Hugging Face's logo

MarfinF
/
emotion_classification_adjusted

Image Classification
Transformers
Safetensors
vit
Generated from Trainer
Eval Results
Model card Files
xet
Community
MarfinF commited on
Commit
cddb48d
·
verified ·
1 Parent(s): f2c5eb8

End of training

Browse files
Files changed (1) hide show
  1. README.md +137 -0
README.md ADDED
@@ -0,0 +1,137 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: apache-2.0
4
+ base_model: google/vit-base-patch16-224-in21k
5
+ tags:
6
+ - generated_from_trainer
7
+ datasets:
8
+ - imagefolder
9
+ metrics:
10
+ - accuracy
11
+ model-index:
12
+ - name: emotion_classification_adjusted
13
+ results:
14
+ - task:
15
+ name: Image Classification
16
+ type: image-classification
17
+ dataset:
18
+ name: imagefolder
19
+ type: imagefolder
20
+ config: default
21
+ split: train
22
+ args: default
23
+ metrics:
24
+ - name: Accuracy
25
+ type: accuracy
26
+ value: 0.8625
27
+ ---
28
+
29
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
30
+ should probably proofread and complete it, then remove this comment. -->
31
+
32
+ # emotion_classification_adjusted
33
+
34
+ This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the imagefolder dataset.
35
+ It achieves the following results on the evaluation set:
36
+ - Loss: 0.8392
37
+ - Accuracy: 0.8625
38
+
39
+ ## Model description
40
+
41
+ More information needed
42
+
43
+ ## Intended uses & limitations
44
+
45
+ More information needed
46
+
47
+ ## Training and evaluation data
48
+
49
+ More information needed
50
+
51
+ ## Training procedure
52
+
53
+ ### Training hyperparameters
54
+
55
+ The following hyperparameters were used during training:
56
+ - learning_rate: 2e-05
57
+ - train_batch_size: 32
58
+ - eval_batch_size: 32
59
+ - seed: 42
60
+ - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
61
+ - lr_scheduler_type: cosine
62
+ - lr_scheduler_warmup_ratio: 0.1
63
+ - num_epochs: 60
64
+ - label_smoothing_factor: 0.1
65
+
66
+ ### Training results
67
+
68
+ | Training Loss | Epoch | Step | Accuracy | Validation Loss |
69
+ |:-------------:|:-----:|:----:|:--------:|:---------------:|
70
+ | 2.0787 | 1.0 | 20 | 0.1625 | 2.0753 |
71
+ | 2.073 | 2.0 | 40 | 0.1187 | 2.0737 |
72
+ | 2.0599 | 3.0 | 60 | 0.1938 | 2.0585 |
73
+ | 2.0363 | 4.0 | 80 | 0.1938 | 2.0368 |
74
+ | 2.0051 | 5.0 | 100 | 0.2625 | 1.9921 |
75
+ | 1.9348 | 6.0 | 120 | 0.3375 | 1.9185 |
76
+ | 1.8466 | 7.0 | 140 | 0.375 | 1.8056 |
77
+ | 1.755 | 8.0 | 160 | 0.4313 | 1.7292 |
78
+ | 1.676 | 9.0 | 180 | 0.45 | 1.6674 |
79
+ | 1.6244 | 10.0 | 200 | 0.475 | 1.6237 |
80
+ | 1.5661 | 11.0 | 220 | 0.5062 | 1.5973 |
81
+ | 1.5252 | 12.0 | 240 | 0.5 | 1.5262 |
82
+ | 1.4729 | 13.0 | 260 | 0.55 | 1.5050 |
83
+ | 1.4203 | 14.0 | 280 | 0.55 | 1.4784 |
84
+ | 1.364 | 15.0 | 300 | 0.525 | 1.5131 |
85
+ | 1.3262 | 16.0 | 320 | 0.5125 | 1.4776 |
86
+ | 1.3102 | 17.0 | 340 | 0.5563 | 1.4200 |
87
+ | 1.2595 | 18.0 | 360 | 0.5563 | 1.4329 |
88
+ | 1.2188 | 19.0 | 380 | 0.5375 | 1.4213 |
89
+ | 1.1991 | 20.0 | 400 | 0.525 | 1.4077 |
90
+ | 1.1526 | 21.0 | 420 | 0.6062 | 1.3625 |
91
+ | 1.1225 | 22.0 | 440 | 0.5437 | 1.3745 |
92
+ | 1.1283 | 23.0 | 460 | 0.5375 | 1.3677 |
93
+ | 1.0856 | 24.0 | 480 | 0.5625 | 1.3283 |
94
+ | 1.0559 | 25.0 | 500 | 0.5687 | 1.3440 |
95
+ | 1.0102 | 26.0 | 520 | 0.5437 | 1.3357 |
96
+ | 0.9915 | 27.0 | 540 | 0.5813 | 1.3377 |
97
+ | 0.9807 | 28.0 | 560 | 0.55 | 1.3824 |
98
+ | 0.9382 | 29.0 | 580 | 0.4938 | 1.4468 |
99
+ | 0.9857 | 30.0 | 600 | 0.8125 | 0.9923 |
100
+ | 0.9956 | 31.0 | 620 | 0.7625 | 1.0361 |
101
+ | 0.9875 | 32.0 | 640 | 0.775 | 1.0310 |
102
+ | 0.9582 | 33.0 | 660 | 0.7625 | 1.0572 |
103
+ | 0.9649 | 34.0 | 680 | 0.8063 | 0.9725 |
104
+ | 0.9099 | 35.0 | 700 | 0.7562 | 1.0355 |
105
+ | 0.9339 | 36.0 | 720 | 0.7937 | 1.0129 |
106
+ | 0.9045 | 37.0 | 740 | 0.7562 | 1.0315 |
107
+ | 0.8903 | 38.0 | 760 | 0.8187 | 0.9923 |
108
+ | 0.8799 | 39.0 | 780 | 0.7625 | 1.0386 |
109
+ | 0.8664 | 40.0 | 800 | 0.7438 | 1.0626 |
110
+ | 0.8351 | 41.0 | 820 | 0.7688 | 0.9885 |
111
+ | 0.8514 | 42.0 | 840 | 0.7875 | 0.9975 |
112
+ | 0.857 | 43.0 | 860 | 0.75 | 1.0169 |
113
+ | 0.8331 | 44.0 | 880 | 0.7937 | 0.9763 |
114
+ | 0.8093 | 45.0 | 900 | 0.7937 | 0.9645 |
115
+ | 0.8303 | 46.0 | 920 | 0.8 | 0.9880 |
116
+ | 0.8077 | 47.0 | 940 | 0.8063 | 1.0094 |
117
+ | 0.8082 | 48.0 | 960 | 0.7937 | 0.9757 |
118
+ | 0.8088 | 49.0 | 980 | 0.7438 | 1.0451 |
119
+ | 0.7985 | 50.0 | 1000 | 0.7875 | 0.9850 |
120
+ | 0.8013 | 51.0 | 1020 | 0.7688 | 1.0362 |
121
+ | 0.7882 | 52.0 | 1040 | 0.775 | 1.0007 |
122
+ | 0.8051 | 53.0 | 1060 | 0.7438 | 1.0314 |
123
+ | 0.812 | 54.0 | 1080 | 0.8 | 0.9782 |
124
+ | 0.7895 | 55.0 | 1100 | 0.725 | 1.0396 |
125
+ | 0.8012 | 56.0 | 1120 | 0.7688 | 0.9894 |
126
+ | 0.7973 | 57.0 | 1140 | 0.7875 | 0.9981 |
127
+ | 0.7946 | 58.0 | 1160 | 0.8063 | 0.9754 |
128
+ | 0.8437 | 59.0 | 1180 | 0.85 | 0.8544 |
129
+ | 0.8489 | 60.0 | 1200 | 0.7991 | 0.9062 |
130
+
131
+
132
+ ### Framework versions
133
+
134
+ - Transformers 4.48.3
135
+ - Pytorch 2.5.1
136
+ - Datasets 3.2.0
137
+ - Tokenizers 0.21.0