Hugging Face's logo

Rolo
/
distilhubert-finetuned-gtzan-4

Audio Classification
Transformers
PyTorch
hubert
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
Rolo commited on
Commit
67d2bc1
•
1 Parent(s): e42a687

End of training

Browse files
Files changed (2) hide show
  1. README.md +155 -0
  2. pytorch_model.bin +1 -1
README.md ADDED
@@ -0,0 +1,155 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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-4
12
+ results:
13
+ - task:
14
+ name: Audio Classification
15
+ type: audio-classification
16
+ dataset:
17
+ name: GTZAN
18
+ type: marsyas/gtzan
19
+ config: default
20
+ split: train
21
+ args: default
22
+ metrics:
23
+ - name: Accuracy
24
+ type: accuracy
25
+ value: 0.82
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
+ # distilhubert-finetuned-gtzan-4
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: 2.8452
36
+ - Accuracy: 0.82
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: 80
63
+
64
+ ### Training results
65
+
66
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
67
+ |:-------------:|:-----:|:-----:|:---------------:|:--------:|
68
+ | 2.2676 | 1.0 | 225 | 2.2400 | 0.33 |
69
+ | 1.9086 | 2.0 | 450 | 1.8716 | 0.55 |
70
+ | 1.417 | 3.0 | 675 | 1.4094 | 0.69 |
71
+ | 1.0484 | 4.0 | 900 | 1.1065 | 0.77 |
72
+ | 1.0122 | 5.0 | 1125 | 0.9172 | 0.75 |
73
+ | 0.8937 | 6.0 | 1350 | 1.1343 | 0.66 |
74
+ | 0.2979 | 7.0 | 1575 | 0.6102 | 0.83 |
75
+ | 0.3413 | 8.0 | 1800 | 1.1212 | 0.71 |
76
+ | 1.459 | 9.0 | 2025 | 1.5433 | 0.75 |
77
+ | 0.5177 | 10.0 | 2250 | 1.3990 | 0.78 |
78
+ | 0.0494 | 11.0 | 2475 | 2.7712 | 0.78 |
79
+ | 0.792 | 12.0 | 2700 | 2.7047 | 0.81 |
80
+ | 0.0 | 13.0 | 2925 | 2.8097 | 0.82 |
81
+ | 0.0 | 14.0 | 3150 | 3.3873 | 0.79 |
82
+ | 0.0 | 15.0 | 3375 | 2.6185 | 0.81 |
83
+ | 0.0 | 16.0 | 3600 | 3.0773 | 0.81 |
84
+ | 0.0 | 17.0 | 3825 | 2.2380 | 0.84 |
85
+ | 0.0 | 18.0 | 4050 | 2.5949 | 0.79 |
86
+ | 0.0 | 19.0 | 4275 | 3.4890 | 0.75 |
87
+ | 0.0 | 20.0 | 4500 | 2.7776 | 0.82 |
88
+ | 0.0 | 21.0 | 4725 | 3.8952 | 0.77 |
89
+ | 0.0 | 22.0 | 4950 | 2.8020 | 0.8 |
90
+ | 0.0 | 23.0 | 5175 | 3.7968 | 0.72 |
91
+ | 0.0 | 24.0 | 5400 | 2.8630 | 0.81 |
92
+ | 0.0 | 25.0 | 5625 | 2.2026 | 0.84 |
93
+ | 0.0 | 26.0 | 5850 | 1.8612 | 0.87 |
94
+ | 0.0 | 27.0 | 6075 | 3.2650 | 0.78 |
95
+ | 0.0 | 28.0 | 6300 | 2.6739 | 0.82 |
96
+ | 0.0 | 29.0 | 6525 | 3.0167 | 0.8 |
97
+ | 0.0 | 30.0 | 6750 | 1.9316 | 0.84 |
98
+ | 0.0 | 31.0 | 6975 | 3.0458 | 0.8 |
99
+ | 0.0 | 32.0 | 7200 | 3.3569 | 0.77 |
100
+ | 0.0 | 33.0 | 7425 | 3.0012 | 0.79 |
101
+ | 0.0 | 34.0 | 7650 | 3.2477 | 0.79 |
102
+ | 0.0 | 35.0 | 7875 | 3.2145 | 0.79 |
103
+ | 0.0 | 36.0 | 8100 | 3.0645 | 0.79 |
104
+ | 0.0 | 37.0 | 8325 | 3.2974 | 0.77 |
105
+ | 0.0 | 38.0 | 8550 | 3.4422 | 0.77 |
106
+ | 0.0 | 39.0 | 8775 | 2.7268 | 0.8 |
107
+ | 0.0 | 40.0 | 9000 | 2.6908 | 0.8 |
108
+ | 0.0 | 41.0 | 9225 | 2.4034 | 0.82 |
109
+ | 0.0 | 42.0 | 9450 | 3.1446 | 0.79 |
110
+ | 0.0 | 43.0 | 9675 | 2.9127 | 0.8 |
111
+ | 0.0 | 44.0 | 9900 | 2.3812 | 0.81 |
112
+ | 0.0 | 45.0 | 10125 | 2.4215 | 0.81 |
113
+ | 0.0 | 46.0 | 10350 | 2.6125 | 0.82 |
114
+ | 0.7338 | 47.0 | 10575 | 2.5113 | 0.82 |
115
+ | 0.0 | 48.0 | 10800 | 2.9264 | 0.81 |
116
+ | 0.0 | 49.0 | 11025 | 2.7811 | 0.81 |
117
+ | 0.0 | 50.0 | 11250 | 2.6749 | 0.8 |
118
+ | 0.0 | 51.0 | 11475 | 3.2003 | 0.78 |
119
+ | 0.0 | 52.0 | 11700 | 3.2670 | 0.78 |
120
+ | 0.0 | 53.0 | 11925 | 3.4001 | 0.76 |
121
+ | 0.0 | 54.0 | 12150 | 2.8570 | 0.76 |
122
+ | 0.0 | 55.0 | 12375 | 2.1772 | 0.83 |
123
+ | 0.0 | 56.0 | 12600 | 2.7977 | 0.81 |
124
+ | 0.0 | 57.0 | 12825 | 2.9106 | 0.78 |
125
+ | 0.0 | 58.0 | 13050 | 2.8428 | 0.8 |
126
+ | 0.0 | 59.0 | 13275 | 2.7308 | 0.78 |
127
+ | 0.0 | 60.0 | 13500 | 2.8214 | 0.8 |
128
+ | 0.0 | 61.0 | 13725 | 2.8194 | 0.79 |
129
+ | 0.0 | 62.0 | 13950 | 1.7708 | 0.85 |
130
+ | 0.0 | 63.0 | 14175 | 2.6017 | 0.81 |
131
+ | 0.0 | 64.0 | 14400 | 2.7698 | 0.78 |
132
+ | 0.0 | 65.0 | 14625 | 2.8218 | 0.81 |
133
+ | 0.0 | 66.0 | 14850 | 2.8252 | 0.82 |
134
+ | 0.0 | 67.0 | 15075 | 2.9149 | 0.81 |
135
+ | 0.0 | 68.0 | 15300 | 2.8106 | 0.81 |
136
+ | 0.0 | 69.0 | 15525 | 2.8514 | 0.8 |
137
+ | 0.0 | 70.0 | 15750 | 2.6649 | 0.82 |
138
+ | 0.0 | 71.0 | 15975 | 2.5629 | 0.81 |
139
+ | 0.0 | 72.0 | 16200 | 2.8140 | 0.81 |
140
+ | 0.0 | 73.0 | 16425 | 2.8164 | 0.79 |
141
+ | 0.0 | 74.0 | 16650 | 2.7022 | 0.81 |
142
+ | 0.0 | 75.0 | 16875 | 2.7376 | 0.81 |
143
+ | 0.0 | 76.0 | 17100 | 2.6498 | 0.8 |
144
+ | 0.0 | 77.0 | 17325 | 2.7363 | 0.81 |
145
+ | 0.0 | 78.0 | 17550 | 2.8057 | 0.81 |
146
+ | 0.0 | 79.0 | 17775 | 2.8526 | 0.81 |
147
+ | 0.0 | 80.0 | 18000 | 2.8452 | 0.82 |
148
+
149
+
150
+ ### Framework versions
151
+
152
+ - Transformers 4.33.0.dev0
153
+ - Pytorch 2.0.1+cu117
154
+ - Datasets 2.14.4
155
+ - Tokenizers 0.13.3
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a80d31cf1004a0e1cbfd3abcf90c11a96b496c1665e2b50e75de4b418e322ada
3
  size 94783376
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:842374e261073797f3ee93b8c38951287983826154726d083d1eebd0f535fd97
3
  size 94783376