PedroSampaio commited on
Commit
b08f99d
1 Parent(s): fdd592f

Model save

Browse files
Files changed (1) hide show
  1. README.md +89 -0
README.md ADDED
@@ -0,0 +1,89 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: google/vit-base-patch16-224
4
+ tags:
5
+ - generated_from_trainer
6
+ datasets:
7
+ - food101
8
+ metrics:
9
+ - accuracy
10
+ model-index:
11
+ - name: vit-base-patch16-224-food101-24-12
12
+ results:
13
+ - task:
14
+ name: Image Classification
15
+ type: image-classification
16
+ dataset:
17
+ name: food101
18
+ type: food101
19
+ config: default
20
+ split: validation
21
+ args: default
22
+ metrics:
23
+ - name: Accuracy
24
+ type: accuracy
25
+ value: 0.9087524752475248
26
+ ---
27
+
28
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
29
+ should probably proofread and complete it, then remove this comment. -->
30
+
31
+ # vit-base-patch16-224-food101-24-12
32
+
33
+ This model is a fine-tuned version of [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224) on the food101 dataset.
34
+ It achieves the following results on the evaluation set:
35
+ - Loss: 0.3328
36
+ - Accuracy: 0.9088
37
+
38
+ ## Model description
39
+
40
+ More information needed
41
+
42
+ ## Intended uses & limitations
43
+
44
+ More information needed
45
+
46
+ ## Training and evaluation data
47
+
48
+ More information needed
49
+
50
+ ## Training procedure
51
+
52
+ ### Training hyperparameters
53
+
54
+ The following hyperparameters were used during training:
55
+ - learning_rate: 5e-05
56
+ - train_batch_size: 24
57
+ - eval_batch_size: 24
58
+ - seed: 42
59
+ - gradient_accumulation_steps: 4
60
+ - total_train_batch_size: 96
61
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
62
+ - lr_scheduler_type: linear
63
+ - lr_scheduler_warmup_ratio: 0.1
64
+ - num_epochs: 12
65
+
66
+ ### Training results
67
+
68
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
+ | 1.1313 | 1.0 | 789 | 0.7486 | 0.8388 |
71
+ | 0.735 | 2.0 | 1578 | 0.4546 | 0.8795 |
72
+ | 0.7166 | 3.0 | 2367 | 0.3896 | 0.8942 |
73
+ | 0.5318 | 4.0 | 3157 | 0.3739 | 0.8961 |
74
+ | 0.5326 | 5.0 | 3946 | 0.3576 | 0.9013 |
75
+ | 0.4753 | 6.0 | 4735 | 0.3557 | 0.9006 |
76
+ | 0.3764 | 7.0 | 5524 | 0.3486 | 0.904 |
77
+ | 0.3399 | 8.0 | 6314 | 0.3457 | 0.9046 |
78
+ | 0.3987 | 9.0 | 7103 | 0.3378 | 0.9065 |
79
+ | 0.2592 | 10.0 | 7892 | 0.3393 | 0.9070 |
80
+ | 0.2661 | 11.0 | 8681 | 0.3366 | 0.9080 |
81
+ | 0.2632 | 12.0 | 9468 | 0.3328 | 0.9088 |
82
+
83
+
84
+ ### Framework versions
85
+
86
+ - Transformers 4.35.0
87
+ - Pytorch 2.1.0+cu118
88
+ - Datasets 2.14.6
89
+ - Tokenizers 0.14.1