ptah23 commited on
Commit
49a7388
1 Parent(s): c1d3e49

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +96 -0
README.md ADDED
@@ -0,0 +1,96 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: bsd-3-clause
3
+ tags:
4
+ - generated_from_trainer
5
+ datasets:
6
+ - marsyas/gtzan
7
+ metrics:
8
+ - accuracy
9
+ model-index:
10
+ - name: ast-finetuned-audioset-10-10-0.4593-finetuned-gtzan
11
+ results:
12
+ - task:
13
+ name: Audio Classification
14
+ type: audio-classification
15
+ dataset:
16
+ name: GTZAN
17
+ type: marsyas/gtzan
18
+ config: all
19
+ split: train
20
+ args: all
21
+ metrics:
22
+ - name: Accuracy
23
+ type: accuracy
24
+ value: 0.9
25
+ ---
26
+
27
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
28
+ should probably proofread and complete it, then remove this comment. -->
29
+
30
+ # ast-finetuned-audioset-10-10-0.4593-finetuned-gtzan
31
+
32
+ This model is a fine-tuned version of [MIT/ast-finetuned-audioset-10-10-0.4593](https://huggingface.co/MIT/ast-finetuned-audioset-10-10-0.4593) on the GTZAN dataset.
33
+ It achieves the following results on the evaluation set:
34
+ - Loss: 0.3548
35
+ - Accuracy: 0.9
36
+
37
+ ## Model description
38
+
39
+ More information needed
40
+
41
+ ## Intended uses & limitations
42
+
43
+ More information needed
44
+
45
+ ## Training and evaluation data
46
+
47
+ More information needed
48
+
49
+ ## Training procedure
50
+
51
+ ### Training hyperparameters
52
+
53
+ The following hyperparameters were used during training:
54
+ - learning_rate: 5e-05
55
+ - train_batch_size: 2
56
+ - eval_batch_size: 2
57
+ - seed: 42
58
+ - gradient_accumulation_steps: 4
59
+ - total_train_batch_size: 8
60
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
61
+ - lr_scheduler_type: linear
62
+ - lr_scheduler_warmup_ratio: 0.1
63
+ - num_epochs: 20
64
+
65
+ ### Training results
66
+
67
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
68
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
69
+ | 0.9569 | 1.0 | 112 | 0.6467 | 0.77 |
70
+ | 0.5441 | 2.0 | 225 | 0.5895 | 0.8 |
71
+ | 0.4536 | 3.0 | 337 | 0.4070 | 0.82 |
72
+ | 0.1096 | 4.0 | 450 | 0.3812 | 0.89 |
73
+ | 0.0116 | 5.0 | 562 | 1.1661 | 0.78 |
74
+ | 0.0165 | 6.0 | 675 | 0.4822 | 0.91 |
75
+ | 0.1206 | 7.0 | 787 | 0.5000 | 0.88 |
76
+ | 0.0001 | 8.0 | 900 | 0.4074 | 0.89 |
77
+ | 0.2068 | 9.0 | 1012 | 0.4769 | 0.87 |
78
+ | 0.0001 | 10.0 | 1125 | 0.3743 | 0.89 |
79
+ | 0.0001 | 11.0 | 1237 | 0.3673 | 0.89 |
80
+ | 0.0001 | 12.0 | 1350 | 0.3952 | 0.91 |
81
+ | 0.0001 | 13.0 | 1462 | 0.3710 | 0.91 |
82
+ | 0.0001 | 14.0 | 1575 | 0.3460 | 0.92 |
83
+ | 0.0 | 15.0 | 1687 | 0.3481 | 0.92 |
84
+ | 0.0 | 16.0 | 1800 | 0.3473 | 0.92 |
85
+ | 0.0 | 17.0 | 1912 | 0.3491 | 0.91 |
86
+ | 0.0 | 18.0 | 2025 | 0.3507 | 0.91 |
87
+ | 0.0 | 19.0 | 2137 | 0.3548 | 0.9 |
88
+ | 0.0001 | 19.91 | 2240 | 0.3548 | 0.9 |
89
+
90
+
91
+ ### Framework versions
92
+
93
+ - Transformers 4.31.0.dev0
94
+ - Pytorch 1.12.1+cu116
95
+ - Datasets 2.4.0
96
+ - Tokenizers 0.12.1