Hugging Face's logo

Hemg
/
heartbeat-detection

Audio Classification
Transformers
TensorBoard
Safetensors
hubert
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
Hemg commited on
Commit
35f7c87
•
1 Parent(s): 6190c68

Model save

Browse files
Files changed (2) hide show
  1. README.md +18 -9
  2. model.safetensors +1 -1
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
- value: 0.5925925925925926
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 [ntu-spml/distilhubert](https://huggingface.co/ntu-spml/distilhubert) on the audiofolder dataset.
34
  It achieves the following results on the evaluation set:
35
- - Loss: 1.5784
36
- - Accuracy: 0.5926
37
 
38
  ## Model description
39
 
@@ -52,23 +52,32 @@ More information needed
52
  ### Training hyperparameters
53
 
54
  The following hyperparameters were used during training:
55
- - learning_rate: 1e-08
56
  - train_batch_size: 8
57
  - eval_batch_size: 8
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: 0.01
62
  - num_epochs: 16
63
 
64
  ### Training results
65
 
66
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
67
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
68
- | 1.5752 | 1.0 | 8 | 1.5789 | 0.5926 |
69
- | 1.5753 | 2.0 | 16 | 1.5787 | 0.5926 |
70
- | 1.5744 | 3.0 | 24 | 1.5786 | 0.5926 |
71
- | 1.5739 | 4.0 | 32 | 1.5784 | 0.5926 |
 
 
 
 
 
 
 
 
 
 
72
 
73
 
74
  ### Framework versions
 
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
+ value: 1.0
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 [ntu-spml/distilhubert](https://huggingface.co/ntu-spml/distilhubert) on the audiofolder dataset.
34
  It achieves the following results on the evaluation set:
35
+ - Loss: 1.4420
36
+ - Accuracy: 1.0
37
 
38
  ## Model description
39
 
 
52
  ### Training hyperparameters
53
 
54
  The following hyperparameters were used during training:
55
+ - learning_rate: 1e-06
56
  - train_batch_size: 8
57
  - eval_batch_size: 8
58
  - seed: 42
59
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
60
  - lr_scheduler_type: linear
 
61
  - num_epochs: 16
62
 
63
  ### Training results
64
 
65
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
66
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
67
+ | 1.6017 | 1.0 | 8 | 1.5921 | 0.1481 |
68
+ | 1.582 | 2.0 | 16 | 1.5723 | 0.4444 |
69
+ | 1.5626 | 3.0 | 24 | 1.5543 | 0.7778 |
70
+ | 1.5442 | 4.0 | 32 | 1.5375 | 0.8148 |
71
+ | 1.5278 | 5.0 | 40 | 1.5220 | 0.8889 |
72
+ | 1.512 | 6.0 | 48 | 1.5077 | 0.9259 |
73
+ | 1.4977 | 7.0 | 56 | 1.4947 | 0.9259 |
74
+ | 1.4872 | 8.0 | 64 | 1.4832 | 0.9630 |
75
+ | 1.4741 | 9.0 | 72 | 1.4729 | 0.9630 |
76
+ | 1.4657 | 10.0 | 80 | 1.4640 | 0.9630 |
77
+ | 1.457 | 11.0 | 88 | 1.4564 | 1.0 |
78
+ | 1.4504 | 12.0 | 96 | 1.4502 | 1.0 |
79
+ | 1.4445 | 13.0 | 104 | 1.4454 | 1.0 |
80
+ | 1.4393 | 14.0 | 112 | 1.4420 | 1.0 |
81
 
82
 
83
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:93baed73f965d704844dc1493be770a0b8c3dde176f7da187c40a1ec73758ea6
3
  size 94766588
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41e7d75fe27b73fdf2dfc9e33eb3e9113a69ef8bb43ddfae7db175f4352be6e1
3
  size 94766588