paul commited on
Commit
c57dbaf
·
1 Parent(s): a499d25

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +111 -0
README.md ADDED
@@ -0,0 +1,111 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ datasets:
6
+ - imagefolder
7
+ metrics:
8
+ - accuracy
9
+ - precision
10
+ - recall
11
+ - f1
12
+ model-index:
13
+ - name: vit-base-patch16-224-FV2-finetuned-memes
14
+ results:
15
+ - task:
16
+ name: Image Classification
17
+ type: image-classification
18
+ dataset:
19
+ name: imagefolder
20
+ type: imagefolder
21
+ config: default
22
+ split: train
23
+ args: default
24
+ metrics:
25
+ - name: Accuracy
26
+ type: accuracy
27
+ value: 0.8647604327666152
28
+ - name: Precision
29
+ type: precision
30
+ value: 0.865115560305398
31
+ - name: Recall
32
+ type: recall
33
+ value: 0.8647604327666152
34
+ - name: F1
35
+ type: f1
36
+ value: 0.8646314523408155
37
+ ---
38
+
39
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
40
+ should probably proofread and complete it, then remove this comment. -->
41
+
42
+ # vit-base-patch16-224-FV2-finetuned-memes
43
+
44
+ This model is a fine-tuned version of [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224) on the imagefolder dataset.
45
+ It achieves the following results on the evaluation set:
46
+ - Loss: 0.5458
47
+ - Accuracy: 0.8648
48
+ - Precision: 0.8651
49
+ - Recall: 0.8648
50
+ - F1: 0.8646
51
+
52
+ ## Model description
53
+
54
+ More information needed
55
+
56
+ ## Intended uses & limitations
57
+
58
+ More information needed
59
+
60
+ ## Training and evaluation data
61
+
62
+ More information needed
63
+
64
+ ## Training procedure
65
+
66
+ ### Training hyperparameters
67
+
68
+ The following hyperparameters were used during training:
69
+ - learning_rate: 0.00012
70
+ - train_batch_size: 64
71
+ - eval_batch_size: 64
72
+ - seed: 42
73
+ - gradient_accumulation_steps: 4
74
+ - total_train_batch_size: 256
75
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
76
+ - lr_scheduler_type: linear
77
+ - lr_scheduler_warmup_ratio: 0.1
78
+ - num_epochs: 20
79
+
80
+ ### Training results
81
+
82
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
83
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
84
+ | 0.994 | 0.99 | 20 | 0.7937 | 0.7257 | 0.7148 | 0.7257 | 0.7025 |
85
+ | 0.509 | 1.99 | 40 | 0.4634 | 0.8346 | 0.8461 | 0.8346 | 0.8303 |
86
+ | 0.2698 | 2.99 | 60 | 0.3851 | 0.8594 | 0.8619 | 0.8594 | 0.8586 |
87
+ | 0.1381 | 3.99 | 80 | 0.4186 | 0.8624 | 0.8716 | 0.8624 | 0.8634 |
88
+ | 0.0899 | 4.99 | 100 | 0.4038 | 0.8586 | 0.8624 | 0.8586 | 0.8594 |
89
+ | 0.0708 | 5.99 | 120 | 0.4170 | 0.8563 | 0.8612 | 0.8563 | 0.8580 |
90
+ | 0.0629 | 6.99 | 140 | 0.4414 | 0.8594 | 0.8599 | 0.8594 | 0.8585 |
91
+ | 0.0554 | 7.99 | 160 | 0.4617 | 0.8539 | 0.8563 | 0.8539 | 0.8550 |
92
+ | 0.0582 | 8.99 | 180 | 0.4712 | 0.8648 | 0.8667 | 0.8648 | 0.8651 |
93
+ | 0.0582 | 9.99 | 200 | 0.4753 | 0.8632 | 0.8647 | 0.8632 | 0.8636 |
94
+ | 0.0535 | 10.99 | 220 | 0.4653 | 0.8694 | 0.8690 | 0.8694 | 0.8684 |
95
+ | 0.0516 | 11.99 | 240 | 0.4937 | 0.8679 | 0.8692 | 0.8679 | 0.8681 |
96
+ | 0.0478 | 12.99 | 260 | 0.5109 | 0.8725 | 0.8741 | 0.8725 | 0.8718 |
97
+ | 0.0484 | 13.99 | 280 | 0.5144 | 0.8640 | 0.8660 | 0.8640 | 0.8647 |
98
+ | 0.0472 | 14.99 | 300 | 0.5249 | 0.8679 | 0.8688 | 0.8679 | 0.8678 |
99
+ | 0.043 | 15.99 | 320 | 0.5324 | 0.8709 | 0.8711 | 0.8709 | 0.8704 |
100
+ | 0.0473 | 16.99 | 340 | 0.5352 | 0.8648 | 0.8660 | 0.8648 | 0.8647 |
101
+ | 0.0502 | 17.99 | 360 | 0.5389 | 0.8694 | 0.8692 | 0.8694 | 0.8687 |
102
+ | 0.0489 | 18.99 | 380 | 0.5564 | 0.8648 | 0.8666 | 0.8648 | 0.8651 |
103
+ | 0.04 | 19.99 | 400 | 0.5458 | 0.8648 | 0.8651 | 0.8648 | 0.8646 |
104
+
105
+
106
+ ### Framework versions
107
+
108
+ - Transformers 4.24.0.dev0
109
+ - Pytorch 1.11.0+cu102
110
+ - Datasets 2.6.1.dev0
111
+ - Tokenizers 0.13.1