Hugging Face's logo

hkivancoral
/
hushem_5x_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
b910b42
•
1 Parent(s): 62eb661

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: hushem_5x_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: 0.7857142857142857
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
+ # hushem_5x_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: 1.7375
36
+ - Accuracy: 0.7857
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
+ | 1.4656 | 1.0 | 28 | 1.3873 | 0.3095 |
69
+ | 1.2586 | 2.0 | 56 | 1.2764 | 0.5 |
70
+ | 1.1469 | 3.0 | 84 | 0.9328 | 0.5 |
71
+ | 1.0441 | 4.0 | 112 | 0.8472 | 0.5952 |
72
+ | 0.811 | 5.0 | 140 | 0.7157 | 0.6667 |
73
+ | 0.9304 | 6.0 | 168 | 1.0112 | 0.5476 |
74
+ | 0.6688 | 7.0 | 196 | 1.1025 | 0.6429 |
75
+ | 0.7046 | 8.0 | 224 | 0.9337 | 0.7143 |
76
+ | 0.6117 | 9.0 | 252 | 0.8164 | 0.7143 |
77
+ | 0.4458 | 10.0 | 280 | 0.9534 | 0.7381 |
78
+ | 0.3231 | 11.0 | 308 | 0.8226 | 0.7381 |
79
+ | 0.2594 | 12.0 | 336 | 1.4042 | 0.6905 |
80
+ | 0.3579 | 13.0 | 364 | 1.0151 | 0.6905 |
81
+ | 0.3051 | 14.0 | 392 | 1.1256 | 0.7619 |
82
+ | 0.212 | 15.0 | 420 | 1.4604 | 0.6905 |
83
+ | 0.1011 | 16.0 | 448 | 1.4776 | 0.7381 |
84
+ | 0.0658 | 17.0 | 476 | 1.5151 | 0.7143 |
85
+ | 0.0916 | 18.0 | 504 | 2.0212 | 0.6667 |
86
+ | 0.12 | 19.0 | 532 | 1.3757 | 0.7143 |
87
+ | 0.1417 | 20.0 | 560 | 1.9592 | 0.6905 |
88
+ | 0.1037 | 21.0 | 588 | 1.5184 | 0.7143 |
89
+ | 0.0812 | 22.0 | 616 | 1.5083 | 0.7381 |
90
+ | 0.0404 | 23.0 | 644 | 1.7932 | 0.7381 |
91
+ | 0.0758 | 24.0 | 672 | 1.5450 | 0.7143 |
92
+ | 0.0384 | 25.0 | 700 | 2.0953 | 0.6667 |
93
+ | 0.0277 | 26.0 | 728 | 1.9894 | 0.6667 |
94
+ | 0.0016 | 27.0 | 756 | 1.8938 | 0.7143 |
95
+ | 0.0008 | 28.0 | 784 | 1.7999 | 0.7619 |
96
+ | 0.0118 | 29.0 | 812 | 1.7512 | 0.7619 |
97
+ | 0.0001 | 30.0 | 840 | 1.8297 | 0.7619 |
98
+ | 0.0002 | 31.0 | 868 | 1.7978 | 0.7381 |
99
+ | 0.0105 | 32.0 | 896 | 1.6941 | 0.7857 |
100
+ | 0.0001 | 33.0 | 924 | 1.6973 | 0.7619 |
101
+ | 0.0 | 34.0 | 952 | 1.6981 | 0.7381 |
102
+ | 0.0 | 35.0 | 980 | 1.7026 | 0.7381 |
103
+ | 0.0 | 36.0 | 1008 | 1.7088 | 0.7619 |
104
+ | 0.0 | 37.0 | 1036 | 1.7123 | 0.7619 |
105
+ | 0.0 | 38.0 | 1064 | 1.7165 | 0.7619 |
106
+ | 0.0 | 39.0 | 1092 | 1.7201 | 0.7619 |
107
+ | 0.0 | 40.0 | 1120 | 1.7234 | 0.7619 |
108
+ | 0.0 | 41.0 | 1148 | 1.7263 | 0.7619 |
109
+ | 0.0 | 42.0 | 1176 | 1.7294 | 0.7619 |
110
+ | 0.0 | 43.0 | 1204 | 1.7316 | 0.7619 |
111
+ | 0.0 | 44.0 | 1232 | 1.7334 | 0.7857 |
112
+ | 0.0 | 45.0 | 1260 | 1.7350 | 0.7857 |
113
+ | 0.0 | 46.0 | 1288 | 1.7363 | 0.7857 |
114
+ | 0.0 | 47.0 | 1316 | 1.7371 | 0.7857 |
115
+ | 0.0 | 48.0 | 1344 | 1.7375 | 0.7857 |
116
+ | 0.0 | 49.0 | 1372 | 1.7375 | 0.7857 |
117
+ | 0.0 | 50.0 | 1400 | 1.7375 | 0.7857 |
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 sha256:2d8ca2ea7ed0ddcd45af71446e4a2af9037f752e1e0c6724146c2121c5b8d8db
3
  size 22123464
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25bb04cce69b44cbc452deb9a6a808ff44ab14f3eef2f1168ec89c5024cd7689
3
  size 22123464