sck commited on
Commit
7cdb9ab
1 Parent(s): dda0980

Model save

Browse files
Files changed (1) hide show
  1. README.md +3 -71
README.md CHANGED
@@ -5,24 +5,9 @@ tags:
5
  - generated_from_trainer
6
  datasets:
7
  - imagefolder
8
- metrics:
9
- - recall
10
  model-index:
11
  - name: vca
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: Recall
24
- type: recall
25
- value: 0.6533333333333333
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -31,9 +16,6 @@ should probably proofread and complete it, then remove this comment. -->
31
  # vca
32
 
33
  This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the imagefolder dataset.
34
- It achieves the following results on the evaluation set:
35
- - Loss: 0.3295
36
- - Recall: 0.6533
37
 
38
  ## Model description
39
 
@@ -61,63 +43,13 @@ The following hyperparameters were used during training:
61
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
62
  - lr_scheduler_type: cosine_with_restarts
63
  - lr_scheduler_warmup_ratio: 0.1
64
- - num_epochs: 100
65
 
66
  ### Training results
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Recall |
69
  |:-------------:|:-----:|:----:|:---------------:|:------:|
70
- | No log | 0.95 | 5 | 0.6389 | 0.0133 |
71
- | No log | 1.9 | 10 | 0.5645 | 0.0 |
72
- | No log | 2.86 | 15 | 0.4792 | 0.0 |
73
- | No log | 4.0 | 21 | 0.4224 | 0.0 |
74
- | No log | 4.95 | 26 | 0.3652 | 0.0 |
75
- | No log | 5.9 | 31 | 0.3357 | 0.0 |
76
- | No log | 6.86 | 36 | 0.2953 | 0.0 |
77
- | No log | 8.0 | 42 | 0.2909 | 0.0133 |
78
- | No log | 8.95 | 47 | 0.2937 | 0.7333 |
79
- | No log | 9.9 | 52 | 0.2718 | 0.68 |
80
- | No log | 10.86 | 57 | 0.2673 | 0.64 |
81
- | No log | 12.0 | 63 | 0.3019 | 0.8667 |
82
- | No log | 12.95 | 68 | 0.2945 | 0.4667 |
83
- | No log | 13.9 | 73 | 0.2669 | 0.6667 |
84
- | No log | 14.86 | 78 | 0.2504 | 0.7467 |
85
- | No log | 16.0 | 84 | 0.2380 | 0.64 |
86
- | No log | 16.95 | 89 | 0.2525 | 0.64 |
87
- | No log | 17.9 | 94 | 0.2648 | 0.7467 |
88
- | No log | 18.86 | 99 | 0.2711 | 0.7067 |
89
- | No log | 20.0 | 105 | 0.2747 | 0.64 |
90
- | No log | 20.95 | 110 | 0.2772 | 0.64 |
91
- | No log | 21.9 | 115 | 0.3000 | 0.6267 |
92
- | No log | 22.86 | 120 | 0.2871 | 0.5733 |
93
- | No log | 24.0 | 126 | 0.3025 | 0.6667 |
94
- | No log | 24.95 | 131 | 0.3317 | 0.5867 |
95
- | No log | 25.9 | 136 | 0.3171 | 0.5467 |
96
- | No log | 26.86 | 141 | 0.3322 | 0.64 |
97
- | No log | 28.0 | 147 | 0.3207 | 0.6533 |
98
- | No log | 28.95 | 152 | 0.3492 | 0.5733 |
99
- | No log | 29.9 | 157 | 0.2965 | 0.68 |
100
- | No log | 30.86 | 162 | 0.3256 | 0.72 |
101
- | No log | 32.0 | 168 | 0.3460 | 0.6267 |
102
- | No log | 32.95 | 173 | 0.3118 | 0.7067 |
103
- | No log | 33.9 | 178 | 0.3656 | 0.6933 |
104
- | No log | 34.86 | 183 | 0.3111 | 0.5867 |
105
- | No log | 36.0 | 189 | 0.3119 | 0.6667 |
106
- | No log | 36.95 | 194 | 0.3524 | 0.72 |
107
- | No log | 37.9 | 199 | 0.3457 | 0.5333 |
108
- | No log | 38.86 | 204 | 0.3460 | 0.56 |
109
- | No log | 40.0 | 210 | 0.3518 | 0.6933 |
110
- | No log | 40.95 | 215 | 0.2948 | 0.5867 |
111
- | No log | 41.9 | 220 | 0.3640 | 0.5867 |
112
- | No log | 42.86 | 225 | 0.3408 | 0.6133 |
113
- | No log | 44.0 | 231 | 0.3350 | 0.6 |
114
- | No log | 44.95 | 236 | 0.3832 | 0.72 |
115
- | No log | 45.9 | 241 | 0.3298 | 0.6667 |
116
- | No log | 46.86 | 246 | 0.3557 | 0.64 |
117
- | No log | 48.0 | 252 | 0.3832 | 0.64 |
118
- | No log | 48.95 | 257 | 0.3317 | 0.6533 |
119
- | No log | 49.9 | 262 | 0.3980 | 0.6933 |
120
- | No log | 50.86 | 267 | 0.3295 | 0.6533 |
121
 
122
 
123
  ### Framework versions
 
5
  - generated_from_trainer
6
  datasets:
7
  - imagefolder
 
 
8
  model-index:
9
  - name: vca
10
+ results: []
 
 
 
 
 
 
 
 
 
 
 
 
 
11
  ---
12
 
13
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
16
  # vca
17
 
18
  This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the imagefolder dataset.
 
 
 
19
 
20
  ## Model description
21
 
 
43
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
  - lr_scheduler_type: cosine_with_restarts
45
  - lr_scheduler_warmup_ratio: 0.1
46
+ - num_epochs: 1
47
 
48
  ### Training results
49
 
50
  | Training Loss | Epoch | Step | Validation Loss | Recall |
51
  |:-------------:|:-----:|:----:|:---------------:|:------:|
52
+ | No log | 0.95 | 5 | 0.4596 | 0.0 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
53
 
54
 
55
  ### Framework versions