JvThunder commited on
Commit
7a39fe1
1 Parent(s): 5ec3e58

End of training

Browse files
Files changed (2) hide show
  1. README.md +25 -15
  2. model.safetensors +1 -1
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
- value: 0.78
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: 0.9204
36
- - Accuracy: 0.78
37
 
38
  ## Model description
39
 
@@ -52,30 +52,40 @@ More information needed
52
  ### Training hyperparameters
53
 
54
  The following hyperparameters were used during training:
55
- - learning_rate: 2e-05
56
  - train_batch_size: 8
57
  - eval_batch_size: 8
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
- | 2.2131 | 1.0 | 113 | 2.0971 | 0.42 |
70
- | 1.786 | 2.0 | 226 | 1.6744 | 0.56 |
71
- | 1.5128 | 3.0 | 339 | 1.4491 | 0.66 |
72
- | 1.2987 | 4.0 | 452 | 1.2673 | 0.74 |
73
- | 1.1823 | 5.0 | 565 | 1.1610 | 0.71 |
74
- | 1.0707 | 6.0 | 678 | 1.0937 | 0.74 |
75
- | 1.0015 | 7.0 | 791 | 1.0214 | 0.75 |
76
- | 0.8765 | 8.0 | 904 | 0.9650 | 0.75 |
77
- | 0.833 | 9.0 | 1017 | 0.9415 | 0.75 |
78
- | 0.7924 | 10.0 | 1130 | 0.9204 | 0.78 |
 
 
 
 
 
 
 
 
 
 
79
 
80
 
81
  ### Framework versions
 
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
+ value: 0.82
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: 0.6623
36
+ - Accuracy: 0.82
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: 8
57
  - eval_batch_size: 8
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: 20
63
  - mixed_precision_training: Native AMP
64
 
65
  ### Training results
66
 
67
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
68
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
69
+ | 2.2457 | 1.0 | 113 | 2.1827 | 0.33 |
70
+ | 1.8385 | 2.0 | 226 | 1.6935 | 0.61 |
71
+ | 1.46 | 3.0 | 339 | 1.4282 | 0.63 |
72
+ | 1.1508 | 4.0 | 452 | 1.1055 | 0.7 |
73
+ | 0.9972 | 5.0 | 565 | 0.8945 | 0.74 |
74
+ | 0.7826 | 6.0 | 678 | 0.7784 | 0.77 |
75
+ | 0.6802 | 7.0 | 791 | 0.7184 | 0.8 |
76
+ | 0.4635 | 8.0 | 904 | 0.7725 | 0.76 |
77
+ | 0.3746 | 9.0 | 1017 | 0.5875 | 0.84 |
78
+ | 0.264 | 10.0 | 1130 | 0.7612 | 0.75 |
79
+ | 0.1995 | 11.0 | 1243 | 0.6099 | 0.81 |
80
+ | 0.135 | 12.0 | 1356 | 0.6306 | 0.81 |
81
+ | 0.0974 | 13.0 | 1469 | 0.5947 | 0.83 |
82
+ | 0.0563 | 14.0 | 1582 | 0.7485 | 0.8 |
83
+ | 0.0443 | 15.0 | 1695 | 0.6977 | 0.79 |
84
+ | 0.0565 | 16.0 | 1808 | 0.6331 | 0.83 |
85
+ | 0.0295 | 17.0 | 1921 | 0.6538 | 0.82 |
86
+ | 0.0178 | 18.0 | 2034 | 0.6977 | 0.82 |
87
+ | 0.0191 | 19.0 | 2147 | 0.6453 | 0.83 |
88
+ | 0.0147 | 20.0 | 2260 | 0.6623 | 0.82 |
89
 
90
 
91
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d1c275152875fd2108c135f71334a5239b164f79b47f937d4d0a07b7217d1811
3
  size 94771728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7cd64385397fe00e287b20426b4b0b1136bc9186d1d4f26571d1fcc9179cdf88
3
  size 94771728