Hugging Face's logo

wetdog
/
ast-finetuned-audioset-10-10-0.4593-TUT-acoustic-scenes

Audio Classification
Transformers
PyTorch
Safetensors
audio-spectrogram-transformer
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
1
wetdog commited on
Commit
9880a6b
·
1 Parent(s): 70a875f

End of training

Browse files
Files changed (3) hide show
  1. README.md +13 -10
  2. pytorch_model.bin +1 -1
  3. training_args.bin +1 -1
README.md CHANGED
@@ -20,7 +20,7 @@ model-index:
20
  metrics:
21
  - name: Accuracy
22
  type: accuracy
23
- value: 0.4265625
24
  ---
25
 
26
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -30,8 +30,8 @@ should probably proofread and complete it, then remove this comment. -->
30
 
31
  This model is a fine-tuned version of [wetdog/TUT-urban-acoustic-scenes-2018-development](https://huggingface.co/wetdog/TUT-urban-acoustic-scenes-2018-development) on the TUT-urban-acoustic-scenes-2018-development dataset.
32
  It achieves the following results on the evaluation set:
33
- - Loss: 1.4156
34
- - Accuracy: 0.4266
35
 
36
  ## Model description
37
 
@@ -50,24 +50,27 @@ More information needed
50
  ### Training hyperparameters
51
 
52
  The following hyperparameters were used during training:
53
- - learning_rate: 0.0003
54
  - train_batch_size: 4
55
  - eval_batch_size: 4
56
  - seed: 42
57
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
58
  - lr_scheduler_type: linear
59
  - lr_scheduler_warmup_ratio: 0.1
60
- - training_steps: 500
61
 
62
  ### Training results
63
 
64
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
65
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
66
- | 1.5412 | 0.2 | 100 | 2.5283 | 0.3719 |
67
- | 1.6506 | 0.4 | 200 | 1.0367 | 0.6297 |
68
- | 1.4406 | 0.6 | 300 | 0.9969 | 0.6281 |
69
- | 1.4052 | 0.8 | 400 | 1.5450 | 0.3969 |
70
- | 1.2354 | 1.0 | 500 | 1.4156 | 0.4266 |
 
 
 
71
 
72
 
73
  ### Framework versions
 
20
  metrics:
21
  - name: Accuracy
22
  type: accuracy
23
+ value: 0.52
24
  ---
25
 
26
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
30
 
31
  This model is a fine-tuned version of [wetdog/TUT-urban-acoustic-scenes-2018-development](https://huggingface.co/wetdog/TUT-urban-acoustic-scenes-2018-development) on the TUT-urban-acoustic-scenes-2018-development dataset.
32
  It achieves the following results on the evaluation set:
33
+ - Loss: 4.4942
34
+ - Accuracy: 0.52
35
 
36
  ## Model description
37
 
 
50
  ### Training hyperparameters
51
 
52
  The following hyperparameters were used during training:
53
+ - learning_rate: 3e-05
54
  - train_batch_size: 4
55
  - eval_batch_size: 4
56
  - seed: 42
57
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
58
  - lr_scheduler_type: linear
59
  - lr_scheduler_warmup_ratio: 0.1
60
+ - training_steps: 4000
61
 
62
  ### Training results
63
 
64
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
65
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
66
+ | 1.212 | 0.12 | 500 | 2.5780 | 0.375 |
67
+ | 0.5031 | 1.12 | 1000 | 3.6818 | 0.435 |
68
+ | 0.2583 | 2.12 | 1500 | 3.8194 | 0.465 |
69
+ | 0.0828 | 3.12 | 2000 | 4.3022 | 0.455 |
70
+ | 0.0367 | 4.12 | 2500 | 4.6687 | 0.45 |
71
+ | 0.0054 | 5.12 | 3000 | 4.8838 | 0.465 |
72
+ | 0.0014 | 6.12 | 3500 | 4.6808 | 0.495 |
73
+ | 0.0029 | 7.12 | 4000 | 4.4942 | 0.52 |
74
 
75
 
76
  ### Framework versions
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e432544595d0aa0d9a36d7e460c9757039daeddc2c6bc0ad4210eeb99ae1db6c
3
  size 344860025
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cbd64872244b5fa19120711014adbe6b1c89a36816c02ecea27b4574560c8ca7
3
  size 344860025
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fb796d4c68054df31a6201ce774dd678792223ef25322204ffd70f794f8ff7e3
3
  size 4091
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1535226bd3b8383179146ce3812049edfe2b4e320360a0a101a8f835651c4290
3
  size 4091