Hugging Face's logo

Augusto777
/
vit-base-patch16-224-ve-U13b-80RX

Image Classification
Transformers
TensorBoard
Safetensors
vit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
Augusto777 commited on
Commit
9108cc3
•
1 Parent(s): a98ffa2

Model save

Browse files
Files changed (3) hide show
  1. README.md +45 -44
  2. model.safetensors +1 -1
  3. runs/Jun23_14-57-58_DESKTOP-SKBE9FB/events.out.tfevents.1719176279.DESKTOP-SKBE9FB.17456.0 +2 -2
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
- value: 0.8695652173913043
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](https://huggingface.co/google/vit-base-patch16-224) on the imagefolder dataset.
34
  It achieves the following results on the evaluation set:
35
- - Loss: 0.6456
36
- - Accuracy: 0.8696
37
 
38
  ## Model description
39
 
@@ -56,8 +56,8 @@ The following hyperparameters were used during training:
56
  - train_batch_size: 8
57
  - eval_batch_size: 8
58
  - seed: 42
59
- - gradient_accumulation_steps: 4
60
- - total_train_batch_size: 32
61
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
62
  - lr_scheduler_type: linear
63
  - lr_scheduler_warmup_ratio: 0.05
@@ -67,45 +67,46 @@ The following hyperparameters were used during training:
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
- | 1.3805 | 0.97 | 25 | 1.3567 | 0.5 |
71
- | 1.1576 | 1.98 | 51 | 1.1360 | 0.4348 |
72
- | 0.9331 | 2.99 | 77 | 0.8531 | 0.8043 |
73
- | 0.6657 | 4.0 | 103 | 0.6856 | 0.7826 |
74
- | 0.5642 | 4.97 | 128 | 0.6162 | 0.7826 |
75
- | 0.3632 | 5.98 | 154 | 0.5902 | 0.8043 |
76
- | 0.3384 | 6.99 | 180 | 0.4995 | 0.8043 |
77
- | 0.2261 | 8.0 | 206 | 0.6854 | 0.7609 |
78
- | 0.2066 | 8.97 | 231 | 0.5605 | 0.7826 |
79
- | 0.1635 | 9.98 | 257 | 0.7209 | 0.7391 |
80
- | 0.1829 | 10.99 | 283 | 0.9293 | 0.6957 |
81
- | 0.1455 | 12.0 | 309 | 0.5999 | 0.7826 |
82
- | 0.1072 | 12.97 | 334 | 0.7919 | 0.7826 |
83
- | 0.1059 | 13.98 | 360 | 0.7782 | 0.8043 |
84
- | 0.0971 | 14.99 | 386 | 0.8249 | 0.8043 |
85
- | 0.0456 | 16.0 | 412 | 0.7965 | 0.7826 |
86
- | 0.0483 | 16.97 | 437 | 0.7163 | 0.8261 |
87
- | 0.0832 | 17.98 | 463 | 0.8122 | 0.7826 |
88
- | 0.055 | 18.99 | 489 | 0.8250 | 0.7826 |
89
- | 0.0753 | 20.0 | 515 | 0.6866 | 0.8478 |
90
- | 0.14 | 20.97 | 540 | 0.6456 | 0.8696 |
91
- | 0.0506 | 21.98 | 566 | 0.9127 | 0.7826 |
92
- | 0.0963 | 22.99 | 592 | 0.6365 | 0.8261 |
93
- | 0.0612 | 24.0 | 618 | 0.8252 | 0.8043 |
94
- | 0.0875 | 24.97 | 643 | 0.8844 | 0.7391 |
95
- | 0.1041 | 25.98 | 669 | 0.6594 | 0.8261 |
96
- | 0.0512 | 26.99 | 695 | 0.9883 | 0.7826 |
97
- | 0.0675 | 28.0 | 721 | 0.9216 | 0.8043 |
98
- | 0.0492 | 28.97 | 746 | 0.9284 | 0.8043 |
99
- | 0.0679 | 29.98 | 772 | 0.9341 | 0.7826 |
100
- | 0.0996 | 30.99 | 798 | 0.9608 | 0.8043 |
101
- | 0.0729 | 32.0 | 824 | 1.0155 | 0.7826 |
102
- | 0.0296 | 32.97 | 849 | 1.0314 | 0.7826 |
103
- | 0.0414 | 33.98 | 875 | 0.8358 | 0.8043 |
104
- | 0.04 | 34.99 | 901 | 0.8912 | 0.8043 |
105
- | 0.0179 | 36.0 | 927 | 0.8544 | 0.8043 |
106
- | 0.0665 | 36.97 | 952 | 0.9154 | 0.8043 |
107
- | 0.0413 | 37.98 | 978 | 0.8834 | 0.8043 |
108
- | 0.04 | 38.83 | 1000 | 0.8808 | 0.8043 |
 
109
 
110
 
111
  ### Framework versions
 
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
+ value: 0.8043478260869565
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](https://huggingface.co/google/vit-base-patch16-224) on the imagefolder dataset.
34
  It achieves the following results on the evaluation set:
35
+ - Loss: 0.8551
36
+ - Accuracy: 0.8043
37
 
38
  ## Model description
39
 
 
56
  - train_batch_size: 8
57
  - eval_batch_size: 8
58
  - seed: 42
59
+ - gradient_accumulation_steps: 6
60
+ - total_train_batch_size: 48
61
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
62
  - lr_scheduler_type: linear
63
  - lr_scheduler_warmup_ratio: 0.05
 
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
+ | 1.3857 | 0.99 | 17 | 1.3703 | 0.5652 |
71
+ | 1.3134 | 1.98 | 34 | 1.2235 | 0.4565 |
72
+ | 1.0384 | 2.97 | 51 | 1.0173 | 0.5435 |
73
+ | 0.908 | 3.96 | 68 | 0.8346 | 0.7826 |
74
+ | 0.75 | 4.95 | 85 | 0.7343 | 0.7826 |
75
+ | 0.5131 | 6.0 | 103 | 0.6099 | 0.8478 |
76
+ | 0.395 | 6.99 | 120 | 0.5932 | 0.7826 |
77
+ | 0.355 | 7.98 | 137 | 0.7209 | 0.7391 |
78
+ | 0.2658 | 8.97 | 154 | 0.5652 | 0.8043 |
79
+ | 0.248 | 9.96 | 171 | 0.7103 | 0.7826 |
80
+ | 0.2086 | 10.95 | 188 | 0.6788 | 0.7609 |
81
+ | 0.1532 | 12.0 | 206 | 0.5725 | 0.7826 |
82
+ | 0.147 | 12.99 | 223 | 0.6130 | 0.8043 |
83
+ | 0.1145 | 13.98 | 240 | 0.6563 | 0.8043 |
84
+ | 0.1053 | 14.97 | 257 | 0.5993 | 0.8043 |
85
+ | 0.0971 | 15.96 | 274 | 0.8840 | 0.7391 |
86
+ | 0.0947 | 16.95 | 291 | 0.6256 | 0.8043 |
87
+ | 0.1055 | 18.0 | 309 | 0.8406 | 0.7609 |
88
+ | 0.0974 | 18.99 | 326 | 0.6355 | 0.8478 |
89
+ | 0.1215 | 19.98 | 343 | 0.6651 | 0.8043 |
90
+ | 0.108 | 20.97 | 360 | 0.8301 | 0.7826 |
91
+ | 0.0784 | 21.96 | 377 | 0.8837 | 0.7609 |
92
+ | 0.0919 | 22.95 | 394 | 0.6985 | 0.8043 |
93
+ | 0.064 | 24.0 | 412 | 0.6426 | 0.8043 |
94
+ | 0.0669 | 24.99 | 429 | 0.8102 | 0.7826 |
95
+ | 0.0878 | 25.98 | 446 | 0.7863 | 0.7391 |
96
+ | 0.0875 | 26.97 | 463 | 0.8777 | 0.7609 |
97
+ | 0.0441 | 27.96 | 480 | 0.7324 | 0.8043 |
98
+ | 0.088 | 28.95 | 497 | 0.8099 | 0.7826 |
99
+ | 0.0739 | 30.0 | 515 | 0.7776 | 0.8043 |
100
+ | 0.0598 | 30.99 | 532 | 0.8188 | 0.7826 |
101
+ | 0.0443 | 31.98 | 549 | 0.8549 | 0.8043 |
102
+ | 0.0376 | 32.97 | 566 | 0.8049 | 0.7826 |
103
+ | 0.0375 | 33.96 | 583 | 0.8037 | 0.8043 |
104
+ | 0.0346 | 34.95 | 600 | 0.8255 | 0.8261 |
105
+ | 0.0471 | 36.0 | 618 | 0.8239 | 0.8043 |
106
+ | 0.0669 | 36.99 | 635 | 0.8188 | 0.8043 |
107
+ | 0.0438 | 37.98 | 652 | 0.8443 | 0.8043 |
108
+ | 0.0549 | 38.97 | 669 | 0.8551 | 0.8043 |
109
+ | 0.0622 | 39.61 | 680 | 0.8551 | 0.8043 |
110
 
111
 
112
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:583110b5578ed76920a246d06c25bd7eeb30c8946b9fb0a879999708b709123f
3
  size 343230128
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d519d94f2bb4df47dc9347a3187e66b4816afc984d9e37dc690ae97419a97d94
3
  size 343230128
runs/Jun23_14-57-58_DESKTOP-SKBE9FB/events.out.tfevents.1719176279.DESKTOP-SKBE9FB.17456.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:59fc9adc65d1f21950aba0848b7c23571b51f5494f03737da971f2b524887530
3
- size 26907
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a986870debb3e2ffa520f0e6dd00cca347c315e3497133defd21a1b95fd7e821
3
+ size 28378