Hugging Face's logo

hkivancoral
/
hushem_5x_deit_base_adamax_0001_fold3

Image Classification
Transformers
TensorBoard
Safetensors
vit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
hkivancoral commited on
Commit
ccbce81
·
1 Parent(s): e117af4

End of training

Browse files
Files changed (3) hide show
  1. README.md +52 -52
  2. model.safetensors +1 -1
  3. runs/Nov21_01-51-11_d943f7bc58f8/events.out.tfevents.1700531472.d943f7bc58f8.2975.33 +2 -2
README.md CHANGED
@@ -32,7 +32,7 @@ should probably proofread and complete it, then remove this comment. -->
32
 
33
  This model is a fine-tuned version of [facebook/deit-base-patch16-224](https://huggingface.co/facebook/deit-base-patch16-224) on the imagefolder dataset.
34
  It achieves the following results on the evaluation set:
35
- - Loss: 0.5462
36
  - Accuracy: 0.8372
37
 
38
  ## Model description
@@ -52,7 +52,7 @@ More information needed
52
  ### Training hyperparameters
53
 
54
  The following hyperparameters were used during training:
55
- - learning_rate: 0.0001
56
  - train_batch_size: 32
57
  - eval_batch_size: 32
58
  - seed: 42
@@ -65,56 +65,56 @@ The following hyperparameters were used during training:
65
 
66
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
67
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
68
- | 0.9594 | 1.0 | 28 | 0.6237 | 0.7442 |
69
- | 0.1236 | 2.0 | 56 | 0.3919 | 0.7907 |
70
- | 0.0109 | 3.0 | 84 | 0.4363 | 0.8837 |
71
- | 0.0096 | 4.0 | 112 | 0.6363 | 0.8605 |
72
- | 0.0012 | 5.0 | 140 | 0.5962 | 0.8140 |
73
- | 0.0005 | 6.0 | 168 | 0.4146 | 0.8605 |
74
- | 0.0003 | 7.0 | 196 | 0.4792 | 0.8605 |
75
- | 0.0002 | 8.0 | 224 | 0.4742 | 0.8372 |
76
- | 0.0002 | 9.0 | 252 | 0.4833 | 0.8372 |
77
- | 0.0002 | 10.0 | 280 | 0.4894 | 0.8372 |
78
- | 0.0002 | 11.0 | 308 | 0.4906 | 0.8372 |
79
- | 0.0002 | 12.0 | 336 | 0.4963 | 0.8372 |
80
- | 0.0002 | 13.0 | 364 | 0.4981 | 0.8372 |
81
- | 0.0001 | 14.0 | 392 | 0.4994 | 0.8372 |
82
- | 0.0001 | 15.0 | 420 | 0.5036 | 0.8372 |
83
- | 0.0001 | 16.0 | 448 | 0.5049 | 0.8372 |
84
- | 0.0001 | 17.0 | 476 | 0.5116 | 0.8372 |
85
- | 0.0001 | 18.0 | 504 | 0.5122 | 0.8372 |
86
- | 0.0001 | 19.0 | 532 | 0.5151 | 0.8372 |
87
- | 0.0001 | 20.0 | 560 | 0.5161 | 0.8372 |
88
- | 0.0001 | 21.0 | 588 | 0.5169 | 0.8372 |
89
- | 0.0001 | 22.0 | 616 | 0.5170 | 0.8372 |
90
- | 0.0001 | 23.0 | 644 | 0.5176 | 0.8372 |
91
- | 0.0001 | 24.0 | 672 | 0.5195 | 0.8372 |
92
- | 0.0001 | 25.0 | 700 | 0.5238 | 0.8372 |
93
- | 0.0001 | 26.0 | 728 | 0.5251 | 0.8372 |
94
- | 0.0001 | 27.0 | 756 | 0.5257 | 0.8372 |
95
- | 0.0001 | 28.0 | 784 | 0.5254 | 0.8372 |
96
- | 0.0001 | 29.0 | 812 | 0.5266 | 0.8372 |
97
- | 0.0001 | 30.0 | 840 | 0.5304 | 0.8372 |
98
- | 0.0001 | 31.0 | 868 | 0.5298 | 0.8372 |
99
- | 0.0001 | 32.0 | 896 | 0.5322 | 0.8372 |
100
- | 0.0001 | 33.0 | 924 | 0.5320 | 0.8372 |
101
- | 0.0001 | 34.0 | 952 | 0.5340 | 0.8372 |
102
- | 0.0001 | 35.0 | 980 | 0.5351 | 0.8372 |
103
- | 0.0001 | 36.0 | 1008 | 0.5372 | 0.8372 |
104
- | 0.0001 | 37.0 | 1036 | 0.5384 | 0.8372 |
105
- | 0.0001 | 38.0 | 1064 | 0.5415 | 0.8372 |
106
- | 0.0001 | 39.0 | 1092 | 0.5442 | 0.8372 |
107
- | 0.0001 | 40.0 | 1120 | 0.5438 | 0.8372 |
108
- | 0.0001 | 41.0 | 1148 | 0.5446 | 0.8372 |
109
- | 0.0001 | 42.0 | 1176 | 0.5455 | 0.8372 |
110
- | 0.0001 | 43.0 | 1204 | 0.5455 | 0.8372 |
111
- | 0.0001 | 44.0 | 1232 | 0.5457 | 0.8372 |
112
- | 0.0001 | 45.0 | 1260 | 0.5460 | 0.8372 |
113
- | 0.0001 | 46.0 | 1288 | 0.5459 | 0.8372 |
114
- | 0.0001 | 47.0 | 1316 | 0.5460 | 0.8372 |
115
- | 0.0001 | 48.0 | 1344 | 0.5462 | 0.8372 |
116
- | 0.0001 | 49.0 | 1372 | 0.5462 | 0.8372 |
117
- | 0.0001 | 50.0 | 1400 | 0.5462 | 0.8372 |
118
 
119
 
120
  ### Framework versions
 
32
 
33
  This model is a fine-tuned version of [facebook/deit-base-patch16-224](https://huggingface.co/facebook/deit-base-patch16-224) on the imagefolder dataset.
34
  It achieves the following results on the evaluation set:
35
+ - Loss: 0.4419
36
  - Accuracy: 0.8372
37
 
38
  ## Model description
 
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
 
65
 
66
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
67
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
68
+ | 1.3275 | 1.0 | 28 | 1.2372 | 0.5814 |
69
+ | 1.0641 | 2.0 | 56 | 1.0484 | 0.6977 |
70
+ | 0.7591 | 3.0 | 84 | 0.8760 | 0.7442 |
71
+ | 0.5652 | 4.0 | 112 | 0.7360 | 0.8140 |
72
+ | 0.3906 | 5.0 | 140 | 0.6489 | 0.8372 |
73
+ | 0.3059 | 6.0 | 168 | 0.5954 | 0.8605 |
74
+ | 0.1994 | 7.0 | 196 | 0.5269 | 0.8372 |
75
+ | 0.134 | 8.0 | 224 | 0.5174 | 0.8605 |
76
+ | 0.0783 | 9.0 | 252 | 0.4602 | 0.8605 |
77
+ | 0.0454 | 10.0 | 280 | 0.4569 | 0.8372 |
78
+ | 0.0318 | 11.0 | 308 | 0.4393 | 0.8837 |
79
+ | 0.018 | 12.0 | 336 | 0.4222 | 0.8605 |
80
+ | 0.0132 | 13.0 | 364 | 0.4453 | 0.8837 |
81
+ | 0.0088 | 14.0 | 392 | 0.4098 | 0.8837 |
82
+ | 0.0068 | 15.0 | 420 | 0.4226 | 0.8605 |
83
+ | 0.0058 | 16.0 | 448 | 0.4268 | 0.8605 |
84
+ | 0.0055 | 17.0 | 476 | 0.4132 | 0.8605 |
85
+ | 0.0045 | 18.0 | 504 | 0.4342 | 0.8605 |
86
+ | 0.004 | 19.0 | 532 | 0.4228 | 0.8605 |
87
+ | 0.0033 | 20.0 | 560 | 0.4271 | 0.8372 |
88
+ | 0.0033 | 21.0 | 588 | 0.4254 | 0.8372 |
89
+ | 0.0029 | 22.0 | 616 | 0.4205 | 0.8372 |
90
+ | 0.0027 | 23.0 | 644 | 0.4207 | 0.8372 |
91
+ | 0.0024 | 24.0 | 672 | 0.4248 | 0.8605 |
92
+ | 0.0022 | 25.0 | 700 | 0.4229 | 0.8372 |
93
+ | 0.0021 | 26.0 | 728 | 0.4293 | 0.8372 |
94
+ | 0.002 | 27.0 | 756 | 0.4267 | 0.8372 |
95
+ | 0.002 | 28.0 | 784 | 0.4239 | 0.8605 |
96
+ | 0.0018 | 29.0 | 812 | 0.4273 | 0.8372 |
97
+ | 0.0018 | 30.0 | 840 | 0.4313 | 0.8372 |
98
+ | 0.0016 | 31.0 | 868 | 0.4289 | 0.8372 |
99
+ | 0.0016 | 32.0 | 896 | 0.4329 | 0.8372 |
100
+ | 0.0016 | 33.0 | 924 | 0.4313 | 0.8372 |
101
+ | 0.0014 | 34.0 | 952 | 0.4362 | 0.8372 |
102
+ | 0.0016 | 35.0 | 980 | 0.4336 | 0.8372 |
103
+ | 0.0014 | 36.0 | 1008 | 0.4353 | 0.8372 |
104
+ | 0.0014 | 37.0 | 1036 | 0.4446 | 0.8372 |
105
+ | 0.0013 | 38.0 | 1064 | 0.4482 | 0.8372 |
106
+ | 0.0013 | 39.0 | 1092 | 0.4496 | 0.8372 |
107
+ | 0.0012 | 40.0 | 1120 | 0.4442 | 0.8372 |
108
+ | 0.0013 | 41.0 | 1148 | 0.4456 | 0.8372 |
109
+ | 0.0013 | 42.0 | 1176 | 0.4450 | 0.8372 |
110
+ | 0.0012 | 43.0 | 1204 | 0.4433 | 0.8372 |
111
+ | 0.0012 | 44.0 | 1232 | 0.4424 | 0.8372 |
112
+ | 0.0011 | 45.0 | 1260 | 0.4418 | 0.8372 |
113
+ | 0.0011 | 46.0 | 1288 | 0.4417 | 0.8372 |
114
+ | 0.0011 | 47.0 | 1316 | 0.4421 | 0.8372 |
115
+ | 0.0011 | 48.0 | 1344 | 0.4419 | 0.8372 |
116
+ | 0.0011 | 49.0 | 1372 | 0.4419 | 0.8372 |
117
+ | 0.0011 | 50.0 | 1400 | 0.4419 | 0.8372 |
118
 
119
 
120
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b2f03efbe7b904e781ca782c33ca88caa82b22287728413ef4807f3f31539f8b
3
  size 343230128
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a720e4ce92030ab7260119ad0522de0256d3e0b6f70b09fd84d882ca7f3a0dc
3
  size 343230128
runs/Nov21_01-51-11_d943f7bc58f8/events.out.tfevents.1700531472.d943f7bc58f8.2975.33 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c499c9fd48566dba33bf2726ec615976d20b6207a291c24dc36bddc66f34452c
3
- size 42465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd18cbabb5318826e2896141b62899b2ba49b025b240acb995bdfbaf83258bcd
3
+ size 42819