Hugging Face's logo

karanjakhar
/
distilhubert-finetuned-gtzan

Audio Classification
Transformers
PyTorch
hubert
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
karanjakhar commited on
Commit
000682e
•
1 Parent(s): 3a0a82a

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +15 -21
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
- value: 0.85
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: 0.6094
36
- - Accuracy: 0.85
37
 
38
  ## Model description
39
 
@@ -52,7 +52,7 @@ More information needed
52
  ### Training hyperparameters
53
 
54
  The following hyperparameters were used during training:
55
- - learning_rate: 5e-05
56
  - train_batch_size: 8
57
  - eval_batch_size: 8
58
  - seed: 42
@@ -61,28 +61,22 @@ The following hyperparameters were used during training:
61
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
62
  - lr_scheduler_type: linear
63
  - lr_scheduler_warmup_ratio: 0.1
64
- - num_epochs: 16
65
 
66
  ### Training results
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
- | 2.1935 | 0.99 | 56 | 2.1282 | 0.42 |
71
- | 1.6089 | 2.0 | 113 | 1.5367 | 0.57 |
72
- | 1.2446 | 2.99 | 169 | 1.1485 | 0.74 |
73
- | 0.98 | 4.0 | 226 | 0.9621 | 0.76 |
74
- | 0.7296 | 4.99 | 282 | 0.7948 | 0.82 |
75
- | 0.5111 | 6.0 | 339 | 0.7578 | 0.79 |
76
- | 0.583 | 6.99 | 395 | 0.6152 | 0.86 |
77
- | 0.4002 | 8.0 | 452 | 0.5863 | 0.85 |
78
- | 0.2924 | 8.99 | 508 | 0.5834 | 0.84 |
79
- | 0.1789 | 10.0 | 565 | 0.6087 | 0.85 |
80
- | 0.1181 | 10.99 | 621 | 0.5911 | 0.84 |
81
- | 0.0673 | 12.0 | 678 | 0.5887 | 0.85 |
82
- | 0.0633 | 12.99 | 734 | 0.6294 | 0.84 |
83
- | 0.0393 | 14.0 | 791 | 0.6205 | 0.84 |
84
- | 0.0362 | 14.99 | 847 | 0.6382 | 0.85 |
85
- | 0.0328 | 15.86 | 896 | 0.6094 | 0.85 |
86
 
87
 
88
  ### Framework versions
 
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
+ value: 0.86
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: 0.5269
36
+ - Accuracy: 0.86
37
 
38
  ## Model description
39
 
 
52
  ### Training hyperparameters
53
 
54
  The following hyperparameters were used during training:
55
+ - learning_rate: 0.0001
56
  - train_batch_size: 8
57
  - eval_batch_size: 8
58
  - seed: 42
 
61
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
62
  - lr_scheduler_type: linear
63
  - lr_scheduler_warmup_ratio: 0.1
64
+ - num_epochs: 10
65
 
66
  ### Training results
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
+ | 1.9286 | 0.99 | 56 | 1.7845 | 0.56 |
71
+ | 1.2162 | 2.0 | 113 | 1.1310 | 0.74 |
72
+ | 0.8715 | 2.99 | 169 | 0.8334 | 0.75 |
73
+ | 0.6735 | 4.0 | 226 | 0.7352 | 0.79 |
74
+ | 0.4007 | 4.99 | 282 | 0.5135 | 0.87 |
75
+ | 0.241 | 6.0 | 339 | 0.7801 | 0.76 |
76
+ | 0.181 | 6.99 | 395 | 0.5440 | 0.81 |
77
+ | 0.1336 | 8.0 | 452 | 0.5280 | 0.85 |
78
+ | 0.0526 | 8.99 | 508 | 0.4992 | 0.87 |
79
+ | 0.0315 | 9.91 | 560 | 0.5269 | 0.86 |
 
 
 
 
 
 
80
 
81
 
82
  ### Framework versions