rwang5688 commited on
Commit
0cc4cdb
1 Parent(s): 52e0886

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +42 -19
README.md CHANGED
@@ -1,23 +1,38 @@
1
  ---
2
  license: apache-2.0
3
  tags:
4
- - generated_from_keras_callback
 
 
 
 
5
  model-index:
6
- - name: rwang5688/vit-base-patch16-224-finetuned-eurosat
7
- results: []
 
 
 
 
 
 
 
 
 
 
 
 
 
8
  ---
9
 
10
- <!-- This model card has been generated automatically according to the information Keras had access to. You should
11
- probably proofread and complete it, then remove this comment. -->
12
 
13
- # rwang5688/vit-base-patch16-224-finetuned-eurosat
14
 
15
- This model is a fine-tuned version of [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224) on an unknown dataset.
16
  It achieves the following results on the evaluation set:
17
- - Train Loss: 0.3145
18
- - Validation Loss: 0.0427
19
- - Validation Accuracy: 0.9870
20
- - Epoch: 2
21
 
22
  ## Model description
23
 
@@ -36,21 +51,29 @@ More information needed
36
  ### Training hyperparameters
37
 
38
  The following hyperparameters were used during training:
39
- - optimizer: {'name': 'AdamWeightDecay', 'learning_rate': 5e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.01}
40
- - training_precision: float32
 
 
 
 
 
 
 
 
41
 
42
  ### Training results
43
 
44
- | Train Loss | Validation Loss | Validation Accuracy | Epoch |
45
- |:----------:|:---------------:|:-------------------:|:-----:|
46
- | 0.4985 | 0.1121 | 0.9641 | 0 |
47
- | 0.3527 | 0.0535 | 0.9826 | 1 |
48
- | 0.3145 | 0.0427 | 0.9870 | 2 |
49
 
50
 
51
  ### Framework versions
52
 
53
  - Transformers 4.21.1
54
- - TensorFlow 2.9.1
55
  - Datasets 2.4.0
56
  - Tokenizers 0.12.1
 
1
  ---
2
  license: apache-2.0
3
  tags:
4
+ - generated_from_trainer
5
+ datasets:
6
+ - imagefolder
7
+ metrics:
8
+ - accuracy
9
  model-index:
10
+ - name: vit-base-patch16-224-finetuned-eurosat
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: train
20
+ args: default
21
+ metrics:
22
+ - name: Accuracy
23
+ type: accuracy
24
+ value: 0.9855555555555555
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
+ # vit-base-patch16-224-finetuned-eurosat
31
 
32
+ 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.
33
  It achieves the following results on the evaluation set:
34
+ - Loss: 0.0469
35
+ - Accuracy: 0.9856
 
 
36
 
37
  ## Model description
38
 
 
51
  ### Training hyperparameters
52
 
53
  The following hyperparameters were used during training:
54
+ - learning_rate: 5e-05
55
+ - train_batch_size: 32
56
+ - eval_batch_size: 32
57
+ - seed: 42
58
+ - gradient_accumulation_steps: 4
59
+ - total_train_batch_size: 128
60
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
61
+ - lr_scheduler_type: linear
62
+ - lr_scheduler_warmup_ratio: 0.1
63
+ - num_epochs: 3
64
 
65
  ### Training results
66
 
67
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
68
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
69
+ | 0.1491 | 1.0 | 190 | 0.0890 | 0.9715 |
70
+ | 0.1021 | 2.0 | 380 | 0.0578 | 0.9811 |
71
+ | 0.0694 | 3.0 | 570 | 0.0469 | 0.9856 |
72
 
73
 
74
  ### Framework versions
75
 
76
  - Transformers 4.21.1
77
+ - Pytorch 1.12.1+cu102
78
  - Datasets 2.4.0
79
  - Tokenizers 0.12.1