Hugging Face's logo

sai17
/
cards_bottom_left_swin-tiny-patch4-window7-224-finetuned-v2_more_Data

Image Classification
Transformers
TensorBoard
Safetensors
swin
generated_from_trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
sai17 commited on
Commit
04a0c31
•
1 Parent(s): 414cbf0

Model save

Browse files
Files changed (3) hide show
  1. README.md +127 -0
  2. model.safetensors +1 -1
  3. runs/Feb19_14-58-14_e2e-84-59/events.out.tfevents.1708334905.e2e-84-59.342249.0 +2 -2
README.md ADDED
@@ -0,0 +1,127 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: microsoft/swin-tiny-patch4-window7-224
4
+ tags:
5
+ - generated_from_trainer
6
+ datasets:
7
+ - imagefolder
8
+ metrics:
9
+ - accuracy
10
+ model-index:
11
+ - name: cards_bottom_left_swin-tiny-patch4-window7-224-finetuned-v2_more_Data
12
+ results:
13
+ - task:
14
+ name: Image Classification
15
+ type: image-classification
16
+ dataset:
17
+ name: imagefolder
18
+ type: imagefolder
19
+ config: default
20
+ split: test
21
+ args: default
22
+ metrics:
23
+ - name: Accuracy
24
+ type: accuracy
25
+ value: 0.5927874941959449
26
+ ---
27
+
28
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
29
+ should probably proofread and complete it, then remove this comment. -->
30
+
31
+ # cards_bottom_left_swin-tiny-patch4-window7-224-finetuned-v2_more_Data
32
+
33
+ This model is a fine-tuned version of [microsoft/swin-tiny-patch4-window7-224](https://huggingface.co/microsoft/swin-tiny-patch4-window7-224) on the imagefolder dataset.
34
+ It achieves the following results on the evaluation set:
35
+ - Loss: 1.0009
36
+ - Accuracy: 0.5928
37
+
38
+ ## Model description
39
+
40
+ More information needed
41
+
42
+ ## Intended uses & limitations
43
+
44
+ More information needed
45
+
46
+ ## Training and evaluation data
47
+
48
+ More information needed
49
+
50
+ ## Training procedure
51
+
52
+ ### Training hyperparameters
53
+
54
+ The following hyperparameters were used during training:
55
+ - learning_rate: 5e-05
56
+ - train_batch_size: 32
57
+ - eval_batch_size: 32
58
+ - seed: 42
59
+ - gradient_accumulation_steps: 4
60
+ - total_train_batch_size: 128
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: 50
65
+
66
+ ### Training results
67
+
68
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
+ |:-------------:|:-----:|:-----:|:---------------:|:--------:|
70
+ | 1.559 | 1.0 | 1362 | 1.3402 | 0.4189 |
71
+ | 1.5165 | 2.0 | 2725 | 1.2308 | 0.4647 |
72
+ | 1.484 | 3.0 | 4087 | 1.1676 | 0.4954 |
73
+ | 1.5037 | 4.0 | 5450 | 1.1206 | 0.5198 |
74
+ | 1.4489 | 5.0 | 6812 | 1.1162 | 0.5284 |
75
+ | 1.4335 | 6.0 | 8175 | 1.1395 | 0.5047 |
76
+ | 1.4281 | 7.0 | 9537 | 1.0606 | 0.5445 |
77
+ | 1.4219 | 8.0 | 10900 | 1.0754 | 0.5408 |
78
+ | 1.3935 | 9.0 | 12262 | 1.0285 | 0.5604 |
79
+ | 1.3542 | 10.0 | 13625 | 1.0497 | 0.5453 |
80
+ | 1.3761 | 11.0 | 14987 | 1.0535 | 0.5450 |
81
+ | 1.3824 | 12.0 | 16350 | 1.0268 | 0.5591 |
82
+ | 1.3709 | 13.0 | 17712 | 1.0015 | 0.5690 |
83
+ | 1.3361 | 14.0 | 19075 | 1.0266 | 0.5595 |
84
+ | 1.3673 | 15.0 | 20437 | 0.9988 | 0.5772 |
85
+ | 1.376 | 16.0 | 21800 | 0.9950 | 0.5744 |
86
+ | 1.3486 | 17.0 | 23162 | 0.9837 | 0.5784 |
87
+ | 1.3333 | 18.0 | 24525 | 0.9771 | 0.5827 |
88
+ | 1.347 | 19.0 | 25887 | 0.9895 | 0.5770 |
89
+ | 1.3381 | 20.0 | 27250 | 0.9709 | 0.5820 |
90
+ | 1.3385 | 21.0 | 28612 | 0.9704 | 0.5833 |
91
+ | 1.336 | 22.0 | 29975 | 0.9646 | 0.5885 |
92
+ | 1.3372 | 23.0 | 31337 | 0.9653 | 0.5879 |
93
+ | 1.2979 | 24.0 | 32700 | 0.9867 | 0.5814 |
94
+ | 1.2948 | 25.0 | 34062 | 0.9633 | 0.5870 |
95
+ | 1.2767 | 26.0 | 35425 | 0.9578 | 0.5877 |
96
+ | 1.3012 | 27.0 | 36787 | 0.9709 | 0.5867 |
97
+ | 1.2667 | 28.0 | 38150 | 0.9648 | 0.5899 |
98
+ | 1.3 | 29.0 | 39512 | 0.9560 | 0.5930 |
99
+ | 1.2735 | 30.0 | 40875 | 0.9595 | 0.5949 |
100
+ | 1.2895 | 31.0 | 42237 | 0.9851 | 0.5809 |
101
+ | 1.2234 | 32.0 | 43600 | 0.9601 | 0.5931 |
102
+ | 1.2212 | 33.0 | 44962 | 0.9800 | 0.5917 |
103
+ | 1.2483 | 34.0 | 46325 | 0.9662 | 0.5982 |
104
+ | 1.2507 | 35.0 | 47687 | 0.9657 | 0.5910 |
105
+ | 1.2539 | 36.0 | 49050 | 0.9954 | 0.5783 |
106
+ | 1.2491 | 37.0 | 50412 | 0.9718 | 0.5924 |
107
+ | 1.2397 | 38.0 | 51775 | 0.9769 | 0.5930 |
108
+ | 1.1903 | 39.0 | 53137 | 0.9717 | 0.5945 |
109
+ | 1.2475 | 40.0 | 54500 | 0.9995 | 0.5855 |
110
+ | 1.2371 | 41.0 | 55862 | 0.9861 | 0.5935 |
111
+ | 1.2561 | 42.0 | 57225 | 0.9856 | 0.5958 |
112
+ | 1.2069 | 43.0 | 58587 | 0.9913 | 0.5892 |
113
+ | 1.2188 | 44.0 | 59950 | 0.9902 | 0.5950 |
114
+ | 1.1732 | 45.0 | 61312 | 0.9892 | 0.5949 |
115
+ | 1.1705 | 46.0 | 62675 | 0.9991 | 0.5914 |
116
+ | 1.18 | 47.0 | 64037 | 0.9952 | 0.5925 |
117
+ | 1.2353 | 48.0 | 65400 | 0.9999 | 0.5933 |
118
+ | 1.2057 | 49.0 | 66762 | 1.0001 | 0.5920 |
119
+ | 1.1833 | 49.98 | 68100 | 1.0009 | 0.5928 |
120
+
121
+
122
+ ### Framework versions
123
+
124
+ - Transformers 4.37.2
125
+ - Pytorch 2.0.1+cu117
126
+ - Datasets 2.17.0
127
+ - Tokenizers 0.15.2
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:42cafcd5731ce561b4f1b1720c825a06fd21e3d75bd9c9efc5e028bae3be9783
3
  size 110364364
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94cbe45617aeb28e57d7aae2da54184f13bc6620960a449904bac30fa70797ce
3
  size 110364364
runs/Feb19_14-58-14_e2e-84-59/events.out.tfevents.1708334905.e2e-84-59.342249.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fa1824febe84c103baaf1190e8c37b4d94f81f2eebee6e08633c6d54c032ca0e
3
- size 1084444
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b155c5892964b1c952e113e4de16a1368f2213987d4ca8e19ea271a52140bee
3
+ size 1106573