Hugging Face's logo

hkivancoral
/
smids_10x_deit_tiny_rms_001_fold4

Image Classification
Transformers
PyTorch
vit
generated_from_trainer
Eval Results
Inference Endpoints
Model card Files Community
hkivancoral commited on
Commit
c98c65d
•
1 Parent(s): 2421b65

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_rms_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: 0.8116666666666666
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_rms_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: 2.8355
36
+ - Accuracy: 0.8117
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
+ | 0.7719 | 1.0 | 750 | 0.7663 | 0.6417 |
69
+ | 0.7164 | 2.0 | 1500 | 0.6422 | 0.7167 |
70
+ | 0.6166 | 3.0 | 2250 | 0.5992 | 0.7233 |
71
+ | 0.5878 | 4.0 | 3000 | 0.6512 | 0.6783 |
72
+ | 0.5907 | 5.0 | 3750 | 0.5898 | 0.7183 |
73
+ | 0.5259 | 6.0 | 4500 | 0.5668 | 0.7617 |
74
+ | 0.4934 | 7.0 | 5250 | 0.5092 | 0.7817 |
75
+ | 0.5606 | 8.0 | 6000 | 0.5230 | 0.76 |
76
+ | 0.5352 | 9.0 | 6750 | 0.5089 | 0.7733 |
77
+ | 0.4475 | 10.0 | 7500 | 0.5880 | 0.745 |
78
+ | 0.4921 | 11.0 | 8250 | 0.5315 | 0.765 |
79
+ | 0.5457 | 12.0 | 9000 | 0.5773 | 0.7583 |
80
+ | 0.4353 | 13.0 | 9750 | 0.5700 | 0.7533 |
81
+ | 0.4266 | 14.0 | 10500 | 0.5929 | 0.7633 |
82
+ | 0.4011 | 15.0 | 11250 | 0.5510 | 0.7883 |
83
+ | 0.4243 | 16.0 | 12000 | 0.5772 | 0.7633 |
84
+ | 0.2788 | 17.0 | 12750 | 0.5913 | 0.7817 |
85
+ | 0.36 | 18.0 | 13500 | 0.5472 | 0.7767 |
86
+ | 0.3727 | 19.0 | 14250 | 0.5501 | 0.7867 |
87
+ | 0.2873 | 20.0 | 15000 | 0.6706 | 0.77 |
88
+ | 0.3441 | 21.0 | 15750 | 0.5563 | 0.8083 |
89
+ | 0.3741 | 22.0 | 16500 | 0.5905 | 0.7767 |
90
+ | 0.2914 | 23.0 | 17250 | 0.6313 | 0.785 |
91
+ | 0.3593 | 24.0 | 18000 | 0.5992 | 0.7983 |
92
+ | 0.2548 | 25.0 | 18750 | 0.6167 | 0.8 |
93
+ | 0.2172 | 26.0 | 19500 | 0.6453 | 0.785 |
94
+ | 0.1957 | 27.0 | 20250 | 0.6311 | 0.815 |
95
+ | 0.2482 | 28.0 | 21000 | 0.7520 | 0.8067 |
96
+ | 0.1858 | 29.0 | 21750 | 0.7460 | 0.7917 |
97
+ | 0.1724 | 30.0 | 22500 | 0.6735 | 0.8183 |
98
+ | 0.1536 | 31.0 | 23250 | 0.8260 | 0.7933 |
99
+ | 0.1432 | 32.0 | 24000 | 0.9327 | 0.765 |
100
+ | 0.1489 | 33.0 | 24750 | 0.8695 | 0.7967 |
101
+ | 0.1215 | 34.0 | 25500 | 0.8392 | 0.8167 |
102
+ | 0.1302 | 35.0 | 26250 | 1.0000 | 0.8133 |
103
+ | 0.0677 | 36.0 | 27000 | 1.0715 | 0.8083 |
104
+ | 0.0727 | 37.0 | 27750 | 1.1501 | 0.7983 |
105
+ | 0.1221 | 38.0 | 28500 | 1.3342 | 0.7883 |
106
+ | 0.0469 | 39.0 | 29250 | 1.3213 | 0.8 |
107
+ | 0.068 | 40.0 | 30000 | 1.4945 | 0.8 |
108
+ | 0.0607 | 41.0 | 30750 | 1.4763 | 0.8133 |
109
+ | 0.0293 | 42.0 | 31500 | 1.8072 | 0.79 |
110
+ | 0.0304 | 43.0 | 32250 | 2.0290 | 0.7817 |
111
+ | 0.0187 | 44.0 | 33000 | 2.2554 | 0.7867 |
112
+ | 0.0136 | 45.0 | 33750 | 2.3220 | 0.8 |
113
+ | 0.0034 | 46.0 | 34500 | 2.4619 | 0.8033 |
114
+ | 0.0045 | 47.0 | 35250 | 2.5490 | 0.8 |
115
+ | 0.0159 | 48.0 | 36000 | 2.5993 | 0.825 |
116
+ | 0.0004 | 49.0 | 36750 | 2.7895 | 0.8083 |
117
+ | 0.0001 | 50.0 | 37500 | 2.8355 | 0.8117 |
118
+
119
+
120
+ ### Framework versions
121
+
122
+ - Transformers 4.32.1
123
+ - Pytorch 2.1.1+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:dde62b4a4b726004277862a7bf3a628046e5b0511726da9e91a53f522f6cff15
3
  size 22167850
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f45a4d4e00c477b9c423065aa52ee1e53ab28e2b5cad37417b2ebab62d134d1
3
  size 22167850