Hugging Face's logo

aalonso-developer
/
vit-base-clothing-leafs-example-full-simple

Image Classification
Transformers
PyTorch
TensorBoard
vit
Generated from Trainer
Model card Files
xet
Metrics Community
3
aalonso-developer commited on
Commit
3d163cb
·
1 Parent(s): 54192d1

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +26 -56
README.md CHANGED
@@ -1,7 +1,6 @@
1
  ---
2
  license: apache-2.0
3
  tags:
4
- - image-classification
5
  - generated_from_trainer
6
  metrics:
7
  - accuracy
@@ -15,10 +14,10 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  # vit-base-clothing-leafs-example-full-simple
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 beans dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 0.9854
21
- - Accuracy: 0.7117
22
 
23
  ## Model description
24
 
@@ -37,69 +36,40 @@ More information needed
37
  ### Training hyperparameters
38
 
39
  The following hyperparameters were used during training:
40
- - learning_rate: 5e-05
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
- - num_epochs: 7
47
  - mixed_precision_training: Native AMP
48
 
49
  ### Training results
50
 
51
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
52
  |:-------------:|:-----:|:-----:|:---------------:|:--------:|
53
- | 1.7292 | 0.14 | 1000 | 1.3213 | 0.6539 |
54
- | 1.2308 | 0.28 | 2000 | 1.1988 | 0.6633 |
55
- | 1.1582 | 0.41 | 3000 | 1.1183 | 0.6819 |
56
- | 1.109 | 0.55 | 4000 | 1.0872 | 0.6854 |
57
- | 1.0772 | 0.69 | 5000 | 1.0495 | 0.6994 |
58
- | 1.0371 | 0.83 | 6000 | 1.0551 | 0.6932 |
59
- | 1.0287 | 0.97 | 7000 | 1.0264 | 0.7008 |
60
- | 0.9387 | 1.11 | 8000 | 1.0256 | 0.7022 |
61
- | 0.9005 | 1.24 | 9000 | 1.0225 | 0.7013 |
62
- | 0.8957 | 1.38 | 10000 | 1.0280 | 0.6994 |
63
- | 0.8924 | 1.52 | 11000 | 1.0162 | 0.7037 |
64
- | 0.8934 | 1.66 | 12000 | 1.0030 | 0.7085 |
65
- | 0.8959 | 1.8 | 13000 | 1.0171 | 0.7021 |
66
- | 0.8927 | 1.94 | 14000 | 0.9854 | 0.7117 |
67
- | 0.8107 | 2.07 | 15000 | 1.0298 | 0.7019 |
68
- | 0.7442 | 2.21 | 16000 | 1.0103 | 0.7075 |
69
- | 0.7421 | 2.35 | 17000 | 1.0142 | 0.7086 |
70
- | 0.7311 | 2.49 | 18000 | 1.0143 | 0.7111 |
71
- | 0.7362 | 2.63 | 19000 | 1.0113 | 0.7099 |
72
- | 0.7392 | 2.77 | 20000 | 1.0305 | 0.7046 |
73
- | 0.7515 | 2.9 | 21000 | 1.0069 | 0.7069 |
74
- | 0.6945 | 3.04 | 22000 | 1.0315 | 0.7096 |
75
- | 0.5912 | 3.18 | 23000 | 1.0635 | 0.7005 |
76
- | 0.58 | 3.32 | 24000 | 1.0592 | 0.7050 |
77
- | 0.576 | 3.46 | 25000 | 1.0624 | 0.7019 |
78
- | 0.5882 | 3.6 | 26000 | 1.0583 | 0.7059 |
79
- | 0.5867 | 3.73 | 27000 | 1.0526 | 0.7077 |
80
- | 0.593 | 3.87 | 28000 | 1.0647 | 0.7048 |
81
- | 0.5745 | 4.01 | 29000 | 1.0814 | 0.7045 |
82
- | 0.4332 | 4.15 | 30000 | 1.1231 | 0.7036 |
83
- | 0.4427 | 4.29 | 31000 | 1.1330 | 0.6982 |
84
- | 0.4475 | 4.43 | 32000 | 1.1269 | 0.7000 |
85
- | 0.4488 | 4.56 | 33000 | 1.1300 | 0.7025 |
86
- | 0.4431 | 4.7 | 34000 | 1.1305 | 0.7019 |
87
- | 0.4514 | 4.84 | 35000 | 1.1445 | 0.6991 |
88
- | 0.4427 | 4.98 | 36000 | 1.1225 | 0.7028 |
89
- | 0.3391 | 5.12 | 37000 | 1.1919 | 0.6964 |
90
- | 0.3222 | 5.26 | 38000 | 1.2108 | 0.6971 |
91
- | 0.315 | 5.39 | 39000 | 1.2175 | 0.6986 |
92
- | 0.3307 | 5.53 | 40000 | 1.2197 | 0.6944 |
93
- | 0.3187 | 5.67 | 41000 | 1.2281 | 0.6988 |
94
- | 0.3327 | 5.81 | 42000 | 1.2379 | 0.6967 |
95
- | 0.3213 | 5.95 | 43000 | 1.2367 | 0.6972 |
96
- | 0.2688 | 6.08 | 44000 | 1.2731 | 0.6941 |
97
- | 0.2395 | 6.22 | 45000 | 1.2904 | 0.6966 |
98
- | 0.2407 | 6.36 | 46000 | 1.2934 | 0.6951 |
99
- | 0.2312 | 6.5 | 47000 | 1.2976 | 0.6955 |
100
- | 0.2369 | 6.64 | 48000 | 1.3018 | 0.6935 |
101
- | 0.2317 | 6.78 | 49000 | 1.3031 | 0.6949 |
102
- | 0.2395 | 6.91 | 50000 | 1.3017 | 0.6958 |
103
 
104
 
105
  ### Framework versions
 
1
  ---
2
  license: apache-2.0
3
  tags:
 
4
  - generated_from_trainer
5
  metrics:
6
  - accuracy
 
14
 
15
  # vit-base-clothing-leafs-example-full-simple
16
 
17
+ 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.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 0.9866
20
+ - Accuracy: 0.7164
21
 
22
  ## Model description
23
 
 
36
  ### Training hyperparameters
37
 
38
  The following hyperparameters were used during training:
39
+ - learning_rate: 0.0001
40
  - train_batch_size: 32
41
  - eval_batch_size: 8
42
  - seed: 42
43
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
  - lr_scheduler_type: linear
45
+ - num_epochs: 3
46
  - mixed_precision_training: Native AMP
47
 
48
  ### Training results
49
 
50
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
51
  |:-------------:|:-----:|:-----:|:---------------:|:--------:|
52
+ | 1.558 | 0.14 | 1000 | 1.2684 | 0.6426 |
53
+ | 1.2184 | 0.28 | 2000 | 1.1551 | 0.6659 |
54
+ | 1.1427 | 0.41 | 3000 | 1.1251 | 0.6678 |
55
+ | 1.1118 | 0.55 | 4000 | 1.1116 | 0.6728 |
56
+ | 1.0768 | 0.69 | 5000 | 1.0770 | 0.6809 |
57
+ | 1.0601 | 0.83 | 6000 | 1.0540 | 0.6890 |
58
+ | 1.0326 | 0.97 | 7000 | 1.0409 | 0.6929 |
59
+ | 0.9398 | 1.11 | 8000 | 1.0343 | 0.6951 |
60
+ | 0.8986 | 1.24 | 9000 | 1.0353 | 0.6951 |
61
+ | 0.8883 | 1.38 | 10000 | 1.0139 | 0.7006 |
62
+ | 0.8731 | 1.52 | 11000 | 0.9994 | 0.7064 |
63
+ | 0.8752 | 1.66 | 12000 | 1.0048 | 0.7020 |
64
+ | 0.8579 | 1.8 | 13000 | 0.9912 | 0.7091 |
65
+ | 0.864 | 1.94 | 14000 | 0.9869 | 0.7096 |
66
+ | 0.7798 | 2.07 | 15000 | 1.0022 | 0.7094 |
67
+ | 0.6883 | 2.21 | 16000 | 1.0081 | 0.7089 |
68
+ | 0.67 | 2.35 | 17000 | 1.0066 | 0.7111 |
69
+ | 0.678 | 2.49 | 18000 | 0.9969 | 0.7132 |
70
+ | 0.6701 | 2.63 | 19000 | 0.9977 | 0.7133 |
71
+ | 0.6652 | 2.77 | 20000 | 0.9938 | 0.7144 |
72
+ | 0.6588 | 2.9 | 21000 | 0.9866 | 0.7164 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
73
 
74
 
75
  ### Framework versions