Jonnhan commited on
Commit
bf67fee
1 Parent(s): e2d962b

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +83 -82
README.md CHANGED
@@ -1,82 +1,83 @@
1
- ---
2
- license: apache-2.0
3
- base_model: ntu-spml/distilhubert
4
- tags:
5
- - generated_from_trainer
6
- datasets:
7
- - marsyas/gtzan
8
- metrics:
9
- - accuracy
10
- model-index:
11
- - name: distilhubert-finetuned-gtzan-v3
12
- results:
13
- - task:
14
- name: Audio Classification
15
- type: audio-classification
16
- dataset:
17
- name: GTZAN
18
- type: marsyas/gtzan
19
- metrics:
20
- - name: Accuracy
21
- type: accuracy
22
- value: 0.87
23
- ---
24
-
25
- <!-- This model card has been generated automatically according to the information the Trainer had access to. You
26
- should probably proofread and complete it, then remove this comment. -->
27
-
28
- # distilhubert-finetuned-gtzan-v3
29
-
30
- This model is a fine-tuned version of [ntu-spml/distilhubert](https://huggingface.co/ntu-spml/distilhubert) on the GTZAN dataset.
31
- It achieves the following results on the evaluation set:
32
- - Loss: 1.0906
33
- - Accuracy: 0.87
34
-
35
- ## Model description
36
-
37
- More information needed
38
-
39
- ## Intended uses & limitations
40
-
41
- More information needed
42
-
43
- ## Training and evaluation data
44
-
45
- More information needed
46
-
47
- ## Training procedure
48
-
49
- ### Training hyperparameters
50
-
51
- The following hyperparameters were used during training:
52
- - learning_rate: 5e-05
53
- - train_batch_size: 1
54
- - eval_batch_size: 1
55
- - seed: 42
56
- - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
57
- - lr_scheduler_type: linear
58
- - num_epochs: 10
59
- - mixed_precision_training: Native AMP
60
-
61
- ### Training results
62
-
63
- | Training Loss | Epoch | Step | Validation Loss | Accuracy |
64
- |:-------------:|:-----:|:----:|:---------------:|:--------:|
65
- | 0.8287 | 1.0 | 899 | 0.8991 | 0.68 |
66
- | 2.2164 | 2.0 | 1798 | 1.3184 | 0.71 |
67
- | 0.0099 | 3.0 | 2697 | 0.9288 | 0.78 |
68
- | 0.0679 | 4.0 | 3596 | 0.8131 | 0.84 |
69
- | 0.0119 | 5.0 | 4495 | 1.1122 | 0.8 |
70
- | 0.0051 | 6.0 | 5394 | 0.9594 | 0.86 |
71
- | 0.0008 | 7.0 | 6293 | 0.9475 | 0.87 |
72
- | 0.0002 | 8.0 | 7192 | 1.1026 | 0.86 |
73
- | 0.0002 | 9.0 | 8091 | 1.0751 | 0.87 |
74
- | 0.0002 | 10.0 | 8990 | 1.0906 | 0.87 |
75
-
76
-
77
- ### Framework versions
78
-
79
- - Transformers 4.44.0
80
- - Pytorch 2.1.1+cu118
81
- - Datasets 2.20.0
82
- - Tokenizers 0.19.1
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: ntu-spml/distilhubert
4
+ tags:
5
+ - generated_from_trainer
6
+ datasets:
7
+ - marsyas/gtzan
8
+ metrics:
9
+ - accuracy
10
+ model-index:
11
+ - name: distilhubert-finetuned-gtzan-v3
12
+ results:
13
+ - task:
14
+ name: Audio Classification
15
+ type: audio-classification
16
+ dataset:
17
+ name: GTZAN
18
+ type: marsyas/gtzan
19
+ metrics:
20
+ - name: Accuracy
21
+ type: accuracy
22
+ value: 0.87
23
+ pipeline_tag: audio-classification
24
+ ---
25
+
26
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
27
+ should probably proofread and complete it, then remove this comment. -->
28
+
29
+ # distilhubert-finetuned-gtzan-v3
30
+
31
+ This model is a fine-tuned version of [ntu-spml/distilhubert](https://huggingface.co/ntu-spml/distilhubert) on the GTZAN dataset.
32
+ It achieves the following results on the evaluation set:
33
+ - Loss: 1.0906
34
+ - Accuracy: 0.87
35
+
36
+ ## Model description
37
+
38
+ More information needed
39
+
40
+ ## Intended uses & limitations
41
+
42
+ More information needed
43
+
44
+ ## Training and evaluation data
45
+
46
+ More information needed
47
+
48
+ ## Training procedure
49
+
50
+ ### Training hyperparameters
51
+
52
+ The following hyperparameters were used during training:
53
+ - learning_rate: 5e-05
54
+ - train_batch_size: 1
55
+ - eval_batch_size: 1
56
+ - seed: 42
57
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
58
+ - lr_scheduler_type: linear
59
+ - num_epochs: 10
60
+ - mixed_precision_training: Native AMP
61
+
62
+ ### Training results
63
+
64
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
65
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
66
+ | 0.8287 | 1.0 | 899 | 0.8991 | 0.68 |
67
+ | 2.2164 | 2.0 | 1798 | 1.3184 | 0.71 |
68
+ | 0.0099 | 3.0 | 2697 | 0.9288 | 0.78 |
69
+ | 0.0679 | 4.0 | 3596 | 0.8131 | 0.84 |
70
+ | 0.0119 | 5.0 | 4495 | 1.1122 | 0.8 |
71
+ | 0.0051 | 6.0 | 5394 | 0.9594 | 0.86 |
72
+ | 0.0008 | 7.0 | 6293 | 0.9475 | 0.87 |
73
+ | 0.0002 | 8.0 | 7192 | 1.1026 | 0.86 |
74
+ | 0.0002 | 9.0 | 8091 | 1.0751 | 0.87 |
75
+ | 0.0002 | 10.0 | 8990 | 1.0906 | 0.87 |
76
+
77
+
78
+ ### Framework versions
79
+
80
+ - Transformers 4.44.0
81
+ - Pytorch 2.1.1+cu118
82
+ - Datasets 2.20.0
83
+ - Tokenizers 0.19.1