Hugging Face's logo

liamxostrander
/
vit-base-patch16-224-in21k-v2025-2-20

Transformers
TensorBoard
Safetensors
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
liamxostrander commited on
Commit
b0678d6
·
verified ·
1 Parent(s): e46b8d0

Model save

Browse files
Files changed (1) hide show
  1. README.md +114 -0
README.md ADDED
@@ -0,0 +1,114 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ metrics:
8
+ - accuracy
9
+ - f1
10
+ - precision
11
+ - recall
12
+ model-index:
13
+ - name: vit-base-patch16-224-in21k-v2025-2-20
14
+ results: []
15
+ ---
16
+
17
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
18
+ should probably proofread and complete it, then remove this comment. -->
19
+
20
+ # vit-base-patch16-224-in21k-v2025-2-20
21
+
22
+ 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 None dataset.
23
+ It achieves the following results on the evaluation set:
24
+ - Loss: 0.2318
25
+ - Accuracy: 0.9143
26
+ - F1: 0.8
27
+ - Precision: 0.8109
28
+ - Recall: 0.7894
29
+
30
+ ## Model description
31
+
32
+ More information needed
33
+
34
+ ## Intended uses & limitations
35
+
36
+ More information needed
37
+
38
+ ## Training and evaluation data
39
+
40
+ More information needed
41
+
42
+ ## Training procedure
43
+
44
+ ### Training hyperparameters
45
+
46
+ The following hyperparameters were used during training:
47
+ - learning_rate: 0.00025
48
+ - train_batch_size: 16
49
+ - eval_batch_size: 8
50
+ - seed: 42
51
+ - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
52
+ - lr_scheduler_type: linear
53
+ - lr_scheduler_warmup_ratio: 0.1
54
+ - num_epochs: 30
55
+ - mixed_precision_training: Native AMP
56
+
57
+ ### Training results
58
+
59
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
60
+ |:-------------:|:-------:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
61
+ | 0.6069 | 0.6410 | 100 | 0.5681 | 0.7146 | 0.5533 | 0.4191 | 0.8137 |
62
+ | 0.4385 | 1.2821 | 200 | 0.4052 | 0.8384 | 0.6334 | 0.6241 | 0.6430 |
63
+ | 0.3415 | 1.9231 | 300 | 0.2995 | 0.8891 | 0.7233 | 0.7893 | 0.6674 |
64
+ | 0.3761 | 2.5641 | 400 | 0.2871 | 0.8809 | 0.6934 | 0.7863 | 0.6201 |
65
+ | 0.3066 | 3.2051 | 500 | 0.2877 | 0.8841 | 0.7072 | 0.7835 | 0.6445 |
66
+ | 0.3236 | 3.8462 | 600 | 0.2608 | 0.8937 | 0.7398 | 0.7901 | 0.6955 |
67
+ | 0.336 | 4.4872 | 700 | 0.2619 | 0.8926 | 0.7301 | 0.8037 | 0.6689 |
68
+ | 0.3003 | 5.1282 | 800 | 0.2736 | 0.8865 | 0.7160 | 0.7843 | 0.6585 |
69
+ | 0.2756 | 5.7692 | 900 | 0.2584 | 0.8945 | 0.7443 | 0.7862 | 0.7066 |
70
+ | 0.2566 | 6.4103 | 1000 | 0.2574 | 0.8928 | 0.7319 | 0.8007 | 0.6741 |
71
+ | 0.2609 | 7.0513 | 1100 | 0.2506 | 0.8966 | 0.75 | 0.7899 | 0.7140 |
72
+ | 0.2721 | 7.6923 | 1200 | 0.2282 | 0.9024 | 0.7599 | 0.8159 | 0.7110 |
73
+ | 0.2317 | 8.3333 | 1300 | 0.2425 | 0.9029 | 0.7613 | 0.8164 | 0.7132 |
74
+ | 0.2953 | 8.9744 | 1400 | 0.2284 | 0.9077 | 0.7758 | 0.8210 | 0.7354 |
75
+ | 0.2485 | 9.6154 | 1500 | 0.2320 | 0.9042 | 0.7669 | 0.8129 | 0.7258 |
76
+ | 0.2387 | 10.2564 | 1600 | 0.2352 | 0.9034 | 0.7672 | 0.8045 | 0.7332 |
77
+ | 0.2288 | 10.8974 | 1700 | 0.2178 | 0.9087 | 0.7816 | 0.8131 | 0.7524 |
78
+ | 0.1979 | 11.5385 | 1800 | 0.2283 | 0.9100 | 0.7881 | 0.8060 | 0.7709 |
79
+ | 0.194 | 12.1795 | 1900 | 0.2298 | 0.9024 | 0.7704 | 0.7876 | 0.7539 |
80
+ | 0.2011 | 12.8205 | 2000 | 0.2204 | 0.9104 | 0.7882 | 0.8103 | 0.7672 |
81
+ | 0.2033 | 13.4615 | 2100 | 0.2149 | 0.9133 | 0.7951 | 0.8168 | 0.7746 |
82
+ | 0.1795 | 14.1026 | 2200 | 0.2278 | 0.9069 | 0.7815 | 0.7971 | 0.7664 |
83
+ | 0.2153 | 14.7436 | 2300 | 0.2177 | 0.9100 | 0.7853 | 0.8143 | 0.7583 |
84
+ | 0.1814 | 15.3846 | 2400 | 0.2169 | 0.9144 | 0.7991 | 0.8154 | 0.7834 |
85
+ | 0.1605 | 16.0256 | 2500 | 0.2127 | 0.9141 | 0.8 | 0.8094 | 0.7908 |
86
+ | 0.172 | 16.6667 | 2600 | 0.2147 | 0.9116 | 0.7942 | 0.8029 | 0.7857 |
87
+ | 0.1622 | 17.3077 | 2700 | 0.2259 | 0.9071 | 0.7837 | 0.7923 | 0.7753 |
88
+ | 0.1676 | 17.9487 | 2800 | 0.2165 | 0.9117 | 0.7915 | 0.8125 | 0.7716 |
89
+ | 0.1581 | 18.5897 | 2900 | 0.2204 | 0.9109 | 0.7919 | 0.8037 | 0.7805 |
90
+ | 0.1725 | 19.2308 | 3000 | 0.2196 | 0.9108 | 0.7919 | 0.8021 | 0.7820 |
91
+ | 0.1306 | 19.8718 | 3100 | 0.2161 | 0.9125 | 0.7936 | 0.8137 | 0.7746 |
92
+ | 0.1304 | 20.5128 | 3200 | 0.2252 | 0.9061 | 0.7813 | 0.7905 | 0.7724 |
93
+ | 0.1248 | 21.1538 | 3300 | 0.2302 | 0.9112 | 0.7928 | 0.8040 | 0.7820 |
94
+ | 0.1214 | 21.7949 | 3400 | 0.2315 | 0.9085 | 0.7856 | 0.8 | 0.7716 |
95
+ | 0.0979 | 22.4359 | 3500 | 0.2298 | 0.9109 | 0.7911 | 0.8060 | 0.7768 |
96
+ | 0.1157 | 23.0769 | 3600 | 0.2284 | 0.9128 | 0.7964 | 0.8082 | 0.7849 |
97
+ | 0.1279 | 23.7179 | 3700 | 0.2327 | 0.9125 | 0.7933 | 0.8146 | 0.7731 |
98
+ | 0.1032 | 24.3590 | 3800 | 0.2316 | 0.9120 | 0.7932 | 0.8103 | 0.7768 |
99
+ | 0.0958 | 25.0 | 3900 | 0.2244 | 0.9156 | 0.8023 | 0.8164 | 0.7886 |
100
+ | 0.1156 | 25.6410 | 4000 | 0.2356 | 0.9127 | 0.7938 | 0.8148 | 0.7738 |
101
+ | 0.106 | 26.2821 | 4100 | 0.2334 | 0.9100 | 0.7912 | 0.7969 | 0.7857 |
102
+ | 0.0966 | 26.9231 | 4200 | 0.2334 | 0.9132 | 0.7975 | 0.8080 | 0.7871 |
103
+ | 0.0746 | 27.5641 | 4300 | 0.2340 | 0.9117 | 0.7939 | 0.8053 | 0.7827 |
104
+ | 0.0905 | 28.2051 | 4400 | 0.2323 | 0.9130 | 0.7973 | 0.8070 | 0.7879 |
105
+ | 0.0899 | 28.8462 | 4500 | 0.2340 | 0.9138 | 0.7987 | 0.8105 | 0.7871 |
106
+ | 0.0804 | 29.4872 | 4600 | 0.2318 | 0.9143 | 0.8 | 0.8109 | 0.7894 |
107
+
108
+
109
+ ### Framework versions
110
+
111
+ - Transformers 4.48.3
112
+ - Pytorch 2.5.1+cu124
113
+ - Datasets 3.3.1
114
+ - Tokenizers 0.21.0