Hugging Face's logo

hkivancoral
/
smids_1x_deit_tiny_rms_001_fold2

Image Classification
Transformers
TensorBoard
Safetensors
vit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
hkivancoral commited on
Commit
5981c96
•
1 Parent(s): 10574d5

End of training

Browse files
Files changed (2) hide show
  1. README.md +125 -0
  2. model.safetensors +1 -1
README.md ADDED
@@ -0,0 +1,125 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: facebook/deit-tiny-patch16-224
4
+ tags:
5
+ - generated_from_trainer
6
+ datasets:
7
+ - imagefolder
8
+ metrics:
9
+ - accuracy
10
+ model-index:
11
+ - name: smids_1x_deit_tiny_rms_001_fold2
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: 0.7554076539101497
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
+ # smids_1x_deit_tiny_rms_001_fold2
32
+
33
+ This model is a fine-tuned version of [facebook/deit-tiny-patch16-224](https://huggingface.co/facebook/deit-tiny-patch16-224) on the imagefolder dataset.
34
+ It achieves the following results on the evaluation set:
35
+ - Loss: 1.2712
36
+ - Accuracy: 0.7554
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: 0.001
56
+ - train_batch_size: 32
57
+ - eval_batch_size: 32
58
+ - seed: 42
59
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
60
+ - lr_scheduler_type: linear
61
+ - lr_scheduler_warmup_ratio: 0.1
62
+ - num_epochs: 50
63
+
64
+ ### Training results
65
+
66
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
67
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
68
+ | 1.1905 | 1.0 | 75 | 1.0709 | 0.4526 |
69
+ | 1.1189 | 2.0 | 150 | 0.9655 | 0.5241 |
70
+ | 0.9756 | 3.0 | 225 | 0.9009 | 0.4626 |
71
+ | 0.9398 | 4.0 | 300 | 0.8912 | 0.5757 |
72
+ | 0.9083 | 5.0 | 375 | 0.8740 | 0.5191 |
73
+ | 0.9033 | 6.0 | 450 | 0.8827 | 0.5092 |
74
+ | 0.8824 | 7.0 | 525 | 0.7939 | 0.5824 |
75
+ | 0.9323 | 8.0 | 600 | 0.8247 | 0.5524 |
76
+ | 0.8419 | 9.0 | 675 | 0.8138 | 0.5807 |
77
+ | 0.8164 | 10.0 | 750 | 0.8013 | 0.5674 |
78
+ | 0.859 | 11.0 | 825 | 0.8565 | 0.5458 |
79
+ | 0.7125 | 12.0 | 900 | 0.8056 | 0.6173 |
80
+ | 0.803 | 13.0 | 975 | 0.8062 | 0.6190 |
81
+ | 0.7687 | 14.0 | 1050 | 0.7699 | 0.6040 |
82
+ | 0.7356 | 15.0 | 1125 | 0.7299 | 0.6589 |
83
+ | 0.7325 | 16.0 | 1200 | 0.7012 | 0.6722 |
84
+ | 0.6848 | 17.0 | 1275 | 0.7155 | 0.6423 |
85
+ | 0.6885 | 18.0 | 1350 | 0.6752 | 0.6689 |
86
+ | 0.6698 | 19.0 | 1425 | 0.6669 | 0.6872 |
87
+ | 0.7037 | 20.0 | 1500 | 0.6890 | 0.6789 |
88
+ | 0.6983 | 21.0 | 1575 | 0.7382 | 0.6423 |
89
+ | 0.6127 | 22.0 | 1650 | 0.6732 | 0.7038 |
90
+ | 0.6242 | 23.0 | 1725 | 0.6106 | 0.7304 |
91
+ | 0.658 | 24.0 | 1800 | 0.6268 | 0.7121 |
92
+ | 0.5546 | 25.0 | 1875 | 0.6631 | 0.7088 |
93
+ | 0.5765 | 26.0 | 1950 | 0.6682 | 0.6988 |
94
+ | 0.6162 | 27.0 | 2025 | 0.6203 | 0.7304 |
95
+ | 0.5296 | 28.0 | 2100 | 0.6174 | 0.7438 |
96
+ | 0.5276 | 29.0 | 2175 | 0.5823 | 0.7371 |
97
+ | 0.4954 | 30.0 | 2250 | 0.7129 | 0.6922 |
98
+ | 0.5509 | 31.0 | 2325 | 0.6075 | 0.7404 |
99
+ | 0.4629 | 32.0 | 2400 | 0.6387 | 0.7488 |
100
+ | 0.4323 | 33.0 | 2475 | 0.6167 | 0.7421 |
101
+ | 0.4094 | 34.0 | 2550 | 0.6489 | 0.7637 |
102
+ | 0.419 | 35.0 | 2625 | 0.6362 | 0.7371 |
103
+ | 0.444 | 36.0 | 2700 | 0.6255 | 0.7621 |
104
+ | 0.4294 | 37.0 | 2775 | 0.6272 | 0.7604 |
105
+ | 0.3866 | 38.0 | 2850 | 0.6218 | 0.7770 |
106
+ | 0.3776 | 39.0 | 2925 | 0.6660 | 0.7637 |
107
+ | 0.3382 | 40.0 | 3000 | 0.7027 | 0.7720 |
108
+ | 0.3406 | 41.0 | 3075 | 0.7627 | 0.7770 |
109
+ | 0.3115 | 42.0 | 3150 | 0.7813 | 0.7737 |
110
+ | 0.2146 | 43.0 | 3225 | 0.8652 | 0.7521 |
111
+ | 0.2529 | 44.0 | 3300 | 0.9528 | 0.7504 |
112
+ | 0.1582 | 45.0 | 3375 | 0.9733 | 0.7704 |
113
+ | 0.1575 | 46.0 | 3450 | 1.0460 | 0.7704 |
114
+ | 0.1254 | 47.0 | 3525 | 1.1356 | 0.7737 |
115
+ | 0.076 | 48.0 | 3600 | 1.2020 | 0.7604 |
116
+ | 0.0433 | 49.0 | 3675 | 1.2652 | 0.7571 |
117
+ | 0.0823 | 50.0 | 3750 | 1.2712 | 0.7554 |
118
+
119
+
120
+ ### Framework versions
121
+
122
+ - Transformers 4.35.2
123
+ - Pytorch 2.1.0+cu118
124
+ - Datasets 2.15.0
125
+ - Tokenizers 0.15.0
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:947006ebcf6f77e03b745915834143fe699812e43bd5ee47ce319f3e8e7fa95c
3
  size 22122692
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:10870dabf05b258bf52b6dfffdadd41a21ac4ed71928eabbc9a5dd31c4662211
3
  size 22122692