Hugging Face's logo

ongkn
/
attraction-classifier

Image Classification
Transformers
Safetensors
vit
Generated from Trainer
Eval Results (legacy)
Model card Files
xet
Community
5
ongkn commited on
Commit
9ac8ad5
·
1 Parent(s): 759d33d

End of training

Browse files
Files changed (2) hide show
  1. README.md +33 -31
  2. model.safetensors +1 -1
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
- value: 0.7955974842767296
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: 0.4691
36
- - Accuracy: 0.7956
37
 
38
  ## Model description
39
 
@@ -60,40 +60,42 @@ The following hyperparameters were used during training:
60
  - total_train_batch_size: 64
61
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
62
  - lr_scheduler_type: cosine
63
- - lr_scheduler_warmup_ratio: 0.15
64
  - num_epochs: 15
65
 
66
  ### Training results
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
- | 0.6703 | 0.34 | 15 | 0.6354 | 0.7327 |
71
- | 0.5449 | 0.67 | 30 | 0.5836 | 0.7421 |
72
- | 0.5407 | 1.01 | 45 | 0.5594 | 0.7421 |
73
- | 0.5255 | 1.34 | 60 | 0.5294 | 0.7547 |
74
- | 0.5586 | 1.68 | 75 | 0.5171 | 0.7642 |
75
- | 0.5438 | 2.01 | 90 | 0.5212 | 0.7704 |
76
- | 0.4807 | 2.35 | 105 | 0.5181 | 0.7390 |
77
- | 0.6202 | 2.68 | 120 | 0.4972 | 0.7704 |
78
- | 0.5021 | 3.02 | 135 | 0.4566 | 0.7987 |
79
- | 0.4313 | 3.35 | 150 | 0.4852 | 0.7925 |
80
- | 0.3532 | 3.69 | 165 | 0.4378 | 0.8113 |
81
- | 0.3577 | 4.02 | 180 | 0.4515 | 0.8019 |
82
- | 0.4736 | 4.36 | 195 | 0.4498 | 0.7893 |
83
- | 0.3516 | 4.69 | 210 | 0.4408 | 0.8239 |
84
- | 0.4437 | 5.03 | 225 | 0.4611 | 0.7799 |
85
- | 0.3543 | 5.36 | 240 | 0.4294 | 0.8208 |
86
- | 0.4029 | 5.7 | 255 | 0.4155 | 0.8428 |
87
- | 0.3808 | 6.03 | 270 | 0.4116 | 0.8302 |
88
- | 0.3211 | 6.37 | 285 | 0.4009 | 0.8302 |
89
- | 0.2949 | 6.7 | 300 | 0.4321 | 0.8176 |
90
- | 0.2663 | 7.04 | 315 | 0.4229 | 0.8396 |
91
- | 0.3049 | 7.37 | 330 | 0.4110 | 0.8365 |
92
- | 0.1303 | 7.71 | 345 | 0.4288 | 0.8333 |
93
- | 0.2079 | 8.04 | 360 | 0.4218 | 0.8208 |
94
- | 0.208 | 8.38 | 375 | 0.3908 | 0.8365 |
95
- | 0.2067 | 8.72 | 390 | 0.5191 | 0.7862 |
96
- | 0.1635 | 9.05 | 405 | 0.4691 | 0.7956 |
 
 
97
 
98
 
99
  ### Framework versions
 
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
+ value: 0.8364779874213837
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: 0.4547
36
+ - Accuracy: 0.8365
37
 
38
  ## Model description
39
 
 
60
  - total_train_batch_size: 64
61
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
62
  - lr_scheduler_type: cosine
63
+ - lr_scheduler_warmup_ratio: 0.1
64
  - num_epochs: 15
65
 
66
  ### Training results
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
+ | 0.6516 | 0.34 | 15 | 0.6155 | 0.7421 |
71
+ | 0.5163 | 0.67 | 30 | 0.5604 | 0.7421 |
72
+ | 0.5583 | 1.01 | 45 | 0.5582 | 0.7579 |
73
+ | 0.5323 | 1.34 | 60 | 0.5358 | 0.7044 |
74
+ | 0.5691 | 1.68 | 75 | 0.5361 | 0.7736 |
75
+ | 0.5143 | 2.01 | 90 | 0.5042 | 0.7421 |
76
+ | 0.4711 | 2.35 | 105 | 0.5435 | 0.7075 |
77
+ | 0.5742 | 2.68 | 120 | 0.4918 | 0.7673 |
78
+ | 0.5406 | 3.02 | 135 | 0.4630 | 0.7987 |
79
+ | 0.4454 | 3.35 | 150 | 0.5241 | 0.7453 |
80
+ | 0.348 | 3.69 | 165 | 0.4116 | 0.8113 |
81
+ | 0.3441 | 4.02 | 180 | 0.4560 | 0.7987 |
82
+ | 0.6001 | 4.36 | 195 | 0.4411 | 0.8113 |
83
+ | 0.2765 | 4.69 | 210 | 0.4282 | 0.8270 |
84
+ | 0.4746 | 5.03 | 225 | 0.4850 | 0.7642 |
85
+ | 0.2547 | 5.36 | 240 | 0.4294 | 0.8176 |
86
+ | 0.3734 | 5.7 | 255 | 0.4351 | 0.8270 |
87
+ | 0.2776 | 6.03 | 270 | 0.4395 | 0.8176 |
88
+ | 0.3024 | 6.37 | 285 | 0.4005 | 0.8491 |
89
+ | 0.2034 | 6.7 | 300 | 0.4476 | 0.8113 |
90
+ | 0.2668 | 7.04 | 315 | 0.4359 | 0.8113 |
91
+ | 0.267 | 7.37 | 330 | 0.4509 | 0.8019 |
92
+ | 0.1185 | 7.71 | 345 | 0.4554 | 0.8208 |
93
+ | 0.1785 | 8.04 | 360 | 0.4258 | 0.8208 |
94
+ | 0.1733 | 8.38 | 375 | 0.4197 | 0.8270 |
95
+ | 0.2107 | 8.72 | 390 | 0.6167 | 0.7484 |
96
+ | 0.1244 | 9.05 | 405 | 0.5048 | 0.7925 |
97
+ | 0.1648 | 9.39 | 420 | 0.4921 | 0.8050 |
98
+ | 0.2374 | 9.72 | 435 | 0.4547 | 0.8365 |
99
 
100
 
101
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:318edc20e934a8335d14d702015b7c0dab191d5034f6f8d101fcf76aca69443e
3
  size 343223968
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49d8ca8d200a34d6a7eecb87a62f5ff46147e1be6f72094fc04ad4bc3449b030
3
  size 343223968