dyaminda commited on
Commit
4d3881c
1 Parent(s): 65d17d6

End of training

Browse files
Files changed (2) hide show
  1. README.md +24 -7
  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: 0.38125
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: 1.8731
36
- - Accuracy: 0.3812
37
 
38
  ## Model description
39
 
@@ -61,15 +61,32 @@ 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: 3
65
 
66
  ### Training results
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
- | 2.0558 | 1.0 | 10 | 2.0062 | 0.2875 |
71
- | 1.9499 | 2.0 | 20 | 1.9315 | 0.3 |
72
- | 1.8675 | 3.0 | 30 | 1.8830 | 0.3625 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
73
 
74
 
75
  ### Framework versions
 
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
+ value: 0.61875
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: 1.2094
36
+ - Accuracy: 0.6188
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: 20
65
 
66
  ### Training results
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
+ | 1.8174 | 1.0 | 10 | 1.8349 | 0.4062 |
71
+ | 1.7364 | 2.0 | 20 | 1.6966 | 0.4 |
72
+ | 1.6087 | 3.0 | 30 | 1.5892 | 0.45 |
73
+ | 1.4904 | 4.0 | 40 | 1.4914 | 0.4875 |
74
+ | 1.4009 | 5.0 | 50 | 1.4288 | 0.5125 |
75
+ | 1.3129 | 6.0 | 60 | 1.3619 | 0.575 |
76
+ | 1.2233 | 7.0 | 70 | 1.3622 | 0.5687 |
77
+ | 1.1419 | 8.0 | 80 | 1.3047 | 0.5188 |
78
+ | 1.094 | 9.0 | 90 | 1.2763 | 0.6062 |
79
+ | 1.0366 | 10.0 | 100 | 1.2496 | 0.5625 |
80
+ | 0.9785 | 11.0 | 110 | 1.2368 | 0.6 |
81
+ | 0.9435 | 12.0 | 120 | 1.1960 | 0.6438 |
82
+ | 0.9031 | 13.0 | 130 | 1.2083 | 0.5563 |
83
+ | 0.8829 | 14.0 | 140 | 1.2629 | 0.5188 |
84
+ | 0.824 | 15.0 | 150 | 1.2061 | 0.5938 |
85
+ | 0.7952 | 16.0 | 160 | 1.2630 | 0.55 |
86
+ | 0.7744 | 17.0 | 170 | 1.2329 | 0.5625 |
87
+ | 0.7487 | 18.0 | 180 | 1.2259 | 0.5437 |
88
+ | 0.7381 | 19.0 | 190 | 1.1750 | 0.5813 |
89
+ | 0.7261 | 20.0 | 200 | 1.1802 | 0.575 |
90
 
91
 
92
  ### Framework versions
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:af2d98752e8fed72eade6ed213ed199cdf6be1631ecf1f4938116d68c9a4484c
3
  size 343287149
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b87c3497948c97cd025b052ce2189842d0fc68cbcdda627aa1e55030908dc3fc
3
  size 343287149