Hugging Face's logo

arielcerdap
/
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
arielcerdap commited on
Commit
bbecb7e
•
1 Parent(s): 4a24f74

End of training

Browse files
Files changed (3) hide show
  1. README.md +21 -15
  2. model.safetensors +1 -1
  3. runs/Sep05_19-52-40_ec0b3710c881/events.out.tfevents.1725565963.ec0b3710c881.3062.6 +2 -2
README.md CHANGED
@@ -1,4 +1,5 @@
1
  ---
 
2
  license: bsd-3-clause
3
  base_model: MIT/ast-finetuned-audioset-10-10-0.4593
4
  tags:
@@ -22,7 +23,7 @@ model-index:
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
- value: 0.92
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -32,8 +33,8 @@ should probably proofread and complete it, then remove this comment. -->
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: 0.3783
36
- - Accuracy: 0.92
37
 
38
  ## Model description
39
 
@@ -59,28 +60,33 @@ The following hyperparameters were used during training:
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: 10
63
  - mixed_precision_training: Native AMP
64
 
65
  ### Training results
66
 
67
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
68
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
69
- | 0.0216 | 1.0 | 113 | 0.8214 | 0.84 |
70
- | 0.0846 | 2.0 | 226 | 0.9806 | 0.79 |
71
- | 0.0008 | 3.0 | 339 | 1.1615 | 0.8 |
72
- | 0.0022 | 4.0 | 452 | 0.9233 | 0.82 |
73
- | 0.0002 | 5.0 | 565 | 0.5763 | 0.87 |
74
- | 0.0001 | 6.0 | 678 | 0.3211 | 0.92 |
75
- | 0.0001 | 7.0 | 791 | 0.3334 | 0.93 |
76
- | 0.0 | 8.0 | 904 | 0.3801 | 0.92 |
77
- | 0.0 | 9.0 | 1017 | 0.3774 | 0.92 |
78
- | 0.0001 | 10.0 | 1130 | 0.3783 | 0.92 |
 
 
 
 
 
79
 
80
 
81
  ### Framework versions
82
 
83
- - Transformers 4.42.4
84
  - Pytorch 2.4.0+cu121
85
  - Datasets 2.21.0
86
  - Tokenizers 0.19.1
 
1
  ---
2
+ library_name: transformers
3
  license: bsd-3-clause
4
  base_model: MIT/ast-finetuned-audioset-10-10-0.4593
5
  tags:
 
23
  metrics:
24
  - name: Accuracy
25
  type: accuracy
26
+ value: 0.9
27
  ---
28
 
29
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
33
 
34
  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.
35
  It achieves the following results on the evaluation set:
36
+ - Loss: 0.4058
37
+ - Accuracy: 0.9
38
 
39
  ## Model description
40
 
 
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: 15
64
  - mixed_precision_training: Native AMP
65
 
66
  ### Training results
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
+ | 0.7832 | 1.0 | 113 | 0.5408 | 0.82 |
71
+ | 0.5775 | 2.0 | 226 | 0.7566 | 0.73 |
72
+ | 0.3894 | 3.0 | 339 | 0.4284 | 0.85 |
73
+ | 0.0137 | 4.0 | 452 | 0.4540 | 0.89 |
74
+ | 0.0961 | 5.0 | 565 | 0.9141 | 0.8 |
75
+ | 0.0454 | 6.0 | 678 | 0.7328 | 0.84 |
76
+ | 0.0028 | 7.0 | 791 | 1.1648 | 0.8 |
77
+ | 0.0001 | 8.0 | 904 | 0.4304 | 0.89 |
78
+ | 0.0001 | 9.0 | 1017 | 0.4028 | 0.9 |
79
+ | 0.0002 | 10.0 | 1130 | 0.4190 | 0.9 |
80
+ | 0.0001 | 11.0 | 1243 | 0.4039 | 0.9 |
81
+ | 0.0001 | 12.0 | 1356 | 0.4051 | 0.9 |
82
+ | 0.0001 | 13.0 | 1469 | 0.4056 | 0.9 |
83
+ | 0.0001 | 14.0 | 1582 | 0.4058 | 0.9 |
84
+ | 0.0001 | 15.0 | 1695 | 0.4058 | 0.9 |
85
 
86
 
87
  ### Framework versions
88
 
89
+ - Transformers 4.44.2
90
  - Pytorch 2.4.0+cu121
91
  - Datasets 2.21.0
92
  - Tokenizers 0.19.1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:769eaf90f11b8270600b0158183204622495a92c71ba502f1a65406b5f3e106a
3
  size 344814656
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d76736d0dc657c2f9a8573b4490669daeeb5c9428103c4742796f826d6d09a6e
3
  size 344814656
runs/Sep05_19-52-40_ec0b3710c881/events.out.tfevents.1725565963.ec0b3710c881.3062.6 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bb518a55eb167d58cf496b95c5d5206096f46119c94c774e513bfd3a3f67d4f9
3
- size 76701
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c595217053f54db6b18a6a9be85312ea5a671e418c833e5bc9141f74052740f
3
+ size 82020