Hugging Face's logo

fullstuck
/
image_classification

Image Classification
Transformers
PyTorch
TensorBoard
Safetensors
vit
Generated from Trainer
Eval Results
Model card Files Metrics Community
fullstuck commited on
Commit
de0080c
·
1 Parent(s): 3ff2f65

End of training

Browse files
Files changed (2) hide show
  1. README.md +55 -8
  2. pytorch_model.bin +1 -1
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
- value: 0.50625
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -32,8 +32,8 @@ should probably proofread and complete it, then remove this comment. -->
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 imagefolder dataset.
34
  It achieves the following results on the evaluation set:
35
- - Loss: 1.3916
36
- - Accuracy: 0.5062
37
 
38
  ## Model description
39
 
@@ -52,21 +52,68 @@ More information needed
52
  ### Training hyperparameters
53
 
54
  The following hyperparameters were used during training:
55
- - learning_rate: 5e-05
56
  - train_batch_size: 16
57
  - eval_batch_size: 16
58
  - seed: 42
59
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
60
  - lr_scheduler_type: linear
61
- - num_epochs: 3
62
 
63
  ### Training results
64
 
65
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
66
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
67
- | No log | 1.0 | 40 | 1.4094 | 0.5375 |
68
- | No log | 2.0 | 80 | 1.3534 | 0.5188 |
69
- | No log | 3.0 | 120 | 1.3492 | 0.5 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
70
 
71
 
72
  ### Framework versions
 
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
+ value: 0.525
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
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 imagefolder dataset.
34
  It achieves the following results on the evaluation set:
35
+ - Loss: 1.9905
36
+ - Accuracy: 0.525
37
 
38
  ## Model description
39
 
 
52
  ### Training hyperparameters
53
 
54
  The following hyperparameters were used during training:
55
+ - learning_rate: 0.0001
56
  - train_batch_size: 16
57
  - eval_batch_size: 16
58
  - seed: 42
59
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
60
  - lr_scheduler_type: linear
61
+ - num_epochs: 50
62
 
63
  ### Training results
64
 
65
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
66
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
67
+ | No log | 1.0 | 40 | 1.7409 | 0.2875 |
68
+ | No log | 2.0 | 80 | 1.5124 | 0.4375 |
69
+ | No log | 3.0 | 120 | 1.4255 | 0.4437 |
70
+ | No log | 4.0 | 160 | 1.4154 | 0.425 |
71
+ | No log | 5.0 | 200 | 1.2886 | 0.4625 |
72
+ | No log | 6.0 | 240 | 1.2963 | 0.5125 |
73
+ | No log | 7.0 | 280 | 1.3139 | 0.55 |
74
+ | No log | 8.0 | 320 | 1.2976 | 0.5312 |
75
+ | No log | 9.0 | 360 | 1.4368 | 0.5062 |
76
+ | No log | 10.0 | 400 | 1.4022 | 0.5062 |
77
+ | No log | 11.0 | 440 | 1.2853 | 0.55 |
78
+ | No log | 12.0 | 480 | 1.3265 | 0.5563 |
79
+ | 0.8831 | 13.0 | 520 | 1.3894 | 0.55 |
80
+ | 0.8831 | 14.0 | 560 | 1.4465 | 0.5312 |
81
+ | 0.8831 | 15.0 | 600 | 1.7185 | 0.475 |
82
+ | 0.8831 | 16.0 | 640 | 1.7408 | 0.4875 |
83
+ | 0.8831 | 17.0 | 680 | 1.5199 | 0.5437 |
84
+ | 0.8831 | 18.0 | 720 | 1.7238 | 0.525 |
85
+ | 0.8831 | 19.0 | 760 | 1.8348 | 0.4875 |
86
+ | 0.8831 | 20.0 | 800 | 1.6278 | 0.5125 |
87
+ | 0.8831 | 21.0 | 840 | 1.7539 | 0.5 |
88
+ | 0.8831 | 22.0 | 880 | 1.9007 | 0.4938 |
89
+ | 0.8831 | 23.0 | 920 | 1.6903 | 0.5375 |
90
+ | 0.8831 | 24.0 | 960 | 1.7954 | 0.5062 |
91
+ | 0.2214 | 25.0 | 1000 | 1.7070 | 0.575 |
92
+ | 0.2214 | 26.0 | 1040 | 1.6764 | 0.5625 |
93
+ | 0.2214 | 27.0 | 1080 | 1.8590 | 0.5188 |
94
+ | 0.2214 | 28.0 | 1120 | 1.7531 | 0.5188 |
95
+ | 0.2214 | 29.0 | 1160 | 1.5238 | 0.5875 |
96
+ | 0.2214 | 30.0 | 1200 | 1.6463 | 0.6 |
97
+ | 0.2214 | 31.0 | 1240 | 1.7955 | 0.5563 |
98
+ | 0.2214 | 32.0 | 1280 | 1.9920 | 0.5 |
99
+ | 0.2214 | 33.0 | 1320 | 1.8826 | 0.55 |
100
+ | 0.2214 | 34.0 | 1360 | 2.0573 | 0.5 |
101
+ | 0.2214 | 35.0 | 1400 | 1.8438 | 0.5312 |
102
+ | 0.2214 | 36.0 | 1440 | 1.9004 | 0.5312 |
103
+ | 0.2214 | 37.0 | 1480 | 1.8215 | 0.5437 |
104
+ | 0.1479 | 38.0 | 1520 | 2.0467 | 0.5437 |
105
+ | 0.1479 | 39.0 | 1560 | 1.8564 | 0.5687 |
106
+ | 0.1479 | 40.0 | 1600 | 1.8381 | 0.5687 |
107
+ | 0.1479 | 41.0 | 1640 | 1.8110 | 0.5687 |
108
+ | 0.1479 | 42.0 | 1680 | 2.0587 | 0.5375 |
109
+ | 0.1479 | 43.0 | 1720 | 1.9597 | 0.5687 |
110
+ | 0.1479 | 44.0 | 1760 | 1.9199 | 0.5687 |
111
+ | 0.1479 | 45.0 | 1800 | 1.8714 | 0.5312 |
112
+ | 0.1479 | 46.0 | 1840 | 1.9463 | 0.575 |
113
+ | 0.1479 | 47.0 | 1880 | 2.0449 | 0.5312 |
114
+ | 0.1479 | 48.0 | 1920 | 1.9172 | 0.525 |
115
+ | 0.1479 | 49.0 | 1960 | 1.9153 | 0.55 |
116
+ | 0.0946 | 50.0 | 2000 | 1.9905 | 0.525 |
117
 
118
 
119
  ### Framework versions
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7429cdd777addaa28e32d6a1b51e826d27eddc24361d43c0fcfd18062fc76f66
3
  size 343287149
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:265c9247698592700f08b23e3a142225e841b98e899b5bb8ceb9796eb88e43ca
3
  size 343287149