neuralhaven commited on
Commit
2348121
1 Parent(s): adc011f

Model save

Browse files
Files changed (1) hide show
  1. README.md +75 -0
README.md ADDED
@@ -0,0 +1,75 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: other
3
+ base_model: apple/mobilevit-xx-small
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - accuracy
8
+ - precision
9
+ - recall
10
+ - f1
11
+ model-index:
12
+ - name: KDRSSC_TinyViT2MobileViT-xx-small
13
+ results: []
14
+ ---
15
+
16
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
17
+ should probably proofread and complete it, then remove this comment. -->
18
+
19
+ # KDRSSC_TinyViT2MobileViT-xx-small
20
+
21
+ This model is a fine-tuned version of [apple/mobilevit-xx-small](https://huggingface.co/apple/mobilevit-xx-small) on an unknown dataset.
22
+ It achieves the following results on the evaluation set:
23
+ - Loss: 0.8217
24
+ - Accuracy: 0.8398
25
+ - Precision: 0.8409
26
+ - Recall: 0.8398
27
+ - F1: 0.8365
28
+
29
+ ## Model description
30
+
31
+ More information needed
32
+
33
+ ## Intended uses & limitations
34
+
35
+ More information needed
36
+
37
+ ## Training and evaluation data
38
+
39
+ More information needed
40
+
41
+ ## Training procedure
42
+
43
+ ### Training hyperparameters
44
+
45
+ The following hyperparameters were used during training:
46
+ - learning_rate: 0.0001
47
+ - train_batch_size: 128
48
+ - eval_batch_size: 128
49
+ - seed: 42
50
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
51
+ - lr_scheduler_type: linear
52
+ - num_epochs: 10
53
+
54
+ ### Training results
55
+
56
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
57
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
58
+ | 2.1113 | 1.0 | 148 | 1.7471 | 0.588 | 0.6313 | 0.588 | 0.5698 |
59
+ | 1.6003 | 2.0 | 296 | 1.3462 | 0.704 | 0.7133 | 0.704 | 0.6844 |
60
+ | 1.2989 | 3.0 | 444 | 1.1278 | 0.759 | 0.7716 | 0.759 | 0.7509 |
61
+ | 1.1115 | 4.0 | 592 | 0.9891 | 0.802 | 0.8022 | 0.802 | 0.7952 |
62
+ | 0.9978 | 5.0 | 740 | 0.9123 | 0.827 | 0.8413 | 0.827 | 0.8255 |
63
+ | 0.9274 | 6.0 | 888 | 0.8512 | 0.843 | 0.8445 | 0.843 | 0.8387 |
64
+ | 0.8748 | 7.0 | 1036 | 0.8210 | 0.842 | 0.8412 | 0.842 | 0.8373 |
65
+ | 0.8411 | 8.0 | 1184 | 0.7952 | 0.842 | 0.8398 | 0.842 | 0.8365 |
66
+ | 0.818 | 9.0 | 1332 | 0.7814 | 0.852 | 0.8574 | 0.852 | 0.8489 |
67
+ | 0.8081 | 10.0 | 1480 | 0.7796 | 0.853 | 0.8591 | 0.853 | 0.8487 |
68
+
69
+
70
+ ### Framework versions
71
+
72
+ - Transformers 4.44.0
73
+ - Pytorch 2.4.0
74
+ - Datasets 2.21.0
75
+ - Tokenizers 0.19.1