Hugging Face's logo

vintage-lavender619
/
vit-large-patch16-224-finetuned-landscape-test

Image Classification
Transformers
TensorBoard
Safetensors
vit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
vintage-lavender619 commited on
Commit
0345df0
·
verified ·
1 Parent(s): 3484b3a

Model save

Browse files
Files changed (2) hide show
  1. README.md +36 -11
  2. model.safetensors +1 -1
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
- value: 0.9564068692206077
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-large-patch16-224](https://huggingface.co/google/vit-large-patch16-224) on the imagefolder dataset.
34
  It achieves the following results on the evaluation set:
35
- - Loss: 0.1456
36
- - Accuracy: 0.9564
37
 
38
  ## Model description
39
 
@@ -61,17 +61,42 @@ The following hyperparameters were used during training:
61
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
62
  - lr_scheduler_type: linear
63
  - lr_scheduler_warmup_ratio: 0.1
64
- - num_epochs: 5
65
 
66
  ### Training results
67
 
68
- | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
- |:-------------:|:------:|:----:|:---------------:|:--------:|
70
- | 0.3395 | 0.9684 | 23 | 0.1844 | 0.9379 |
71
- | 0.2125 | 1.9789 | 47 | 0.1652 | 0.9366 |
72
- | 0.1725 | 2.9895 | 71 | 0.1384 | 0.9498 |
73
- | 0.1371 | 4.0 | 95 | 0.1456 | 0.9564 |
74
- | 0.096 | 4.8421 | 115 | 0.1405 | 0.9524 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
75
 
76
 
77
  ### Framework versions
 
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
+ value: 0.896875
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-large-patch16-224](https://huggingface.co/google/vit-large-patch16-224) on the imagefolder dataset.
34
  It achieves the following results on the evaluation set:
35
+ - Loss: 0.3321
36
+ - Accuracy: 0.8969
37
 
38
  ## Model description
39
 
 
61
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
62
  - lr_scheduler_type: linear
63
  - lr_scheduler_warmup_ratio: 0.1
64
+ - num_epochs: 30
65
 
66
  ### Training results
67
 
68
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
+ | 1.3906 | 1.0 | 10 | 1.1521 | 0.4969 |
71
+ | 0.914 | 2.0 | 20 | 0.7812 | 0.6687 |
72
+ | 0.6704 | 3.0 | 30 | 0.5566 | 0.7688 |
73
+ | 0.4609 | 4.0 | 40 | 0.4363 | 0.8313 |
74
+ | 0.404 | 5.0 | 50 | 0.4807 | 0.8156 |
75
+ | 0.3948 | 6.0 | 60 | 0.4216 | 0.8531 |
76
+ | 0.3535 | 7.0 | 70 | 0.3281 | 0.8688 |
77
+ | 0.3107 | 8.0 | 80 | 0.2972 | 0.9 |
78
+ | 0.3086 | 9.0 | 90 | 0.3328 | 0.8812 |
79
+ | 0.2564 | 10.0 | 100 | 0.3517 | 0.8875 |
80
+ | 0.2654 | 11.0 | 110 | 0.3985 | 0.8594 |
81
+ | 0.2733 | 12.0 | 120 | 0.2870 | 0.9062 |
82
+ | 0.2511 | 13.0 | 130 | 0.4177 | 0.8875 |
83
+ | 0.2762 | 14.0 | 140 | 0.3579 | 0.8938 |
84
+ | 0.2188 | 15.0 | 150 | 0.3348 | 0.8906 |
85
+ | 0.2265 | 16.0 | 160 | 0.3046 | 0.9031 |
86
+ | 0.2054 | 17.0 | 170 | 0.3305 | 0.8969 |
87
+ | 0.1951 | 18.0 | 180 | 0.3576 | 0.8812 |
88
+ | 0.1762 | 19.0 | 190 | 0.3985 | 0.8812 |
89
+ | 0.2264 | 20.0 | 200 | 0.3711 | 0.9031 |
90
+ | 0.1958 | 21.0 | 210 | 0.3259 | 0.8875 |
91
+ | 0.1765 | 22.0 | 220 | 0.3804 | 0.8938 |
92
+ | 0.1859 | 23.0 | 230 | 0.3464 | 0.9 |
93
+ | 0.1915 | 24.0 | 240 | 0.3742 | 0.8906 |
94
+ | 0.1667 | 25.0 | 250 | 0.3200 | 0.9062 |
95
+ | 0.1744 | 26.0 | 260 | 0.3545 | 0.8938 |
96
+ | 0.1595 | 27.0 | 270 | 0.3101 | 0.9094 |
97
+ | 0.1793 | 28.0 | 280 | 0.3230 | 0.8969 |
98
+ | 0.1596 | 29.0 | 290 | 0.3268 | 0.9 |
99
+ | 0.169 | 30.0 | 300 | 0.3321 | 0.8969 |
100
 
101
 
102
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4486764aa0e823223738addb7dde07b0826f2ab7e3c252a8455351526b6dab63
3
  size 1213269472
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8c9a8c93f1acdbd426e4d26ff60356a6476103b6b3273b3db7e3d6367c1eae4
3
  size 1213269472