Hugging Face's logo

hkivancoral
/
smids_1x_deit_tiny_rms_001_fold5

Image Classification
Transformers
TensorBoard
Safetensors
vit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
hkivancoral commited on
Commit
d726b3b
•
1 Parent(s): 60549b9

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_fold5
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: 0.765
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_fold5
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: 1.8052
36
+ - Accuracy: 0.765
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
+ | 1.2535 | 1.0 | 75 | 0.9734 | 0.4717 |
69
+ | 1.0172 | 2.0 | 150 | 0.8857 | 0.5217 |
70
+ | 0.9205 | 3.0 | 225 | 0.8219 | 0.5633 |
71
+ | 0.8404 | 4.0 | 300 | 0.8833 | 0.54 |
72
+ | 0.8125 | 5.0 | 375 | 0.7752 | 0.615 |
73
+ | 0.8375 | 6.0 | 450 | 0.7791 | 0.6133 |
74
+ | 0.7706 | 7.0 | 525 | 0.7651 | 0.6433 |
75
+ | 0.6843 | 8.0 | 600 | 0.7674 | 0.6083 |
76
+ | 0.717 | 9.0 | 675 | 0.7318 | 0.655 |
77
+ | 0.6266 | 10.0 | 750 | 0.7160 | 0.6867 |
78
+ | 0.674 | 11.0 | 825 | 0.6761 | 0.69 |
79
+ | 0.6618 | 12.0 | 900 | 0.7236 | 0.6433 |
80
+ | 0.6204 | 13.0 | 975 | 0.7093 | 0.6733 |
81
+ | 0.6403 | 14.0 | 1050 | 0.6526 | 0.7133 |
82
+ | 0.5728 | 15.0 | 1125 | 0.7313 | 0.6617 |
83
+ | 0.5566 | 16.0 | 1200 | 0.6152 | 0.7317 |
84
+ | 0.5735 | 17.0 | 1275 | 0.6901 | 0.7083 |
85
+ | 0.6111 | 18.0 | 1350 | 0.6429 | 0.7317 |
86
+ | 0.6075 | 19.0 | 1425 | 0.6044 | 0.7533 |
87
+ | 0.5675 | 20.0 | 1500 | 0.5922 | 0.7633 |
88
+ | 0.4747 | 21.0 | 1575 | 0.6118 | 0.7483 |
89
+ | 0.5157 | 22.0 | 1650 | 0.6322 | 0.7383 |
90
+ | 0.4995 | 23.0 | 1725 | 0.6300 | 0.745 |
91
+ | 0.4632 | 24.0 | 1800 | 0.6076 | 0.74 |
92
+ | 0.4596 | 25.0 | 1875 | 0.6047 | 0.7733 |
93
+ | 0.4702 | 26.0 | 1950 | 0.6096 | 0.7633 |
94
+ | 0.5043 | 27.0 | 2025 | 0.6045 | 0.7567 |
95
+ | 0.5051 | 28.0 | 2100 | 0.5905 | 0.75 |
96
+ | 0.4664 | 29.0 | 2175 | 0.6085 | 0.7567 |
97
+ | 0.3949 | 30.0 | 2250 | 0.6634 | 0.76 |
98
+ | 0.3708 | 31.0 | 2325 | 0.6461 | 0.7667 |
99
+ | 0.3964 | 32.0 | 2400 | 0.6482 | 0.7617 |
100
+ | 0.3827 | 33.0 | 2475 | 0.6696 | 0.76 |
101
+ | 0.3422 | 34.0 | 2550 | 0.6799 | 0.765 |
102
+ | 0.3716 | 35.0 | 2625 | 0.7307 | 0.7767 |
103
+ | 0.3007 | 36.0 | 2700 | 0.7490 | 0.7583 |
104
+ | 0.2019 | 37.0 | 2775 | 0.8838 | 0.7533 |
105
+ | 0.232 | 38.0 | 2850 | 0.8738 | 0.76 |
106
+ | 0.221 | 39.0 | 2925 | 0.8842 | 0.7733 |
107
+ | 0.1875 | 40.0 | 3000 | 1.0078 | 0.7383 |
108
+ | 0.203 | 41.0 | 3075 | 1.0476 | 0.7567 |
109
+ | 0.1699 | 42.0 | 3150 | 1.0739 | 0.7567 |
110
+ | 0.171 | 43.0 | 3225 | 1.1644 | 0.7417 |
111
+ | 0.1205 | 44.0 | 3300 | 1.2501 | 0.7533 |
112
+ | 0.0811 | 45.0 | 3375 | 1.2967 | 0.755 |
113
+ | 0.0202 | 46.0 | 3450 | 1.5619 | 0.745 |
114
+ | 0.0237 | 47.0 | 3525 | 1.5862 | 0.7617 |
115
+ | 0.0127 | 48.0 | 3600 | 1.6631 | 0.7667 |
116
+ | 0.0204 | 49.0 | 3675 | 1.7536 | 0.7667 |
117
+ | 0.0042 | 50.0 | 3750 | 1.8052 | 0.765 |
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 sha256:796d430e397a16695b9f7bcedf78c22a4f1841cf5ef7010b065d7a0f15426c5b
3
  size 22122692
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62894534d7eea0fa35460aa2cdc10eda46b2d5dcf80f0aed628c251da6528b49
3
  size 22122692