Hugging Face's logo

SiddharthaM
/
beit-base-patch16-224-pt22k-ft22k-rim_one-new

Image Classification
Transformers
PyTorch
TensorBoard
beit
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
1
SiddharthaM commited on
Commit
26b7c66
·
1 Parent(s): 6047fac

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +104 -0
README.md ADDED
@@ -0,0 +1,104 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ datasets:
6
+ - imagefolder
7
+ metrics:
8
+ - accuracy
9
+ model-index:
10
+ - name: beit-base-patch16-224-pt22k-ft22k-rim_one-new
11
+ results:
12
+ - task:
13
+ name: Image Classification
14
+ type: image-classification
15
+ dataset:
16
+ name: imagefolder
17
+ type: imagefolder
18
+ args: default
19
+ metrics:
20
+ - name: Accuracy
21
+ type: accuracy
22
+ value: 0.8767123287671232
23
+ ---
24
+
25
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
26
+ should probably proofread and complete it, then remove this comment. -->
27
+
28
+ # beit-base-patch16-224-pt22k-ft22k-rim_one-new
29
+
30
+ This model is a fine-tuned version of [microsoft/beit-base-patch16-224-pt22k-ft22k](https://huggingface.co/microsoft/beit-base-patch16-224-pt22k-ft22k) on the imagefolder dataset.
31
+ It achieves the following results on the evaluation set:
32
+ - Loss: 0.4550
33
+ - Accuracy: 0.8767
34
+
35
+ ## Model description
36
+
37
+ More information needed
38
+
39
+ ## Intended uses & limitations
40
+
41
+ More information needed
42
+
43
+ ## Training and evaluation data
44
+
45
+ More information needed
46
+
47
+ ## Training procedure
48
+
49
+ ### Training hyperparameters
50
+
51
+ The following hyperparameters were used during training:
52
+ - learning_rate: 5e-05
53
+ - train_batch_size: 32
54
+ - eval_batch_size: 32
55
+ - seed: 42
56
+ - gradient_accumulation_steps: 4
57
+ - total_train_batch_size: 128
58
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
59
+ - lr_scheduler_type: linear
60
+ - lr_scheduler_warmup_ratio: 0.1
61
+ - num_epochs: 30
62
+
63
+ ### Training results
64
+
65
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
66
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
67
+ | No log | 0.73 | 2 | 0.2411 | 0.9178 |
68
+ | No log | 1.73 | 4 | 0.2182 | 0.8973 |
69
+ | No log | 2.73 | 6 | 0.3085 | 0.8973 |
70
+ | No log | 3.73 | 8 | 0.2794 | 0.8973 |
71
+ | 0.1392 | 4.73 | 10 | 0.2398 | 0.9110 |
72
+ | 0.1392 | 5.73 | 12 | 0.2925 | 0.8973 |
73
+ | 0.1392 | 6.73 | 14 | 0.2798 | 0.9110 |
74
+ | 0.1392 | 7.73 | 16 | 0.2184 | 0.9178 |
75
+ | 0.1392 | 8.73 | 18 | 0.3007 | 0.9110 |
76
+ | 0.0416 | 9.73 | 20 | 0.3344 | 0.9041 |
77
+ | 0.0416 | 10.73 | 22 | 0.3626 | 0.9110 |
78
+ | 0.0416 | 11.73 | 24 | 0.4842 | 0.8904 |
79
+ | 0.0416 | 12.73 | 26 | 0.3664 | 0.8973 |
80
+ | 0.0416 | 13.73 | 28 | 0.3458 | 0.9110 |
81
+ | 0.0263 | 14.73 | 30 | 0.2810 | 0.9110 |
82
+ | 0.0263 | 15.73 | 32 | 0.4695 | 0.8699 |
83
+ | 0.0263 | 16.73 | 34 | 0.3723 | 0.9041 |
84
+ | 0.0263 | 17.73 | 36 | 0.3447 | 0.9041 |
85
+ | 0.0263 | 18.73 | 38 | 0.3708 | 0.8904 |
86
+ | 0.0264 | 19.73 | 40 | 0.4052 | 0.9110 |
87
+ | 0.0264 | 20.73 | 42 | 0.4492 | 0.9041 |
88
+ | 0.0264 | 21.73 | 44 | 0.4649 | 0.8904 |
89
+ | 0.0264 | 22.73 | 46 | 0.4061 | 0.9178 |
90
+ | 0.0264 | 23.73 | 48 | 0.4136 | 0.9110 |
91
+ | 0.0139 | 24.73 | 50 | 0.4183 | 0.8973 |
92
+ | 0.0139 | 25.73 | 52 | 0.4504 | 0.8904 |
93
+ | 0.0139 | 26.73 | 54 | 0.4368 | 0.8973 |
94
+ | 0.0139 | 27.73 | 56 | 0.4711 | 0.9110 |
95
+ | 0.0139 | 28.73 | 58 | 0.3928 | 0.9110 |
96
+ | 0.005 | 29.73 | 60 | 0.4550 | 0.8767 |
97
+
98
+
99
+ ### Framework versions
100
+
101
+ - Transformers 4.20.1
102
+ - Pytorch 1.11.0+cu113
103
+ - Datasets 2.3.2
104
+ - Tokenizers 0.12.1