Hugging Face's logo

Professor
/
CGIAR

Image Classification
Transformers
Safetensors
swin
Generated from Trainer
Model card Files
xet
Community
Professor commited on
Commit
6cc6679
·
1 Parent(s): f8936cb

End of training

Browse files
Files changed (1) hide show
  1. README.md +35 -45
README.md CHANGED
@@ -17,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  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 None dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 0.6887
21
- - Accuracy: 0.7211
22
 
23
  ## Model description
24
 
@@ -37,64 +37,54 @@ More information needed
37
  ### Training hyperparameters
38
 
39
  The following hyperparameters were used during training:
40
- - learning_rate: 0.0001
41
  - train_batch_size: 32
42
  - eval_batch_size: 8
43
  - seed: 42
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: linear
46
  - lr_scheduler_warmup_steps: 50
47
- - num_epochs: 40
48
 
49
  ### Training results
50
 
51
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
52
  |:-------------:|:-----:|:-----:|:---------------:|:--------:|
53
- | 0.8524 | 1.0 | 652 | 0.7425 | 0.6910 |
54
- | 0.7133 | 2.0 | 1304 | 0.7050 | 0.7106 |
55
- | 0.6627 | 3.0 | 1956 | 0.6887 | 0.7211 |
56
- | 0.5699 | 4.0 | 2608 | 0.6967 | 0.7244 |
57
- | 0.4901 | 5.0 | 3260 | 0.6904 | 0.7292 |
58
- | 0.4374 | 6.0 | 3912 | 0.7500 | 0.7255 |
59
- | 0.3277 | 7.0 | 4564 | 0.8507 | 0.7083 |
60
- | 0.2602 | 8.0 | 5216 | 0.8675 | 0.7259 |
61
- | 0.2324 | 9.0 | 5868 | 0.9844 | 0.7315 |
62
- | 0.1703 | 10.0 | 6520 | 1.0635 | 0.7112 |
63
- | 0.1349 | 11.0 | 7172 | 1.0992 | 0.7229 |
64
- | 0.1203 | 12.0 | 7824 | 1.2086 | 0.7215 |
65
- | 0.1148 | 13.0 | 8476 | 1.2128 | 0.7250 |
66
- | 0.087 | 14.0 | 9128 | 1.2238 | 0.7300 |
67
- | 0.0842 | 15.0 | 9780 | 1.2935 | 0.7294 |
68
- | 0.0765 | 16.0 | 10432 | 1.3468 | 0.7282 |
69
- | 0.0609 | 17.0 | 11084 | 1.3041 | 0.7271 |
70
- | 0.0543 | 18.0 | 11736 | 1.4513 | 0.7259 |
71
- | 0.0507 | 19.0 | 12388 | 1.4640 | 0.7382 |
72
- | 0.0457 | 20.0 | 13040 | 1.5730 | 0.7298 |
73
- | 0.0376 | 21.0 | 13692 | 1.5676 | 0.7315 |
74
- | 0.0434 | 22.0 | 14344 | 1.6493 | 0.7315 |
75
- | 0.0324 | 23.0 | 14996 | 1.6090 | 0.7294 |
76
- | 0.0318 | 24.0 | 15648 | 1.7164 | 0.7348 |
77
- | 0.0256 | 25.0 | 16300 | 1.6981 | 0.7413 |
78
- | 0.0252 | 26.0 | 16952 | 1.6465 | 0.7317 |
79
- | 0.0189 | 27.0 | 17604 | 1.7949 | 0.7265 |
80
- | 0.0211 | 28.0 | 18256 | 1.7796 | 0.7284 |
81
- | 0.0184 | 29.0 | 18908 | 1.8446 | 0.7319 |
82
- | 0.0128 | 30.0 | 19560 | 1.8685 | 0.7300 |
83
- | 0.0098 | 31.0 | 20212 | 1.9648 | 0.7278 |
84
- | 0.008 | 32.0 | 20864 | 1.9593 | 0.7303 |
85
- | 0.006 | 33.0 | 21516 | 1.9797 | 0.7325 |
86
- | 0.0064 | 34.0 | 22168 | 1.9700 | 0.7401 |
87
- | 0.0077 | 35.0 | 22820 | 2.0103 | 0.7307 |
88
- | 0.0036 | 36.0 | 23472 | 2.0696 | 0.7334 |
89
- | 0.0019 | 37.0 | 24124 | 2.0095 | 0.7374 |
90
- | 0.0024 | 38.0 | 24776 | 2.0186 | 0.7394 |
91
- | 0.001 | 39.0 | 25428 | 2.0157 | 0.7432 |
92
- | 0.0013 | 40.0 | 26080 | 2.0033 | 0.7438 |
93
 
94
 
95
  ### Framework versions
96
 
97
- - Transformers 4.36.1
98
  - Pytorch 2.0.0
99
  - Datasets 2.15.0
100
  - Tokenizers 0.15.0
 
17
 
18
  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 None dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 0.8587
21
+ - Accuracy: 0.6214
22
 
23
  ## Model description
24
 
 
37
  ### Training hyperparameters
38
 
39
  The following hyperparameters were used during training:
40
+ - learning_rate: 0.001
41
  - train_batch_size: 32
42
  - eval_batch_size: 8
43
  - seed: 42
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: linear
46
  - lr_scheduler_warmup_steps: 50
47
+ - num_epochs: 30
48
 
49
  ### Training results
50
 
51
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
52
  |:-------------:|:-----:|:-----:|:---------------:|:--------:|
53
+ | 1.1422 | 1.0 | 652 | 1.1329 | 0.4645 |
54
+ | 1.1314 | 2.0 | 1304 | 1.0424 | 0.5230 |
55
+ | 1.115 | 3.0 | 1956 | 1.0801 | 0.4988 |
56
+ | 1.0937 | 4.0 | 2608 | 1.0455 | 0.5069 |
57
+ | 1.0764 | 5.0 | 3260 | 1.0277 | 0.5184 |
58
+ | 1.0728 | 6.0 | 3912 | 1.0600 | 0.5236 |
59
+ | 1.0629 | 7.0 | 4564 | 0.9992 | 0.5495 |
60
+ | 1.0513 | 8.0 | 5216 | 1.0137 | 0.5483 |
61
+ | 1.0415 | 9.0 | 5868 | 0.9810 | 0.5679 |
62
+ | 1.023 | 10.0 | 6520 | 0.9669 | 0.5552 |
63
+ | 1.0161 | 11.0 | 7172 | 0.9502 | 0.5717 |
64
+ | 1.0137 | 12.0 | 7824 | 0.9645 | 0.5683 |
65
+ | 1.0051 | 13.0 | 8476 | 0.9538 | 0.5508 |
66
+ | 1.0049 | 14.0 | 9128 | 0.9380 | 0.5794 |
67
+ | 0.9919 | 15.0 | 9780 | 0.9338 | 0.5865 |
68
+ | 0.9908 | 16.0 | 10432 | 0.9196 | 0.5857 |
69
+ | 0.9805 | 17.0 | 11084 | 0.9443 | 0.5585 |
70
+ | 0.9738 | 18.0 | 11736 | 0.9224 | 0.5842 |
71
+ | 0.9566 | 19.0 | 12388 | 0.9142 | 0.5867 |
72
+ | 0.9511 | 20.0 | 13040 | 0.9038 | 0.6087 |
73
+ | 0.9494 | 21.0 | 13692 | 0.9079 | 0.5919 |
74
+ | 0.9462 | 22.0 | 14344 | 0.8822 | 0.6133 |
75
+ | 0.9321 | 23.0 | 14996 | 0.8908 | 0.6009 |
76
+ | 0.9375 | 24.0 | 15648 | 0.8813 | 0.6045 |
77
+ | 0.9315 | 25.0 | 16300 | 0.8792 | 0.6093 |
78
+ | 0.9195 | 26.0 | 16952 | 0.8740 | 0.6128 |
79
+ | 0.9085 | 27.0 | 17604 | 0.8734 | 0.6110 |
80
+ | 0.9086 | 28.0 | 18256 | 0.8639 | 0.6170 |
81
+ | 0.9111 | 29.0 | 18908 | 0.8606 | 0.6208 |
82
+ | 0.9061 | 30.0 | 19560 | 0.8587 | 0.6214 |
 
 
 
 
 
 
 
 
 
 
83
 
84
 
85
  ### Framework versions
86
 
87
+ - Transformers 4.36.2
88
  - Pytorch 2.0.0
89
  - Datasets 2.15.0
90
  - Tokenizers 0.15.0