Hugging Face's logo

hkivancoral
/
hushem_5x_deit_small_rms_001_fold4

Image Classification
Transformers
TensorBoard
Safetensors
vit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
hkivancoral commited on
Commit
23c268a
•
1 Parent(s): 3afe7ee

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-small-patch16-224
4
+ tags:
5
+ - generated_from_trainer
6
+ datasets:
7
+ - imagefolder
8
+ metrics:
9
+ - accuracy
10
+ model-index:
11
+ - name: hushem_5x_deit_small_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: 0.5952380952380952
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_small_rms_001_fold4
32
+
33
+ This model is a fine-tuned version of [facebook/deit-small-patch16-224](https://huggingface.co/facebook/deit-small-patch16-224) on the imagefolder dataset.
34
+ It achieves the following results on the evaluation set:
35
+ - Loss: 1.6694
36
+ - Accuracy: 0.5952
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
+ | 2.1638 | 1.0 | 28 | 1.7503 | 0.2381 |
69
+ | 1.4446 | 2.0 | 56 | 1.5611 | 0.2619 |
70
+ | 1.4481 | 3.0 | 84 | 1.4312 | 0.2381 |
71
+ | 1.3982 | 4.0 | 112 | 1.3919 | 0.2619 |
72
+ | 1.3867 | 5.0 | 140 | 1.4053 | 0.2619 |
73
+ | 1.382 | 6.0 | 168 | 1.3617 | 0.2619 |
74
+ | 1.2911 | 7.0 | 196 | 1.5439 | 0.4048 |
75
+ | 1.1486 | 8.0 | 224 | 1.1564 | 0.4286 |
76
+ | 1.0554 | 9.0 | 252 | 1.0568 | 0.4762 |
77
+ | 1.0402 | 10.0 | 280 | 0.8946 | 0.6190 |
78
+ | 0.9192 | 11.0 | 308 | 0.7214 | 0.7381 |
79
+ | 1.0116 | 12.0 | 336 | 0.8931 | 0.6905 |
80
+ | 0.9735 | 13.0 | 364 | 0.8359 | 0.6905 |
81
+ | 0.9105 | 14.0 | 392 | 0.6761 | 0.7619 |
82
+ | 0.8218 | 15.0 | 420 | 0.6339 | 0.7857 |
83
+ | 0.8745 | 16.0 | 448 | 0.7396 | 0.7619 |
84
+ | 0.8355 | 17.0 | 476 | 0.7738 | 0.7381 |
85
+ | 0.8644 | 18.0 | 504 | 0.6532 | 0.7619 |
86
+ | 0.8014 | 19.0 | 532 | 0.7016 | 0.7381 |
87
+ | 0.8685 | 20.0 | 560 | 0.7175 | 0.7381 |
88
+ | 0.7709 | 21.0 | 588 | 0.6588 | 0.7619 |
89
+ | 0.778 | 22.0 | 616 | 0.8635 | 0.7381 |
90
+ | 0.8232 | 23.0 | 644 | 0.6385 | 0.7143 |
91
+ | 0.891 | 24.0 | 672 | 0.7133 | 0.6667 |
92
+ | 0.714 | 25.0 | 700 | 0.6807 | 0.6905 |
93
+ | 0.6766 | 26.0 | 728 | 0.9128 | 0.6429 |
94
+ | 0.734 | 27.0 | 756 | 0.7515 | 0.6905 |
95
+ | 0.7087 | 28.0 | 784 | 0.6378 | 0.6905 |
96
+ | 0.6295 | 29.0 | 812 | 0.9113 | 0.6667 |
97
+ | 0.6414 | 30.0 | 840 | 0.9201 | 0.6190 |
98
+ | 0.6359 | 31.0 | 868 | 0.7354 | 0.7143 |
99
+ | 0.6485 | 32.0 | 896 | 0.6558 | 0.6429 |
100
+ | 0.6242 | 33.0 | 924 | 0.7790 | 0.6429 |
101
+ | 0.647 | 34.0 | 952 | 1.0490 | 0.5952 |
102
+ | 0.6524 | 35.0 | 980 | 0.7508 | 0.6667 |
103
+ | 0.5325 | 36.0 | 1008 | 0.9344 | 0.6667 |
104
+ | 0.476 | 37.0 | 1036 | 1.0580 | 0.5952 |
105
+ | 0.4941 | 38.0 | 1064 | 0.9380 | 0.7143 |
106
+ | 0.4232 | 39.0 | 1092 | 1.0384 | 0.5476 |
107
+ | 0.4302 | 40.0 | 1120 | 1.0844 | 0.6190 |
108
+ | 0.4057 | 41.0 | 1148 | 1.3995 | 0.5952 |
109
+ | 0.3483 | 42.0 | 1176 | 1.4823 | 0.5476 |
110
+ | 0.3043 | 43.0 | 1204 | 1.2186 | 0.6667 |
111
+ | 0.2598 | 44.0 | 1232 | 1.3028 | 0.5952 |
112
+ | 0.2113 | 45.0 | 1260 | 1.5042 | 0.6190 |
113
+ | 0.2104 | 46.0 | 1288 | 1.6174 | 0.5952 |
114
+ | 0.1769 | 47.0 | 1316 | 1.5011 | 0.6429 |
115
+ | 0.1341 | 48.0 | 1344 | 1.6784 | 0.5714 |
116
+ | 0.1239 | 49.0 | 1372 | 1.6694 | 0.5952 |
117
+ | 0.1545 | 50.0 | 1400 | 1.6694 | 0.5952 |
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:ecaf657bff21ede1c0aa1e5d35fdbc26436587cf6f2af2c3e8e4029c42026e34
3
  size 86691704
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12ed4ebb4efe6773112441be5fdf82043d447e8ff8ee5044873346e2fdd71413
3
  size 86691704