Hugging Face's logo

StatsGary
/
distilhubert-finetuned-gtzan

Audio Classification
Transformers
PyTorch
TensorBoard
hubert
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
1
StatsGary commited on
Commit
ca7fcbb
•
1 Parent(s): c926efa

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +14 -15
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: 0.5868
36
- - Accuracy: 0.85
37
 
38
  ## Model description
39
 
@@ -59,23 +59,22 @@ The following hyperparameters were used during training:
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: 11
63
 
64
  ### Training results
65
 
66
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
67
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
68
- | 1.8862 | 1.0 | 113 | 1.6953 | 0.43 |
69
- | 1.244 | 2.0 | 226 | 1.1139 | 0.64 |
70
- | 0.9373 | 3.0 | 339 | 0.9080 | 0.74 |
71
- | 0.7731 | 4.0 | 452 | 0.7958 | 0.74 |
72
- | 0.5718 | 5.0 | 565 | 0.6637 | 0.81 |
73
- | 0.3095 | 6.0 | 678 | 0.6204 | 0.84 |
74
- | 0.391 | 7.0 | 791 | 0.6014 | 0.82 |
75
- | 0.1033 | 8.0 | 904 | 0.5147 | 0.87 |
76
- | 0.1199 | 9.0 | 1017 | 0.5189 | 0.86 |
77
- | 0.1336 | 10.0 | 1130 | 0.5594 | 0.87 |
78
- | 0.0549 | 11.0 | 1243 | 0.5868 | 0.85 |
79
 
80
 
81
  ### Framework versions
 
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
+ value: 0.84
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: 0.5648
36
+ - Accuracy: 0.84
37
 
38
  ## Model description
39
 
 
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
 
64
  ### Training results
65
 
66
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
67
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
68
+ | 1.9131 | 1.0 | 113 | 1.7119 | 0.52 |
69
+ | 1.268 | 2.0 | 226 | 1.1698 | 0.67 |
70
+ | 0.975 | 3.0 | 339 | 0.9355 | 0.73 |
71
+ | 0.7562 | 4.0 | 452 | 0.8353 | 0.73 |
72
+ | 0.5713 | 5.0 | 565 | 0.6598 | 0.8 |
73
+ | 0.3281 | 6.0 | 678 | 0.6118 | 0.83 |
74
+ | 0.4627 | 7.0 | 791 | 0.6481 | 0.79 |
75
+ | 0.1068 | 8.0 | 904 | 0.5379 | 0.85 |
76
+ | 0.2164 | 9.0 | 1017 | 0.5363 | 0.85 |
77
+ | 0.1061 | 10.0 | 1130 | 0.5648 | 0.84 |
 
78
 
79
 
80
  ### Framework versions