Hugging Face's logo

weifeng1994
/
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
weifeng1994 commited on
Commit
71540e8
•
1 Parent(s): 2f206fc

End of training

Browse files
Files changed (3) hide show
  1. README.md +14 -13
  2. model.safetensors +1 -1
  3. runs/Jan29_13-25-42_ef417846d033/events.out.tfevents.1706534763.ef417846d033.23155.0 +2 -2
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
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
@@ -32,8 +32,8 @@ 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: 0.5926
36
- - Accuracy: 0.85
37
 
38
  ## Model description
39
 
@@ -60,21 +60,22 @@ The following hyperparameters were used during training:
60
  - lr_scheduler_type: linear
61
  - lr_scheduler_warmup_ratio: 0.1
62
  - num_epochs: 10
 
63
 
64
  ### Training results
65
 
66
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
67
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
68
- | 1.0682 | 1.0 | 225 | 0.6954 | 0.73 |
69
- | 0.6581 | 2.0 | 450 | 0.7311 | 0.82 |
70
- | 0.382 | 3.0 | 675 | 0.6811 | 0.83 |
71
- | 0.023 | 4.0 | 900 | 0.5241 | 0.87 |
72
- | 0.1036 | 5.0 | 1125 | 0.7010 | 0.85 |
73
- | 0.0002 | 6.0 | 1350 | 0.6130 | 0.85 |
74
- | 0.2376 | 7.0 | 1575 | 0.6206 | 0.85 |
75
- | 0.0001 | 8.0 | 1800 | 0.6264 | 0.85 |
76
- | 0.0001 | 9.0 | 2025 | 0.5948 | 0.85 |
77
- | 0.0 | 10.0 | 2250 | 0.5926 | 0.85 |
78
 
79
 
80
  ### Framework versions
 
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
+ value: 0.87
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
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: 0.5965
36
+ - Accuracy: 0.87
37
 
38
  ## Model description
39
 
 
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
+ | 1.0357 | 1.0 | 225 | 0.8347 | 0.77 |
70
+ | 0.6592 | 2.0 | 450 | 0.6398 | 0.83 |
71
+ | 0.8437 | 3.0 | 675 | 0.8383 | 0.8 |
72
+ | 0.0105 | 4.0 | 900 | 0.5734 | 0.86 |
73
+ | 0.0124 | 5.0 | 1125 | 0.9027 | 0.86 |
74
+ | 0.0001 | 6.0 | 1350 | 0.6319 | 0.85 |
75
+ | 0.128 | 7.0 | 1575 | 0.5766 | 0.89 |
76
+ | 0.0001 | 8.0 | 1800 | 0.5357 | 0.87 |
77
+ | 0.0001 | 9.0 | 2025 | 0.5984 | 0.87 |
78
+ | 0.0 | 10.0 | 2250 | 0.5965 | 0.87 |
79
 
80
 
81
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c2d47d9762bb69b3a46f073397f2cea5d7881079ea78675251801f98d99fd5bb
3
  size 344814656
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f74ab9228bfb4f1ef71e389ab04bb7ef317c414ba0f6932223765dcf27b4c1b1
3
  size 344814656
runs/Jan29_13-25-42_ef417846d033/events.out.tfevents.1706534763.ef417846d033.23155.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6b56366565e16d37a4600f8da38e8be6e406e2d9c4b74864e0a395ca8a598190
3
- size 78650
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf38111215926e17c321c8ef67f847629430ea14b8bc1328b96fc5873c2a7778
3
+ size 79004