Hugging Face's logo

hkivancoral
/
hushem_5x_beit_base_adamax_00001_fold4

Image Classification
Transformers
TensorBoard
Safetensors
beit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
hkivancoral commited on
Commit
3a26f3e
•
1 Parent(s): 2a53dbc

End of training

Browse files
Files changed (3) hide show
  1. README.md +125 -0
  2. model.safetensors +1 -1
  3. runs/Nov28_04-31-52_0a7ba84d0833/events.out.tfevents.1701145916.0a7ba84d0833.1449.9 +2 -2
README.md ADDED
@@ -0,0 +1,125 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: microsoft/beit-base-patch16-224
4
+ tags:
5
+ - generated_from_trainer
6
+ datasets:
7
+ - imagefolder
8
+ metrics:
9
+ - accuracy
10
+ model-index:
11
+ - name: hushem_5x_beit_base_adamax_00001_fold4
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: 0.9285714285714286
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
+ # hushem_5x_beit_base_adamax_00001_fold4
32
+
33
+ This model is a fine-tuned version of [microsoft/beit-base-patch16-224](https://huggingface.co/microsoft/beit-base-patch16-224) on the imagefolder dataset.
34
+ It achieves the following results on the evaluation set:
35
+ - Loss: 0.2768
36
+ - Accuracy: 0.9286
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
+ | 1.2143 | 1.0 | 28 | 1.1034 | 0.5714 |
69
+ | 0.7775 | 2.0 | 56 | 0.7868 | 0.7143 |
70
+ | 0.4533 | 3.0 | 84 | 0.5700 | 0.8571 |
71
+ | 0.3037 | 4.0 | 112 | 0.4325 | 0.9048 |
72
+ | 0.1612 | 5.0 | 140 | 0.3176 | 0.9524 |
73
+ | 0.1058 | 6.0 | 168 | 0.2780 | 0.9524 |
74
+ | 0.0913 | 7.0 | 196 | 0.2215 | 0.9524 |
75
+ | 0.0514 | 8.0 | 224 | 0.1972 | 0.9524 |
76
+ | 0.0348 | 9.0 | 252 | 0.1996 | 0.9524 |
77
+ | 0.0351 | 10.0 | 280 | 0.1992 | 0.9524 |
78
+ | 0.0183 | 11.0 | 308 | 0.2116 | 0.9286 |
79
+ | 0.0237 | 12.0 | 336 | 0.2277 | 0.9286 |
80
+ | 0.0106 | 13.0 | 364 | 0.2270 | 0.9286 |
81
+ | 0.0108 | 14.0 | 392 | 0.2101 | 0.9524 |
82
+ | 0.0149 | 15.0 | 420 | 0.2231 | 0.9524 |
83
+ | 0.0076 | 16.0 | 448 | 0.2350 | 0.9048 |
84
+ | 0.0086 | 17.0 | 476 | 0.2204 | 0.9286 |
85
+ | 0.0033 | 18.0 | 504 | 0.2707 | 0.9286 |
86
+ | 0.0048 | 19.0 | 532 | 0.2227 | 0.9286 |
87
+ | 0.0041 | 20.0 | 560 | 0.2590 | 0.9286 |
88
+ | 0.0023 | 21.0 | 588 | 0.2904 | 0.9048 |
89
+ | 0.0045 | 22.0 | 616 | 0.2887 | 0.9286 |
90
+ | 0.0027 | 23.0 | 644 | 0.2955 | 0.9286 |
91
+ | 0.0033 | 24.0 | 672 | 0.2912 | 0.9286 |
92
+ | 0.0028 | 25.0 | 700 | 0.2636 | 0.9286 |
93
+ | 0.0018 | 26.0 | 728 | 0.2618 | 0.9286 |
94
+ | 0.0028 | 27.0 | 756 | 0.2893 | 0.9286 |
95
+ | 0.0019 | 28.0 | 784 | 0.2937 | 0.9286 |
96
+ | 0.0014 | 29.0 | 812 | 0.2912 | 0.9048 |
97
+ | 0.0031 | 30.0 | 840 | 0.2819 | 0.9048 |
98
+ | 0.0013 | 31.0 | 868 | 0.2819 | 0.9524 |
99
+ | 0.006 | 32.0 | 896 | 0.2996 | 0.9286 |
100
+ | 0.001 | 33.0 | 924 | 0.2836 | 0.9048 |
101
+ | 0.0011 | 34.0 | 952 | 0.2841 | 0.9286 |
102
+ | 0.0015 | 35.0 | 980 | 0.2638 | 0.9286 |
103
+ | 0.0022 | 36.0 | 1008 | 0.2845 | 0.9286 |
104
+ | 0.001 | 37.0 | 1036 | 0.2920 | 0.9286 |
105
+ | 0.0015 | 38.0 | 1064 | 0.2827 | 0.9286 |
106
+ | 0.0029 | 39.0 | 1092 | 0.2797 | 0.9286 |
107
+ | 0.002 | 40.0 | 1120 | 0.2954 | 0.9286 |
108
+ | 0.0017 | 41.0 | 1148 | 0.3039 | 0.9286 |
109
+ | 0.001 | 42.0 | 1176 | 0.3143 | 0.9286 |
110
+ | 0.0014 | 43.0 | 1204 | 0.3005 | 0.9286 |
111
+ | 0.0014 | 44.0 | 1232 | 0.2937 | 0.9286 |
112
+ | 0.0019 | 45.0 | 1260 | 0.2833 | 0.9286 |
113
+ | 0.0042 | 46.0 | 1288 | 0.2805 | 0.9286 |
114
+ | 0.0013 | 47.0 | 1316 | 0.2768 | 0.9286 |
115
+ | 0.0008 | 48.0 | 1344 | 0.2768 | 0.9286 |
116
+ | 0.0031 | 49.0 | 1372 | 0.2768 | 0.9286 |
117
+ | 0.0013 | 50.0 | 1400 | 0.2768 | 0.9286 |
118
+
119
+
120
+ ### Framework versions
121
+
122
+ - Transformers 4.35.2
123
+ - Pytorch 2.1.0+cu118
124
+ - Datasets 2.15.0
125
+ - Tokenizers 0.15.0
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0ed95414bc7b51423d7ed5eb0e9c98381d45b01764b58cbb2c9d8fb994790620
3
  size 343086480
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c958034d83ebc194b0d47aae82649b3a8628c5c7487bdaf7480218899b40d12
3
  size 343086480
runs/Nov28_04-31-52_0a7ba84d0833/events.out.tfevents.1701145916.0a7ba84d0833.1449.9 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1d91d3130859c4c44d576ee51ab2ccbd55b1d85e6a9bf0662c022f8be2d57922
3
- size 43013
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a99bda53c1375adaf23bd9d61330967ef170c1b2f8e62c806b270819ed39a2e4
3
+ size 43367