Hugging Face's logo

Marcos12886
/
distilhubert-finetuned-cry-detector

Audio Classification
Transformers
TensorBoard
Safetensors
hubert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
Marcos12886 commited on
Commit
ac3fed5
•
1 Parent(s): 3ff5ed8

End of training

Browse files
Files changed (3) hide show
  1. README.md +15 -15
  2. model.safetensors +1 -1
  3. training_args.bin +1 -1
README.md CHANGED
@@ -26,16 +26,16 @@ model-index:
26
  metrics:
27
  - name: Accuracy
28
  type: accuracy
29
- value: 0.9647577092511013
30
  - name: F1
31
  type: f1
32
- value: 0.9648767292681042
33
  - name: Precision
34
  type: precision
35
- value: 0.9651623077005758
36
  - name: Recall
37
  type: recall
38
- value: 0.9647577092511013
39
  ---
40
 
41
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -45,11 +45,11 @@ should probably proofread and complete it, then remove this comment. -->
45
 
46
  This model is a fine-tuned version of [ntu-spml/distilhubert](https://huggingface.co/ntu-spml/distilhubert) on the audiofolder dataset.
47
  It achieves the following results on the evaluation set:
48
- - Loss: 0.1135
49
- - Accuracy: 0.9648
50
- - F1: 0.9649
51
- - Precision: 0.9652
52
- - Recall: 0.9648
53
 
54
  ## Model description
55
 
@@ -76,18 +76,18 @@ The following hyperparameters were used during training:
76
  - total_train_batch_size: 64
77
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
78
  - lr_scheduler_type: cosine
79
- - lr_scheduler_warmup_ratio: 0.1
80
  - num_epochs: 5
81
 
82
  ### Training results
83
 
84
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
85
  |:-------------:|:------:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
86
- | No log | 0.9825 | 14 | 0.2255 | 0.9427 | 0.9434 | 0.9459 | 0.9427 |
87
- | No log | 1.9649 | 28 | 0.1302 | 0.9559 | 0.9561 | 0.9564 | 0.9559 |
88
- | No log | 2.9474 | 42 | 0.1557 | 0.9559 | 0.9552 | 0.9574 | 0.9559 |
89
- | No log | 4.0 | 57 | 0.1118 | 0.9559 | 0.9561 | 0.9564 | 0.9559 |
90
- | No log | 4.9123 | 70 | 0.1135 | 0.9648 | 0.9649 | 0.9652 | 0.9648 |
91
 
92
 
93
  ### Framework versions
 
26
  metrics:
27
  - name: Accuracy
28
  type: accuracy
29
+ value: 0.9691629955947136
30
  - name: F1
31
  type: f1
32
+ value: 0.9692159230090303
33
  - name: Precision
34
  type: precision
35
+ value: 0.969310997758714
36
  - name: Recall
37
  type: recall
38
+ value: 0.9691629955947136
39
  ---
40
 
41
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
45
 
46
  This model is a fine-tuned version of [ntu-spml/distilhubert](https://huggingface.co/ntu-spml/distilhubert) on the audiofolder dataset.
47
  It achieves the following results on the evaluation set:
48
+ - Loss: 0.0944
49
+ - Accuracy: 0.9692
50
+ - F1: 0.9692
51
+ - Precision: 0.9693
52
+ - Recall: 0.9692
53
 
54
  ## Model description
55
 
 
76
  - total_train_batch_size: 64
77
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
78
  - lr_scheduler_type: cosine
79
+ - lr_scheduler_warmup_ratio: 0.001
80
  - num_epochs: 5
81
 
82
  ### Training results
83
 
84
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
85
  |:-------------:|:------:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
86
+ | No log | 0.9825 | 14 | 0.1775 | 0.9427 | 0.9434 | 0.9459 | 0.9427 |
87
+ | No log | 1.9649 | 28 | 0.1464 | 0.9515 | 0.9519 | 0.9533 | 0.9515 |
88
+ | No log | 2.9474 | 42 | 0.1139 | 0.9559 | 0.9556 | 0.9560 | 0.9559 |
89
+ | No log | 4.0 | 57 | 0.1042 | 0.9648 | 0.9649 | 0.9652 | 0.9648 |
90
+ | No log | 4.9123 | 70 | 0.0944 | 0.9692 | 0.9692 | 0.9693 | 0.9692 |
91
 
92
 
93
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4e8b05fb4133de6cf1bda70af693b86069d93048c753736d77fd306f0b107d03
3
  size 94763496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ec8c96078435e2d6387b9c637a56592918ae756da25cd14314c7a53bf1ddc60
3
  size 94763496
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:69a4ba3bf8cda65236e6033bc6c30a69ce3de1b79f708ae0d9fe632a886afe34
3
  size 5176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1347bf8e2700ce726a9ee6e199c64e819b37798bb99a31a0c08ba8fcc1fba661
3
  size 5176