Hugging Face's logo

hkivancoral
/
hushem_1x_deit_tiny_rms_lr00001_fold1

Image Classification
Transformers
TensorBoard
Safetensors
vit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
hkivancoral commited on
Commit
b474243
•
1 Parent(s): fdff90c

End of training

Browse files
Files changed (2) hide show
  1. README.md +53 -39
  2. model.safetensors +1 -1
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
- value: 0.6666666666666666
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -32,8 +32,8 @@ should probably proofread and complete it, then remove this comment. -->
32
 
33
  This model is a fine-tuned version of [facebook/deit-tiny-patch16-224](https://huggingface.co/facebook/deit-tiny-patch16-224) on the imagefolder dataset.
34
  It achieves the following results on the evaluation set:
35
- - Loss: 1.0041
36
- - Accuracy: 0.6667
37
 
38
  ## Model description
39
 
@@ -56,8 +56,6 @@ The following hyperparameters were used during training:
56
  - train_batch_size: 32
57
  - eval_batch_size: 32
58
  - seed: 42
59
- - gradient_accumulation_steps: 4
60
- - total_train_batch_size: 128
61
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
62
  - lr_scheduler_type: linear
63
  - lr_scheduler_warmup_ratio: 0.1
@@ -67,40 +65,56 @@ The following hyperparameters were used during training:
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
- | No log | 0.67 | 1 | 1.7459 | 0.2667 |
71
- | No log | 2.0 | 3 | 1.4578 | 0.3111 |
72
- | No log | 2.67 | 4 | 1.4179 | 0.3333 |
73
- | No log | 4.0 | 6 | 1.3720 | 0.3333 |
74
- | No log | 4.67 | 7 | 1.2817 | 0.3778 |
75
- | No log | 6.0 | 9 | 1.2475 | 0.5333 |
76
- | 1.1452 | 6.67 | 10 | 1.3553 | 0.3556 |
77
- | 1.1452 | 8.0 | 12 | 1.2165 | 0.4222 |
78
- | 1.1452 | 8.67 | 13 | 1.1259 | 0.5778 |
79
- | 1.1452 | 10.0 | 15 | 1.1917 | 0.4667 |
80
- | 1.1452 | 10.67 | 16 | 1.0971 | 0.5111 |
81
- | 1.1452 | 12.0 | 18 | 1.0749 | 0.5111 |
82
- | 1.1452 | 12.67 | 19 | 1.0701 | 0.4889 |
83
- | 0.4031 | 14.0 | 21 | 1.0259 | 0.5333 |
84
- | 0.4031 | 14.67 | 22 | 1.2004 | 0.4222 |
85
- | 0.4031 | 16.0 | 24 | 1.0966 | 0.4667 |
86
- | 0.4031 | 16.67 | 25 | 0.9736 | 0.5333 |
87
- | 0.4031 | 18.0 | 27 | 1.0248 | 0.5556 |
88
- | 0.4031 | 18.67 | 28 | 0.9806 | 0.6222 |
89
- | 0.1191 | 20.0 | 30 | 0.9437 | 0.6222 |
90
- | 0.1191 | 20.67 | 31 | 1.0574 | 0.5778 |
91
- | 0.1191 | 22.0 | 33 | 1.0173 | 0.6 |
92
- | 0.1191 | 22.67 | 34 | 0.9322 | 0.6222 |
93
- | 0.1191 | 24.0 | 36 | 0.9638 | 0.6222 |
94
- | 0.1191 | 24.67 | 37 | 1.0436 | 0.6 |
95
- | 0.1191 | 26.0 | 39 | 1.0020 | 0.6222 |
96
- | 0.0416 | 26.67 | 40 | 0.9820 | 0.6 |
97
- | 0.0416 | 28.0 | 42 | 0.9872 | 0.6222 |
98
- | 0.0416 | 28.67 | 43 | 1.0109 | 0.6222 |
99
- | 0.0416 | 30.0 | 45 | 0.9982 | 0.6444 |
100
- | 0.0416 | 30.67 | 46 | 0.9968 | 0.6222 |
101
- | 0.0416 | 32.0 | 48 | 1.0043 | 0.6667 |
102
- | 0.0416 | 32.67 | 49 | 1.0074 | 0.6667 |
103
- | 0.0206 | 33.33 | 50 | 1.0041 | 0.6667 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
104
 
105
 
106
  ### Framework versions
 
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
+ value: 0.6888888888888889
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
32
 
33
  This model is a fine-tuned version of [facebook/deit-tiny-patch16-224](https://huggingface.co/facebook/deit-tiny-patch16-224) on the imagefolder dataset.
34
  It achieves the following results on the evaluation set:
35
+ - Loss: 1.2449
36
+ - Accuracy: 0.6889
37
 
38
  ## Model description
39
 
 
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
 
65
 
66
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
67
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
68
+ | No log | 1.0 | 6 | 1.2771 | 0.4 |
69
+ | 1.263 | 2.0 | 12 | 1.0784 | 0.5556 |
70
+ | 1.263 | 3.0 | 18 | 0.9616 | 0.5556 |
71
+ | 0.5461 | 4.0 | 24 | 1.0339 | 0.6889 |
72
+ | 0.2446 | 5.0 | 30 | 0.9939 | 0.6667 |
73
+ | 0.2446 | 6.0 | 36 | 1.2442 | 0.4889 |
74
+ | 0.0817 | 7.0 | 42 | 0.7980 | 0.6222 |
75
+ | 0.0817 | 8.0 | 48 | 0.8675 | 0.6444 |
76
+ | 0.0302 | 9.0 | 54 | 0.8969 | 0.6889 |
77
+ | 0.009 | 10.0 | 60 | 0.9399 | 0.6222 |
78
+ | 0.009 | 11.0 | 66 | 1.0591 | 0.7111 |
79
+ | 0.0037 | 12.0 | 72 | 1.0283 | 0.6667 |
80
+ | 0.0037 | 13.0 | 78 | 1.0855 | 0.6667 |
81
+ | 0.0025 | 14.0 | 84 | 1.1121 | 0.6667 |
82
+ | 0.0019 | 15.0 | 90 | 1.1082 | 0.6667 |
83
+ | 0.0019 | 16.0 | 96 | 1.1158 | 0.6667 |
84
+ | 0.0015 | 17.0 | 102 | 1.1382 | 0.6667 |
85
+ | 0.0015 | 18.0 | 108 | 1.1574 | 0.6667 |
86
+ | 0.0013 | 19.0 | 114 | 1.1739 | 0.6667 |
87
+ | 0.0011 | 20.0 | 120 | 1.1736 | 0.6667 |
88
+ | 0.0011 | 21.0 | 126 | 1.1594 | 0.6889 |
89
+ | 0.001 | 22.0 | 132 | 1.1738 | 0.6889 |
90
+ | 0.001 | 23.0 | 138 | 1.1962 | 0.6667 |
91
+ | 0.0009 | 24.0 | 144 | 1.1951 | 0.6889 |
92
+ | 0.0008 | 25.0 | 150 | 1.2004 | 0.6889 |
93
+ | 0.0008 | 26.0 | 156 | 1.1996 | 0.6889 |
94
+ | 0.0008 | 27.0 | 162 | 1.2076 | 0.6889 |
95
+ | 0.0008 | 28.0 | 168 | 1.2144 | 0.6889 |
96
+ | 0.0007 | 29.0 | 174 | 1.2117 | 0.6889 |
97
+ | 0.0007 | 30.0 | 180 | 1.2204 | 0.6889 |
98
+ | 0.0007 | 31.0 | 186 | 1.2217 | 0.6889 |
99
+ | 0.0006 | 32.0 | 192 | 1.2270 | 0.6889 |
100
+ | 0.0006 | 33.0 | 198 | 1.2321 | 0.6889 |
101
+ | 0.0006 | 34.0 | 204 | 1.2307 | 0.6889 |
102
+ | 0.0006 | 35.0 | 210 | 1.2313 | 0.6889 |
103
+ | 0.0006 | 36.0 | 216 | 1.2374 | 0.6889 |
104
+ | 0.0006 | 37.0 | 222 | 1.2446 | 0.6889 |
105
+ | 0.0006 | 38.0 | 228 | 1.2471 | 0.6889 |
106
+ | 0.0005 | 39.0 | 234 | 1.2452 | 0.6889 |
107
+ | 0.0006 | 40.0 | 240 | 1.2458 | 0.6889 |
108
+ | 0.0006 | 41.0 | 246 | 1.2454 | 0.6889 |
109
+ | 0.0005 | 42.0 | 252 | 1.2449 | 0.6889 |
110
+ | 0.0005 | 43.0 | 258 | 1.2449 | 0.6889 |
111
+ | 0.0005 | 44.0 | 264 | 1.2449 | 0.6889 |
112
+ | 0.0005 | 45.0 | 270 | 1.2449 | 0.6889 |
113
+ | 0.0005 | 46.0 | 276 | 1.2449 | 0.6889 |
114
+ | 0.0005 | 47.0 | 282 | 1.2449 | 0.6889 |
115
+ | 0.0005 | 48.0 | 288 | 1.2449 | 0.6889 |
116
+ | 0.0005 | 49.0 | 294 | 1.2449 | 0.6889 |
117
+ | 0.0005 | 50.0 | 300 | 1.2449 | 0.6889 |
118
 
119
 
120
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:171d6dcc9acdb0ed09743edfec3d013d60b684ff2702f65f48112c910de1829e
3
  size 22123464
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ceee280472ab0549d17681682256d24273209cdc59a78d0264a9905c8511c16
3
  size 22123464