Hugging Face's logo

hkivancoral
/
smids_5x_deit_tiny_rms_001_fold2

Image Classification
Transformers
PyTorch
vit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
hkivancoral commited on
Commit
0aeb7e6
•
1 Parent(s): 146c789

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_5x_deit_tiny_rms_001_fold2
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: 0.848585690515807
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_5x_deit_tiny_rms_001_fold2
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: 1.4964
36
+ - Accuracy: 0.8486
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
+ | 1.0328 | 1.0 | 375 | 0.9569 | 0.4459 |
69
+ | 0.8929 | 2.0 | 750 | 0.8978 | 0.5374 |
70
+ | 0.8224 | 3.0 | 1125 | 0.7888 | 0.5574 |
71
+ | 0.8327 | 4.0 | 1500 | 0.8571 | 0.5641 |
72
+ | 0.7266 | 5.0 | 1875 | 1.1729 | 0.5025 |
73
+ | 0.6507 | 6.0 | 2250 | 0.7875 | 0.6456 |
74
+ | 0.6983 | 7.0 | 2625 | 0.6489 | 0.6972 |
75
+ | 0.6312 | 8.0 | 3000 | 0.7326 | 0.6789 |
76
+ | 0.641 | 9.0 | 3375 | 0.5505 | 0.7488 |
77
+ | 0.6354 | 10.0 | 3750 | 0.5766 | 0.7354 |
78
+ | 0.5813 | 11.0 | 4125 | 0.4910 | 0.7920 |
79
+ | 0.6084 | 12.0 | 4500 | 0.5458 | 0.7720 |
80
+ | 0.4944 | 13.0 | 4875 | 0.4657 | 0.8020 |
81
+ | 0.5555 | 14.0 | 5250 | 0.5401 | 0.7621 |
82
+ | 0.526 | 15.0 | 5625 | 0.4958 | 0.7837 |
83
+ | 0.3751 | 16.0 | 6000 | 0.4911 | 0.8037 |
84
+ | 0.4264 | 17.0 | 6375 | 0.5204 | 0.7837 |
85
+ | 0.4312 | 18.0 | 6750 | 0.5011 | 0.7953 |
86
+ | 0.3686 | 19.0 | 7125 | 0.4979 | 0.7970 |
87
+ | 0.3954 | 20.0 | 7500 | 0.4812 | 0.8120 |
88
+ | 0.3782 | 21.0 | 7875 | 0.4706 | 0.8120 |
89
+ | 0.3544 | 22.0 | 8250 | 0.4461 | 0.8353 |
90
+ | 0.3759 | 23.0 | 8625 | 0.4516 | 0.8319 |
91
+ | 0.3473 | 24.0 | 9000 | 0.4332 | 0.8270 |
92
+ | 0.2572 | 25.0 | 9375 | 0.5951 | 0.8203 |
93
+ | 0.3628 | 26.0 | 9750 | 0.5630 | 0.7887 |
94
+ | 0.2737 | 27.0 | 10125 | 0.5304 | 0.8336 |
95
+ | 0.2272 | 28.0 | 10500 | 0.5597 | 0.8319 |
96
+ | 0.2226 | 29.0 | 10875 | 0.5680 | 0.8419 |
97
+ | 0.1778 | 30.0 | 11250 | 0.6295 | 0.8170 |
98
+ | 0.2382 | 31.0 | 11625 | 0.6223 | 0.8270 |
99
+ | 0.1721 | 32.0 | 12000 | 0.6049 | 0.8469 |
100
+ | 0.219 | 33.0 | 12375 | 0.5556 | 0.8569 |
101
+ | 0.0972 | 34.0 | 12750 | 0.6389 | 0.8502 |
102
+ | 0.1781 | 35.0 | 13125 | 0.7873 | 0.8253 |
103
+ | 0.1052 | 36.0 | 13500 | 0.8815 | 0.8236 |
104
+ | 0.1087 | 37.0 | 13875 | 0.7444 | 0.8453 |
105
+ | 0.09 | 38.0 | 14250 | 0.9779 | 0.8253 |
106
+ | 0.0859 | 39.0 | 14625 | 0.8817 | 0.8386 |
107
+ | 0.0521 | 40.0 | 15000 | 0.9849 | 0.8453 |
108
+ | 0.081 | 41.0 | 15375 | 1.0555 | 0.8203 |
109
+ | 0.0225 | 42.0 | 15750 | 1.1081 | 0.8303 |
110
+ | 0.0521 | 43.0 | 16125 | 1.2294 | 0.8253 |
111
+ | 0.0259 | 44.0 | 16500 | 1.3035 | 0.8336 |
112
+ | 0.0403 | 45.0 | 16875 | 1.3613 | 0.8253 |
113
+ | 0.0225 | 46.0 | 17250 | 1.4500 | 0.8103 |
114
+ | 0.0235 | 47.0 | 17625 | 1.5096 | 0.8270 |
115
+ | 0.0002 | 48.0 | 18000 | 1.5022 | 0.8469 |
116
+ | 0.0101 | 49.0 | 18375 | 1.4968 | 0.8469 |
117
+ | 0.0029 | 50.0 | 18750 | 1.4964 | 0.8486 |
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 sha256:0396dfe3b07b347f90680786fffb26c83c033ad8c687ff884dfe7d1934d042a2
3
  size 22167850
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:118aa4f6a9afd74d67d8e5c8bb8e4cc72613ef033e647ddd20dd9a88e9e0a040
3
  size 22167850