Hugging Face's logo

ppicazo
/
tobikoi-classifier-alpha1

Image Classification
Transformers
Safetensors
vit
vision
Generated from Trainer
Eval Results (legacy)
Model card Files
xet
Community
ppicazo commited on
Commit
dbad192
·
1 Parent(s): 1886c4e

Model save

Browse files
Files changed (4) hide show
  1. README.md +224 -0
  2. config.json +0 -1
  3. model.safetensors +1 -1
  4. training_args.bin +1 -1
README.md ADDED
@@ -0,0 +1,224 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: google/vit-base-patch16-224-in21k
4
+ tags:
5
+ - generated_from_trainer
6
+ datasets:
7
+ - imagefolder
8
+ metrics:
9
+ - accuracy
10
+ model-index:
11
+ - name: tobikoi-classifier-alpha1
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: train
21
+ args: default
22
+ metrics:
23
+ - name: Accuracy
24
+ type: accuracy
25
+ value: 1.0
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
+ # tobikoi-classifier-alpha1
32
+
33
+ This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the imagefolder dataset.
34
+ It achieves the following results on the evaluation set:
35
+ - Accuracy: 1.0
36
+ - Loss: 0.0002
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: 2e-05
56
+ - train_batch_size: 8
57
+ - eval_batch_size: 8
58
+ - seed: 1337
59
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
60
+ - lr_scheduler_type: linear
61
+ - num_epochs: 150.0
62
+
63
+ ### Training results
64
+
65
+ | Training Loss | Epoch | Step | Accuracy | Validation Loss |
66
+ |:-------------:|:-----:|:----:|:--------:|:---------------:|
67
+ | 0.4014 | 1.0 | 54 | 0.7632 | 0.3552 |
68
+ | 0.2253 | 2.0 | 108 | 0.9737 | 0.1712 |
69
+ | 0.0768 | 3.0 | 162 | 0.9868 | 0.0763 |
70
+ | 0.0694 | 4.0 | 216 | 0.9868 | 0.0615 |
71
+ | 0.0433 | 5.0 | 270 | 0.9868 | 0.0504 |
72
+ | 0.1045 | 6.0 | 324 | 0.9868 | 0.0323 |
73
+ | 0.0148 | 7.0 | 378 | 0.9868 | 0.0436 |
74
+ | 0.0156 | 8.0 | 432 | 0.9868 | 0.0271 |
75
+ | 0.0109 | 9.0 | 486 | 0.9868 | 0.0511 |
76
+ | 0.0142 | 10.0 | 540 | 0.9868 | 0.0563 |
77
+ | 0.0307 | 11.0 | 594 | 0.9868 | 0.0633 |
78
+ | 0.0092 | 12.0 | 648 | 0.9868 | 0.0430 |
79
+ | 0.007 | 13.0 | 702 | 0.9868 | 0.0508 |
80
+ | 0.0059 | 14.0 | 756 | 0.9868 | 0.0598 |
81
+ | 0.0057 | 15.0 | 810 | 0.9868 | 0.0639 |
82
+ | 0.0513 | 16.0 | 864 | 0.9868 | 0.0579 |
83
+ | 0.0259 | 17.0 | 918 | 0.9868 | 0.0707 |
84
+ | 0.0111 | 18.0 | 972 | 0.9868 | 0.0611 |
85
+ | 0.014 | 19.0 | 1026 | 0.9868 | 0.0620 |
86
+ | 0.004 | 20.0 | 1080 | 1.0 | 0.0058 |
87
+ | 0.0036 | 21.0 | 1134 | 1.0 | 0.0044 |
88
+ | 0.0545 | 22.0 | 1188 | 1.0 | 0.0114 |
89
+ | 0.0131 | 23.0 | 1242 | 0.9868 | 0.0621 |
90
+ | 0.0651 | 24.0 | 1296 | 0.9868 | 0.0692 |
91
+ | 0.0047 | 25.0 | 1350 | 1.0 | 0.0034 |
92
+ | 0.0374 | 26.0 | 1404 | 1.0 | 0.0031 |
93
+ | 0.0482 | 27.0 | 1458 | 1.0 | 0.0045 |
94
+ | 0.0026 | 28.0 | 1512 | 1.0 | 0.0028 |
95
+ | 0.0038 | 29.0 | 1566 | 1.0 | 0.0025 |
96
+ | 0.0027 | 30.0 | 1620 | 1.0 | 0.0023 |
97
+ | 0.0145 | 31.0 | 1674 | 0.9868 | 0.0698 |
98
+ | 0.0022 | 32.0 | 1728 | 0.9868 | 0.0255 |
99
+ | 0.0025 | 33.0 | 1782 | 1.0 | 0.0095 |
100
+ | 0.0022 | 34.0 | 1836 | 0.9868 | 0.0725 |
101
+ | 0.0019 | 35.0 | 1890 | 0.9868 | 0.0592 |
102
+ | 0.0159 | 36.0 | 1944 | 0.9868 | 0.0747 |
103
+ | 0.0018 | 37.0 | 1998 | 0.9868 | 0.0244 |
104
+ | 0.0016 | 38.0 | 2052 | 1.0 | 0.0019 |
105
+ | 0.0017 | 39.0 | 2106 | 1.0 | 0.0018 |
106
+ | 0.053 | 40.0 | 2160 | 1.0 | 0.0023 |
107
+ | 0.0016 | 41.0 | 2214 | 1.0 | 0.0061 |
108
+ | 0.0015 | 42.0 | 2268 | 1.0 | 0.0102 |
109
+ | 0.0015 | 43.0 | 2322 | 1.0 | 0.0019 |
110
+ | 0.0015 | 44.0 | 2376 | 1.0 | 0.0062 |
111
+ | 0.0014 | 45.0 | 2430 | 1.0 | 0.0014 |
112
+ | 0.0015 | 46.0 | 2484 | 1.0 | 0.0015 |
113
+ | 0.0013 | 47.0 | 2538 | 0.9868 | 0.0672 |
114
+ | 0.0012 | 48.0 | 2592 | 1.0 | 0.0015 |
115
+ | 0.0012 | 49.0 | 2646 | 0.9868 | 0.0700 |
116
+ | 0.0012 | 50.0 | 2700 | 0.9868 | 0.0579 |
117
+ | 0.0011 | 51.0 | 2754 | 0.9868 | 0.0571 |
118
+ | 0.001 | 52.0 | 2808 | 0.9868 | 0.0670 |
119
+ | 0.001 | 53.0 | 2862 | 0.9868 | 0.0730 |
120
+ | 0.0013 | 54.0 | 2916 | 0.9868 | 0.0135 |
121
+ | 0.001 | 55.0 | 2970 | 0.9868 | 0.0836 |
122
+ | 0.0009 | 56.0 | 3024 | 1.0 | 0.0010 |
123
+ | 0.0009 | 57.0 | 3078 | 0.9868 | 0.0122 |
124
+ | 0.001 | 58.0 | 3132 | 0.9868 | 0.0105 |
125
+ | 0.0017 | 59.0 | 3186 | 1.0 | 0.0074 |
126
+ | 0.0009 | 60.0 | 3240 | 1.0 | 0.0010 |
127
+ | 0.0009 | 61.0 | 3294 | 1.0 | 0.0009 |
128
+ | 0.0381 | 62.0 | 3348 | 1.0 | 0.0020 |
129
+ | 0.0008 | 63.0 | 3402 | 1.0 | 0.0008 |
130
+ | 0.0099 | 64.0 | 3456 | 1.0 | 0.0008 |
131
+ | 0.0007 | 65.0 | 3510 | 0.9868 | 0.0757 |
132
+ | 0.0008 | 66.0 | 3564 | 0.9868 | 0.0764 |
133
+ | 0.0007 | 67.0 | 3618 | 0.9737 | 0.1257 |
134
+ | 0.0007 | 68.0 | 3672 | 0.9868 | 0.0098 |
135
+ | 0.0736 | 69.0 | 3726 | 1.0 | 0.0008 |
136
+ | 0.0007 | 70.0 | 3780 | 0.9868 | 0.0605 |
137
+ | 0.0006 | 71.0 | 3834 | 1.0 | 0.0012 |
138
+ | 0.001 | 72.0 | 3888 | 0.9737 | 0.1666 |
139
+ | 0.0042 | 73.0 | 3942 | 1.0 | 0.0007 |
140
+ | 0.0006 | 74.0 | 3996 | 1.0 | 0.0007 |
141
+ | 0.0007 | 75.0 | 4050 | 1.0 | 0.0007 |
142
+ | 0.0006 | 76.0 | 4104 | 0.9868 | 0.0331 |
143
+ | 0.0006 | 77.0 | 4158 | 0.9868 | 0.0169 |
144
+ | 0.0345 | 78.0 | 4212 | 1.0 | 0.0006 |
145
+ | 0.0005 | 79.0 | 4266 | 0.9868 | 0.0762 |
146
+ | 0.0005 | 80.0 | 4320 | 1.0 | 0.0007 |
147
+ | 0.0005 | 81.0 | 4374 | 1.0 | 0.0005 |
148
+ | 0.0005 | 82.0 | 4428 | 1.0 | 0.0006 |
149
+ | 0.0005 | 83.0 | 4482 | 1.0 | 0.0005 |
150
+ | 0.0005 | 84.0 | 4536 | 1.0 | 0.0005 |
151
+ | 0.0047 | 85.0 | 4590 | 1.0 | 0.0007 |
152
+ | 0.0005 | 86.0 | 4644 | 1.0 | 0.0005 |
153
+ | 0.0005 | 87.0 | 4698 | 1.0 | 0.0005 |
154
+ | 0.0004 | 88.0 | 4752 | 1.0 | 0.0004 |
155
+ | 0.0004 | 89.0 | 4806 | 1.0 | 0.0004 |
156
+ | 0.0005 | 90.0 | 4860 | 1.0 | 0.0005 |
157
+ | 0.0004 | 91.0 | 4914 | 1.0 | 0.0005 |
158
+ | 0.0067 | 92.0 | 4968 | 1.0 | 0.0004 |
159
+ | 0.0004 | 93.0 | 5022 | 1.0 | 0.0004 |
160
+ | 0.0004 | 94.0 | 5076 | 1.0 | 0.0004 |
161
+ | 0.0004 | 95.0 | 5130 | 1.0 | 0.0004 |
162
+ | 0.0004 | 96.0 | 5184 | 1.0 | 0.0004 |
163
+ | 0.0004 | 97.0 | 5238 | 1.0 | 0.0004 |
164
+ | 0.0004 | 98.0 | 5292 | 1.0 | 0.0004 |
165
+ | 0.0003 | 99.0 | 5346 | 1.0 | 0.0004 |
166
+ | 0.0003 | 100.0 | 5400 | 1.0 | 0.0003 |
167
+ | 0.0003 | 101.0 | 5454 | 1.0 | 0.0004 |
168
+ | 0.0004 | 102.0 | 5508 | 1.0 | 0.0005 |
169
+ | 0.0004 | 103.0 | 5562 | 1.0 | 0.0005 |
170
+ | 0.0004 | 104.0 | 5616 | 1.0 | 0.0004 |
171
+ | 0.0006 | 105.0 | 5670 | 1.0 | 0.0003 |
172
+ | 0.0005 | 106.0 | 5724 | 1.0 | 0.0003 |
173
+ | 0.0003 | 107.0 | 5778 | 1.0 | 0.0003 |
174
+ | 0.0003 | 108.0 | 5832 | 1.0 | 0.0003 |
175
+ | 0.0003 | 109.0 | 5886 | 1.0 | 0.0003 |
176
+ | 0.0003 | 110.0 | 5940 | 1.0 | 0.0003 |
177
+ | 0.0003 | 111.0 | 5994 | 1.0 | 0.0003 |
178
+ | 0.0003 | 112.0 | 6048 | 1.0 | 0.0003 |
179
+ | 0.0003 | 113.0 | 6102 | 1.0 | 0.0003 |
180
+ | 0.0003 | 114.0 | 6156 | 1.0 | 0.0003 |
181
+ | 0.0003 | 115.0 | 6210 | 1.0 | 0.0003 |
182
+ | 0.0003 | 116.0 | 6264 | 1.0 | 0.0003 |
183
+ | 0.0003 | 117.0 | 6318 | 1.0 | 0.0003 |
184
+ | 0.0003 | 118.0 | 6372 | 1.0 | 0.0003 |
185
+ | 0.0002 | 119.0 | 6426 | 1.0 | 0.0002 |
186
+ | 0.0002 | 120.0 | 6480 | 1.0 | 0.0002 |
187
+ | 0.0002 | 121.0 | 6534 | 1.0 | 0.0002 |
188
+ | 0.0003 | 122.0 | 6588 | 1.0 | 0.0002 |
189
+ | 0.0002 | 123.0 | 6642 | 1.0 | 0.0002 |
190
+ | 0.0002 | 124.0 | 6696 | 1.0 | 0.0002 |
191
+ | 0.0002 | 125.0 | 6750 | 1.0 | 0.0002 |
192
+ | 0.0002 | 126.0 | 6804 | 1.0 | 0.0002 |
193
+ | 0.0712 | 127.0 | 6858 | 1.0 | 0.0002 |
194
+ | 0.0002 | 128.0 | 6912 | 1.0 | 0.0002 |
195
+ | 0.0002 | 129.0 | 6966 | 1.0 | 0.0002 |
196
+ | 0.0002 | 130.0 | 7020 | 1.0 | 0.0002 |
197
+ | 0.0002 | 131.0 | 7074 | 1.0 | 0.0002 |
198
+ | 0.0002 | 132.0 | 7128 | 1.0 | 0.0002 |
199
+ | 0.0002 | 133.0 | 7182 | 1.0 | 0.0002 |
200
+ | 0.0002 | 134.0 | 7236 | 1.0 | 0.0002 |
201
+ | 0.0002 | 135.0 | 7290 | 1.0 | 0.0002 |
202
+ | 0.0003 | 136.0 | 7344 | 1.0 | 0.0002 |
203
+ | 0.0002 | 137.0 | 7398 | 1.0 | 0.0002 |
204
+ | 0.0002 | 138.0 | 7452 | 1.0 | 0.0002 |
205
+ | 0.0028 | 139.0 | 7506 | 1.0 | 0.0002 |
206
+ | 0.0006 | 140.0 | 7560 | 1.0 | 0.0002 |
207
+ | 0.0002 | 141.0 | 7614 | 1.0 | 0.0002 |
208
+ | 0.0002 | 142.0 | 7668 | 1.0 | 0.0002 |
209
+ | 0.0004 | 143.0 | 7722 | 1.0 | 0.0002 |
210
+ | 0.0002 | 144.0 | 7776 | 1.0 | 0.0002 |
211
+ | 0.0002 | 145.0 | 7830 | 1.0 | 0.0002 |
212
+ | 0.1028 | 146.0 | 7884 | 1.0 | 0.0002 |
213
+ | 0.0002 | 147.0 | 7938 | 1.0 | 0.0002 |
214
+ | 0.0002 | 148.0 | 7992 | 1.0 | 0.0002 |
215
+ | 0.0002 | 149.0 | 8046 | 1.0 | 0.0002 |
216
+ | 0.0002 | 150.0 | 8100 | 1.0 | 0.0002 |
217
+
218
+
219
+ ### Framework versions
220
+
221
+ - Transformers 4.36.0.dev0
222
+ - Pytorch 2.1.1+cu121
223
+ - Datasets 2.15.0
224
+ - Tokenizers 0.15.0
config.json CHANGED
@@ -26,7 +26,6 @@
26
  "num_channels": 3,
27
  "num_hidden_layers": 12,
28
  "patch_size": 16,
29
- "problem_type": "single_label_classification",
30
  "qkv_bias": true,
31
  "torch_dtype": "float32",
32
  "transformers_version": "4.36.0.dev0"
 
26
  "num_channels": 3,
27
  "num_hidden_layers": 12,
28
  "patch_size": 16,
 
29
  "qkv_bias": true,
30
  "torch_dtype": "float32",
31
  "transformers_version": "4.36.0.dev0"
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:374248cd69dfe6e3ccc44e35cb0265c46c1f8b0580fbf5dd392ca4b230f74644
3
  size 343223968
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c49a4d280b6ce0e14a2c2b116b44cb893ac9fecda0fb20a731014e334b8397a
3
  size 343223968
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6d8aeec3ec2d15e6446d07b17e4559b1a330f255380a99dd6a4488cba6d79581
3
  size 4728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be005dd615a9c7754c3c54a7d9adec68002561ca5bb4a766285e5d8433fbdeaf
3
  size 4728