Hugging Face's logo

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

Image Classification
Transformers
PyTorch
TensorBoard
vit
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
3
aalonso-developer commited on
Commit
94bfe18
·
1 Parent(s): 046176d

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +33 -27
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: 0.9966
21
- - Accuracy: 0.7101
22
 
23
  ## Model description
24
 
@@ -37,40 +36,47 @@ More information needed
37
  ### Training hyperparameters
38
 
39
  The following hyperparameters were used during training:
40
- - learning_rate: 0.0002
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: 3
47
  - mixed_precision_training: Native AMP
48
 
49
  ### Training results
50
 
51
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
52
  |:-------------:|:-----:|:-----:|:---------------:|:--------:|
53
- | 1.5419 | 0.14 | 1000 | 1.3017 | 0.6224 |
54
- | 1.2619 | 0.28 | 2000 | 1.2609 | 0.6317 |
55
- | 1.2244 | 0.41 | 3000 | 1.2237 | 0.6371 |
56
- | 1.1924 | 0.55 | 4000 | 1.2325 | 0.6339 |
57
- | 1.1572 | 0.69 | 5000 | 1.1637 | 0.6550 |
58
- | 1.1382 | 0.83 | 6000 | 1.1444 | 0.6618 |
59
- | 1.1403 | 0.97 | 7000 | 1.1294 | 0.6624 |
60
- | 1.0204 | 1.11 | 8000 | 1.1082 | 0.6721 |
61
- | 0.9853 | 1.24 | 9000 | 1.1094 | 0.6693 |
62
- | 0.9767 | 1.38 | 10000 | 1.0899 | 0.6742 |
63
- | 0.9815 | 1.52 | 11000 | 1.0532 | 0.6872 |
64
- | 0.9672 | 1.66 | 12000 | 1.0569 | 0.6864 |
65
- | 0.9439 | 1.8 | 13000 | 1.0358 | 0.6934 |
66
- | 0.9228 | 1.94 | 14000 | 1.0430 | 0.6884 |
67
- | 0.8511 | 2.07 | 15000 | 1.0438 | 0.6958 |
68
- | 0.7619 | 2.21 | 16000 | 1.0432 | 0.6980 |
69
- | 0.7672 | 2.35 | 17000 | 1.0283 | 0.7023 |
70
- | 0.7378 | 2.49 | 18000 | 1.0175 | 0.7030 |
71
- | 0.7217 | 2.63 | 19000 | 1.0188 | 0.7042 |
72
- | 0.7285 | 2.77 | 20000 | 0.9978 | 0.7104 |
73
- | 0.7206 | 2.9 | 21000 | 0.9966 | 0.7101 |
 
 
 
 
 
 
 
74
 
75
 
76
  ### 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: 1.0260
20
+ - Accuracy: 0.7112
21
 
22
  ## Model description
23
 
 
36
  ### Training hyperparameters
37
 
38
  The following hyperparameters were used during training:
39
+ - learning_rate: 5e-05
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: 4
46
  - mixed_precision_training: Native AMP
47
 
48
  ### Training results
49
 
50
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
51
  |:-------------:|:-----:|:-----:|:---------------:|:--------:|
52
+ | 1.7384 | 0.14 | 1000 | 1.3281 | 0.6473 |
53
+ | 1.2367 | 0.28 | 2000 | 1.1815 | 0.6703 |
54
+ | 1.1348 | 0.41 | 3000 | 1.1290 | 0.6794 |
55
+ | 1.1003 | 0.55 | 4000 | 1.0927 | 0.6883 |
56
+ | 1.0695 | 0.69 | 5000 | 1.0641 | 0.6911 |
57
+ | 1.0426 | 0.83 | 6000 | 1.0410 | 0.6958 |
58
+ | 1.0247 | 0.97 | 7000 | 1.0402 | 0.6937 |
59
+ | 0.9406 | 1.11 | 8000 | 1.0244 | 0.7004 |
60
+ | 0.8824 | 1.24 | 9000 | 1.0365 | 0.6993 |
61
+ | 0.8979 | 1.38 | 10000 | 1.0051 | 0.7067 |
62
+ | 0.8947 | 1.52 | 11000 | 0.9986 | 0.7089 |
63
+ | 0.8785 | 1.66 | 12000 | 0.9866 | 0.7118 |
64
+ | 0.8881 | 1.8 | 13000 | 0.9892 | 0.7112 |
65
+ | 0.8652 | 1.94 | 14000 | 0.9875 | 0.7112 |
66
+ | 0.7969 | 2.07 | 15000 | 1.0030 | 0.7083 |
67
+ | 0.7153 | 2.21 | 16000 | 1.0069 | 0.7085 |
68
+ | 0.7158 | 2.35 | 17000 | 1.0076 | 0.7080 |
69
+ | 0.7248 | 2.49 | 18000 | 1.0020 | 0.7108 |
70
+ | 0.7204 | 2.63 | 19000 | 0.9929 | 0.7131 |
71
+ | 0.7127 | 2.77 | 20000 | 0.9929 | 0.7139 |
72
+ | 0.7274 | 2.9 | 21000 | 0.9929 | 0.7105 |
73
+ | 0.6769 | 3.04 | 22000 | 1.0152 | 0.7118 |
74
+ | 0.5859 | 3.18 | 23000 | 1.0314 | 0.7089 |
75
+ | 0.5811 | 3.32 | 24000 | 1.0340 | 0.7106 |
76
+ | 0.5863 | 3.46 | 25000 | 1.0253 | 0.7105 |
77
+ | 0.5656 | 3.6 | 26000 | 1.0279 | 0.7104 |
78
+ | 0.5753 | 3.73 | 27000 | 1.0284 | 0.7108 |
79
+ | 0.5681 | 3.87 | 28000 | 1.0260 | 0.7112 |
80
 
81
 
82
  ### Framework versions