Added model and dataset details.

#1
Files changed (1) hide show
  1. README.md +91 -91
README.md CHANGED
@@ -1,91 +1,91 @@
1
- ---
2
- library_name: transformers
3
- tags:
4
- - multitask-learning
5
- - efficientnet
6
- - computer-vision
7
- - generated_from_trainer
8
- model-index:
9
- - name: EfficientNetV1-B4-FacesMTL-EXP1
10
- results: []
11
- ---
12
-
13
- <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
- should probably proofread and complete it, then remove this comment. -->
15
-
16
- # EfficientNetV1-B4-FacesMTL-EXP1
17
-
18
- This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
19
- It achieves the following results on the evaluation set:
20
- - Gender Accuracy: 0.9006
21
- - Gender F1: 0.8651
22
- - Age Mae: 6.7354
23
- - Age Rmse: 9.1662
24
- - Loss: 84.2761
25
-
26
- ## Model description
27
-
28
- More information needed
29
-
30
- ## Intended uses & limitations
31
-
32
- More information needed
33
-
34
- ## Training and evaluation data
35
-
36
- More information needed
37
-
38
- ## Training procedure
39
-
40
- ### Training hyperparameters
41
-
42
- The following hyperparameters were used during training:
43
- - learning_rate: 0.0001
44
- - train_batch_size: 32
45
- - eval_batch_size: 32
46
- - seed: 42
47
- - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
48
- - lr_scheduler_type: cosine
49
- - num_epochs: 5
50
- - mixed_precision_training: Native AMP
51
-
52
- ### Training results
53
-
54
- | Training Loss | Epoch | Step | Gender Accuracy | Gender F1 | Age Mae | Age Rmse | Validation Loss |
55
- |:-------------:|:------:|:----:|:---------------:|:---------:|:-------:|:--------:|:---------------:|
56
- | 221.2506 | 0.1728 | 150 | 0.8704 | 0.7993 | 10.4148 | 13.8506 | 192.2673 |
57
- | 163.1323 | 0.3456 | 300 | 0.8637 | 0.7814 | 9.4884 | 12.8120 | 164.4855 |
58
- | 188.8794 | 0.5184 | 450 | 0.8680 | 0.8299 | 9.0322 | 12.2782 | 151.1256 |
59
- | 147.5274 | 0.6912 | 600 | 0.8741 | 0.8056 | 8.1886 | 10.9624 | 120.4869 |
60
- | 121.8239 | 0.8641 | 750 | 0.8879 | 0.8379 | 7.8131 | 10.4025 | 108.5096 |
61
- | 110.5511 | 1.0369 | 900 | 0.8856 | 0.8386 | 7.7040 | 10.3324 | 107.0565 |
62
- | 116.5555 | 1.2097 | 1050 | 0.8741 | 0.8046 | 7.4726 | 9.9674 | 99.6567 |
63
- | 126.6334 | 1.3825 | 1200 | 0.8902 | 0.8415 | 7.5891 | 10.3014 | 106.3999 |
64
- | 147.6252 | 1.5553 | 1350 | 0.8911 | 0.8509 | 7.3201 | 9.8158 | 96.6354 |
65
- | 124.724 | 1.7281 | 1500 | 0.8951 | 0.8546 | 7.2476 | 9.6878 | 94.1328 |
66
- | 107.5 | 1.9009 | 1650 | 0.8897 | 0.8372 | 7.0946 | 9.4325 | 89.2502 |
67
- | 91.8285 | 2.0737 | 1800 | 0.8980 | 0.8612 | 7.0833 | 9.5193 | 90.9008 |
68
- | 94.1933 | 2.2465 | 1950 | 0.8871 | 0.8302 | 7.0344 | 9.4989 | 90.5074 |
69
- | 98.9504 | 2.4194 | 2100 | 0.8928 | 0.8459 | 6.9311 | 9.3160 | 87.0540 |
70
- | 94.4654 | 2.5922 | 2250 | 0.8977 | 0.8611 | 6.9284 | 9.3570 | 87.8282 |
71
- | 85.7435 | 2.7650 | 2400 | 0.8983 | 0.8634 | 6.8776 | 9.3332 | 87.3804 |
72
- | 125.3979 | 2.9378 | 2550 | 0.8989 | 0.8589 | 6.8158 | 9.2204 | 85.2777 |
73
- | 79.05 | 3.1106 | 2700 | 0.8977 | 0.8555 | 6.8892 | 9.3617 | 87.9025 |
74
- | 81.3652 | 3.2834 | 2850 | 0.8954 | 0.8492 | 6.7664 | 9.1391 | 83.7815 |
75
- | 82.3679 | 3.4562 | 3000 | 0.8989 | 0.8641 | 6.8370 | 9.2874 | 86.5219 |
76
- | 83.2362 | 3.6290 | 3150 | 0.8951 | 0.8620 | 6.7723 | 9.1703 | 84.3717 |
77
- | 80.1852 | 3.8018 | 3300 | 0.8995 | 0.8652 | 6.6909 | 9.0639 | 82.4177 |
78
- | 111.4015 | 3.9747 | 3450 | 0.9012 | 0.8645 | 6.7183 | 9.1129 | 83.3005 |
79
- | 76.6393 | 4.1475 | 3600 | 0.9018 | 0.8635 | 6.7800 | 9.1985 | 84.8666 |
80
- | 80.495 | 4.3203 | 3750 | 0.9023 | 0.8673 | 6.6952 | 9.0644 | 82.4208 |
81
- | 104.2716 | 4.4931 | 3900 | 0.9023 | 0.8655 | 6.7867 | 9.2289 | 85.4275 |
82
- | 77.721 | 4.6659 | 4050 | 0.9020 | 0.8674 | 6.9182 | 9.4068 | 88.7482 |
83
- | 70.1717 | 4.8387 | 4200 | 0.9009 | 0.8621 | 6.7354 | 9.1496 | 83.9694 |
84
-
85
-
86
- ### Framework versions
87
-
88
- - Transformers 4.57.1
89
- - Pytorch 2.9.0+cu130
90
- - Datasets 4.4.1
91
- - Tokenizers 0.22.1
 
1
+ ---
2
+ library_name: transformers
3
+ tags:
4
+ - multitask-learning
5
+ - efficientnet
6
+ - computer-vision
7
+ - generated_from_trainer
8
+ model-index:
9
+ - name: EfficientNetV1-B4-FacesMTL-EXP1
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ # EfficientNetV1-B4-FacesMTL-EXP1
17
+
18
+ This model is a fine-tuned version of EfficientNetV2-s on faces-mtl.
19
+ It achieves the following results on the evaluation set:
20
+ - Gender Accuracy: 0.9006
21
+ - Gender F1: 0.8651
22
+ - Age Mae: 6.7354
23
+ - Age Rmse: 9.1662
24
+ - Loss: 84.2761
25
+
26
+ ## Model description
27
+
28
+ More information needed
29
+
30
+ ## Intended uses & limitations
31
+
32
+ More information needed
33
+
34
+ ## Training and evaluation data
35
+
36
+ More information needed
37
+
38
+ ## Training procedure
39
+
40
+ ### Training hyperparameters
41
+
42
+ The following hyperparameters were used during training:
43
+ - learning_rate: 0.0001
44
+ - train_batch_size: 32
45
+ - eval_batch_size: 32
46
+ - seed: 42
47
+ - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
48
+ - lr_scheduler_type: cosine
49
+ - num_epochs: 5
50
+ - mixed_precision_training: Native AMP
51
+
52
+ ### Training results
53
+
54
+ | Training Loss | Epoch | Step | Gender Accuracy | Gender F1 | Age Mae | Age Rmse | Validation Loss |
55
+ |:-------------:|:------:|:----:|:---------------:|:---------:|:-------:|:--------:|:---------------:|
56
+ | 221.2506 | 0.1728 | 150 | 0.8704 | 0.7993 | 10.4148 | 13.8506 | 192.2673 |
57
+ | 163.1323 | 0.3456 | 300 | 0.8637 | 0.7814 | 9.4884 | 12.8120 | 164.4855 |
58
+ | 188.8794 | 0.5184 | 450 | 0.8680 | 0.8299 | 9.0322 | 12.2782 | 151.1256 |
59
+ | 147.5274 | 0.6912 | 600 | 0.8741 | 0.8056 | 8.1886 | 10.9624 | 120.4869 |
60
+ | 121.8239 | 0.8641 | 750 | 0.8879 | 0.8379 | 7.8131 | 10.4025 | 108.5096 |
61
+ | 110.5511 | 1.0369 | 900 | 0.8856 | 0.8386 | 7.7040 | 10.3324 | 107.0565 |
62
+ | 116.5555 | 1.2097 | 1050 | 0.8741 | 0.8046 | 7.4726 | 9.9674 | 99.6567 |
63
+ | 126.6334 | 1.3825 | 1200 | 0.8902 | 0.8415 | 7.5891 | 10.3014 | 106.3999 |
64
+ | 147.6252 | 1.5553 | 1350 | 0.8911 | 0.8509 | 7.3201 | 9.8158 | 96.6354 |
65
+ | 124.724 | 1.7281 | 1500 | 0.8951 | 0.8546 | 7.2476 | 9.6878 | 94.1328 |
66
+ | 107.5 | 1.9009 | 1650 | 0.8897 | 0.8372 | 7.0946 | 9.4325 | 89.2502 |
67
+ | 91.8285 | 2.0737 | 1800 | 0.8980 | 0.8612 | 7.0833 | 9.5193 | 90.9008 |
68
+ | 94.1933 | 2.2465 | 1950 | 0.8871 | 0.8302 | 7.0344 | 9.4989 | 90.5074 |
69
+ | 98.9504 | 2.4194 | 2100 | 0.8928 | 0.8459 | 6.9311 | 9.3160 | 87.0540 |
70
+ | 94.4654 | 2.5922 | 2250 | 0.8977 | 0.8611 | 6.9284 | 9.3570 | 87.8282 |
71
+ | 85.7435 | 2.7650 | 2400 | 0.8983 | 0.8634 | 6.8776 | 9.3332 | 87.3804 |
72
+ | 125.3979 | 2.9378 | 2550 | 0.8989 | 0.8589 | 6.8158 | 9.2204 | 85.2777 |
73
+ | 79.05 | 3.1106 | 2700 | 0.8977 | 0.8555 | 6.8892 | 9.3617 | 87.9025 |
74
+ | 81.3652 | 3.2834 | 2850 | 0.8954 | 0.8492 | 6.7664 | 9.1391 | 83.7815 |
75
+ | 82.3679 | 3.4562 | 3000 | 0.8989 | 0.8641 | 6.8370 | 9.2874 | 86.5219 |
76
+ | 83.2362 | 3.6290 | 3150 | 0.8951 | 0.8620 | 6.7723 | 9.1703 | 84.3717 |
77
+ | 80.1852 | 3.8018 | 3300 | 0.8995 | 0.8652 | 6.6909 | 9.0639 | 82.4177 |
78
+ | 111.4015 | 3.9747 | 3450 | 0.9012 | 0.8645 | 6.7183 | 9.1129 | 83.3005 |
79
+ | 76.6393 | 4.1475 | 3600 | 0.9018 | 0.8635 | 6.7800 | 9.1985 | 84.8666 |
80
+ | 80.495 | 4.3203 | 3750 | 0.9023 | 0.8673 | 6.6952 | 9.0644 | 82.4208 |
81
+ | 104.2716 | 4.4931 | 3900 | 0.9023 | 0.8655 | 6.7867 | 9.2289 | 85.4275 |
82
+ | 77.721 | 4.6659 | 4050 | 0.9020 | 0.8674 | 6.9182 | 9.4068 | 88.7482 |
83
+ | 70.1717 | 4.8387 | 4200 | 0.9009 | 0.8621 | 6.7354 | 9.1496 | 83.9694 |
84
+
85
+
86
+ ### Framework versions
87
+
88
+ - Transformers 4.57.1
89
+ - Pytorch 2.9.0+cu130
90
+ - Datasets 4.4.1
91
+ - Tokenizers 0.22.1