Hugging Face's logo

itsLeen
/
finetuned-fake-food

Image Classification
Transformers
TensorBoard
Safetensors
vit
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
itsLeen commited on
Commit
08b38cd
•
1 Parent(s): d64532b

Model save

Browse files
Files changed (8) hide show
  1. README.md +27 -109
  2. model.safetensors +1 -1
  3. runs/Oct01_10-26-33_a59caee1d103/events.out.tfevents.1727778405.a59caee1d103.4704.0 +3 -0
  4. runs/Oct01_10-27-03_a59caee1d103/events.out.tfevents.1727778433.a59caee1d103.4704.1 +3 -0
  5. runs/Oct01_10-28-36_a59caee1d103/events.out.tfevents.1727778524.a59caee1d103.4704.2 +3 -0
  6. runs/Oct01_10-37-37_a59caee1d103/events.out.tfevents.1727779068.a59caee1d103.4704.3 +3 -0
  7. runs/Oct01_10-42-26_a59caee1d103/events.out.tfevents.1727779356.a59caee1d103.4704.4 +3 -0
  8. training_args.bin +1 -1
README.md CHANGED
@@ -3,13 +3,27 @@ library_name: transformers
3
  license: apache-2.0
4
  base_model: google/vit-base-patch16-224-in21k
5
  tags:
6
- - image-classification
7
  - generated_from_trainer
 
 
8
  metrics:
9
  - accuracy
10
  model-index:
11
  - name: finetuned-fake-food
12
- results: []
 
 
 
 
 
 
 
 
 
 
 
 
 
13
  ---
14
 
15
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -17,10 +31,10 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  # finetuned-fake-food
19
 
20
- 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 indian_food_images dataset.
21
  It achieves the following results on the evaluation set:
22
- - Loss: 0.1348
23
- - Accuracy: 0.9563
24
 
25
  ## Model description
26
 
@@ -40,122 +54,26 @@ More information needed
40
 
41
  The following hyperparameters were used during training:
42
  - learning_rate: 0.0002
43
- - train_batch_size: 16
44
  - eval_batch_size: 8
45
  - seed: 42
46
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
  - lr_scheduler_type: linear
48
- - num_epochs: 10
49
  - mixed_precision_training: Native AMP
50
 
51
  ### Training results
52
 
53
- | Training Loss | Epoch | Step | Validation Loss | Accuracy |
54
- |:-------------:|:------:|:----:|:---------------:|:--------:|
55
- | 0.3831 | 0.1010 | 100 | 0.2663 | 0.8912 |
56
- | 0.3699 | 0.2020 | 200 | 0.2570 | 0.8990 |
57
- | 0.2135 | 0.3030 | 300 | 0.6753 | 0.7837 |
58
- | 0.214 | 0.4040 | 400 | 0.2690 | 0.8901 |
59
- | 0.1947 | 0.5051 | 500 | 0.2533 | 0.9112 |
60
- | 0.3618 | 0.6061 | 600 | 0.3738 | 0.8571 |
61
- | 0.2065 | 0.7071 | 700 | 0.2919 | 0.8919 |
62
- | 0.3103 | 0.8081 | 800 | 0.2165 | 0.9169 |
63
- | 0.1479 | 0.9091 | 900 | 0.2135 | 0.9173 |
64
- | 0.2421 | 1.0101 | 1000 | 0.2187 | 0.9184 |
65
- | 0.2264 | 1.1111 | 1100 | 0.1888 | 0.9205 |
66
- | 0.1664 | 1.2121 | 1200 | 0.2607 | 0.8876 |
67
- | 0.2049 | 1.3131 | 1300 | 0.2502 | 0.9005 |
68
- | 0.1503 | 1.4141 | 1400 | 0.2305 | 0.9177 |
69
- | 0.1846 | 1.5152 | 1500 | 0.1881 | 0.9219 |
70
- | 0.1571 | 1.6162 | 1600 | 0.1788 | 0.9284 |
71
- | 0.4091 | 1.7172 | 1700 | 0.2228 | 0.9216 |
72
- | 0.2954 | 1.8182 | 1800 | 0.1653 | 0.9366 |
73
- | 0.1366 | 1.9192 | 1900 | 0.1529 | 0.9420 |
74
- | 0.1657 | 2.0202 | 2000 | 0.1745 | 0.9255 |
75
- | 0.2531 | 2.1212 | 2100 | 0.1744 | 0.9381 |
76
- | 0.152 | 2.2222 | 2200 | 0.2513 | 0.8951 |
77
- | 0.145 | 2.3232 | 2300 | 0.1718 | 0.9302 |
78
- | 0.202 | 2.4242 | 2400 | 0.2436 | 0.9033 |
79
- | 0.1346 | 2.5253 | 2500 | 0.1839 | 0.9234 |
80
- | 0.1554 | 2.6263 | 2600 | 0.1447 | 0.9463 |
81
- | 0.183 | 2.7273 | 2700 | 0.2474 | 0.8822 |
82
- | 0.0972 | 2.8283 | 2800 | 0.2223 | 0.9205 |
83
- | 0.1073 | 2.9293 | 2900 | 0.1860 | 0.9345 |
84
- | 0.1824 | 3.0303 | 3000 | 0.2324 | 0.9194 |
85
- | 0.1221 | 3.1313 | 3100 | 0.1475 | 0.9449 |
86
- | 0.1039 | 3.2323 | 3200 | 0.1480 | 0.9427 |
87
- | 0.276 | 3.3333 | 3300 | 0.1591 | 0.9402 |
88
- | 0.2498 | 3.4343 | 3400 | 0.2447 | 0.9098 |
89
- | 0.1453 | 3.5354 | 3500 | 0.1556 | 0.9416 |
90
- | 0.1794 | 3.6364 | 3600 | 0.2272 | 0.9083 |
91
- | 0.1467 | 3.7374 | 3700 | 0.1673 | 0.9413 |
92
- | 0.1372 | 3.8384 | 3800 | 0.1763 | 0.9341 |
93
- | 0.2283 | 3.9394 | 3900 | 0.1671 | 0.9373 |
94
- | 0.164 | 4.0404 | 4000 | 0.1490 | 0.9477 |
95
- | 0.1513 | 4.1414 | 4100 | 0.1547 | 0.9488 |
96
- | 0.0991 | 4.2424 | 4200 | 0.1536 | 0.9431 |
97
- | 0.1419 | 4.3434 | 4300 | 0.1568 | 0.9445 |
98
- | 0.1452 | 4.4444 | 4400 | 0.2328 | 0.9320 |
99
- | 0.1445 | 4.5455 | 4500 | 0.1351 | 0.9513 |
100
- | 0.1366 | 4.6465 | 4600 | 0.1571 | 0.9416 |
101
- | 0.097 | 4.7475 | 4700 | 0.1506 | 0.9424 |
102
- | 0.0603 | 4.8485 | 4800 | 0.1435 | 0.9499 |
103
- | 0.1179 | 4.9495 | 4900 | 0.1754 | 0.9363 |
104
- | 0.1948 | 5.0505 | 5000 | 0.1609 | 0.9402 |
105
- | 0.1021 | 5.1515 | 5100 | 0.1566 | 0.9459 |
106
- | 0.0652 | 5.2525 | 5200 | 0.1564 | 0.9481 |
107
- | 0.1029 | 5.3535 | 5300 | 0.1410 | 0.9492 |
108
- | 0.1014 | 5.4545 | 5400 | 0.1490 | 0.9531 |
109
- | 0.1338 | 5.5556 | 5500 | 0.1865 | 0.9406 |
110
- | 0.0844 | 5.6566 | 5600 | 0.1631 | 0.9456 |
111
- | 0.1059 | 5.7576 | 5700 | 0.1738 | 0.9409 |
112
- | 0.0788 | 5.8586 | 5800 | 0.1801 | 0.9370 |
113
- | 0.0941 | 5.9596 | 5900 | 0.1575 | 0.9495 |
114
- | 0.112 | 6.0606 | 6000 | 0.1796 | 0.9470 |
115
- | 0.0691 | 6.1616 | 6100 | 0.1697 | 0.9499 |
116
- | 0.1385 | 6.2626 | 6200 | 0.1348 | 0.9563 |
117
- | 0.1173 | 6.3636 | 6300 | 0.1522 | 0.9502 |
118
- | 0.046 | 6.4646 | 6400 | 0.2114 | 0.9391 |
119
- | 0.0319 | 6.5657 | 6500 | 0.1723 | 0.9477 |
120
- | 0.0757 | 6.6667 | 6600 | 0.1561 | 0.9527 |
121
- | 0.0744 | 6.7677 | 6700 | 0.1587 | 0.9567 |
122
- | 0.0341 | 6.8687 | 6800 | 0.1458 | 0.9578 |
123
- | 0.1512 | 6.9697 | 6900 | 0.1572 | 0.9531 |
124
- | 0.0153 | 7.0707 | 7000 | 0.1402 | 0.9617 |
125
- | 0.0711 | 7.1717 | 7100 | 0.1527 | 0.9610 |
126
- | 0.0453 | 7.2727 | 7200 | 0.1512 | 0.9570 |
127
- | 0.0052 | 7.3737 | 7300 | 0.1936 | 0.9520 |
128
- | 0.0477 | 7.4747 | 7400 | 0.1699 | 0.9513 |
129
- | 0.091 | 7.5758 | 7500 | 0.1628 | 0.9513 |
130
- | 0.063 | 7.6768 | 7600 | 0.1474 | 0.9578 |
131
- | 0.0497 | 7.7778 | 7700 | 0.1389 | 0.9613 |
132
- | 0.0552 | 7.8788 | 7800 | 0.2587 | 0.9381 |
133
- | 0.0364 | 7.9798 | 7900 | 0.1361 | 0.9603 |
134
- | 0.0124 | 8.0808 | 8000 | 0.1438 | 0.9606 |
135
- | 0.0703 | 8.1818 | 8100 | 0.1577 | 0.9585 |
136
- | 0.025 | 8.2828 | 8200 | 0.1943 | 0.9484 |
137
- | 0.0259 | 8.3838 | 8300 | 0.1590 | 0.9613 |
138
- | 0.0049 | 8.4848 | 8400 | 0.1521 | 0.9581 |
139
- | 0.0174 | 8.5859 | 8500 | 0.1522 | 0.9599 |
140
- | 0.0194 | 8.6869 | 8600 | 0.1456 | 0.9606 |
141
- | 0.0315 | 8.7879 | 8700 | 0.1411 | 0.9599 |
142
- | 0.0419 | 8.8889 | 8800 | 0.1426 | 0.9592 |
143
- | 0.0193 | 8.9899 | 8900 | 0.1375 | 0.9642 |
144
- | 0.0027 | 9.0909 | 9000 | 0.1379 | 0.9635 |
145
- | 0.0345 | 9.1919 | 9100 | 0.1444 | 0.9631 |
146
- | 0.0291 | 9.2929 | 9200 | 0.1492 | 0.9624 |
147
- | 0.017 | 9.3939 | 9300 | 0.1466 | 0.9635 |
148
- | 0.0269 | 9.4949 | 9400 | 0.1523 | 0.9631 |
149
- | 0.003 | 9.5960 | 9500 | 0.1445 | 0.9628 |
150
- | 0.0471 | 9.6970 | 9600 | 0.1454 | 0.9617 |
151
- | 0.0356 | 9.7980 | 9700 | 0.1452 | 0.9620 |
152
- | 0.0034 | 9.8990 | 9800 | 0.1445 | 0.9624 |
153
- | 0.0162 | 10.0 | 9900 | 0.1451 | 0.9628 |
154
 
155
 
156
  ### Framework versions
157
 
158
  - Transformers 4.44.2
159
  - Pytorch 2.4.1+cu121
160
- - Datasets 3.0.0
161
  - Tokenizers 0.19.1
 
3
  license: apache-2.0
4
  base_model: google/vit-base-patch16-224-in21k
5
  tags:
 
6
  - generated_from_trainer
7
+ datasets:
8
+ - imagefolder
9
  metrics:
10
  - accuracy
11
  model-index:
12
  - name: finetuned-fake-food
13
+ results:
14
+ - task:
15
+ name: Image Classification
16
+ type: image-classification
17
+ dataset:
18
+ name: imagefolder
19
+ type: imagefolder
20
+ config: default
21
+ split: train
22
+ args: default
23
+ metrics:
24
+ - name: Accuracy
25
+ type: accuracy
26
+ value: 0.9523809523809523
27
  ---
28
 
29
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
31
 
32
  # finetuned-fake-food
33
 
34
+ 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.
35
  It achieves the following results on the evaluation set:
36
+ - Loss: 0.2076
37
+ - Accuracy: 0.9524
38
 
39
  ## Model description
40
 
 
54
 
55
  The following hyperparameters were used during training:
56
  - learning_rate: 0.0002
57
+ - train_batch_size: 8
58
  - eval_batch_size: 8
59
  - seed: 42
60
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
61
  - lr_scheduler_type: linear
62
+ - num_epochs: 20
63
  - mixed_precision_training: Native AMP
64
 
65
  ### Training results
66
 
67
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
68
+ |:-------------:|:-------:|:----:|:---------------:|:--------:|
69
+ | 0.328 | 6.6667 | 100 | 0.3854 | 0.8571 |
70
+ | 0.1729 | 13.3333 | 200 | 0.1446 | 0.9524 |
71
+ | 0.0508 | 20.0 | 300 | 0.2076 | 0.9524 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
72
 
73
 
74
  ### Framework versions
75
 
76
  - Transformers 4.44.2
77
  - Pytorch 2.4.1+cu121
78
+ - Datasets 3.0.1
79
  - Tokenizers 0.19.1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5670d4e357d5b36b50a436e57942b3f863601dc5140d643f30384c1fab75a8df
3
  size 343223968
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57a0f42eb555cf7f84b8068d7a5570c26bb79050ac4b62a86c16f177804068bc
3
  size 343223968
runs/Oct01_10-26-33_a59caee1d103/events.out.tfevents.1727778405.a59caee1d103.4704.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb777a4c786af5790113439986d60b2689d1bf21618e8bd17d204820e00498bc
3
+ size 4872
runs/Oct01_10-27-03_a59caee1d103/events.out.tfevents.1727778433.a59caee1d103.4704.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd2d23462d09d2ce67f4b073155d0e2435e043fa84e67238b805d5f113d52849
3
+ size 4922
runs/Oct01_10-28-36_a59caee1d103/events.out.tfevents.1727778524.a59caee1d103.4704.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0af3742776c8c211bb89933259995081b03a972a80d33760d0f0384416dd02e8
3
+ size 5397
runs/Oct01_10-37-37_a59caee1d103/events.out.tfevents.1727779068.a59caee1d103.4704.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ceb2ff7184d21fd36f61494604284ebdfd585e788326aa03247713aeb045f75
3
+ size 4873
runs/Oct01_10-42-26_a59caee1d103/events.out.tfevents.1727779356.a59caee1d103.4704.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98bb5446fa48a58953318608717be01fd001607632ef608446c1c1024897972d
3
+ size 6819
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fb34530cd081c6a7f36f25b1cdcaab96cb062c10e3c23748630020fea0547ba5
3
  size 5176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:491f5ee4f5d28aebb4c244d7745661d13229ae30aa917a57c1397ff9a0e96751
3
  size 5176