Hugging Face's logo

Bagus
/
ast-finetuned-audioset-10-10-0.4593-finetuned-gtzan-2

Audio Classification
Transformers
Safetensors
audio-spectrogram-transformer
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
Bagus commited on
Commit
2973a46
•
1 Parent(s): c77712a

End of training

Browse files
Files changed (2) hide show
  1. README.md +176 -0
  2. model.safetensors +1 -1
README.md ADDED
@@ -0,0 +1,176 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: bsd-3-clause
3
+ base_model: MIT/ast-finetuned-audioset-10-10-0.4593
4
+ tags:
5
+ - generated_from_trainer
6
+ datasets:
7
+ - marsyas/gtzan
8
+ metrics:
9
+ - accuracy
10
+ model-index:
11
+ - name: ast-finetuned-audioset-10-10-0.4593-finetuned-gtzan
12
+ results:
13
+ - task:
14
+ name: Audio Classification
15
+ type: audio-classification
16
+ dataset:
17
+ name: GTZAN
18
+ type: marsyas/gtzan
19
+ config: all
20
+ split: train
21
+ args: all
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
29
+ should probably proofread and complete it, then remove this comment. -->
30
+
31
+ # ast-finetuned-audioset-10-10-0.4593-finetuned-gtzan
32
+
33
+ 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.
34
+ It achieves the following results on the evaluation set:
35
+ - Loss: 2.3496
36
+ - Accuracy: 0.85
37
+
38
+ ## Model description
39
+
40
+ More information needed
41
+
42
+ ## Intended uses & limitations
43
+
44
+ More information needed
45
+
46
+ ## Training and evaluation data
47
+
48
+ More information needed
49
+
50
+ ## Training procedure
51
+
52
+ ### Training hyperparameters
53
+
54
+ The following hyperparameters were used during training:
55
+ - learning_rate: 5e-05
56
+ - train_batch_size: 4
57
+ - eval_batch_size: 4
58
+ - seed: 42
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: 100
63
+ - mixed_precision_training: Native AMP
64
+
65
+ ### Training results
66
+
67
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
68
+ |:-------------:|:-----:|:-----:|:---------------:|:--------:|
69
+ | 0.9076 | 1.0 | 225 | 0.8234 | 0.75 |
70
+ | 0.3522 | 2.0 | 450 | 0.4291 | 0.9 |
71
+ | 0.4656 | 3.0 | 675 | 0.4656 | 0.83 |
72
+ | 0.2739 | 4.0 | 900 | 0.6314 | 0.9 |
73
+ | 0.575 | 5.0 | 1125 | 0.7786 | 0.85 |
74
+ | 0.4433 | 6.0 | 1350 | 1.1706 | 0.88 |
75
+ | 1.4075 | 7.0 | 1575 | 2.5171 | 0.83 |
76
+ | 0.1059 | 8.0 | 1800 | 1.5907 | 0.84 |
77
+ | 0.1521 | 9.0 | 2025 | 3.7424 | 0.72 |
78
+ | 0.5736 | 10.0 | 2250 | 2.0911 | 0.82 |
79
+ | 0.7552 | 11.0 | 2475 | 3.2042 | 0.81 |
80
+ | 0.166 | 12.0 | 2700 | 1.8762 | 0.86 |
81
+ | 0.0 | 13.0 | 2925 | 1.0614 | 0.91 |
82
+ | 1.2229 | 14.0 | 3150 | 3.0105 | 0.78 |
83
+ | 1.0135 | 15.0 | 3375 | 2.2024 | 0.85 |
84
+ | 0.098 | 16.0 | 3600 | 1.6070 | 0.87 |
85
+ | 0.0 | 17.0 | 3825 | 2.5323 | 0.82 |
86
+ | 0.0 | 18.0 | 4050 | 2.2202 | 0.86 |
87
+ | 0.0 | 19.0 | 4275 | 2.2681 | 0.85 |
88
+ | 0.0 | 20.0 | 4500 | 2.2394 | 0.86 |
89
+ | 1.8867 | 21.0 | 4725 | 4.2168 | 0.74 |
90
+ | 0.6094 | 22.0 | 4950 | 4.7781 | 0.72 |
91
+ | 0.3684 | 23.0 | 5175 | 2.6412 | 0.81 |
92
+ | 0.0 | 24.0 | 5400 | 2.8745 | 0.82 |
93
+ | 0.0 | 25.0 | 5625 | 2.9487 | 0.79 |
94
+ | 0.0 | 26.0 | 5850 | 2.5325 | 0.82 |
95
+ | 0.1597 | 27.0 | 6075 | 2.0327 | 0.85 |
96
+ | 0.0 | 28.0 | 6300 | 3.0062 | 0.84 |
97
+ | 0.0 | 29.0 | 6525 | 2.3104 | 0.8 |
98
+ | 0.0 | 30.0 | 6750 | 2.9985 | 0.83 |
99
+ | 0.0 | 31.0 | 6975 | 2.9385 | 0.82 |
100
+ | 0.0 | 32.0 | 7200 | 2.1102 | 0.87 |
101
+ | 0.0 | 33.0 | 7425 | 2.0060 | 0.86 |
102
+ | 1.1173 | 34.0 | 7650 | 1.9131 | 0.87 |
103
+ | 0.0 | 35.0 | 7875 | 2.4819 | 0.84 |
104
+ | 0.0 | 36.0 | 8100 | 2.0951 | 0.87 |
105
+ | 0.0 | 37.0 | 8325 | 1.9796 | 0.85 |
106
+ | 0.0 | 38.0 | 8550 | 2.0940 | 0.85 |
107
+ | 0.9059 | 39.0 | 8775 | 2.0714 | 0.85 |
108
+ | 0.0 | 40.0 | 9000 | 4.0729 | 0.75 |
109
+ | 0.0 | 41.0 | 9225 | 2.8627 | 0.83 |
110
+ | 0.0 | 42.0 | 9450 | 4.0389 | 0.76 |
111
+ | 0.0 | 43.0 | 9675 | 2.3248 | 0.85 |
112
+ | 0.6586 | 44.0 | 9900 | 4.9549 | 0.75 |
113
+ | 0.0 | 45.0 | 10125 | 3.3910 | 0.81 |
114
+ | 0.0 | 46.0 | 10350 | 3.9627 | 0.77 |
115
+ | 0.0 | 47.0 | 10575 | 3.4481 | 0.83 |
116
+ | 0.0 | 48.0 | 10800 | 2.7042 | 0.85 |
117
+ | 0.0 | 49.0 | 11025 | 2.8337 | 0.85 |
118
+ | 0.0 | 50.0 | 11250 | 2.4333 | 0.85 |
119
+ | 0.0 | 51.0 | 11475 | 2.6346 | 0.84 |
120
+ | 0.0 | 52.0 | 11700 | 1.8957 | 0.88 |
121
+ | 1.7162 | 53.0 | 11925 | 2.7006 | 0.85 |
122
+ | 0.0 | 54.0 | 12150 | 2.2261 | 0.86 |
123
+ | 0.0 | 55.0 | 12375 | 1.5562 | 0.89 |
124
+ | 0.0 | 56.0 | 12600 | 1.4557 | 0.91 |
125
+ | 0.0 | 57.0 | 12825 | 1.6862 | 0.89 |
126
+ | 0.0 | 58.0 | 13050 | 1.6635 | 0.9 |
127
+ | 0.0 | 59.0 | 13275 | 2.5130 | 0.85 |
128
+ | 0.0 | 60.0 | 13500 | 2.1794 | 0.84 |
129
+ | 0.0 | 61.0 | 13725 | 3.1630 | 0.82 |
130
+ | 0.0 | 62.0 | 13950 | 2.4938 | 0.84 |
131
+ | 0.0 | 63.0 | 14175 | 2.9464 | 0.82 |
132
+ | 0.0 | 64.0 | 14400 | 3.0567 | 0.81 |
133
+ | 0.0 | 65.0 | 14625 | 3.0951 | 0.82 |
134
+ | 0.0 | 66.0 | 14850 | 2.8673 | 0.82 |
135
+ | 0.0 | 67.0 | 15075 | 2.9092 | 0.82 |
136
+ | 0.0 | 68.0 | 15300 | 2.2521 | 0.85 |
137
+ | 0.0 | 69.0 | 15525 | 2.5049 | 0.82 |
138
+ | 0.0 | 70.0 | 15750 | 2.4376 | 0.84 |
139
+ | 0.0 | 71.0 | 15975 | 2.6660 | 0.82 |
140
+ | 0.0 | 72.0 | 16200 | 2.5182 | 0.86 |
141
+ | 0.0 | 73.0 | 16425 | 2.3814 | 0.85 |
142
+ | 0.0 | 74.0 | 16650 | 2.3093 | 0.85 |
143
+ | 0.0 | 75.0 | 16875 | 2.3014 | 0.85 |
144
+ | 0.0 | 76.0 | 17100 | 2.3845 | 0.86 |
145
+ | 0.0 | 77.0 | 17325 | 2.2978 | 0.85 |
146
+ | 0.0 | 78.0 | 17550 | 2.4215 | 0.85 |
147
+ | 0.7047 | 79.0 | 17775 | 2.3462 | 0.84 |
148
+ | 0.0 | 80.0 | 18000 | 2.3230 | 0.85 |
149
+ | 0.0 | 81.0 | 18225 | 2.3648 | 0.85 |
150
+ | 0.0 | 82.0 | 18450 | 2.2962 | 0.85 |
151
+ | 0.0 | 83.0 | 18675 | 2.4231 | 0.84 |
152
+ | 0.0 | 84.0 | 18900 | 2.2588 | 0.86 |
153
+ | 0.0 | 85.0 | 19125 | 2.4144 | 0.84 |
154
+ | 0.0 | 86.0 | 19350 | 2.4220 | 0.84 |
155
+ | 0.0 | 87.0 | 19575 | 2.3860 | 0.84 |
156
+ | 0.0 | 88.0 | 19800 | 2.3356 | 0.84 |
157
+ | 0.0 | 89.0 | 20025 | 2.3223 | 0.85 |
158
+ | 0.0 | 90.0 | 20250 | 2.3554 | 0.83 |
159
+ | 0.0 | 91.0 | 20475 | 2.3344 | 0.84 |
160
+ | 0.6906 | 92.0 | 20700 | 2.3568 | 0.85 |
161
+ | 0.0 | 93.0 | 20925 | 2.3905 | 0.84 |
162
+ | 0.0 | 94.0 | 21150 | 2.3920 | 0.85 |
163
+ | 0.0 | 95.0 | 21375 | 2.3935 | 0.85 |
164
+ | 0.0 | 96.0 | 21600 | 2.3392 | 0.85 |
165
+ | 0.0 | 97.0 | 21825 | 2.3437 | 0.85 |
166
+ | 0.0 | 98.0 | 22050 | 2.3434 | 0.85 |
167
+ | 0.0 | 99.0 | 22275 | 2.3503 | 0.85 |
168
+ | 0.0 | 100.0 | 22500 | 2.3496 | 0.85 |
169
+
170
+
171
+ ### Framework versions
172
+
173
+ - Transformers 4.35.2
174
+ - Pytorch 2.1.0
175
+ - Datasets 2.15.0
176
+ - Tokenizers 0.15.0
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:609f90de8c2493e7e44c25fa7edd7063ace6bd1b5fe88208893315751ec8d5dd
3
  size 344814656
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ebc565f0c34a1cc3805290cc6bbc71c0fbfa039f7f4cd36804c2389b41ad3805
3
  size 344814656