sck commited on
Commit
d8e8589
1 Parent(s): f75f120

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +82 -0
README.md ADDED
@@ -0,0 +1,82 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ datasets:
6
+ - imagefolder
7
+ metrics:
8
+ - recall
9
+ model-index:
10
+ - name: vca
11
+ results:
12
+ - task:
13
+ name: Image Classification
14
+ type: image-classification
15
+ dataset:
16
+ name: imagefolder
17
+ type: imagefolder
18
+ config: default
19
+ split: test
20
+ args: default
21
+ metrics:
22
+ - name: Recall
23
+ type: recall
24
+ value: 0.7818181818181819
25
+ ---
26
+
27
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
28
+ should probably proofread and complete it, then remove this comment. -->
29
+
30
+ # vca
31
+
32
+ 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.
33
+ It achieves the following results on the evaluation set:
34
+ - Loss: 0.3844
35
+ - Recall: 0.7818
36
+
37
+ ## Model description
38
+
39
+ More information needed
40
+
41
+ ## Intended uses & limitations
42
+
43
+ More information needed
44
+
45
+ ## Training and evaluation data
46
+
47
+ More information needed
48
+
49
+ ## Training procedure
50
+
51
+ ### Training hyperparameters
52
+
53
+ The following hyperparameters were used during training:
54
+ - learning_rate: 5e-05
55
+ - train_batch_size: 64
56
+ - eval_batch_size: 64
57
+ - seed: 42
58
+ - gradient_accumulation_steps: 4
59
+ - total_train_batch_size: 256
60
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
61
+ - lr_scheduler_type: cosine_with_restarts
62
+ - lr_scheduler_warmup_ratio: 0.1
63
+ - num_epochs: 30
64
+
65
+ ### Training results
66
+
67
+ | Training Loss | Epoch | Step | Validation Loss | Recall |
68
+ |:-------------:|:-----:|:----:|:---------------:|:------:|
69
+ | No log | 1.0 | 11 | 0.4763 | 0.6987 |
70
+ | No log | 2.0 | 22 | 0.4438 | 0.6390 |
71
+ | No log | 3.0 | 33 | 0.4511 | 0.5870 |
72
+ | No log | 4.0 | 44 | 0.4084 | 0.7610 |
73
+ | No log | 5.0 | 55 | 0.3562 | 0.8078 |
74
+ | No log | 6.0 | 66 | 0.3844 | 0.7818 |
75
+
76
+
77
+ ### Framework versions
78
+
79
+ - Transformers 4.31.0.dev0
80
+ - Pytorch 1.13.1+cu117
81
+ - Datasets 2.11.0
82
+ - Tokenizers 0.13.3