Hugging Face's logo

bbillapati
/
ast-finetuned-audioset-10-10-0.4593-finetuned-gtzan

Audio Classification
Transformers
TensorBoard
Safetensors
audio-spectrogram-transformer
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
bbillapati commited on
Commit
2e2ae20
•
1 Parent(s): eb74ee7

End of training

Browse files
Files changed (3) hide show
  1. README.md +103 -0
  2. model.safetensors +1 -1
  3. runs/Jan09_10-43-58_Billapati-Home/events.out.tfevents.1704777243.Billapati-Home.703.0 +2 -2
README.md ADDED
@@ -0,0 +1,103 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: 0.9
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: 0.4793
36
+ - Accuracy: 0.9
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: 2
57
+ - eval_batch_size: 2
58
+ - seed: 42
59
+ - gradient_accumulation_steps: 4
60
+ - total_train_batch_size: 8
61
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
62
+ - lr_scheduler_type: linear
63
+ - lr_scheduler_warmup_ratio: 0.1
64
+ - num_epochs: 25
65
+ - mixed_precision_training: Native AMP
66
+
67
+ ### Training results
68
+
69
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
70
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
71
+ | 0.6559 | 1.0 | 112 | 0.5081 | 0.86 |
72
+ | 0.5141 | 2.0 | 225 | 0.5618 | 0.77 |
73
+ | 0.5517 | 3.0 | 337 | 0.5009 | 0.84 |
74
+ | 0.6651 | 4.0 | 450 | 0.7811 | 0.82 |
75
+ | 0.0057 | 5.0 | 562 | 0.3074 | 0.93 |
76
+ | 0.0018 | 6.0 | 675 | 0.4843 | 0.87 |
77
+ | 0.0007 | 7.0 | 787 | 0.6949 | 0.85 |
78
+ | 0.0007 | 8.0 | 900 | 0.6981 | 0.88 |
79
+ | 0.0007 | 9.0 | 1012 | 0.8356 | 0.87 |
80
+ | 0.0001 | 10.0 | 1125 | 0.6164 | 0.89 |
81
+ | 0.1709 | 11.0 | 1237 | 0.5464 | 0.89 |
82
+ | 0.0001 | 12.0 | 1350 | 0.4885 | 0.88 |
83
+ | 0.0003 | 13.0 | 1462 | 0.4970 | 0.91 |
84
+ | 0.0 | 14.0 | 1575 | 0.5346 | 0.88 |
85
+ | 0.0001 | 15.0 | 1687 | 0.5526 | 0.89 |
86
+ | 0.0 | 16.0 | 1800 | 0.4808 | 0.91 |
87
+ | 0.0 | 17.0 | 1912 | 0.4999 | 0.9 |
88
+ | 0.0 | 18.0 | 2025 | 0.4909 | 0.89 |
89
+ | 0.0 | 19.0 | 2137 | 0.4953 | 0.89 |
90
+ | 0.0 | 20.0 | 2250 | 0.4883 | 0.9 |
91
+ | 0.0543 | 21.0 | 2362 | 0.4830 | 0.91 |
92
+ | 0.0 | 22.0 | 2475 | 0.4811 | 0.9 |
93
+ | 0.0 | 23.0 | 2587 | 0.4805 | 0.9 |
94
+ | 0.0 | 24.0 | 2700 | 0.4785 | 0.91 |
95
+ | 0.0 | 24.89 | 2800 | 0.4793 | 0.9 |
96
+
97
+
98
+ ### Framework versions
99
+
100
+ - Transformers 4.36.0.dev0
101
+ - Pytorch 2.0.1
102
+ - Datasets 2.14.5
103
+ - Tokenizers 0.15.0
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a917630e46a63708c211a992a1b4e88d3e4a7993f2c291dcb3c6d581e73432f8
3
  size 344814656
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21a2e1d4a7f527ec492abc397a7f8abaa5d8766ccfc7c10498d3dfb6f2283602
3
  size 344814656
runs/Jan09_10-43-58_Billapati-Home/events.out.tfevents.1704777243.Billapati-Home.703.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b31eda5920a7f19997e8a29c06c2e674b552296c5e692b954363904fe8190a30
3
- size 100766
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:267cc0c08606d8d874021ae7789d47363617f4c9cb20e18dfd76c872f0cc12ec
3
+ size 101120