Hugging Face's logo

hkivancoral
/
smids_1x_deit_tiny_sgd_001_fold5

Image Classification
Transformers
TensorBoard
Safetensors
vit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
hkivancoral commited on
Commit
b56e0ec
•
1 Parent(s): e7a2d65

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: smids_1x_deit_tiny_sgd_001_fold5
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: 0.855
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_1x_deit_tiny_sgd_001_fold5
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: 0.3402
36
+ - Accuracy: 0.855
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
+ | 1.0561 | 1.0 | 75 | 1.0620 | 0.43 |
69
+ | 0.937 | 2.0 | 150 | 0.9594 | 0.51 |
70
+ | 0.8543 | 3.0 | 225 | 0.8655 | 0.62 |
71
+ | 0.8165 | 4.0 | 300 | 0.7890 | 0.6667 |
72
+ | 0.7134 | 5.0 | 375 | 0.7178 | 0.7017 |
73
+ | 0.7528 | 6.0 | 450 | 0.6594 | 0.715 |
74
+ | 0.6452 | 7.0 | 525 | 0.6058 | 0.75 |
75
+ | 0.597 | 8.0 | 600 | 0.5655 | 0.7717 |
76
+ | 0.5415 | 9.0 | 675 | 0.5324 | 0.7867 |
77
+ | 0.5088 | 10.0 | 750 | 0.5114 | 0.8117 |
78
+ | 0.5609 | 11.0 | 825 | 0.4871 | 0.8067 |
79
+ | 0.4661 | 12.0 | 900 | 0.4691 | 0.8117 |
80
+ | 0.4495 | 13.0 | 975 | 0.4552 | 0.8217 |
81
+ | 0.4956 | 14.0 | 1050 | 0.4435 | 0.8217 |
82
+ | 0.4383 | 15.0 | 1125 | 0.4330 | 0.83 |
83
+ | 0.3764 | 16.0 | 1200 | 0.4243 | 0.8317 |
84
+ | 0.4263 | 17.0 | 1275 | 0.4146 | 0.83 |
85
+ | 0.39 | 18.0 | 1350 | 0.4087 | 0.83 |
86
+ | 0.4056 | 19.0 | 1425 | 0.4021 | 0.8367 |
87
+ | 0.4427 | 20.0 | 1500 | 0.3960 | 0.835 |
88
+ | 0.3559 | 21.0 | 1575 | 0.3906 | 0.84 |
89
+ | 0.3313 | 22.0 | 1650 | 0.3861 | 0.8383 |
90
+ | 0.3291 | 23.0 | 1725 | 0.3822 | 0.8383 |
91
+ | 0.3377 | 24.0 | 1800 | 0.3784 | 0.8383 |
92
+ | 0.3287 | 25.0 | 1875 | 0.3755 | 0.8433 |
93
+ | 0.3695 | 26.0 | 1950 | 0.3722 | 0.8467 |
94
+ | 0.3651 | 27.0 | 2025 | 0.3680 | 0.845 |
95
+ | 0.3421 | 28.0 | 2100 | 0.3650 | 0.845 |
96
+ | 0.3095 | 29.0 | 2175 | 0.3617 | 0.85 |
97
+ | 0.3232 | 30.0 | 2250 | 0.3592 | 0.8467 |
98
+ | 0.2955 | 31.0 | 2325 | 0.3570 | 0.8467 |
99
+ | 0.273 | 32.0 | 2400 | 0.3554 | 0.8483 |
100
+ | 0.3566 | 33.0 | 2475 | 0.3529 | 0.8467 |
101
+ | 0.3239 | 34.0 | 2550 | 0.3508 | 0.85 |
102
+ | 0.3231 | 35.0 | 2625 | 0.3501 | 0.8517 |
103
+ | 0.2755 | 36.0 | 2700 | 0.3491 | 0.8517 |
104
+ | 0.2727 | 37.0 | 2775 | 0.3485 | 0.8433 |
105
+ | 0.2931 | 38.0 | 2850 | 0.3470 | 0.845 |
106
+ | 0.2624 | 39.0 | 2925 | 0.3453 | 0.85 |
107
+ | 0.3211 | 40.0 | 3000 | 0.3440 | 0.855 |
108
+ | 0.2988 | 41.0 | 3075 | 0.3437 | 0.855 |
109
+ | 0.3248 | 42.0 | 3150 | 0.3424 | 0.855 |
110
+ | 0.3151 | 43.0 | 3225 | 0.3419 | 0.855 |
111
+ | 0.3064 | 44.0 | 3300 | 0.3415 | 0.8533 |
112
+ | 0.2827 | 45.0 | 3375 | 0.3410 | 0.8533 |
113
+ | 0.2824 | 46.0 | 3450 | 0.3410 | 0.8517 |
114
+ | 0.2636 | 47.0 | 3525 | 0.3406 | 0.8567 |
115
+ | 0.275 | 48.0 | 3600 | 0.3403 | 0.8567 |
116
+ | 0.2811 | 49.0 | 3675 | 0.3402 | 0.8567 |
117
+ | 0.2711 | 50.0 | 3750 | 0.3402 | 0.855 |
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:de3c7418ab9ec94909cae50f5b91e07e7591df76f43b2f8163ee5c3643dd0383
3
  size 22122692
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a99c93a4a4c0449ad108643db948f3d947297c3c6f46a3b2d4f3649afe18134
3
  size 22122692