Hugging Face's logo

pedromatias97
/
genre-recognizer-finetuned-gtzan_dset

Audio Classification
Transformers
PyTorch
hubert
generated_from_trainer
Eval Results
Inference Endpoints
Model card Files Community
2
pedromatias97 commited on
Commit
3fd388c
•
1 Parent(s): a02debb

End of training

Browse files
Files changed (1) hide show
  1. README.md +17 -20
README.md CHANGED
@@ -22,16 +22,16 @@ model-index:
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
- value: 0.9298245614035088
26
  - name: Precision
27
  type: precision
28
- value: 0.9292447472185437
29
  - name: Recall
30
  type: recall
31
- value: 0.9298245614035088
32
  - name: F1
33
  type: f1
34
- value: 0.9293437948869628
35
  ---
36
 
37
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -41,11 +41,11 @@ should probably proofread and complete it, then remove this comment. -->
41
 
42
  This model is a fine-tuned version of [ntu-spml/distilhubert](https://huggingface.co/ntu-spml/distilhubert) on the GTZAN dataset.
43
  It achieves the following results on the evaluation set:
44
- - Loss: 0.2288
45
- - Accuracy: 0.9298
46
- - Precision: 0.9292
47
- - Recall: 0.9298
48
- - F1: 0.9293
49
 
50
  ## Model description
51
 
@@ -73,22 +73,19 @@ The following hyperparameters were used during training:
73
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
74
  - lr_scheduler_type: linear
75
  - lr_scheduler_warmup_ratio: 0.1
76
- - num_epochs: 10
77
 
78
  ### Training results
79
 
80
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
81
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
82
- | 2.2522 | 0.98 | 49 | 1.6370 | 0.6090 | 0.6189 | 0.6090 | 0.5764 |
83
- | 1.2901 | 1.98 | 99 | 0.9974 | 0.7556 | 0.7655 | 0.7556 | 0.7426 |
84
- | 1.0046 | 2.99 | 149 | 0.6645 | 0.8195 | 0.8226 | 0.8195 | 0.8162 |
85
- | 0.5952 | 3.99 | 199 | 0.5054 | 0.8459 | 0.8561 | 0.8459 | 0.8460 |
86
- | 0.3596 | 4.99 | 249 | 0.3729 | 0.9023 | 0.9117 | 0.9023 | 0.9041 |
87
- | 0.2534 | 5.99 | 299 | 0.2953 | 0.9073 | 0.9088 | 0.9073 | 0.9075 |
88
- | 0.1413 | 7.0 | 349 | 0.2545 | 0.9223 | 0.9229 | 0.9223 | 0.9216 |
89
- | 0.0759 | 8.0 | 399 | 0.2593 | 0.9198 | 0.9209 | 0.9198 | 0.9190 |
90
- | 0.0491 | 8.98 | 448 | 0.2288 | 0.9298 | 0.9292 | 0.9298 | 0.9293 |
91
- | 0.0355 | 9.82 | 490 | 0.2392 | 0.9223 | 0.9231 | 0.9223 | 0.9221 |
92
 
93
 
94
  ### Framework versions
 
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
+ value: 0.8972431077694235
26
  - name: Precision
27
  type: precision
28
+ value: 0.8989153352434833
29
  - name: Recall
30
  type: recall
31
+ value: 0.8972431077694235
32
  - name: F1
33
  type: f1
34
+ value: 0.8974179462177999
35
  ---
36
 
37
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
41
 
42
  This model is a fine-tuned version of [ntu-spml/distilhubert](https://huggingface.co/ntu-spml/distilhubert) on the GTZAN dataset.
43
  It achieves the following results on the evaluation set:
44
+ - Loss: 0.3892
45
+ - Accuracy: 0.8972
46
+ - Precision: 0.8989
47
+ - Recall: 0.8972
48
+ - F1: 0.8974
49
 
50
  ## Model description
51
 
 
73
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
74
  - lr_scheduler_type: linear
75
  - lr_scheduler_warmup_ratio: 0.1
76
+ - num_epochs: 7
77
 
78
  ### Training results
79
 
80
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
81
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
82
+ | 2.2319 | 0.98 | 49 | 1.5808 | 0.5263 | 0.5682 | 0.5263 | 0.4767 |
83
+ | 1.2682 | 1.98 | 99 | 0.9750 | 0.7556 | 0.7524 | 0.7556 | 0.7510 |
84
+ | 0.9462 | 2.99 | 149 | 0.7403 | 0.7945 | 0.7964 | 0.7945 | 0.7921 |
85
+ | 0.5946 | 3.99 | 199 | 0.5921 | 0.8233 | 0.8281 | 0.8233 | 0.8214 |
86
+ | 0.4095 | 4.99 | 249 | 0.4772 | 0.8634 | 0.8663 | 0.8634 | 0.8638 |
87
+ | 0.3349 | 5.99 | 299 | 0.4167 | 0.8835 | 0.8866 | 0.8835 | 0.8841 |
88
+ | 0.2427 | 6.88 | 343 | 0.3892 | 0.8972 | 0.8989 | 0.8972 | 0.8974 |
 
 
 
89
 
90
 
91
  ### Framework versions