Hugging Face's logo

Marcos12886
/
distilhubert-finetuned-mixed-data

Audio Classification
Transformers
TensorBoard
Safetensors
hubert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
Marcos12886 commited on
Commit
b9a704a
•
1 Parent(s): 4cd5635

End of training

Browse files
Files changed (5) hide show
  1. README.md +24 -22
  2. model.safetensors +1 -1
  3. runs/Sep01_18-37-56_ubumarcos/events.out.tfevents.1725208678.ubumarcos +3 -0
  4. runs/Sep01_18-58-29_ubumarcos/events.out.tfevents.1725209913.ubumarcos +3 -0
  5. training_args.bin +1 -1
README.md CHANGED
@@ -26,16 +26,16 @@ model-index:
26
  metrics:
27
  - name: Accuracy
28
  type: accuracy
29
- value: 0.889261744966443
30
  - name: F1
31
  type: f1
32
- value: 0.8883742273982193
33
  - name: Precision
34
  type: precision
35
- value: 0.8879660679296787
36
  - name: Recall
37
  type: recall
38
- value: 0.889261744966443
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: 0.2853
49
- - Accuracy: 0.8893
50
- - F1: 0.8884
51
- - Precision: 0.8880
52
- - Recall: 0.8893
53
 
54
  ## Model description
55
 
@@ -77,22 +77,24 @@ The following hyperparameters were used during training:
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: 10
81
 
82
  ### Training results
83
 
84
- | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
85
- |:-------------:|:------:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
86
- | No log | 0.9664 | 18 | 0.6892 | 0.7617 | 0.7077 | 0.6737 | 0.7617 |
87
- | No log | 1.9866 | 37 | 0.5095 | 0.8087 | 0.7505 | 0.7108 | 0.8087 |
88
- | No log | 2.9530 | 55 | 0.4728 | 0.7819 | 0.7226 | 0.6874 | 0.7819 |
89
- | No log | 3.9732 | 74 | 0.3589 | 0.8658 | 0.8559 | 0.8575 | 0.8658 |
90
- | No log | 4.9933 | 93 | 0.3575 | 0.8456 | 0.8440 | 0.8494 | 0.8456 |
91
- | No log | 5.9597 | 111 | 0.3389 | 0.8557 | 0.8550 | 0.8720 | 0.8557 |
92
- | No log | 6.9799 | 130 | 0.3046 | 0.8725 | 0.8723 | 0.8766 | 0.8725 |
93
- | No log | 8.0 | 149 | 0.2980 | 0.8826 | 0.8814 | 0.8820 | 0.8826 |
94
- | No log | 8.9664 | 167 | 0.2848 | 0.8859 | 0.8848 | 0.8840 | 0.8859 |
95
- | No log | 9.6644 | 180 | 0.2853 | 0.8893 | 0.8884 | 0.8880 | 0.8893 |
 
 
96
 
97
 
98
  ### Framework versions
 
26
  metrics:
27
  - name: Accuracy
28
  type: accuracy
29
+ value: 0.9026845637583892
30
  - name: F1
31
  type: f1
32
+ value: 0.9017814679012008
33
  - name: Precision
34
  type: precision
35
+ value: 0.901095676384633
36
  - name: Recall
37
  type: recall
38
+ value: 0.9026845637583892
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: 0.2976
49
+ - Accuracy: 0.9027
50
+ - F1: 0.9018
51
+ - Precision: 0.9011
52
+ - Recall: 0.9027
53
 
54
  ## Model description
55
 
 
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: 12
81
 
82
  ### Training results
83
 
84
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
85
+ |:-------------:|:-------:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
86
+ | No log | 0.9664 | 18 | 0.6696 | 0.7819 | 0.7264 | 0.6898 | 0.7819 |
87
+ | No log | 1.9866 | 37 | 0.5068 | 0.7752 | 0.7203 | 0.6849 | 0.7752 |
88
+ | No log | 2.9530 | 55 | 0.4304 | 0.8087 | 0.7535 | 0.7242 | 0.8087 |
89
+ | No log | 3.9732 | 74 | 0.4109 | 0.8523 | 0.8434 | 0.8728 | 0.8523 |
90
+ | No log | 4.9933 | 93 | 0.3263 | 0.8725 | 0.8718 | 0.8719 | 0.8725 |
91
+ | No log | 5.9597 | 111 | 0.3036 | 0.8826 | 0.8824 | 0.8824 | 0.8826 |
92
+ | No log | 6.9799 | 130 | 0.3046 | 0.8893 | 0.8876 | 0.8892 | 0.8893 |
93
+ | No log | 8.0 | 149 | 0.3244 | 0.8758 | 0.8770 | 0.8787 | 0.8758 |
94
+ | No log | 8.9664 | 167 | 0.2962 | 0.9027 | 0.9018 | 0.9012 | 0.9027 |
95
+ | No log | 9.9866 | 186 | 0.2971 | 0.9027 | 0.9010 | 0.9014 | 0.9027 |
96
+ | No log | 10.9530 | 204 | 0.2974 | 0.9094 | 0.9082 | 0.9077 | 0.9094 |
97
+ | No log | 11.5973 | 216 | 0.2976 | 0.9027 | 0.9018 | 0.9011 | 0.9027 |
98
 
99
 
100
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:183c1e13e10305d6b8076bcaf712f7e88803bb8ff5a44a21879a9559ed22abfc
3
  size 94765560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:add11297401b595ef24d8a66b9cf4f5bca92dae882193b715a5917dff07be685
3
  size 94765560
runs/Sep01_18-37-56_ubumarcos/events.out.tfevents.1725208678.ubumarcos ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89a53ddca3d3e14aaa79cdf3f34a7372c81ff26a12033d1c130786d2060ec1ef
3
+ size 9620
runs/Sep01_18-58-29_ubumarcos/events.out.tfevents.1725209913.ubumarcos ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:802ee1ace83491bfe95253196b16242c4d1f6e6d88ef2aca4fe68871ac06c4fd
3
+ size 11862
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fe3428151155ef7796462efbb081d472101fbc6af944f18c5de69fecb3e1043d
3
  size 5240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:296be9afae72ab3934d873f0cf92f87ef76899c18b11651de670afb49aa1a5d6
3
  size 5240