Hugging Face's logo

thethinkmachine
/
ScratchCNN-FacesMTL-EXP1

Transformers
Safetensors
facesmultitasknet
Generated from Trainer
Model card Files
xet
Community
1

Update README.md

#1
by thethinkmachine - opened
base: refs/heads/main
←
from: refs/pr/1
Discussion Files changed
+88
-88
Files changed (1) hide show
  1. README.md +88 -88
README.md CHANGED
@@ -1,88 +1,88 @@
1
- ---
2
- library_name: transformers
3
- tags:
4
- - generated_from_trainer
5
- model-index:
6
- - name: ScratchCNN-FacesMTL-EXP1
7
- results: []
8
- ---
9
-
10
- <!-- This model card has been generated automatically according to the information the Trainer had access to. You
11
- should probably proofread and complete it, then remove this comment. -->
12
-
13
- # ScratchCNN-FacesMTL-EXP1
14
-
15
- This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
16
- It achieves the following results on the evaluation set:
17
- - Gender Accuracy: 0.7496
18
- - Gender F1: 0.4285
19
- - Age Mae: 11.5140
20
- - Age Rmse: 14.6737
21
- - Loss: 215.8605
22
-
23
- ## Model description
24
-
25
- More information needed
26
-
27
- ## Intended uses & limitations
28
-
29
- More information needed
30
-
31
- ## Training and evaluation data
32
-
33
- More information needed
34
-
35
- ## Training procedure
36
-
37
- ### Training hyperparameters
38
-
39
- The following hyperparameters were used during training:
40
- - learning_rate: 0.0001
41
- - train_batch_size: 32
42
- - eval_batch_size: 32
43
- - seed: 42
44
- - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
45
- - lr_scheduler_type: cosine
46
- - num_epochs: 5
47
- - mixed_precision_training: Native AMP
48
-
49
- ### Training results
50
-
51
- | Training Loss | Epoch | Step | Gender Accuracy | Gender F1 | Age Mae | Age Rmse | Validation Loss |
52
- |:-------------:|:------:|:----:|:---------------:|:---------:|:-------:|:--------:|:---------------:|
53
- | 461.5582 | 0.1728 | 150 | 0.7502 | 0.4286 | 16.4067 | 22.4096 | 502.7608 |
54
- | 247.5034 | 0.3456 | 300 | 0.7502 | 0.4286 | 12.8211 | 17.7391 | 315.2488 |
55
- | 277.9706 | 0.5184 | 450 | 0.7502 | 0.4286 | 12.0017 | 15.9622 | 255.3581 |
56
- | 262.517 | 0.6912 | 600 | 0.7502 | 0.4286 | 12.5625 | 15.3095 | 234.9443 |
57
- | 272.0832 | 0.8641 | 750 | 0.7502 | 0.4286 | 12.4385 | 15.1538 | 230.1988 |
58
- | 276.318 | 1.0369 | 900 | 0.7502 | 0.4286 | 12.2044 | 15.1683 | 230.6356 |
59
- | 225.0257 | 1.2097 | 1050 | 0.7502 | 0.4286 | 12.6894 | 15.6222 | 244.6085 |
60
- | 222.1815 | 1.3825 | 1200 | 0.7502 | 0.4286 | 11.6216 | 14.8317 | 220.5305 |
61
- | 284.4039 | 1.5553 | 1350 | 0.7502 | 0.4286 | 12.0362 | 14.8581 | 221.3155 |
62
- | 273.2046 | 1.7281 | 1500 | 0.7502 | 0.4286 | 12.0341 | 14.7725 | 218.7777 |
63
- | 212.378 | 1.9009 | 1650 | 0.7502 | 0.4286 | 11.6115 | 15.3262 | 235.4443 |
64
- | 229.5636 | 2.0737 | 1800 | 0.7502 | 0.4286 | 11.5028 | 14.6914 | 216.3843 |
65
- | 247.4141 | 2.2465 | 1950 | 0.7502 | 0.4286 | 11.5840 | 15.4565 | 239.4500 |
66
- | 219.0596 | 2.4194 | 2100 | 0.7502 | 0.4286 | 11.6788 | 14.6211 | 214.3237 |
67
- | 218.1279 | 2.5922 | 2250 | 0.7502 | 0.4286 | 11.3897 | 14.7950 | 219.4363 |
68
- | 215.6589 | 2.7650 | 2400 | 0.7502 | 0.4286 | 11.4476 | 14.6256 | 214.4511 |
69
- | 278.3962 | 2.9378 | 2550 | 0.7502 | 0.4286 | 12.0106 | 14.7823 | 219.0586 |
70
- | 237.293 | 3.1106 | 2700 | 0.7502 | 0.4286 | 11.3412 | 14.4551 | 209.4899 |
71
- | 199.9965 | 3.2834 | 2850 | 0.7502 | 0.4286 | 11.4439 | 14.3701 | 207.0407 |
72
- | 252.8384 | 3.4562 | 3000 | 0.7505 | 0.4299 | 11.3330 | 14.3047 | 205.1660 |
73
- | 215.6976 | 3.6290 | 3150 | 0.7502 | 0.4286 | 11.2316 | 14.3694 | 207.0205 |
74
- | 231.9552 | 3.8018 | 3300 | 0.7502 | 0.4286 | 11.3182 | 14.2583 | 203.8388 |
75
- | 265.6475 | 3.9747 | 3450 | 0.7502 | 0.4286 | 11.2547 | 14.5174 | 211.2962 |
76
- | 217.5101 | 4.1475 | 3600 | 0.7502 | 0.4286 | 11.1854 | 14.2591 | 203.8592 |
77
- | 211.7694 | 4.3203 | 3750 | 0.7502 | 0.4286 | 11.2458 | 14.2679 | 204.1106 |
78
- | 256.7229 | 4.4931 | 3900 | 0.7502 | 0.4286 | 11.1988 | 14.2688 | 204.1362 |
79
- | 184.4238 | 4.6659 | 4050 | 0.7502 | 0.4286 | 11.1603 | 14.2800 | 204.4571 |
80
- | 211.074 | 4.8387 | 4200 | 0.7502 | 0.4286 | 11.1595 | 14.2715 | 204.2160 |
81
-
82
-
83
- ### Framework versions
84
-
85
- - Transformers 4.57.1
86
- - Pytorch 2.9.0+cu130
87
- - Datasets 4.4.1
88
- - Tokenizers 0.22.1
 
1
+ ---
2
+ library_name: transformers
3
+ tags:
4
+ - generated_from_trainer
5
+ model-index:
6
+ - name: ScratchCNN-FacesMTL-EXP1
7
+ results: []
8
+ ---
9
+
10
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
11
+ should probably proofread and complete it, then remove this comment. -->
12
+
13
+ # ScratchCNN-FacesMTL-EXP1
14
+
15
+ This model has been pretrained on [[thethinkmachine/faces-mtl](huggingface.co/thethinkmachine/faces-mtl)](https://huggingface.co/datasets/thethinkmachine/faces-mtl) dataset.
16
+ It achieves the following results on the evaluation set:
17
+ - Gender Accuracy: 0.7496
18
+ - Gender F1: 0.4285
19
+ - Age Mae: 11.5140
20
+ - Age Rmse: 14.6737
21
+ - Loss: 215.8605
22
+
23
+ ## Model description
24
+
25
+ More information needed
26
+
27
+ ## Intended uses & limitations
28
+
29
+ More information needed
30
+
31
+ ## Training and evaluation data
32
+
33
+ More information needed
34
+
35
+ ## Training procedure
36
+
37
+ ### Training hyperparameters
38
+
39
+ The following hyperparameters were used during training:
40
+ - learning_rate: 0.0001
41
+ - train_batch_size: 32
42
+ - eval_batch_size: 32
43
+ - seed: 42
44
+ - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
45
+ - lr_scheduler_type: cosine
46
+ - num_epochs: 5
47
+ - mixed_precision_training: Native AMP
48
+
49
+ ### Training results
50
+
51
+ | Training Loss | Epoch | Step | Gender Accuracy | Gender F1 | Age Mae | Age Rmse | Validation Loss |
52
+ |:-------------:|:------:|:----:|:---------------:|:---------:|:-------:|:--------:|:---------------:|
53
+ | 461.5582 | 0.1728 | 150 | 0.7502 | 0.4286 | 16.4067 | 22.4096 | 502.7608 |
54
+ | 247.5034 | 0.3456 | 300 | 0.7502 | 0.4286 | 12.8211 | 17.7391 | 315.2488 |
55
+ | 277.9706 | 0.5184 | 450 | 0.7502 | 0.4286 | 12.0017 | 15.9622 | 255.3581 |
56
+ | 262.517 | 0.6912 | 600 | 0.7502 | 0.4286 | 12.5625 | 15.3095 | 234.9443 |
57
+ | 272.0832 | 0.8641 | 750 | 0.7502 | 0.4286 | 12.4385 | 15.1538 | 230.1988 |
58
+ | 276.318 | 1.0369 | 900 | 0.7502 | 0.4286 | 12.2044 | 15.1683 | 230.6356 |
59
+ | 225.0257 | 1.2097 | 1050 | 0.7502 | 0.4286 | 12.6894 | 15.6222 | 244.6085 |
60
+ | 222.1815 | 1.3825 | 1200 | 0.7502 | 0.4286 | 11.6216 | 14.8317 | 220.5305 |
61
+ | 284.4039 | 1.5553 | 1350 | 0.7502 | 0.4286 | 12.0362 | 14.8581 | 221.3155 |
62
+ | 273.2046 | 1.7281 | 1500 | 0.7502 | 0.4286 | 12.0341 | 14.7725 | 218.7777 |
63
+ | 212.378 | 1.9009 | 1650 | 0.7502 | 0.4286 | 11.6115 | 15.3262 | 235.4443 |
64
+ | 229.5636 | 2.0737 | 1800 | 0.7502 | 0.4286 | 11.5028 | 14.6914 | 216.3843 |
65
+ | 247.4141 | 2.2465 | 1950 | 0.7502 | 0.4286 | 11.5840 | 15.4565 | 239.4500 |
66
+ | 219.0596 | 2.4194 | 2100 | 0.7502 | 0.4286 | 11.6788 | 14.6211 | 214.3237 |
67
+ | 218.1279 | 2.5922 | 2250 | 0.7502 | 0.4286 | 11.3897 | 14.7950 | 219.4363 |
68
+ | 215.6589 | 2.7650 | 2400 | 0.7502 | 0.4286 | 11.4476 | 14.6256 | 214.4511 |
69
+ | 278.3962 | 2.9378 | 2550 | 0.7502 | 0.4286 | 12.0106 | 14.7823 | 219.0586 |
70
+ | 237.293 | 3.1106 | 2700 | 0.7502 | 0.4286 | 11.3412 | 14.4551 | 209.4899 |
71
+ | 199.9965 | 3.2834 | 2850 | 0.7502 | 0.4286 | 11.4439 | 14.3701 | 207.0407 |
72
+ | 252.8384 | 3.4562 | 3000 | 0.7505 | 0.4299 | 11.3330 | 14.3047 | 205.1660 |
73
+ | 215.6976 | 3.6290 | 3150 | 0.7502 | 0.4286 | 11.2316 | 14.3694 | 207.0205 |
74
+ | 231.9552 | 3.8018 | 3300 | 0.7502 | 0.4286 | 11.3182 | 14.2583 | 203.8388 |
75
+ | 265.6475 | 3.9747 | 3450 | 0.7502 | 0.4286 | 11.2547 | 14.5174 | 211.2962 |
76
+ | 217.5101 | 4.1475 | 3600 | 0.7502 | 0.4286 | 11.1854 | 14.2591 | 203.8592 |
77
+ | 211.7694 | 4.3203 | 3750 | 0.7502 | 0.4286 | 11.2458 | 14.2679 | 204.1106 |
78
+ | 256.7229 | 4.4931 | 3900 | 0.7502 | 0.4286 | 11.1988 | 14.2688 | 204.1362 |
79
+ | 184.4238 | 4.6659 | 4050 | 0.7502 | 0.4286 | 11.1603 | 14.2800 | 204.4571 |
80
+ | 211.074 | 4.8387 | 4200 | 0.7502 | 0.4286 | 11.1595 | 14.2715 | 204.2160 |
81
+
82
+
83
+ ### Framework versions
84
+
85
+ - Transformers 4.57.1
86
+ - Pytorch 2.9.0+cu130
87
+ - Datasets 4.4.1
88
+ - Tokenizers 0.22.1