hkivancoral commited on
Commit
0895e13
1 Parent(s): 9a22c06

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_fold2
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: 0.6472545757071547
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_fold2
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: 0.7989
36
+ - Accuracy: 0.6473
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
+ | 1.1712 | 1.0 | 750 | 1.2053 | 0.3594 |
69
+ | 1.1095 | 2.0 | 1500 | 1.1744 | 0.3677 |
70
+ | 1.079 | 3.0 | 2250 | 1.1476 | 0.3677 |
71
+ | 1.0868 | 4.0 | 3000 | 1.1238 | 0.3760 |
72
+ | 1.0188 | 5.0 | 3750 | 1.1026 | 0.4043 |
73
+ | 1.0313 | 6.0 | 4500 | 1.0830 | 0.4176 |
74
+ | 0.9867 | 7.0 | 5250 | 1.0650 | 0.4343 |
75
+ | 0.9922 | 8.0 | 6000 | 1.0482 | 0.4509 |
76
+ | 1.0089 | 9.0 | 6750 | 1.0324 | 0.4626 |
77
+ | 0.9248 | 10.0 | 7500 | 1.0176 | 0.4809 |
78
+ | 0.9924 | 11.0 | 8250 | 1.0037 | 0.4942 |
79
+ | 0.9341 | 12.0 | 9000 | 0.9905 | 0.5042 |
80
+ | 0.9032 | 13.0 | 9750 | 0.9777 | 0.5158 |
81
+ | 0.9223 | 14.0 | 10500 | 0.9658 | 0.5241 |
82
+ | 0.8875 | 15.0 | 11250 | 0.9546 | 0.5275 |
83
+ | 0.8812 | 16.0 | 12000 | 0.9440 | 0.5408 |
84
+ | 0.8383 | 17.0 | 12750 | 0.9339 | 0.5524 |
85
+ | 0.8368 | 18.0 | 13500 | 0.9242 | 0.5557 |
86
+ | 0.8681 | 19.0 | 14250 | 0.9150 | 0.5657 |
87
+ | 0.8552 | 20.0 | 15000 | 0.9065 | 0.5674 |
88
+ | 0.8564 | 21.0 | 15750 | 0.8983 | 0.5691 |
89
+ | 0.8254 | 22.0 | 16500 | 0.8905 | 0.5740 |
90
+ | 0.842 | 23.0 | 17250 | 0.8831 | 0.5807 |
91
+ | 0.802 | 24.0 | 18000 | 0.8761 | 0.5857 |
92
+ | 0.8617 | 25.0 | 18750 | 0.8694 | 0.5973 |
93
+ | 0.8384 | 26.0 | 19500 | 0.8631 | 0.6057 |
94
+ | 0.8257 | 27.0 | 20250 | 0.8572 | 0.6106 |
95
+ | 0.8327 | 28.0 | 21000 | 0.8516 | 0.6156 |
96
+ | 0.8111 | 29.0 | 21750 | 0.8464 | 0.6173 |
97
+ | 0.7892 | 30.0 | 22500 | 0.8414 | 0.6206 |
98
+ | 0.7974 | 31.0 | 23250 | 0.8368 | 0.6256 |
99
+ | 0.8791 | 32.0 | 24000 | 0.8325 | 0.6256 |
100
+ | 0.7583 | 33.0 | 24750 | 0.8285 | 0.6306 |
101
+ | 0.7714 | 34.0 | 25500 | 0.8248 | 0.6323 |
102
+ | 0.7891 | 35.0 | 26250 | 0.8214 | 0.6356 |
103
+ | 0.7659 | 36.0 | 27000 | 0.8182 | 0.6389 |
104
+ | 0.8096 | 37.0 | 27750 | 0.8154 | 0.6356 |
105
+ | 0.7644 | 38.0 | 28500 | 0.8128 | 0.6373 |
106
+ | 0.8029 | 39.0 | 29250 | 0.8104 | 0.6406 |
107
+ | 0.7912 | 40.0 | 30000 | 0.8082 | 0.6406 |
108
+ | 0.7766 | 41.0 | 30750 | 0.8063 | 0.6423 |
109
+ | 0.7693 | 42.0 | 31500 | 0.8047 | 0.6439 |
110
+ | 0.735 | 43.0 | 32250 | 0.8032 | 0.6456 |
111
+ | 0.7637 | 44.0 | 33000 | 0.8020 | 0.6456 |
112
+ | 0.7733 | 45.0 | 33750 | 0.8010 | 0.6473 |
113
+ | 0.7268 | 46.0 | 34500 | 0.8002 | 0.6473 |
114
+ | 0.8097 | 47.0 | 35250 | 0.7996 | 0.6473 |
115
+ | 0.7648 | 48.0 | 36000 | 0.7991 | 0.6473 |
116
+ | 0.7593 | 49.0 | 36750 | 0.7989 | 0.6473 |
117
+ | 0.7579 | 50.0 | 37500 | 0.7989 | 0.6473 |
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 sha256:7476bb56dadd78ae8770d895d7fbac1eda1c17875462dbae3abe5bb19c8b4955
3
  size 1213785638
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a1c465d953d194aeadb8d32915bd15703e23a20ab26839e6d7183a0bf0fb9ea
3
  size 1213785638