omarhkh commited on
Commit
8227f2f
1 Parent(s): 1085b52

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +106 -0
README.md ADDED
@@ -0,0 +1,106 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: resnet-50-finetuned-omars5
11
+ results:
12
+ - task:
13
+ name: Image Classification
14
+ type: image-classification
15
+ dataset:
16
+ name: imagefolder
17
+ type: imagefolder
18
+ config: default
19
+ split: train
20
+ args: default
21
+ metrics:
22
+ - name: Accuracy
23
+ type: accuracy
24
+ value: 0.8844984802431611
25
+ ---
26
+
27
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
28
+ should probably proofread and complete it, then remove this comment. -->
29
+
30
+ # resnet-50-finetuned-omars5
31
+
32
+ This model is a fine-tuned version of [microsoft/resnet-50](https://huggingface.co/microsoft/resnet-50) on the imagefolder dataset.
33
+ It achieves the following results on the evaluation set:
34
+ - Loss: 0.5844
35
+ - Accuracy: 0.8845
36
+
37
+ ## Model description
38
+
39
+ More information needed
40
+
41
+ ## Intended uses & limitations
42
+
43
+ More information needed
44
+
45
+ ## Training and evaluation data
46
+
47
+ More information needed
48
+
49
+ ## Training procedure
50
+
51
+ ### Training hyperparameters
52
+
53
+ The following hyperparameters were used during training:
54
+ - learning_rate: 0.0005
55
+ - train_batch_size: 8
56
+ - eval_batch_size: 8
57
+ - seed: 42
58
+ - gradient_accumulation_steps: 4
59
+ - total_train_batch_size: 32
60
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
61
+ - lr_scheduler_type: linear
62
+ - lr_scheduler_warmup_ratio: 0.1
63
+ - num_epochs: 30
64
+
65
+ ### Training results
66
+
67
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
68
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
69
+ | 1.3431 | 0.99 | 92 | 1.2810 | 0.5836 |
70
+ | 1.0465 | 2.0 | 185 | 0.8740 | 0.8176 |
71
+ | 0.8755 | 2.99 | 277 | 0.6467 | 0.7994 |
72
+ | 0.7459 | 4.0 | 370 | 0.5379 | 0.8480 |
73
+ | 0.7983 | 4.99 | 462 | 0.4385 | 0.8207 |
74
+ | 0.7692 | 6.0 | 555 | 0.5795 | 0.7842 |
75
+ | 0.5158 | 6.99 | 647 | 0.4936 | 0.8207 |
76
+ | 0.625 | 8.0 | 740 | 0.5316 | 0.8298 |
77
+ | 0.511 | 8.99 | 832 | 0.5202 | 0.8845 |
78
+ | 0.5025 | 10.0 | 925 | 0.5260 | 0.8784 |
79
+ | 0.508 | 10.99 | 1017 | 0.5307 | 0.8632 |
80
+ | 0.4652 | 12.0 | 1110 | 0.6060 | 0.8480 |
81
+ | 0.4432 | 12.99 | 1202 | 0.5051 | 0.8845 |
82
+ | 0.3373 | 14.0 | 1295 | 0.8695 | 0.8845 |
83
+ | 0.3968 | 14.99 | 1387 | 0.6805 | 0.8571 |
84
+ | 0.4268 | 16.0 | 1480 | 0.6541 | 0.8815 |
85
+ | 0.3029 | 16.99 | 1572 | 0.5710 | 0.8906 |
86
+ | 0.3801 | 18.0 | 1665 | 0.6499 | 0.8571 |
87
+ | 0.3545 | 18.99 | 1757 | 0.6727 | 0.8419 |
88
+ | 0.3526 | 20.0 | 1850 | 0.6542 | 0.8571 |
89
+ | 0.3458 | 20.99 | 1942 | 0.6625 | 0.8997 |
90
+ | 0.3078 | 22.0 | 2035 | 0.6551 | 0.8784 |
91
+ | 0.3677 | 22.99 | 2127 | 0.5953 | 0.8815 |
92
+ | 0.3386 | 24.0 | 2220 | 0.6549 | 0.8693 |
93
+ | 0.213 | 24.99 | 2312 | 0.5846 | 0.8997 |
94
+ | 0.3778 | 26.0 | 2405 | 0.6746 | 0.8602 |
95
+ | 0.3079 | 26.99 | 2497 | 0.6594 | 0.8997 |
96
+ | 0.2943 | 28.0 | 2590 | 0.6246 | 0.8815 |
97
+ | 0.2782 | 28.99 | 2682 | 0.6550 | 0.8906 |
98
+ | 0.2931 | 29.84 | 2760 | 0.5844 | 0.8845 |
99
+
100
+
101
+ ### Framework versions
102
+
103
+ - Transformers 4.30.2
104
+ - Pytorch 2.0.1+cu117
105
+ - Datasets 2.13.0
106
+ - Tokenizers 0.13.3