Hugging Face's logo

hkivancoral
/
smids_10x_beit_large_sgd_00001_fold3

Image Classification
Transformers
PyTorch
beit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
hkivancoral commited on
Commit
26fc1da
·
1 Parent(s): ca44c92

End of training

Browse files
Files changed (2) hide show
  1. README.md +125 -0
  2. pytorch_model.bin +1 -1
README.md ADDED
@@ -0,0 +1,125 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: microsoft/beit-large-patch16-224
4
+ tags:
5
+ - generated_from_trainer
6
+ datasets:
7
+ - imagefolder
8
+ metrics:
9
+ - accuracy
10
+ model-index:
11
+ - name: smids_10x_beit_large_sgd_00001_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: 0.6316666666666667
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_10x_beit_large_sgd_00001_fold3
32
+
33
+ This model is a fine-tuned version of [microsoft/beit-large-patch16-224](https://huggingface.co/microsoft/beit-large-patch16-224) on the imagefolder dataset.
34
+ It achieves the following results on the evaluation set:
35
+ - Loss: 0.8246
36
+ - Accuracy: 0.6317
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: 1e-05
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
+ | 1.2284 | 1.0 | 750 | 1.2241 | 0.3517 |
69
+ | 1.1457 | 2.0 | 1500 | 1.1930 | 0.365 |
70
+ | 1.1396 | 3.0 | 2250 | 1.1661 | 0.3783 |
71
+ | 1.0897 | 4.0 | 3000 | 1.1425 | 0.385 |
72
+ | 1.025 | 5.0 | 3750 | 1.1215 | 0.3883 |
73
+ | 1.0158 | 6.0 | 4500 | 1.1022 | 0.3883 |
74
+ | 0.9975 | 7.0 | 5250 | 1.0842 | 0.4017 |
75
+ | 1.0278 | 8.0 | 6000 | 1.0673 | 0.4067 |
76
+ | 0.9784 | 9.0 | 6750 | 1.0514 | 0.4133 |
77
+ | 0.9157 | 10.0 | 7500 | 1.0366 | 0.4317 |
78
+ | 0.9554 | 11.0 | 8250 | 1.0228 | 0.4467 |
79
+ | 0.8899 | 12.0 | 9000 | 1.0096 | 0.4667 |
80
+ | 0.9379 | 13.0 | 9750 | 0.9973 | 0.4767 |
81
+ | 0.944 | 14.0 | 10500 | 0.9856 | 0.4867 |
82
+ | 0.9071 | 15.0 | 11250 | 0.9745 | 0.4983 |
83
+ | 0.8922 | 16.0 | 12000 | 0.9641 | 0.505 |
84
+ | 0.8643 | 17.0 | 12750 | 0.9544 | 0.5133 |
85
+ | 0.8278 | 18.0 | 13500 | 0.9449 | 0.52 |
86
+ | 0.9039 | 19.0 | 14250 | 0.9361 | 0.5317 |
87
+ | 0.8559 | 20.0 | 15000 | 0.9279 | 0.5383 |
88
+ | 0.8179 | 21.0 | 15750 | 0.9199 | 0.545 |
89
+ | 0.8248 | 22.0 | 16500 | 0.9124 | 0.56 |
90
+ | 0.8379 | 23.0 | 17250 | 0.9052 | 0.56 |
91
+ | 0.864 | 24.0 | 18000 | 0.8985 | 0.565 |
92
+ | 0.8458 | 25.0 | 18750 | 0.8922 | 0.575 |
93
+ | 0.8014 | 26.0 | 19500 | 0.8861 | 0.5783 |
94
+ | 0.7589 | 27.0 | 20250 | 0.8805 | 0.5883 |
95
+ | 0.8089 | 28.0 | 21000 | 0.8752 | 0.595 |
96
+ | 0.8337 | 29.0 | 21750 | 0.8701 | 0.5983 |
97
+ | 0.7734 | 30.0 | 22500 | 0.8654 | 0.6033 |
98
+ | 0.7463 | 31.0 | 23250 | 0.8610 | 0.6033 |
99
+ | 0.7746 | 32.0 | 24000 | 0.8569 | 0.6067 |
100
+ | 0.8126 | 33.0 | 24750 | 0.8532 | 0.6117 |
101
+ | 0.7894 | 34.0 | 25500 | 0.8496 | 0.615 |
102
+ | 0.7634 | 35.0 | 26250 | 0.8463 | 0.615 |
103
+ | 0.7765 | 36.0 | 27000 | 0.8433 | 0.6167 |
104
+ | 0.8136 | 37.0 | 27750 | 0.8405 | 0.6217 |
105
+ | 0.8117 | 38.0 | 28500 | 0.8380 | 0.6217 |
106
+ | 0.7707 | 39.0 | 29250 | 0.8357 | 0.6217 |
107
+ | 0.7678 | 40.0 | 30000 | 0.8337 | 0.6267 |
108
+ | 0.7823 | 41.0 | 30750 | 0.8319 | 0.6283 |
109
+ | 0.7728 | 42.0 | 31500 | 0.8303 | 0.63 |
110
+ | 0.7705 | 43.0 | 32250 | 0.8289 | 0.6283 |
111
+ | 0.7342 | 44.0 | 33000 | 0.8277 | 0.6283 |
112
+ | 0.7107 | 45.0 | 33750 | 0.8267 | 0.6283 |
113
+ | 0.7263 | 46.0 | 34500 | 0.8259 | 0.63 |
114
+ | 0.7101 | 47.0 | 35250 | 0.8253 | 0.63 |
115
+ | 0.7724 | 48.0 | 36000 | 0.8249 | 0.6317 |
116
+ | 0.7714 | 49.0 | 36750 | 0.8247 | 0.6317 |
117
+ | 0.7461 | 50.0 | 37500 | 0.8246 | 0.6317 |
118
+
119
+
120
+ ### Framework versions
121
+
122
+ - Transformers 4.32.1
123
+ - Pytorch 2.1.0+cu121
124
+ - Datasets 2.12.0
125
+ - Tokenizers 0.13.2
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6a76b31121cd8e898649f801a9ae63cc716cca106fa16131ce164863b7f728ba
3
  size 1213785638
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d6c723a30603335147d92ed6f955ac99b866f44ede92e75536ec3677bbf53e9
3
  size 1213785638