_batch_size: 16
44
  - seed: 42
45
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-05
46
+ - lr_scheduler_type: cosine
47
  - lr_scheduler_warmup_ratio: 0.1
48
+ - num_epochs: 8
49
  - label_smoothing_factor: 0.05
50
 
51
  ### Training results
52
 
53
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
54
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
55
+ | 1.5923 | 1.0 | 113 | 1.7310 | 0.44 |
56
+ | 1.2071 | 2.0 | 226 | 1.2546 | 0.62 |
57
+ | 1.0673 | 3.0 | 339 | 0.9320 | 0.76 |
58
+ | 0.8149 | 4.0 | 452 | 0.8768 | 0.81 |
59
+ | 0.4999 | 5.0 | 565 | 0.7154 | 0.86 |
60
+ | 0.3562 | 6.0 | 678 | 0.6631 | 0.89 |
61
+ | 0.3852 | 7.0 | 791 | 0.7136 | 0.87 |
62
+ | 0.4476 | 8.0 | 904 | 0.7162 | 0.88 |
 
 
 
 
63
 
64
 
65
  ### Framework versions