Hugging Face's logo

hkivancoral
/
smids_1x_deit_small_adamax_001_fold3

Image Classification
Transformers
TensorBoard
Safetensors
vit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
hkivancoral commited on
Commit
109908a
·
1 Parent(s): 65c7e4b

End of training

Browse files
Files changed (3) hide show
  1. README.md +125 -0
  2. model.safetensors +1 -1
  3. runs/Dec04_10-53-00_e7698b4f2488/events.out.tfevents.1701687181.e7698b4f2488.1907.23 +2 -2
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: smids_1x_deit_small_adamax_001_fold3
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: 0.8566666666666667
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_small_adamax_001_fold3
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: 1.1786
36
+ - Accuracy: 0.8567
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
+ | 0.6005 | 1.0 | 75 | 0.4146 | 0.83 |
69
+ | 0.4739 | 2.0 | 150 | 0.5214 | 0.7783 |
70
+ | 0.3159 | 3.0 | 225 | 0.3979 | 0.8467 |
71
+ | 0.3044 | 4.0 | 300 | 0.4320 | 0.845 |
72
+ | 0.3525 | 5.0 | 375 | 0.3215 | 0.8817 |
73
+ | 0.1872 | 6.0 | 450 | 0.4978 | 0.8267 |
74
+ | 0.2467 | 7.0 | 525 | 0.5551 | 0.8 |
75
+ | 0.1504 | 8.0 | 600 | 0.5301 | 0.8367 |
76
+ | 0.1309 | 9.0 | 675 | 0.5781 | 0.84 |
77
+ | 0.2177 | 10.0 | 750 | 0.5269 | 0.865 |
78
+ | 0.0844 | 11.0 | 825 | 0.5112 | 0.865 |
79
+ | 0.0758 | 12.0 | 900 | 0.6543 | 0.8617 |
80
+ | 0.1176 | 13.0 | 975 | 0.5860 | 0.855 |
81
+ | 0.0455 | 14.0 | 1050 | 0.7995 | 0.8317 |
82
+ | 0.0687 | 15.0 | 1125 | 0.6395 | 0.8633 |
83
+ | 0.0296 | 16.0 | 1200 | 0.8580 | 0.8517 |
84
+ | 0.0214 | 17.0 | 1275 | 0.9274 | 0.85 |
85
+ | 0.0164 | 18.0 | 1350 | 0.8318 | 0.8733 |
86
+ | 0.0192 | 19.0 | 1425 | 0.9491 | 0.8567 |
87
+ | 0.0338 | 20.0 | 1500 | 0.7653 | 0.8567 |
88
+ | 0.0007 | 21.0 | 1575 | 0.9985 | 0.8517 |
89
+ | 0.0001 | 22.0 | 1650 | 0.9967 | 0.87 |
90
+ | 0.0156 | 23.0 | 1725 | 1.1459 | 0.85 |
91
+ | 0.0033 | 24.0 | 1800 | 1.1111 | 0.8517 |
92
+ | 0.005 | 25.0 | 1875 | 1.1114 | 0.8467 |
93
+ | 0.0195 | 26.0 | 1950 | 1.0184 | 0.8617 |
94
+ | 0.0001 | 27.0 | 2025 | 1.0582 | 0.8567 |
95
+ | 0.0022 | 28.0 | 2100 | 1.1162 | 0.86 |
96
+ | 0.0 | 29.0 | 2175 | 1.1193 | 0.86 |
97
+ | 0.0 | 30.0 | 2250 | 1.1254 | 0.8567 |
98
+ | 0.0 | 31.0 | 2325 | 1.1372 | 0.86 |
99
+ | 0.0016 | 32.0 | 2400 | 1.1758 | 0.8583 |
100
+ | 0.0051 | 33.0 | 2475 | 1.1778 | 0.845 |
101
+ | 0.0047 | 34.0 | 2550 | 1.0600 | 0.8667 |
102
+ | 0.01 | 35.0 | 2625 | 1.1195 | 0.855 |
103
+ | 0.0037 | 36.0 | 2700 | 1.1381 | 0.8533 |
104
+ | 0.0025 | 37.0 | 2775 | 1.1434 | 0.855 |
105
+ | 0.0 | 38.0 | 2850 | 1.1612 | 0.8583 |
106
+ | 0.0 | 39.0 | 2925 | 1.1652 | 0.8567 |
107
+ | 0.0 | 40.0 | 3000 | 1.1711 | 0.855 |
108
+ | 0.0 | 41.0 | 3075 | 1.1589 | 0.86 |
109
+ | 0.0028 | 42.0 | 3150 | 1.1617 | 0.8617 |
110
+ | 0.0032 | 43.0 | 3225 | 1.1622 | 0.86 |
111
+ | 0.0 | 44.0 | 3300 | 1.1672 | 0.86 |
112
+ | 0.0027 | 45.0 | 3375 | 1.1668 | 0.86 |
113
+ | 0.0026 | 46.0 | 3450 | 1.1710 | 0.86 |
114
+ | 0.0057 | 47.0 | 3525 | 1.1686 | 0.86 |
115
+ | 0.0 | 48.0 | 3600 | 1.1767 | 0.8567 |
116
+ | 0.0 | 49.0 | 3675 | 1.1760 | 0.8583 |
117
+ | 0.0044 | 50.0 | 3750 | 1.1786 | 0.8567 |
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:b9997ae3a95ccff32c487b1d45e933bfa1d5d305e917b0f9568ca8ce43ee493b
3
  size 86690164
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff20903cb270f158c89bde1976f50bb5d1f598e536705fbc68c46183625d9c78
3
  size 86690164
runs/Dec04_10-53-00_e7698b4f2488/events.out.tfevents.1701687181.e7698b4f2488.1907.23 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d7d9b8ff98a580e199d0d16a34d1af7d6148d088271a21f8e9af25f2c7ae0019
3
- size 79335
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4be8c99f16bf1434c3bbcff108cc1eaa4d076fa0fbbd2590050d3aab10a2370
3
+ size 79689