Hugging Face's logo

hkivancoral
/
smids_10x_deit_tiny_sgd_0001_fold4

Image Classification
Transformers
PyTorch
vit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
hkivancoral commited on
Commit
8c6751b
·
1 Parent(s): 05dec10

End of training

Browse files
Files changed (2) hide show
  1. README.md +125 -0
  2. pytorch_model.bin +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_10x_deit_tiny_sgd_0001_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: 0.8416666666666667
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_10x_deit_tiny_sgd_0001_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: 0.4161
36
+ - Accuracy: 0.8417
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: 0.0001
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
+ | 1.0688 | 1.0 | 750 | 1.0895 | 0.3983 |
69
+ | 0.9867 | 2.0 | 1500 | 0.9975 | 0.4833 |
70
+ | 0.9278 | 3.0 | 2250 | 0.9175 | 0.54 |
71
+ | 0.8528 | 4.0 | 3000 | 0.8474 | 0.5783 |
72
+ | 0.714 | 5.0 | 3750 | 0.7808 | 0.635 |
73
+ | 0.6866 | 6.0 | 4500 | 0.7206 | 0.6917 |
74
+ | 0.6101 | 7.0 | 5250 | 0.6718 | 0.7167 |
75
+ | 0.6452 | 8.0 | 6000 | 0.6299 | 0.7333 |
76
+ | 0.6113 | 9.0 | 6750 | 0.5989 | 0.7467 |
77
+ | 0.5055 | 10.0 | 7500 | 0.5743 | 0.7633 |
78
+ | 0.4983 | 11.0 | 8250 | 0.5553 | 0.7717 |
79
+ | 0.5538 | 12.0 | 9000 | 0.5377 | 0.7733 |
80
+ | 0.4959 | 13.0 | 9750 | 0.5236 | 0.7833 |
81
+ | 0.4737 | 14.0 | 10500 | 0.5129 | 0.7867 |
82
+ | 0.4376 | 15.0 | 11250 | 0.5024 | 0.7967 |
83
+ | 0.3926 | 16.0 | 12000 | 0.4941 | 0.8033 |
84
+ | 0.397 | 17.0 | 12750 | 0.4866 | 0.805 |
85
+ | 0.4304 | 18.0 | 13500 | 0.4793 | 0.8067 |
86
+ | 0.4526 | 19.0 | 14250 | 0.4737 | 0.81 |
87
+ | 0.4267 | 20.0 | 15000 | 0.4680 | 0.81 |
88
+ | 0.3746 | 21.0 | 15750 | 0.4626 | 0.8183 |
89
+ | 0.4237 | 22.0 | 16500 | 0.4581 | 0.815 |
90
+ | 0.4022 | 23.0 | 17250 | 0.4540 | 0.82 |
91
+ | 0.465 | 24.0 | 18000 | 0.4503 | 0.8233 |
92
+ | 0.3585 | 25.0 | 18750 | 0.4464 | 0.8267 |
93
+ | 0.3671 | 26.0 | 19500 | 0.4431 | 0.8267 |
94
+ | 0.3889 | 27.0 | 20250 | 0.4400 | 0.8283 |
95
+ | 0.3836 | 28.0 | 21000 | 0.4372 | 0.83 |
96
+ | 0.3751 | 29.0 | 21750 | 0.4351 | 0.83 |
97
+ | 0.3772 | 30.0 | 22500 | 0.4334 | 0.8333 |
98
+ | 0.3959 | 31.0 | 23250 | 0.4312 | 0.8333 |
99
+ | 0.3701 | 32.0 | 24000 | 0.4290 | 0.8317 |
100
+ | 0.3441 | 33.0 | 24750 | 0.4274 | 0.8317 |
101
+ | 0.371 | 34.0 | 25500 | 0.4262 | 0.8333 |
102
+ | 0.327 | 35.0 | 26250 | 0.4246 | 0.8333 |
103
+ | 0.3799 | 36.0 | 27000 | 0.4233 | 0.8367 |
104
+ | 0.3186 | 37.0 | 27750 | 0.4226 | 0.835 |
105
+ | 0.3955 | 38.0 | 28500 | 0.4215 | 0.835 |
106
+ | 0.4171 | 39.0 | 29250 | 0.4206 | 0.835 |
107
+ | 0.4116 | 40.0 | 30000 | 0.4196 | 0.8367 |
108
+ | 0.369 | 41.0 | 30750 | 0.4189 | 0.8383 |
109
+ | 0.3461 | 42.0 | 31500 | 0.4184 | 0.8383 |
110
+ | 0.3837 | 43.0 | 32250 | 0.4178 | 0.8417 |
111
+ | 0.3565 | 44.0 | 33000 | 0.4174 | 0.8417 |
112
+ | 0.3745 | 45.0 | 33750 | 0.4170 | 0.8417 |
113
+ | 0.3413 | 46.0 | 34500 | 0.4167 | 0.8417 |
114
+ | 0.301 | 47.0 | 35250 | 0.4164 | 0.8417 |
115
+ | 0.3105 | 48.0 | 36000 | 0.4162 | 0.8417 |
116
+ | 0.3511 | 49.0 | 36750 | 0.4161 | 0.8417 |
117
+ | 0.3221 | 50.0 | 37500 | 0.4161 | 0.8417 |
118
+
119
+
120
+ ### Framework versions
121
+
122
+ - Transformers 4.32.1
123
+ - Pytorch 2.1.0+cu121
124
+ - Datasets 2.12.0
125
+ - Tokenizers 0.13.2
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3aec5767a30bec21d3dc1af1da50674af9c8b6745398c4b6e4545c6cc0104027
3
  size 22167850
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:485327695ebb65cc2dd135042b40ccde2e161455b5f8a1837f74268facfec527
3
  size 22167850