Hugging Face's logo

hkivancoral
/
smids_1x_deit_tiny_adamax_001_fold4

Image Classification
Transformers
TensorBoard
Safetensors
vit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
hkivancoral commited on
Commit
e062a34
•
1 Parent(s): 4eb2f37

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_adamax_001_fold4
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: 0.84
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_adamax_001_fold4
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: 1.6471
36
+ - Accuracy: 0.84
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
+ | 0.7464 | 1.0 | 75 | 0.5642 | 0.795 |
69
+ | 0.5514 | 2.0 | 150 | 0.5108 | 0.8017 |
70
+ | 0.3856 | 3.0 | 225 | 0.5385 | 0.8033 |
71
+ | 0.4541 | 4.0 | 300 | 0.4488 | 0.825 |
72
+ | 0.4047 | 5.0 | 375 | 0.4448 | 0.815 |
73
+ | 0.2699 | 6.0 | 450 | 0.5321 | 0.8267 |
74
+ | 0.3444 | 7.0 | 525 | 0.4477 | 0.8367 |
75
+ | 0.1984 | 8.0 | 600 | 0.5491 | 0.81 |
76
+ | 0.1797 | 9.0 | 675 | 0.7263 | 0.8167 |
77
+ | 0.1145 | 10.0 | 750 | 0.6218 | 0.8317 |
78
+ | 0.1353 | 11.0 | 825 | 0.7800 | 0.8183 |
79
+ | 0.1658 | 12.0 | 900 | 0.6252 | 0.835 |
80
+ | 0.101 | 13.0 | 975 | 0.8640 | 0.805 |
81
+ | 0.0897 | 14.0 | 1050 | 0.9357 | 0.8 |
82
+ | 0.0267 | 15.0 | 1125 | 1.0487 | 0.8283 |
83
+ | 0.0597 | 16.0 | 1200 | 1.0545 | 0.8283 |
84
+ | 0.0984 | 17.0 | 1275 | 0.9221 | 0.83 |
85
+ | 0.0994 | 18.0 | 1350 | 0.9468 | 0.8367 |
86
+ | 0.0261 | 19.0 | 1425 | 1.1404 | 0.8117 |
87
+ | 0.0439 | 20.0 | 1500 | 1.1737 | 0.8233 |
88
+ | 0.0258 | 21.0 | 1575 | 1.1898 | 0.8383 |
89
+ | 0.0027 | 22.0 | 1650 | 1.4604 | 0.8217 |
90
+ | 0.0296 | 23.0 | 1725 | 1.3681 | 0.8267 |
91
+ | 0.004 | 24.0 | 1800 | 1.5826 | 0.83 |
92
+ | 0.0296 | 25.0 | 1875 | 1.2731 | 0.8167 |
93
+ | 0.0022 | 26.0 | 1950 | 1.4166 | 0.83 |
94
+ | 0.0213 | 27.0 | 2025 | 1.3755 | 0.8433 |
95
+ | 0.0191 | 28.0 | 2100 | 1.6417 | 0.82 |
96
+ | 0.0068 | 29.0 | 2175 | 1.3938 | 0.8417 |
97
+ | 0.0003 | 30.0 | 2250 | 1.4213 | 0.8317 |
98
+ | 0.0002 | 31.0 | 2325 | 1.4622 | 0.8417 |
99
+ | 0.0 | 32.0 | 2400 | 1.5110 | 0.8367 |
100
+ | 0.0291 | 33.0 | 2475 | 1.4845 | 0.8383 |
101
+ | 0.0005 | 34.0 | 2550 | 1.5757 | 0.8333 |
102
+ | 0.0089 | 35.0 | 2625 | 1.6525 | 0.83 |
103
+ | 0.0053 | 36.0 | 2700 | 1.6166 | 0.84 |
104
+ | 0.0078 | 37.0 | 2775 | 1.5899 | 0.8467 |
105
+ | 0.0 | 38.0 | 2850 | 1.6250 | 0.8433 |
106
+ | 0.0004 | 39.0 | 2925 | 1.6311 | 0.8433 |
107
+ | 0.0 | 40.0 | 3000 | 1.6268 | 0.8433 |
108
+ | 0.0032 | 41.0 | 3075 | 1.6310 | 0.8417 |
109
+ | 0.0 | 42.0 | 3150 | 1.6322 | 0.84 |
110
+ | 0.0 | 43.0 | 3225 | 1.6387 | 0.84 |
111
+ | 0.0 | 44.0 | 3300 | 1.6405 | 0.84 |
112
+ | 0.0 | 45.0 | 3375 | 1.6426 | 0.84 |
113
+ | 0.0 | 46.0 | 3450 | 1.6435 | 0.84 |
114
+ | 0.0 | 47.0 | 3525 | 1.6443 | 0.84 |
115
+ | 0.0 | 48.0 | 3600 | 1.6452 | 0.84 |
116
+ | 0.0 | 49.0 | 3675 | 1.6465 | 0.84 |
117
+ | 0.0 | 50.0 | 3750 | 1.6471 | 0.84 |
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 sha256:5260e7f509625a587bcfee5d9b640ff28fc399444010722da62ab930a33c8adc
3
  size 22122692
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5118e95ffed9744eed7fbce393310c25db1116cbd56bec2ae5155cab4127719
3
  size 22122692