Hugging Face's logo

hkivancoral
/
smids_1x_deit_tiny_rms_00001_fold1

Image Classification
Transformers
TensorBoard
Safetensors
vit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
hkivancoral commited on
Commit
979bbbd
•
1 Parent(s): 4a38093

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_00001_fold1
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: 0.8631051752921536
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_00001_fold1
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: 0.8877
36
+ - Accuracy: 0.8631
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: 1e-05
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
+ | 0.4093 | 1.0 | 76 | 0.4066 | 0.8264 |
69
+ | 0.3822 | 2.0 | 152 | 0.3553 | 0.8614 |
70
+ | 0.1979 | 3.0 | 228 | 0.3399 | 0.8631 |
71
+ | 0.1648 | 4.0 | 304 | 0.3252 | 0.8815 |
72
+ | 0.0965 | 5.0 | 380 | 0.3551 | 0.8531 |
73
+ | 0.072 | 6.0 | 456 | 0.4036 | 0.8631 |
74
+ | 0.0292 | 7.0 | 532 | 0.4208 | 0.8598 |
75
+ | 0.0237 | 8.0 | 608 | 0.5314 | 0.8497 |
76
+ | 0.0407 | 9.0 | 684 | 0.5484 | 0.8497 |
77
+ | 0.0074 | 10.0 | 760 | 0.5780 | 0.8715 |
78
+ | 0.0366 | 11.0 | 836 | 0.5799 | 0.8631 |
79
+ | 0.0022 | 12.0 | 912 | 0.8054 | 0.8414 |
80
+ | 0.0514 | 13.0 | 988 | 0.5849 | 0.8748 |
81
+ | 0.0003 | 14.0 | 1064 | 0.6713 | 0.8664 |
82
+ | 0.0448 | 15.0 | 1140 | 0.6921 | 0.8715 |
83
+ | 0.0014 | 16.0 | 1216 | 0.6848 | 0.8631 |
84
+ | 0.0001 | 17.0 | 1292 | 0.7084 | 0.8648 |
85
+ | 0.0152 | 18.0 | 1368 | 0.8109 | 0.8681 |
86
+ | 0.0001 | 19.0 | 1444 | 0.7361 | 0.8698 |
87
+ | 0.004 | 20.0 | 1520 | 0.7743 | 0.8664 |
88
+ | 0.0035 | 21.0 | 1596 | 0.7272 | 0.8748 |
89
+ | 0.0282 | 22.0 | 1672 | 0.7515 | 0.8731 |
90
+ | 0.0001 | 23.0 | 1748 | 0.8060 | 0.8581 |
91
+ | 0.0001 | 24.0 | 1824 | 0.7763 | 0.8581 |
92
+ | 0.0156 | 25.0 | 1900 | 0.7302 | 0.8831 |
93
+ | 0.0068 | 26.0 | 1976 | 0.8763 | 0.8514 |
94
+ | 0.0045 | 27.0 | 2052 | 0.8144 | 0.8664 |
95
+ | 0.0058 | 28.0 | 2128 | 0.7716 | 0.8614 |
96
+ | 0.009 | 29.0 | 2204 | 0.8016 | 0.8664 |
97
+ | 0.0 | 30.0 | 2280 | 0.8234 | 0.8631 |
98
+ | 0.0087 | 31.0 | 2356 | 0.8420 | 0.8631 |
99
+ | 0.0102 | 32.0 | 2432 | 0.8218 | 0.8698 |
100
+ | 0.0 | 33.0 | 2508 | 0.8439 | 0.8564 |
101
+ | 0.0 | 34.0 | 2584 | 0.8448 | 0.8598 |
102
+ | 0.0154 | 35.0 | 2660 | 0.8638 | 0.8631 |
103
+ | 0.0044 | 36.0 | 2736 | 0.8664 | 0.8715 |
104
+ | 0.0088 | 37.0 | 2812 | 0.8649 | 0.8598 |
105
+ | 0.0 | 38.0 | 2888 | 0.8771 | 0.8598 |
106
+ | 0.0028 | 39.0 | 2964 | 0.8789 | 0.8631 |
107
+ | 0.0 | 40.0 | 3040 | 0.8645 | 0.8648 |
108
+ | 0.0044 | 41.0 | 3116 | 0.8681 | 0.8664 |
109
+ | 0.0 | 42.0 | 3192 | 0.8746 | 0.8631 |
110
+ | 0.0056 | 43.0 | 3268 | 0.8786 | 0.8664 |
111
+ | 0.0 | 44.0 | 3344 | 0.8858 | 0.8648 |
112
+ | 0.0 | 45.0 | 3420 | 0.8848 | 0.8648 |
113
+ | 0.0 | 46.0 | 3496 | 0.8858 | 0.8648 |
114
+ | 0.0 | 47.0 | 3572 | 0.8868 | 0.8631 |
115
+ | 0.0023 | 48.0 | 3648 | 0.8879 | 0.8631 |
116
+ | 0.0 | 49.0 | 3724 | 0.8884 | 0.8631 |
117
+ | 0.0 | 50.0 | 3800 | 0.8877 | 0.8631 |
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:b449d437aff2a70d3f7799ba87726004985bbad3de006b4918c90ba07ca7df15
3
  size 22122692
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d59165767007e97a163ae5064b17686016df91af6ba87995235deb66a1d3a846
3
  size 22122692