Hugging Face's logo

HorcruxNo13
/
vit-base-patch16-224

Image Classification
Transformers
PyTorch
vit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
HorcruxNo13 commited on
Commit
0d48740
•
1 Parent(s): 89c92c0

Model save

Browse files
Files changed (2) hide show
  1. README.md +39 -24
  2. pytorch_model.bin +1 -1
README.md CHANGED
@@ -24,13 +24,13 @@ model-index:
24
  metrics:
25
  - name: Accuracy
26
  type: accuracy
27
- value: 0.7833333333333333
28
  - name: Precision
29
  type: precision
30
- value: 0.7701923076923076
31
  - name: Recall
32
  type: recall
33
- value: 0.7833333333333333
34
  ---
35
 
36
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -40,11 +40,11 @@ should probably proofread and complete it, then remove this comment. -->
40
 
41
  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.
42
  It achieves the following results on the evaluation set:
43
- - Loss: 0.4772
44
- - Accuracy: 0.7833
45
- - Precision: 0.7702
46
- - Recall: 0.7833
47
- - F1 Score: 0.7559
48
 
49
  ## Model description
50
 
@@ -72,27 +72,42 @@ The following hyperparameters were used during training:
72
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
73
  - lr_scheduler_type: linear
74
  - lr_scheduler_warmup_ratio: 0.1
75
- - num_epochs: 15
76
 
77
  ### Training results
78
 
79
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 Score |
80
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:--------:|
81
- | No log | 1.0 | 4 | 0.6010 | 0.7333 | 0.6725 | 0.7333 | 0.6280 |
82
- | No log | 2.0 | 8 | 0.5552 | 0.7375 | 0.8067 | 0.7375 | 0.6302 |
83
- | No log | 3.0 | 12 | 0.5450 | 0.7542 | 0.7598 | 0.7542 | 0.6782 |
84
- | 0.576 | 4.0 | 16 | 0.5325 | 0.75 | 0.7707 | 0.75 | 0.6641 |
85
- | 0.576 | 5.0 | 20 | 0.5234 | 0.75 | 0.7232 | 0.75 | 0.6900 |
86
- | 0.576 | 6.0 | 24 | 0.5112 | 0.7625 | 0.7506 | 0.7625 | 0.7076 |
87
- | 0.576 | 7.0 | 28 | 0.5082 | 0.7667 | 0.7503 | 0.7667 | 0.7221 |
88
- | 0.4876 | 8.0 | 32 | 0.5067 | 0.7667 | 0.7466 | 0.7667 | 0.7288 |
89
- | 0.4876 | 9.0 | 36 | 0.5091 | 0.7792 | 0.7623 | 0.7792 | 0.7528 |
90
- | 0.4876 | 10.0 | 40 | 0.5023 | 0.7583 | 0.7393 | 0.7583 | 0.7045 |
91
- | 0.4876 | 11.0 | 44 | 0.4911 | 0.7708 | 0.7507 | 0.7708 | 0.7435 |
92
- | 0.4379 | 12.0 | 48 | 0.4921 | 0.7667 | 0.7487 | 0.7667 | 0.7513 |
93
- | 0.4379 | 13.0 | 52 | 0.4906 | 0.7917 | 0.7792 | 0.7917 | 0.7680 |
94
- | 0.4379 | 14.0 | 56 | 0.4919 | 0.7875 | 0.7731 | 0.7875 | 0.7645 |
95
- | 0.4003 | 15.0 | 60 | 0.4929 | 0.7833 | 0.7678 | 0.7833 | 0.7587 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
96
 
97
 
98
  ### Framework versions
 
24
  metrics:
25
  - name: Accuracy
26
  type: accuracy
27
+ value: 0.7766666666666666
28
  - name: Precision
29
  type: precision
30
+ value: 0.7660774253731343
31
  - name: Recall
32
  type: recall
33
+ value: 0.7766666666666666
34
  ---
35
 
36
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
40
 
41
  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.
42
  It achieves the following results on the evaluation set:
43
+ - Loss: 0.5054
44
+ - Accuracy: 0.7767
45
+ - Precision: 0.7661
46
+ - Recall: 0.7767
47
+ - F1 Score: 0.7395
48
 
49
  ## Model description
50
 
 
72
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
73
  - lr_scheduler_type: linear
74
  - lr_scheduler_warmup_ratio: 0.1
75
+ - num_epochs: 30
76
 
77
  ### Training results
78
 
79
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 Score |
80
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:--------:|
81
+ | No log | 1.0 | 4 | 0.6002 | 0.7208 | 0.6144 | 0.7208 | 0.6282 |
82
+ | No log | 2.0 | 8 | 0.5620 | 0.7333 | 0.5378 | 0.7333 | 0.6205 |
83
+ | No log | 3.0 | 12 | 0.5641 | 0.7208 | 0.6144 | 0.7208 | 0.6282 |
84
+ | No log | 4.0 | 16 | 0.5504 | 0.7208 | 0.6453 | 0.7208 | 0.6460 |
85
+ | No log | 5.0 | 20 | 0.5444 | 0.7292 | 0.6795 | 0.7292 | 0.6754 |
86
+ | No log | 6.0 | 24 | 0.5713 | 0.7333 | 0.5378 | 0.7333 | 0.6205 |
87
+ | No log | 7.0 | 28 | 0.5488 | 0.7375 | 0.8067 | 0.7375 | 0.6302 |
88
+ | 0.5813 | 8.0 | 32 | 0.5408 | 0.7417 | 0.8090 | 0.7417 | 0.6397 |
89
+ | 0.5813 | 9.0 | 36 | 0.5387 | 0.7542 | 0.7292 | 0.7542 | 0.7015 |
90
+ | 0.5813 | 10.0 | 40 | 0.5314 | 0.75 | 0.7212 | 0.75 | 0.6943 |
91
+ | 0.5813 | 11.0 | 44 | 0.5283 | 0.7792 | 0.7813 | 0.7792 | 0.7318 |
92
+ | 0.5813 | 12.0 | 48 | 0.5227 | 0.7667 | 0.7819 | 0.7667 | 0.7019 |
93
+ | 0.5813 | 13.0 | 52 | 0.5283 | 0.7583 | 0.7336 | 0.7583 | 0.7308 |
94
+ | 0.5813 | 14.0 | 56 | 0.5263 | 0.7583 | 0.7393 | 0.7583 | 0.7045 |
95
+ | 0.5092 | 15.0 | 60 | 0.5205 | 0.7667 | 0.7819 | 0.7667 | 0.7019 |
96
+ | 0.5092 | 16.0 | 64 | 0.5236 | 0.7625 | 0.8206 | 0.7625 | 0.6837 |
97
+ | 0.5092 | 17.0 | 68 | 0.5241 | 0.7667 | 0.8230 | 0.7667 | 0.6919 |
98
+ | 0.5092 | 18.0 | 72 | 0.4962 | 0.7708 | 0.7639 | 0.7708 | 0.7217 |
99
+ | 0.5092 | 19.0 | 76 | 0.4942 | 0.7708 | 0.7878 | 0.7708 | 0.7094 |
100
+ | 0.5092 | 20.0 | 80 | 0.4909 | 0.7667 | 0.7503 | 0.7667 | 0.7221 |
101
+ | 0.5092 | 21.0 | 84 | 0.4964 | 0.7583 | 0.7343 | 0.7583 | 0.7334 |
102
+ | 0.5092 | 22.0 | 88 | 0.4928 | 0.7583 | 0.7393 | 0.7583 | 0.7045 |
103
+ | 0.4804 | 23.0 | 92 | 0.4938 | 0.7542 | 0.7292 | 0.7542 | 0.7015 |
104
+ | 0.4804 | 24.0 | 96 | 0.4949 | 0.7583 | 0.7327 | 0.7583 | 0.7253 |
105
+ | 0.4804 | 25.0 | 100 | 0.4946 | 0.7542 | 0.7268 | 0.7542 | 0.7220 |
106
+ | 0.4804 | 26.0 | 104 | 0.4935 | 0.7583 | 0.7330 | 0.7583 | 0.7281 |
107
+ | 0.4804 | 27.0 | 108 | 0.4927 | 0.7542 | 0.7268 | 0.7542 | 0.7220 |
108
+ | 0.4804 | 28.0 | 112 | 0.4943 | 0.7542 | 0.7268 | 0.7542 | 0.7220 |
109
+ | 0.4804 | 29.0 | 116 | 0.4951 | 0.7542 | 0.7268 | 0.7542 | 0.7220 |
110
+ | 0.4442 | 30.0 | 120 | 0.4952 | 0.75 | 0.7203 | 0.75 | 0.7158 |
111
 
112
 
113
  ### Framework versions
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e37006c9799ff311b5050642a9abc91de8a1a1fa2223b7ce030fe4b72128c3ff
3
  size 343268717
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c24f92e4b25ab9a442b57711851f1da0d189b34fe3f49c7e8ee71a0c148960c9
3
  size 343268717