vit-base-beans-demo / README.md
1
---
2
license: apache-2.0
3
tags:
4
- image-classification
5
- other-image-classification
6
- generated_from_trainer
7
datasets:
8
- beans
9
metrics:
10
- accuracy
11
12
model-index:
13
- name: vit-base-beans-demo
14
  results:
15
  - task:
16
      name: Image Classification
17
      type: image-classification
18
    dataset:
19
      name: beans
20
      type: beans
21
      args: default
22
    metrics:
23
      - name: Accuracy
24
        type: accuracy
25
        value: 0.9774436090225563
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-beans-demo
32
33
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 beans dataset.
34
It achieves the following results on the evaluation set:
35
- Loss: 0.0853
36
- Accuracy: 0.9774
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: 0.0002
56
- train_batch_size: 16
57
- eval_batch_size: 8
58
- seed: 42
59
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
60
- lr_scheduler_type: linear
61
- num_epochs: 5
62
- mixed_precision_training: Native AMP
63
64
### Training results
65
66
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
67
|:-------------:|:-----:|:----:|:---------------:|:--------:|
68
| 0.0545        | 1.54  | 100  | 0.1436          | 0.9624   |
69
| 0.006         | 3.08  | 200  | 0.1058          | 0.9699   |
70
| 0.0038        | 4.62  | 300  | 0.0853          | 0.9774   |
71
72
73
### Framework versions
74
75
- Transformers 4.9.2
76
- Pytorch 1.9.0+cu102
77
- Datasets 1.11.0
78
- Tokenizers 0.10.3
79