Hugging Face's logo

vadhri
/
distilhubert-finetuned-gtzan

Audio Classification
Transformers
TensorBoard
Safetensors
hubert
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
vadhri commited on
Commit
ac5396b
•
1 Parent(s): 58d836f

End of training

Browse files
Files changed (3) hide show
  1. README.md +29 -39
  2. model.safetensors +1 -1
  3. runs/Apr18_16-24-35_60760ba8fdb5/events.out.tfevents.1713458217.60760ba8fdb5.319.0 +2 -2
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
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
@@ -32,8 +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: 0.5510
36
- - Accuracy: 0.82
37
 
38
  ## Model description
39
 
@@ -52,50 +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: 30
63
  - mixed_precision_training: Native AMP
64
 
65
  ### Training results
66
 
67
- | Training Loss | Epoch | Step | Accuracy | Validation Loss |
68
- |:-------------:|:-----:|:----:|:--------:|:---------------:|
69
- | 2.201 | 1.0 | 113 | 0.39 | 2.1256 |
70
- | 1.6789 | 2.0 | 226 | 0.59 | 1.6543 |
71
- | 1.5602 | 3.0 | 339 | 0.64 | 1.3917 |
72
- | 1.1966 | 4.0 | 452 | 0.67 | 1.1946 |
73
- | 1.1131 | 5.0 | 565 | 0.77 | 1.0492 |
74
- | 1.0258 | 6.0 | 678 | 0.76 | 0.9712 |
75
- | 0.988 | 7.0 | 791 | 0.76 | 0.9160 |
76
- | 0.7303 | 8.0 | 904 | 0.8 | 0.8704 |
77
- | 0.8036 | 9.0 | 1017 | 0.8 | 0.8425 |
78
- | 0.742 | 10.0 | 1130 | 0.81 | 0.8224 |
79
- | 0.7463 | 11.0 | 1243 | 0.81 | 0.8140 |
80
- | 0.7428 | 12.0 | 1356 | 0.78 | 0.8112 |
81
- | 0.6081 | 13.0 | 1469 | 0.82 | 0.6975 |
82
- | 0.8154 | 14.0 | 1582 | 0.84 | 0.6636 |
83
- | 0.3758 | 15.0 | 1695 | 0.84 | 0.6215 |
84
- | 0.503 | 16.0 | 1808 | 0.81 | 0.6251 |
85
- | 0.4542 | 17.0 | 1921 | 0.84 | 0.5869 |
86
- | 0.3285 | 18.0 | 2034 | 0.85 | 0.5830 |
87
- | 0.4309 | 19.0 | 2147 | 0.82 | 0.5844 |
88
- | 0.342 | 20.0 | 2260 | 0.85 | 0.5840 |
89
- | 0.3051 | 21.0 | 2373 | 0.83 | 0.5843 |
90
- | 0.3558 | 22.0 | 2486 | 0.6144 | 0.79 |
91
- | 0.3371 | 23.0 | 2599 | 0.5673 | 0.81 |
92
- | 0.2882 | 24.0 | 2712 | 0.5365 | 0.84 |
93
- | 0.2326 | 25.0 | 2825 | 0.5848 | 0.83 |
94
- | 0.192 | 26.0 | 2938 | 0.5406 | 0.85 |
95
- | 0.1528 | 27.0 | 3051 | 0.5482 | 0.82 |
96
- | 0.1937 | 28.0 | 3164 | 0.5448 | 0.84 |
97
- | 0.1264 | 29.0 | 3277 | 0.5487 | 0.84 |
98
- | 0.1356 | 30.0 | 3390 | 0.5510 | 0.82 |
99
 
100
 
101
  ### Framework versions
 
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
+ value: 0.87
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: 1.1035
36
+ - Accuracy: 0.87
37
 
38
  ## Model description
39
 
 
52
  ### Training hyperparameters
53
 
54
  The following hyperparameters were used during training:
55
+ - learning_rate: 5e-05
56
+ - train_batch_size: 4
57
+ - eval_batch_size: 4
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
+ | 2.0544 | 1.0 | 225 | 1.9608 | 0.47 |
70
+ | 1.2995 | 2.0 | 450 | 1.3852 | 0.51 |
71
+ | 0.8875 | 3.0 | 675 | 0.9288 | 0.71 |
72
+ | 0.4092 | 4.0 | 900 | 0.8114 | 0.76 |
73
+ | 0.5624 | 5.0 | 1125 | 0.8704 | 0.77 |
74
+ | 0.0609 | 6.0 | 1350 | 0.7951 | 0.82 |
75
+ | 0.1018 | 7.0 | 1575 | 0.7055 | 0.86 |
76
+ | 0.2941 | 8.0 | 1800 | 0.8832 | 0.83 |
77
+ | 0.0044 | 9.0 | 2025 | 0.9883 | 0.83 |
78
+ | 0.0025 | 10.0 | 2250 | 0.9306 | 0.88 |
79
+ | 0.0016 | 11.0 | 2475 | 0.9535 | 0.86 |
80
+ | 0.0012 | 12.0 | 2700 | 1.0921 | 0.85 |
81
+ | 0.001 | 13.0 | 2925 | 1.0428 | 0.86 |
82
+ | 0.0011 | 14.0 | 3150 | 1.2270 | 0.83 |
83
+ | 0.0008 | 15.0 | 3375 | 1.1831 | 0.84 |
84
+ | 0.0007 | 16.0 | 3600 | 1.2124 | 0.84 |
85
+ | 0.0007 | 17.0 | 3825 | 1.0806 | 0.86 |
86
+ | 0.2454 | 18.0 | 4050 | 1.1530 | 0.85 |
87
+ | 0.0006 | 19.0 | 4275 | 1.1078 | 0.86 |
88
+ | 0.0006 | 20.0 | 4500 | 1.1035 | 0.87 |
 
 
 
 
 
 
 
 
 
 
89
 
90
 
91
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7274194a92f9baa8b1a97e8ceea6c22820737d8e0432d6ac4f5e9a206a69d34e
3
  size 94771728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c29763feeb5c84fe05a95fc2df04f78cadfed7ec1b5729ced944f1e763a0843
3
  size 94771728
runs/Apr18_16-24-35_60760ba8fdb5/events.out.tfevents.1713458217.60760ba8fdb5.319.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f05bbcddf17ae38a49729422b92569a46cc983d30a70e775444a8815aa13665c
3
- size 182434
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0bbb0a798e979558895ea31907c6215c350dc4108047c484123447eb4e28a906
3
+ size 202424