Hugging Face's logo

hkivancoral
/
smids_10x_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
5f5f35f
•
1 Parent(s): e7a7b4e

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_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: 0.8019966722129783
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_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: 2.1068
36
+ - Accuracy: 0.8020
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
+ | 0.8332 | 1.0 | 750 | 0.7567 | 0.6090 |
69
+ | 0.7395 | 2.0 | 1500 | 0.7599 | 0.6123 |
70
+ | 0.682 | 3.0 | 2250 | 0.6859 | 0.6905 |
71
+ | 0.725 | 4.0 | 3000 | 0.6463 | 0.7171 |
72
+ | 0.6632 | 5.0 | 3750 | 0.6560 | 0.7238 |
73
+ | 0.5777 | 6.0 | 4500 | 0.6347 | 0.7072 |
74
+ | 0.6357 | 7.0 | 5250 | 0.6141 | 0.7321 |
75
+ | 0.595 | 8.0 | 6000 | 0.6313 | 0.7121 |
76
+ | 0.5551 | 9.0 | 6750 | 0.6406 | 0.6955 |
77
+ | 0.5544 | 10.0 | 7500 | 0.5482 | 0.7720 |
78
+ | 0.5611 | 11.0 | 8250 | 0.5288 | 0.7704 |
79
+ | 0.6632 | 12.0 | 9000 | 0.5868 | 0.7537 |
80
+ | 0.5709 | 13.0 | 9750 | 0.6149 | 0.7288 |
81
+ | 0.4511 | 14.0 | 10500 | 0.4977 | 0.8020 |
82
+ | 0.4295 | 15.0 | 11250 | 0.5625 | 0.7770 |
83
+ | 0.4618 | 16.0 | 12000 | 0.5273 | 0.7837 |
84
+ | 0.4342 | 17.0 | 12750 | 0.5207 | 0.7804 |
85
+ | 0.4253 | 18.0 | 13500 | 0.5301 | 0.7720 |
86
+ | 0.4352 | 19.0 | 14250 | 0.5236 | 0.7754 |
87
+ | 0.418 | 20.0 | 15000 | 0.5318 | 0.7804 |
88
+ | 0.4496 | 21.0 | 15750 | 0.5216 | 0.7970 |
89
+ | 0.4003 | 22.0 | 16500 | 0.5391 | 0.7720 |
90
+ | 0.4411 | 23.0 | 17250 | 0.4904 | 0.8003 |
91
+ | 0.3266 | 24.0 | 18000 | 0.5436 | 0.7854 |
92
+ | 0.3733 | 25.0 | 18750 | 0.6780 | 0.7521 |
93
+ | 0.3536 | 26.0 | 19500 | 0.5100 | 0.8003 |
94
+ | 0.4154 | 27.0 | 20250 | 0.5545 | 0.8020 |
95
+ | 0.414 | 28.0 | 21000 | 0.5841 | 0.7937 |
96
+ | 0.3146 | 29.0 | 21750 | 0.5867 | 0.7887 |
97
+ | 0.3401 | 30.0 | 22500 | 0.5923 | 0.7987 |
98
+ | 0.2331 | 31.0 | 23250 | 0.6367 | 0.7837 |
99
+ | 0.238 | 32.0 | 24000 | 0.6276 | 0.8070 |
100
+ | 0.209 | 33.0 | 24750 | 0.6337 | 0.8070 |
101
+ | 0.2121 | 34.0 | 25500 | 0.6961 | 0.7854 |
102
+ | 0.2544 | 35.0 | 26250 | 0.7936 | 0.7870 |
103
+ | 0.2442 | 36.0 | 27000 | 0.7270 | 0.7970 |
104
+ | 0.2459 | 37.0 | 27750 | 0.7553 | 0.8020 |
105
+ | 0.1428 | 38.0 | 28500 | 0.8600 | 0.7987 |
106
+ | 0.0788 | 39.0 | 29250 | 0.9727 | 0.7937 |
107
+ | 0.1811 | 40.0 | 30000 | 1.0324 | 0.7937 |
108
+ | 0.1405 | 41.0 | 30750 | 1.0037 | 0.8103 |
109
+ | 0.1282 | 42.0 | 31500 | 1.1830 | 0.7937 |
110
+ | 0.0664 | 43.0 | 32250 | 1.2624 | 0.7970 |
111
+ | 0.04 | 44.0 | 33000 | 1.4942 | 0.7987 |
112
+ | 0.0582 | 45.0 | 33750 | 1.4631 | 0.8103 |
113
+ | 0.0738 | 46.0 | 34500 | 1.6687 | 0.8120 |
114
+ | 0.0282 | 47.0 | 35250 | 1.8321 | 0.8087 |
115
+ | 0.0021 | 48.0 | 36000 | 1.9181 | 0.8087 |
116
+ | 0.01 | 49.0 | 36750 | 2.0036 | 0.8037 |
117
+ | 0.0004 | 50.0 | 37500 | 2.1068 | 0.8020 |
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:bcf9a74a2ac735313504e698c48c6a2dd5bdf189a82fb294bdcac446ac69c103
3
  size 22167850
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a7dde5ea232aaaef28f7390f9bfbecb12192c3126b754f1c45339d43eb4b80a
3
  size 22167850