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
f25614b
•
1 Parent(s): 7eddb7e

End of training

Browse files
Files changed (9) hide show
  1. README.md +11 -14
  2. model.safetensors +1 -1
  3. runs/Sep06_15-54-59_ubumarcos/events.out.tfevents.1725630900.ubumarcos +3 -0
  4. runs/Sep06_17-32-26_ubumarcos/events.out.tfevents.1725636747.ubumarcos +3 -0
  5. runs/Sep08_21-41-41_ubumarcos/events.out.tfevents.1725824502.ubumarcos +3 -0
  6. runs/Sep08_21-41-41_ubumarcos/events.out.tfevents.1725824503.ubumarcos +3 -0
  7. runs/Sep08_21-42-34_ubumarcos/events.out.tfevents.1725824555.ubumarcos +3 -0
  8. runs/Sep08_21-50-57_ubumarcos/events.out.tfevents.1725825058.ubumarcos +3 -0
  9. training_args.bin +1 -1
README.md CHANGED
@@ -21,11 +21,11 @@ should probably proofread and complete it, then remove this comment. -->
21
 
22
  This model is a fine-tuned version of [ntu-spml/distilhubert](https://huggingface.co/ntu-spml/distilhubert) on an unknown dataset.
23
  It achieves the following results on the evaluation set:
24
- - Loss: 0.0359
25
- - Accuracy: 0.9883
26
- - Precision: 0.9883
27
- - Recall: 0.9883
28
- - F1: 0.9883
29
 
30
  ## Model description
31
 
@@ -44,7 +44,7 @@ More information needed
44
  ### Training hyperparameters
45
 
46
  The following hyperparameters were used during training:
47
- - learning_rate: 5e-05
48
  - train_batch_size: 8
49
  - eval_batch_size: 8
50
  - seed: 123
@@ -53,19 +53,16 @@ The following hyperparameters were used during training:
53
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
54
  - lr_scheduler_type: cosine
55
  - lr_scheduler_warmup_ratio: 0.001
56
- - num_epochs: 10
57
 
58
  ### Training results
59
 
60
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
61
  |:-------------:|:------:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
62
- | No log | 0.9956 | 85 | 0.1341 | 0.9538 | 0.9543 | 0.9538 | 0.9532 |
63
- | No log | 1.9912 | 170 | 0.0831 | 0.9700 | 0.9720 | 0.9700 | 0.9703 |
64
- | No log | 2.9985 | 256 | 0.0570 | 0.9846 | 0.9847 | 0.9846 | 0.9846 |
65
- | No log | 3.9941 | 341 | 0.0340 | 0.9897 | 0.9898 | 0.9897 | 0.9898 |
66
- | No log | 4.9898 | 426 | 0.0460 | 0.9875 | 0.9879 | 0.9875 | 0.9876 |
67
- | 0.0707 | 5.9971 | 512 | 0.0431 | 0.9897 | 0.9899 | 0.9897 | 0.9898 |
68
- | 0.0707 | 6.9927 | 597 | 0.0359 | 0.9883 | 0.9883 | 0.9883 | 0.9883 |
69
 
70
 
71
  ### Framework versions
 
21
 
22
  This model is a fine-tuned version of [ntu-spml/distilhubert](https://huggingface.co/ntu-spml/distilhubert) on an unknown dataset.
23
  It achieves the following results on the evaluation set:
24
+ - Loss: 0.0625
25
+ - Accuracy: 0.9824
26
+ - Precision: 0.9825
27
+ - Recall: 0.9824
28
+ - F1: 0.9824
29
 
30
  ## Model description
31
 
 
44
  ### Training hyperparameters
45
 
46
  The following hyperparameters were used during training:
47
+ - learning_rate: 3e-05
48
  - train_batch_size: 8
49
  - eval_batch_size: 8
50
  - seed: 123
 
53
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
54
  - lr_scheduler_type: cosine
55
  - lr_scheduler_warmup_ratio: 0.001
56
+ - num_epochs: 4
57
 
58
  ### Training results
59
 
60
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
61
  |:-------------:|:------:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
62
+ | No log | 0.9956 | 85 | 0.1378 | 0.9546 | 0.9543 | 0.9546 | 0.9544 |
63
+ | No log | 1.9912 | 170 | 0.0802 | 0.9714 | 0.9713 | 0.9714 | 0.9714 |
64
+ | No log | 2.9985 | 256 | 0.0682 | 0.9780 | 0.9783 | 0.9780 | 0.9781 |
65
+ | No log | 3.9824 | 340 | 0.0625 | 0.9824 | 0.9825 | 0.9824 | 0.9824 |
 
 
 
66
 
67
 
68
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:937ffa1cb79f16f4e7753ea842c3e32fe34e525562027e5b33ce48fc4b308a82
3
  size 94763496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02108e5b5b6258f37f5cf8b56d34f77aa8b483e760491525d71597e196663a68
3
  size 94763496
runs/Sep06_15-54-59_ubumarcos/events.out.tfevents.1725630900.ubumarcos ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1acef9821029fd1212d748efd26c746ef609728916bb04756b301a4027aed9d7
3
+ size 5850
runs/Sep06_17-32-26_ubumarcos/events.out.tfevents.1725636747.ubumarcos ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89395943d8de67b3553472ad01aa836188c676359cc9b10e225dd488dbb1d7ac
3
+ size 9238
runs/Sep08_21-41-41_ubumarcos/events.out.tfevents.1725824502.ubumarcos ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89c619e470e68f874e4cb0664e10f8a4fdf35a1bdd0c2527edd075706f92d81a
3
+ size 5851
runs/Sep08_21-41-41_ubumarcos/events.out.tfevents.1725824503.ubumarcos ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90c52b45df2498fc461d9ed2383ef00e8683f52764e29e553f2a7d683c6062eb
3
+ size 5851
runs/Sep08_21-42-34_ubumarcos/events.out.tfevents.1725824555.ubumarcos ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2a93d1da540cf716d2ca78b8fc4f898ca82630a2e7b3aef2aef2cf70d974709
3
+ size 7730
runs/Sep08_21-50-57_ubumarcos/events.out.tfevents.1725825058.ubumarcos ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:733dd4196f81f5f0672f6e91223ee12db5b02db4b8f6bfa80103cd6ccffdce87
3
+ size 8083
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:831297954221509dc3f32e8eaf01789c3f660cf430e186799d52e58ec3b5b334
3
  size 5240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7bd8e997c05f23ae464180f8e5e9f881e9c68322e4fcd3f855e79e2e5d54fbb
3
  size 5240