Hugging Face's logo

kedimestan
/
mobilevit-x-small

Image Classification
Transformers
TensorBoard
Safetensors
mobilevit
Generated from Trainer
Eval Results (legacy)
Model card Files
xet
 Metrics Community
kedimestan commited on
Commit
ee96229
·
verified ·
1 Parent(s): f029da1

Model save

Browse files
Files changed (2) hide show
  1. README.md +108 -0
  2. model.safetensors +1 -1
README.md ADDED
@@ -0,0 +1,108 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: other
4
+ base_model: apple/mobilevit-x-small
5
+ tags:
6
+ - generated_from_trainer
7
+ datasets:
8
+ - imagefolder
9
+ metrics:
10
+ - accuracy
11
+ model-index:
12
+ - name: mobilevit-x-small
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: 0.995850622406639
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
+ # mobilevit-x-small
33
+
34
+ This model is a fine-tuned version of [apple/mobilevit-x-small](https://huggingface.co/apple/mobilevit-x-small) on the imagefolder dataset.
35
+ It achieves the following results on the evaluation set:
36
+ - Loss: 0.0196
37
+ - Accuracy: 0.9959
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: 5e-05
57
+ - train_batch_size: 32
58
+ - eval_batch_size: 32
59
+ - seed: 42
60
+ - gradient_accumulation_steps: 4
61
+ - total_train_batch_size: 128
62
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
63
+ - lr_scheduler_type: linear
64
+ - lr_scheduler_warmup_ratio: 0.1
65
+ - num_epochs: 30
66
+
67
+ ### Training results
68
+
69
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
70
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
71
+ | 0.6911 | 1.0 | 34 | 0.6932 | 0.5083 |
72
+ | 0.6584 | 2.0 | 68 | 0.6287 | 0.7510 |
73
+ | 0.5388 | 3.0 | 102 | 0.4852 | 0.8734 |
74
+ | 0.3891 | 4.0 | 136 | 0.3065 | 0.9357 |
75
+ | 0.2915 | 5.0 | 170 | 0.2005 | 0.9647 |
76
+ | 0.2319 | 6.0 | 204 | 0.1498 | 0.9689 |
77
+ | 0.2038 | 7.0 | 238 | 0.1228 | 0.9710 |
78
+ | 0.1641 | 8.0 | 272 | 0.0892 | 0.9855 |
79
+ | 0.1525 | 9.0 | 306 | 0.0778 | 0.9834 |
80
+ | 0.1584 | 10.0 | 340 | 0.0565 | 0.9896 |
81
+ | 0.1194 | 11.0 | 374 | 0.0491 | 0.9917 |
82
+ | 0.1222 | 12.0 | 408 | 0.0436 | 0.9896 |
83
+ | 0.1229 | 13.0 | 442 | 0.0360 | 0.9979 |
84
+ | 0.1334 | 14.0 | 476 | 0.0326 | 0.9959 |
85
+ | 0.122 | 15.0 | 510 | 0.0425 | 0.9896 |
86
+ | 0.096 | 16.0 | 544 | 0.0315 | 0.9959 |
87
+ | 0.0989 | 17.0 | 578 | 0.0303 | 0.9938 |
88
+ | 0.1085 | 18.0 | 612 | 0.0262 | 0.9959 |
89
+ | 0.0957 | 19.0 | 646 | 0.0232 | 0.9959 |
90
+ | 0.1129 | 20.0 | 680 | 0.0266 | 0.9959 |
91
+ | 0.0843 | 21.0 | 714 | 0.0234 | 0.9959 |
92
+ | 0.0868 | 22.0 | 748 | 0.0217 | 0.9959 |
93
+ | 0.0867 | 23.0 | 782 | 0.0233 | 0.9959 |
94
+ | 0.0947 | 24.0 | 816 | 0.0204 | 0.9959 |
95
+ | 0.0786 | 25.0 | 850 | 0.0199 | 0.9959 |
96
+ | 0.1009 | 26.0 | 884 | 0.0212 | 0.9959 |
97
+ | 0.0785 | 27.0 | 918 | 0.0204 | 0.9959 |
98
+ | 0.0811 | 28.0 | 952 | 0.0180 | 0.9959 |
99
+ | 0.0883 | 29.0 | 986 | 0.0193 | 0.9959 |
100
+ | 0.0988 | 30.0 | 1020 | 0.0196 | 0.9959 |
101
+
102
+
103
+ ### Framework versions
104
+
105
+ - Transformers 4.44.2
106
+ - Pytorch 2.4.1+cu121
107
+ - Datasets 3.2.0
108
+ - Tokenizers 0.19.1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5a5507d6b4cf7189c45db3ed2cbcba86ab6ee59db038757dda372e996e84dd57
3
  size 7814816
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31f343254fcab3e8ce4389801d85ed98235b3d10e916c8fe62693d9e6dc52207
3
  size 7814816