Hugging Face's logo

JOECHAN890
/
vit-base-beans

Image Classification
Transformers
Safetensors
vit
vision
Generated from Trainer
Model card Files
xet
Community
JOECHAN890 commited on
Commit
1644f63
·
verified ·
1 Parent(s): 068f12d

Model save

Browse files
Files changed (2) hide show
  1. README.md +55 -12
  2. model.safetensors +1 -1
README.md CHANGED
@@ -3,8 +3,6 @@ library_name: transformers
3
  license: apache-2.0
4
  base_model: google/vit-base-patch16-224-in21k
5
  tags:
6
- - image-classification
7
- - vision
8
  - generated_from_trainer
9
  metrics:
10
  - accuracy
@@ -18,9 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  # vit-base-beans
20
 
21
- 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 AI-Lab-Makerere/beans dataset.
22
  It achieves the following results on the evaluation set:
23
- - Loss: 0.0655
24
  - Accuracy: 0.9925
25
 
26
  ## Model description
@@ -46,17 +44,62 @@ The following hyperparameters were used during training:
46
  - seed: 1337
47
  - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
48
  - lr_scheduler_type: linear
49
- - num_epochs: 5.0
50
 
51
  ### Training results
52
 
53
- | Training Loss | Epoch | Step | Accuracy | Validation Loss |
54
- |:-------------:|:-----:|:----:|:--------:|:---------------:|
55
- | 0.281 | 1.0 | 130 | 0.9624 | 0.2159 |
56
- | 0.1296 | 2.0 | 260 | 0.9699 | 0.1304 |
57
- | 0.1373 | 3.0 | 390 | 0.9774 | 0.0972 |
58
- | 0.0845 | 4.0 | 520 | 0.9925 | 0.0655 |
59
- | 0.1147 | 5.0 | 650 | 0.9774 | 0.0827 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
60
 
61
 
62
  ### Framework versions
 
3
  license: apache-2.0
4
  base_model: google/vit-base-patch16-224-in21k
5
  tags:
 
 
6
  - generated_from_trainer
7
  metrics:
8
  - accuracy
 
16
 
17
  # vit-base-beans
18
 
19
+ This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.0286
22
  - Accuracy: 0.9925
23
 
24
  ## Model description
 
44
  - seed: 1337
45
  - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
46
  - lr_scheduler_type: linear
47
+ - num_epochs: 50.0
48
 
49
  ### Training results
50
 
51
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
52
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
53
+ | 0.2628 | 1.0 | 130 | 0.1949 | 0.9624 |
54
+ | 0.118 | 2.0 | 260 | 0.1251 | 0.9699 |
55
+ | 0.1361 | 3.0 | 390 | 0.0617 | 0.9925 |
56
+ | 0.0528 | 4.0 | 520 | 0.0738 | 0.9774 |
57
+ | 0.1193 | 5.0 | 650 | 0.0450 | 0.9925 |
58
+ | 0.0533 | 6.0 | 780 | 0.0440 | 0.9850 |
59
+ | 0.112 | 7.0 | 910 | 0.0817 | 0.9850 |
60
+ | 0.1805 | 8.0 | 1040 | 0.0566 | 0.9850 |
61
+ | 0.0257 | 9.0 | 1170 | 0.0193 | 0.9925 |
62
+ | 0.0132 | 10.0 | 1300 | 0.0122 | 1.0 |
63
+ | 0.0138 | 11.0 | 1430 | 0.0113 | 1.0 |
64
+ | 0.0702 | 12.0 | 1560 | 0.0733 | 0.9850 |
65
+ | 0.0631 | 13.0 | 1690 | 0.1681 | 0.9624 |
66
+ | 0.0234 | 14.0 | 1820 | 0.0080 | 1.0 |
67
+ | 0.088 | 15.0 | 1950 | 0.0077 | 1.0 |
68
+ | 0.0502 | 16.0 | 2080 | 0.0069 | 1.0 |
69
+ | 0.007 | 17.0 | 2210 | 0.0070 | 1.0 |
70
+ | 0.0787 | 18.0 | 2340 | 0.0159 | 0.9925 |
71
+ | 0.0322 | 19.0 | 2470 | 0.0927 | 0.9699 |
72
+ | 0.0051 | 20.0 | 2600 | 0.0704 | 0.9774 |
73
+ | 0.0053 | 21.0 | 2730 | 0.0051 | 1.0 |
74
+ | 0.0056 | 22.0 | 2860 | 0.0311 | 0.9925 |
75
+ | 0.0763 | 23.0 | 2990 | 0.0043 | 1.0 |
76
+ | 0.0045 | 24.0 | 3120 | 0.0045 | 1.0 |
77
+ | 0.0039 | 25.0 | 3250 | 0.0042 | 1.0 |
78
+ | 0.0041 | 26.0 | 3380 | 0.0038 | 1.0 |
79
+ | 0.0038 | 27.0 | 3510 | 0.0038 | 1.0 |
80
+ | 0.0732 | 28.0 | 3640 | 0.0368 | 0.9925 |
81
+ | 0.003 | 29.0 | 3770 | 0.0618 | 0.9774 |
82
+ | 0.003 | 30.0 | 3900 | 0.0770 | 0.9774 |
83
+ | 0.0029 | 31.0 | 4030 | 0.0280 | 0.9925 |
84
+ | 0.0027 | 32.0 | 4160 | 0.0055 | 1.0 |
85
+ | 0.0027 | 33.0 | 4290 | 0.0046 | 1.0 |
86
+ | 0.0073 | 34.0 | 4420 | 0.0027 | 1.0 |
87
+ | 0.0325 | 35.0 | 4550 | 0.0102 | 0.9925 |
88
+ | 0.003 | 36.0 | 4680 | 0.0334 | 0.9925 |
89
+ | 0.0023 | 37.0 | 4810 | 0.0319 | 0.9925 |
90
+ | 0.0042 | 38.0 | 4940 | 0.0031 | 1.0 |
91
+ | 0.0024 | 39.0 | 5070 | 0.0191 | 0.9925 |
92
+ | 0.0022 | 40.0 | 5200 | 0.0036 | 1.0 |
93
+ | 0.0029 | 41.0 | 5330 | 0.0101 | 0.9925 |
94
+ | 0.0021 | 42.0 | 5460 | 0.0144 | 0.9925 |
95
+ | 0.0021 | 43.0 | 5590 | 0.0069 | 1.0 |
96
+ | 0.065 | 44.0 | 5720 | 0.0103 | 0.9925 |
97
+ | 0.0022 | 45.0 | 5850 | 0.0109 | 0.9925 |
98
+ | 0.002 | 46.0 | 5980 | 0.0076 | 1.0 |
99
+ | 0.0021 | 47.0 | 6110 | 0.0104 | 0.9925 |
100
+ | 0.0034 | 48.0 | 6240 | 0.0231 | 0.9850 |
101
+ | 0.0578 | 49.0 | 6370 | 0.0278 | 0.9925 |
102
+ | 0.0041 | 50.0 | 6500 | 0.0286 | 0.9925 |
103
 
104
 
105
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0c3c11c7b4632f8b9cacccb7269c16536f4214e58571213a80f98a59c9fcc267
3
  size 343227052
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46b525d6bb6e83bd4f4d31862f1528286fa4cc142aa916491a376b5b43492fc7
3
  size 343227052