Hugging Face's logo

hkivancoral
/
hushem_1x_beit_base_sgd_001_fold2

Image Classification
Transformers
TensorBoard
Safetensors
beit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
hkivancoral commited on
Commit
0c9db5d
•
1 Parent(s): 416aa5f

End of training

Browse files
Files changed (3) hide show
  1. README.md +125 -0
  2. model.safetensors +1 -1
  3. runs/Nov25_03-02-49_23c9de965386/events.out.tfevents.1700881370.23c9de965386.7636.15 +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_1x_beit_base_sgd_001_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: 0.3333333333333333
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_1x_beit_base_sgd_001_fold2
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: 1.2883
36
+ - Accuracy: 0.3333
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: 0.001
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
+ | No log | 1.0 | 6 | 1.5095 | 0.2667 |
69
+ | 1.5706 | 2.0 | 12 | 1.4767 | 0.2667 |
70
+ | 1.5706 | 3.0 | 18 | 1.4520 | 0.2667 |
71
+ | 1.4609 | 4.0 | 24 | 1.4339 | 0.3111 |
72
+ | 1.4723 | 5.0 | 30 | 1.4175 | 0.3111 |
73
+ | 1.4723 | 6.0 | 36 | 1.4043 | 0.3111 |
74
+ | 1.4256 | 7.0 | 42 | 1.3928 | 0.3111 |
75
+ | 1.4256 | 8.0 | 48 | 1.3810 | 0.3111 |
76
+ | 1.3951 | 9.0 | 54 | 1.3717 | 0.3111 |
77
+ | 1.359 | 10.0 | 60 | 1.3630 | 0.3111 |
78
+ | 1.359 | 11.0 | 66 | 1.3563 | 0.3111 |
79
+ | 1.3542 | 12.0 | 72 | 1.3514 | 0.2889 |
80
+ | 1.3542 | 13.0 | 78 | 1.3444 | 0.2889 |
81
+ | 1.3277 | 14.0 | 84 | 1.3408 | 0.2667 |
82
+ | 1.3111 | 15.0 | 90 | 1.3350 | 0.2667 |
83
+ | 1.3111 | 16.0 | 96 | 1.3320 | 0.2889 |
84
+ | 1.3054 | 17.0 | 102 | 1.3278 | 0.2889 |
85
+ | 1.3054 | 18.0 | 108 | 1.3233 | 0.2889 |
86
+ | 1.2953 | 19.0 | 114 | 1.3199 | 0.2889 |
87
+ | 1.2867 | 20.0 | 120 | 1.3171 | 0.2889 |
88
+ | 1.2867 | 21.0 | 126 | 1.3151 | 0.2889 |
89
+ | 1.2581 | 22.0 | 132 | 1.3144 | 0.2889 |
90
+ | 1.2581 | 23.0 | 138 | 1.3095 | 0.2889 |
91
+ | 1.2646 | 24.0 | 144 | 1.3068 | 0.3111 |
92
+ | 1.2188 | 25.0 | 150 | 1.3045 | 0.3111 |
93
+ | 1.2188 | 26.0 | 156 | 1.3025 | 0.3333 |
94
+ | 1.2206 | 27.0 | 162 | 1.3017 | 0.3333 |
95
+ | 1.2206 | 28.0 | 168 | 1.2992 | 0.3333 |
96
+ | 1.2061 | 29.0 | 174 | 1.2990 | 0.3333 |
97
+ | 1.2221 | 30.0 | 180 | 1.2969 | 0.3333 |
98
+ | 1.2221 | 31.0 | 186 | 1.2951 | 0.3333 |
99
+ | 1.2025 | 32.0 | 192 | 1.2945 | 0.3333 |
100
+ | 1.2025 | 33.0 | 198 | 1.2933 | 0.3333 |
101
+ | 1.2187 | 34.0 | 204 | 1.2926 | 0.3333 |
102
+ | 1.2089 | 35.0 | 210 | 1.2913 | 0.3333 |
103
+ | 1.2089 | 36.0 | 216 | 1.2899 | 0.3333 |
104
+ | 1.1998 | 37.0 | 222 | 1.2891 | 0.3333 |
105
+ | 1.1998 | 38.0 | 228 | 1.2890 | 0.3333 |
106
+ | 1.2017 | 39.0 | 234 | 1.2884 | 0.3333 |
107
+ | 1.1887 | 40.0 | 240 | 1.2883 | 0.3333 |
108
+ | 1.1887 | 41.0 | 246 | 1.2883 | 0.3333 |
109
+ | 1.1807 | 42.0 | 252 | 1.2883 | 0.3333 |
110
+ | 1.1807 | 43.0 | 258 | 1.2883 | 0.3333 |
111
+ | 1.2122 | 44.0 | 264 | 1.2883 | 0.3333 |
112
+ | 1.2003 | 45.0 | 270 | 1.2883 | 0.3333 |
113
+ | 1.2003 | 46.0 | 276 | 1.2883 | 0.3333 |
114
+ | 1.1882 | 47.0 | 282 | 1.2883 | 0.3333 |
115
+ | 1.1882 | 48.0 | 288 | 1.2883 | 0.3333 |
116
+ | 1.1992 | 49.0 | 294 | 1.2883 | 0.3333 |
117
+ | 1.1934 | 50.0 | 300 | 1.2883 | 0.3333 |
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:e7c5c89fb271b417b1c9a1b997048ed8ba12baae4d52d68bc7c80f9cba48f3bf
3
  size 343086480
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:566eb7f69a34ac59ce914587a10c8bfcfa010305f130104f4b344736c3664def
3
  size 343086480
runs/Nov25_03-02-49_23c9de965386/events.out.tfevents.1700881370.23c9de965386.7636.15 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5f12ebcd47c31a435d62f3c8d561afff211d4cd373d9d2b029f20d3665e7f959
3
- size 25146
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e74cb9db6f8ce31afd1da0a637e29a67f98297344768a29444747740be7eb96
3
+ size 25980