Hugging Face's logo

hkivancoral
/
hushem_40x_deit_small_sgd_001_fold1

Image Classification
Transformers
PyTorch
vit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
hkivancoral commited on
Commit
45315b6
•
1 Parent(s): 219696d

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-small-patch16-224
4
+ tags:
5
+ - generated_from_trainer
6
+ datasets:
7
+ - imagefolder
8
+ metrics:
9
+ - accuracy
10
+ model-index:
11
+ - name: hushem_40x_deit_small_sgd_001_fold1
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: 0.7777777777777778
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_40x_deit_small_sgd_001_fold1
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: 0.6398
36
+ - Accuracy: 0.7778
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
+ | 1.1952 | 1.0 | 215 | 1.4276 | 0.3778 |
69
+ | 1.0042 | 2.0 | 430 | 1.4162 | 0.2889 |
70
+ | 0.8488 | 3.0 | 645 | 1.3544 | 0.3778 |
71
+ | 0.7465 | 4.0 | 860 | 1.2674 | 0.4889 |
72
+ | 0.6036 | 5.0 | 1075 | 1.1735 | 0.5111 |
73
+ | 0.5355 | 6.0 | 1290 | 1.0934 | 0.5556 |
74
+ | 0.4712 | 7.0 | 1505 | 1.0208 | 0.6 |
75
+ | 0.3805 | 8.0 | 1720 | 0.9372 | 0.6222 |
76
+ | 0.3422 | 9.0 | 1935 | 0.8901 | 0.6444 |
77
+ | 0.2964 | 10.0 | 2150 | 0.8433 | 0.6667 |
78
+ | 0.2485 | 11.0 | 2365 | 0.7909 | 0.6889 |
79
+ | 0.2255 | 12.0 | 2580 | 0.7693 | 0.7111 |
80
+ | 0.1717 | 13.0 | 2795 | 0.7309 | 0.7556 |
81
+ | 0.1588 | 14.0 | 3010 | 0.7252 | 0.7556 |
82
+ | 0.1672 | 15.0 | 3225 | 0.6986 | 0.7333 |
83
+ | 0.1097 | 16.0 | 3440 | 0.6863 | 0.7333 |
84
+ | 0.1167 | 17.0 | 3655 | 0.6753 | 0.7556 |
85
+ | 0.0952 | 18.0 | 3870 | 0.6754 | 0.7556 |
86
+ | 0.0806 | 19.0 | 4085 | 0.6768 | 0.7556 |
87
+ | 0.0794 | 20.0 | 4300 | 0.6533 | 0.7556 |
88
+ | 0.0649 | 21.0 | 4515 | 0.6553 | 0.7556 |
89
+ | 0.0639 | 22.0 | 4730 | 0.6451 | 0.7556 |
90
+ | 0.0578 | 23.0 | 4945 | 0.6498 | 0.7556 |
91
+ | 0.0439 | 24.0 | 5160 | 0.6457 | 0.7556 |
92
+ | 0.0437 | 25.0 | 5375 | 0.6423 | 0.7556 |
93
+ | 0.038 | 26.0 | 5590 | 0.6342 | 0.7556 |
94
+ | 0.0346 | 27.0 | 5805 | 0.6184 | 0.7556 |
95
+ | 0.0278 | 28.0 | 6020 | 0.6299 | 0.7556 |
96
+ | 0.035 | 29.0 | 6235 | 0.6381 | 0.7556 |
97
+ | 0.0226 | 30.0 | 6450 | 0.6272 | 0.7556 |
98
+ | 0.0178 | 31.0 | 6665 | 0.6325 | 0.7556 |
99
+ | 0.019 | 32.0 | 6880 | 0.6409 | 0.7556 |
100
+ | 0.0184 | 33.0 | 7095 | 0.6323 | 0.7778 |
101
+ | 0.0238 | 34.0 | 7310 | 0.6091 | 0.7556 |
102
+ | 0.0126 | 35.0 | 7525 | 0.6363 | 0.7778 |
103
+ | 0.0156 | 36.0 | 7740 | 0.6253 | 0.7556 |
104
+ | 0.0165 | 37.0 | 7955 | 0.6280 | 0.7556 |
105
+ | 0.0106 | 38.0 | 8170 | 0.6294 | 0.7778 |
106
+ | 0.0189 | 39.0 | 8385 | 0.6262 | 0.7778 |
107
+ | 0.0098 | 40.0 | 8600 | 0.6454 | 0.7556 |
108
+ | 0.0098 | 41.0 | 8815 | 0.6342 | 0.7778 |
109
+ | 0.0112 | 42.0 | 9030 | 0.6356 | 0.7778 |
110
+ | 0.0128 | 43.0 | 9245 | 0.6416 | 0.7778 |
111
+ | 0.0115 | 44.0 | 9460 | 0.6374 | 0.7778 |
112
+ | 0.0087 | 45.0 | 9675 | 0.6423 | 0.7778 |
113
+ | 0.0077 | 46.0 | 9890 | 0.6446 | 0.7778 |
114
+ | 0.0087 | 47.0 | 10105 | 0.6388 | 0.7778 |
115
+ | 0.0071 | 48.0 | 10320 | 0.6394 | 0.7778 |
116
+ | 0.0087 | 49.0 | 10535 | 0.6404 | 0.7778 |
117
+ | 0.0108 | 50.0 | 10750 | 0.6398 | 0.7778 |
118
+
119
+
120
+ ### Framework versions
121
+
122
+ - Transformers 4.32.1
123
+ - Pytorch 2.1.0+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 sha256:0cc54e88b7fe1591dbdccee3259348d0f60aba487945f6dfe4415dba2dd830a9
3
  size 86737194
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4b64234c7b01f362afc0b1276aaf8a056d059471d8433e4dbd150163877d323
3
  size 86737194