Hugging Face's logo

dyaminda
/
image_classification

Image Classification
Transformers
PyTorch
vit
Generated from Trainer
Eval Results (legacy)
Model card Files
xet
Community
1
dyaminda commited on
Commit
ab66e1a
·
1 Parent(s): fd770df

End of training

Browse files
Files changed (2) hide show
  1. README.md +34 -24
  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: 0.5125
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: 1.3634
36
- - Accuracy: 0.5125
37
 
38
  ## Model description
39
 
@@ -61,32 +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: 20
65
 
66
  ### Training results
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
- | 2.0947 | 1.0 | 10 | 2.0806 | 0.1375 |
71
- | 2.0549 | 2.0 | 20 | 2.0395 | 0.175 |
72
- | 1.9588 | 3.0 | 30 | 1.9427 | 0.2812 |
73
- | 1.8014 | 4.0 | 40 | 1.7817 | 0.3438 |
74
- | 1.6343 | 5.0 | 50 | 1.6330 | 0.4313 |
75
- | 1.5099 | 6.0 | 60 | 1.5820 | 0.4125 |
76
- | 1.4078 | 7.0 | 70 | 1.4982 | 0.4625 |
77
- | 1.3281 | 8.0 | 80 | 1.4624 | 0.4813 |
78
- | 1.253 | 9.0 | 90 | 1.4064 | 0.4813 |
79
- | 1.1858 | 10.0 | 100 | 1.4197 | 0.4938 |
80
- | 1.1196 | 11.0 | 110 | 1.3527 | 0.55 |
81
- | 1.0653 | 12.0 | 120 | 1.3507 | 0.4688 |
82
- | 1.0107 | 13.0 | 130 | 1.3738 | 0.5125 |
83
- | 0.988 | 14.0 | 140 | 1.3758 | 0.4938 |
84
- | 0.9433 | 15.0 | 150 | 1.3541 | 0.4813 |
85
- | 0.9243 | 16.0 | 160 | 1.3265 | 0.5125 |
86
- | 0.8914 | 17.0 | 170 | 1.3634 | 0.4938 |
87
- | 0.8715 | 18.0 | 180 | 1.3683 | 0.4875 |
88
- | 0.8679 | 19.0 | 190 | 1.3197 | 0.55 |
89
- | 0.8479 | 20.0 | 200 | 1.3085 | 0.5188 |
 
 
 
 
 
 
 
 
 
 
90
 
91
 
92
  ### Framework versions
 
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
+ value: 0.5375
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: 1.3106
36
+ - Accuracy: 0.5375
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
+ | 1.367 | 1.0 | 10 | 1.5172 | 0.4437 |
71
+ | 1.3337 | 2.0 | 20 | 1.5171 | 0.3875 |
72
+ | 1.2582 | 3.0 | 30 | 1.4672 | 0.4813 |
73
+ | 1.1813 | 4.0 | 40 | 1.3955 | 0.5 |
74
+ | 1.1025 | 5.0 | 50 | 1.3617 | 0.5125 |
75
+ | 1.0447 | 6.0 | 60 | 1.3491 | 0.5125 |
76
+ | 0.9362 | 7.0 | 70 | 1.3079 | 0.5437 |
77
+ | 0.8991 | 8.0 | 80 | 1.3291 | 0.4938 |
78
+ | 0.8562 | 9.0 | 90 | 1.3445 | 0.4625 |
79
+ | 0.7978 | 10.0 | 100 | 1.3168 | 0.5 |
80
+ | 0.7183 | 11.0 | 110 | 1.2865 | 0.4875 |
81
+ | 0.6941 | 12.0 | 120 | 1.2461 | 0.55 |
82
+ | 0.6455 | 13.0 | 130 | 1.2330 | 0.6062 |
83
+ | 0.6164 | 14.0 | 140 | 1.3818 | 0.4813 |
84
+ | 0.5807 | 15.0 | 150 | 1.3250 | 0.5062 |
85
+ | 0.5643 | 16.0 | 160 | 1.3206 | 0.5188 |
86
+ | 0.5061 | 17.0 | 170 | 1.2957 | 0.5125 |
87
+ | 0.478 | 18.0 | 180 | 1.3782 | 0.4625 |
88
+ | 0.4615 | 19.0 | 190 | 1.2772 | 0.5563 |
89
+ | 0.4514 | 20.0 | 200 | 1.2278 | 0.5375 |
90
+ | 0.4196 | 21.0 | 210 | 1.2861 | 0.5188 |
91
+ | 0.4589 | 22.0 | 220 | 1.2778 | 0.5375 |
92
+ | 0.4303 | 23.0 | 230 | 1.2534 | 0.5687 |
93
+ | 0.4023 | 24.0 | 240 | 1.3352 | 0.5312 |
94
+ | 0.3967 | 25.0 | 250 | 1.3381 | 0.5375 |
95
+ | 0.3725 | 26.0 | 260 | 1.2320 | 0.5625 |
96
+ | 0.3757 | 27.0 | 270 | 1.2201 | 0.5625 |
97
+ | 0.3913 | 28.0 | 280 | 1.2204 | 0.5563 |
98
+ | 0.3982 | 29.0 | 290 | 1.2564 | 0.5437 |
99
+ | 0.3765 | 30.0 | 300 | 1.3752 | 0.5 |
100
 
101
 
102
  ### Framework versions
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bd8101d932086a9bc907f13391f9ff133a1f1ad40892e4e843b6661606d1ccc0
3
  size 343287149
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e34474f8dd1a3e970d28d94ac765d2d39581f7cb7d41ac61e457caa38b787710
3
  size 343287149