Hugging Face's logo

hkivancoral
/
smids_1x_deit_tiny_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
984e8b9
·
1 Parent(s): 38bba80

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_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: 0.7333333333333333
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_rms_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: 0.9960
36
+ - Accuracy: 0.7333
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
+ | 1.1598 | 1.0 | 75 | 4.0739 | 0.3033 |
69
+ | 1.1025 | 2.0 | 150 | 1.1472 | 0.335 |
70
+ | 1.0056 | 3.0 | 225 | 0.8843 | 0.5617 |
71
+ | 0.9034 | 4.0 | 300 | 0.8985 | 0.5117 |
72
+ | 0.8764 | 5.0 | 375 | 0.9613 | 0.5017 |
73
+ | 0.9617 | 6.0 | 450 | 0.9074 | 0.5317 |
74
+ | 0.8578 | 7.0 | 525 | 0.8240 | 0.5717 |
75
+ | 0.8424 | 8.0 | 600 | 0.8437 | 0.5617 |
76
+ | 0.8025 | 9.0 | 675 | 0.7942 | 0.5833 |
77
+ | 0.7777 | 10.0 | 750 | 0.7683 | 0.57 |
78
+ | 0.8053 | 11.0 | 825 | 0.7474 | 0.5983 |
79
+ | 0.818 | 12.0 | 900 | 0.7555 | 0.61 |
80
+ | 0.8018 | 13.0 | 975 | 0.7629 | 0.5833 |
81
+ | 0.8411 | 14.0 | 1050 | 0.7216 | 0.635 |
82
+ | 0.6416 | 15.0 | 1125 | 0.8742 | 0.56 |
83
+ | 0.8084 | 16.0 | 1200 | 0.7814 | 0.6083 |
84
+ | 0.7505 | 17.0 | 1275 | 0.7600 | 0.6183 |
85
+ | 0.6996 | 18.0 | 1350 | 0.7346 | 0.6283 |
86
+ | 0.7648 | 19.0 | 1425 | 0.7240 | 0.6617 |
87
+ | 0.6916 | 20.0 | 1500 | 0.6768 | 0.6767 |
88
+ | 0.7556 | 21.0 | 1575 | 0.7263 | 0.6617 |
89
+ | 0.6471 | 22.0 | 1650 | 0.7297 | 0.6583 |
90
+ | 0.752 | 23.0 | 1725 | 0.7501 | 0.635 |
91
+ | 0.7349 | 24.0 | 1800 | 0.6751 | 0.6883 |
92
+ | 0.6802 | 25.0 | 1875 | 0.6689 | 0.6817 |
93
+ | 0.6239 | 26.0 | 1950 | 0.8871 | 0.5817 |
94
+ | 0.6865 | 27.0 | 2025 | 0.6485 | 0.7033 |
95
+ | 0.6138 | 28.0 | 2100 | 0.6457 | 0.7233 |
96
+ | 0.6707 | 29.0 | 2175 | 0.6937 | 0.6833 |
97
+ | 0.6824 | 30.0 | 2250 | 0.6688 | 0.7033 |
98
+ | 0.5913 | 31.0 | 2325 | 0.6725 | 0.715 |
99
+ | 0.5797 | 32.0 | 2400 | 0.6508 | 0.7167 |
100
+ | 0.5524 | 33.0 | 2475 | 0.7048 | 0.7 |
101
+ | 0.4736 | 34.0 | 2550 | 0.6807 | 0.6933 |
102
+ | 0.5263 | 35.0 | 2625 | 0.6317 | 0.7233 |
103
+ | 0.5348 | 36.0 | 2700 | 0.6398 | 0.7367 |
104
+ | 0.5082 | 37.0 | 2775 | 0.6440 | 0.7183 |
105
+ | 0.4972 | 38.0 | 2850 | 0.6697 | 0.7167 |
106
+ | 0.4567 | 39.0 | 2925 | 0.6947 | 0.73 |
107
+ | 0.4313 | 40.0 | 3000 | 0.6527 | 0.7383 |
108
+ | 0.4762 | 41.0 | 3075 | 0.6875 | 0.74 |
109
+ | 0.4293 | 42.0 | 3150 | 0.7259 | 0.7333 |
110
+ | 0.4594 | 43.0 | 3225 | 0.7531 | 0.7367 |
111
+ | 0.379 | 44.0 | 3300 | 0.7792 | 0.7383 |
112
+ | 0.3265 | 45.0 | 3375 | 0.7882 | 0.74 |
113
+ | 0.2807 | 46.0 | 3450 | 0.8615 | 0.7367 |
114
+ | 0.2733 | 47.0 | 3525 | 0.9438 | 0.73 |
115
+ | 0.2273 | 48.0 | 3600 | 0.9312 | 0.73 |
116
+ | 0.2189 | 49.0 | 3675 | 0.9889 | 0.7383 |
117
+ | 0.1609 | 50.0 | 3750 | 0.9960 | 0.7333 |
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 sha256:03d02cb05fd2b409e2b955c96c01c513bf296e511976e77d8d279a9f80f228ce
3
  size 22122692
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aad69e943f0a40931f7577c372f9d865c29c4a3385ca3384adee7d4867fdbfe4
3
  size 22122692