Hugging Face's logo

mmomm25
/
vit-base-patch16-224-in21k-FINALLaneClassifier-VIT50epochsAUGMENTED

TensorBoard
Safetensors
vit
Generated from Trainer
Eval Results
Model card Files Metrics Community
mmomm25 commited on
Commit
07d1361
·
verified ·
1 Parent(s): bee61cb

Model save

Browse files
Files changed (1) hide show
  1. README.md +146 -0
README.md ADDED
@@ -0,0 +1,146 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: google/vit-base-patch16-224-in21k
4
+ tags:
5
+ - generated_from_trainer
6
+ datasets:
7
+ - imagefolder
8
+ metrics:
9
+ - accuracy
10
+ - f1
11
+ - precision
12
+ - recall
13
+ model-index:
14
+ - name: vit-base-patch16-224-in21k-FINALLaneClassifier-VIT50epochsAUGMENTED
15
+ results:
16
+ - task:
17
+ name: Image Classification
18
+ type: image-classification
19
+ dataset:
20
+ name: imagefolder
21
+ type: imagefolder
22
+ config: default
23
+ split: train
24
+ args: default
25
+ metrics:
26
+ - name: Accuracy
27
+ type: accuracy
28
+ value:
29
+ accuracy: 1.0
30
+ - name: F1
31
+ type: f1
32
+ value:
33
+ f1: 1.0
34
+ - name: Precision
35
+ type: precision
36
+ value:
37
+ precision: 1.0
38
+ - name: Recall
39
+ type: recall
40
+ value:
41
+ recall: 1.0
42
+ ---
43
+
44
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
45
+ should probably proofread and complete it, then remove this comment. -->
46
+
47
+ # vit-base-patch16-224-in21k-FINALLaneClassifier-VIT50epochsAUGMENTED
48
+
49
+ 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.
50
+ It achieves the following results on the evaluation set:
51
+ - Loss: 0.0000
52
+ - Accuracy: {'accuracy': 1.0}
53
+ - F1: {'f1': 1.0}
54
+ - Precision: {'precision': 1.0}
55
+ - Recall: {'recall': 1.0}
56
+
57
+ ## Model description
58
+
59
+ More information needed
60
+
61
+ ## Intended uses & limitations
62
+
63
+ More information needed
64
+
65
+ ## Training and evaluation data
66
+
67
+ More information needed
68
+
69
+ ## Training procedure
70
+
71
+ ### Training hyperparameters
72
+
73
+ The following hyperparameters were used during training:
74
+ - learning_rate: 5e-05
75
+ - train_batch_size: 32
76
+ - eval_batch_size: 32
77
+ - seed: 42
78
+ - gradient_accumulation_steps: 4
79
+ - total_train_batch_size: 128
80
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
81
+ - lr_scheduler_type: linear
82
+ - lr_scheduler_warmup_ratio: 0.1
83
+ - num_epochs: 50
84
+
85
+ ### Training results
86
+
87
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
88
+ |:-------------:|:-------:|:-----:|:---------------:|:--------------------------------:|:--------------------------:|:---------------------------------:|:------------------------------:|
89
+ | 0.0297 | 0.9981 | 392 | 0.0204 | {'accuracy': 0.9998408150270615} | {'f1': 0.9998407816167802} | {'precision': 0.9998385012919897} | {'recall': 0.9998431126451208} |
90
+ | 0.0082 | 1.9987 | 785 | 0.0069 | {'accuracy': 1.0} | {'f1': 1.0} | {'precision': 1.0} | {'recall': 1.0} |
91
+ | 0.008 | 2.9994 | 1178 | 0.0038 | {'accuracy': 1.0} | {'f1': 1.0} | {'precision': 1.0} | {'recall': 1.0} |
92
+ | 0.0023 | 4.0 | 1571 | 0.0020 | {'accuracy': 1.0} | {'f1': 1.0} | {'precision': 1.0} | {'recall': 1.0} |
93
+ | 0.0035 | 4.9981 | 1963 | 0.0031 | {'accuracy': 0.9993632601082458} | {'f1': 0.9993631351350802} | {'precision': 0.9993546305259762} | {'recall': 0.9993724505804833} |
94
+ | 0.0011 | 5.9987 | 2356 | 0.0007 | {'accuracy': 1.0} | {'f1': 1.0} | {'precision': 1.0} | {'recall': 1.0} |
95
+ | 0.0013 | 6.9994 | 2749 | 0.0005 | {'accuracy': 1.0} | {'f1': 1.0} | {'precision': 1.0} | {'recall': 1.0} |
96
+ | 0.0006 | 8.0 | 3142 | 0.0003 | {'accuracy': 1.0} | {'f1': 1.0} | {'precision': 1.0} | {'recall': 1.0} |
97
+ | 0.001 | 8.9981 | 3534 | 0.0002 | {'accuracy': 1.0} | {'f1': 1.0} | {'precision': 1.0} | {'recall': 1.0} |
98
+ | 0.0002 | 9.9987 | 3927 | 0.0002 | {'accuracy': 1.0} | {'f1': 1.0} | {'precision': 1.0} | {'recall': 1.0} |
99
+ | 0.0004 | 10.9994 | 4320 | 0.0002 | {'accuracy': 1.0} | {'f1': 1.0} | {'precision': 1.0} | {'recall': 1.0} |
100
+ | 0.0001 | 12.0 | 4713 | 0.0001 | {'accuracy': 1.0} | {'f1': 1.0} | {'precision': 1.0} | {'recall': 1.0} |
101
+ | 0.0007 | 12.9981 | 5105 | 0.0001 | {'accuracy': 1.0} | {'f1': 1.0} | {'precision': 1.0} | {'recall': 1.0} |
102
+ | 0.0028 | 13.9987 | 5498 | 0.0001 | {'accuracy': 1.0} | {'f1': 1.0} | {'precision': 1.0} | {'recall': 1.0} |
103
+ | 0.0006 | 14.9994 | 5891 | 0.0001 | {'accuracy': 1.0} | {'f1': 1.0} | {'precision': 1.0} | {'recall': 1.0} |
104
+ | 0.0036 | 16.0 | 6284 | 0.0001 | {'accuracy': 1.0} | {'f1': 1.0} | {'precision': 1.0} | {'recall': 1.0} |
105
+ | 0.0016 | 16.9981 | 6676 | 0.0001 | {'accuracy': 1.0} | {'f1': 1.0} | {'precision': 1.0} | {'recall': 1.0} |
106
+ | 0.0026 | 17.9987 | 7069 | 0.0000 | {'accuracy': 1.0} | {'f1': 1.0} | {'precision': 1.0} | {'recall': 1.0} |
107
+ | 0.0007 | 18.9994 | 7462 | 0.0000 | {'accuracy': 1.0} | {'f1': 1.0} | {'precision': 1.0} | {'recall': 1.0} |
108
+ | 0.0011 | 20.0 | 7855 | 0.0000 | {'accuracy': 1.0} | {'f1': 1.0} | {'precision': 1.0} | {'recall': 1.0} |
109
+ | 0.0003 | 20.9981 | 8247 | 0.0000 | {'accuracy': 1.0} | {'f1': 1.0} | {'precision': 1.0} | {'recall': 1.0} |
110
+ | 0.0008 | 21.9987 | 8640 | 0.0000 | {'accuracy': 1.0} | {'f1': 1.0} | {'precision': 1.0} | {'recall': 1.0} |
111
+ | 0.0001 | 22.9994 | 9033 | 0.0000 | {'accuracy': 1.0} | {'f1': 1.0} | {'precision': 1.0} | {'recall': 1.0} |
112
+ | 0.0 | 24.0 | 9426 | 0.0000 | {'accuracy': 1.0} | {'f1': 1.0} | {'precision': 1.0} | {'recall': 1.0} |
113
+ | 0.0002 | 24.9981 | 9818 | 0.0000 | {'accuracy': 1.0} | {'f1': 1.0} | {'precision': 1.0} | {'recall': 1.0} |
114
+ | 0.0 | 25.9987 | 10211 | 0.0000 | {'accuracy': 1.0} | {'f1': 1.0} | {'precision': 1.0} | {'recall': 1.0} |
115
+ | 0.0002 | 26.9994 | 10604 | 0.0002 | {'accuracy': 1.0} | {'f1': 1.0} | {'precision': 1.0} | {'recall': 1.0} |
116
+ | 0.0001 | 28.0 | 10997 | 0.0000 | {'accuracy': 1.0} | {'f1': 1.0} | {'precision': 1.0} | {'recall': 1.0} |
117
+ | 0.0 | 28.9981 | 11389 | 0.0000 | {'accuracy': 1.0} | {'f1': 1.0} | {'precision': 1.0} | {'recall': 1.0} |
118
+ | 0.0002 | 29.9987 | 11782 | 0.0000 | {'accuracy': 1.0} | {'f1': 1.0} | {'precision': 1.0} | {'recall': 1.0} |
119
+ | 0.0001 | 30.9994 | 12175 | 0.0000 | {'accuracy': 1.0} | {'f1': 1.0} | {'precision': 1.0} | {'recall': 1.0} |
120
+ | 0.0004 | 32.0 | 12568 | 0.0000 | {'accuracy': 1.0} | {'f1': 1.0} | {'precision': 1.0} | {'recall': 1.0} |
121
+ | 0.0 | 32.9981 | 12960 | 0.0000 | {'accuracy': 1.0} | {'f1': 1.0} | {'precision': 1.0} | {'recall': 1.0} |
122
+ | 0.002 | 33.9987 | 13353 | 0.0000 | {'accuracy': 1.0} | {'f1': 1.0} | {'precision': 1.0} | {'recall': 1.0} |
123
+ | 0.0 | 34.9994 | 13746 | 0.0000 | {'accuracy': 1.0} | {'f1': 1.0} | {'precision': 1.0} | {'recall': 1.0} |
124
+ | 0.0 | 36.0 | 14139 | 0.0000 | {'accuracy': 1.0} | {'f1': 1.0} | {'precision': 1.0} | {'recall': 1.0} |
125
+ | 0.0001 | 36.9981 | 14531 | 0.0000 | {'accuracy': 1.0} | {'f1': 1.0} | {'precision': 1.0} | {'recall': 1.0} |
126
+ | 0.0 | 37.9987 | 14924 | 0.0000 | {'accuracy': 1.0} | {'f1': 1.0} | {'precision': 1.0} | {'recall': 1.0} |
127
+ | 0.0 | 38.9994 | 15317 | 0.0000 | {'accuracy': 1.0} | {'f1': 1.0} | {'precision': 1.0} | {'recall': 1.0} |
128
+ | 0.0035 | 40.0 | 15710 | 0.0000 | {'accuracy': 1.0} | {'f1': 1.0} | {'precision': 1.0} | {'recall': 1.0} |
129
+ | 0.0002 | 40.9981 | 16102 | 0.0000 | {'accuracy': 1.0} | {'f1': 1.0} | {'precision': 1.0} | {'recall': 1.0} |
130
+ | 0.0 | 41.9987 | 16495 | 0.0000 | {'accuracy': 1.0} | {'f1': 1.0} | {'precision': 1.0} | {'recall': 1.0} |
131
+ | 0.0 | 42.9994 | 16888 | 0.0000 | {'accuracy': 1.0} | {'f1': 1.0} | {'precision': 1.0} | {'recall': 1.0} |
132
+ | 0.0 | 44.0 | 17281 | 0.0000 | {'accuracy': 1.0} | {'f1': 1.0} | {'precision': 1.0} | {'recall': 1.0} |
133
+ | 0.0 | 44.9981 | 17673 | 0.0000 | {'accuracy': 1.0} | {'f1': 1.0} | {'precision': 1.0} | {'recall': 1.0} |
134
+ | 0.0 | 45.9987 | 18066 | 0.0000 | {'accuracy': 1.0} | {'f1': 1.0} | {'precision': 1.0} | {'recall': 1.0} |
135
+ | 0.0 | 46.9994 | 18459 | 0.0000 | {'accuracy': 1.0} | {'f1': 1.0} | {'precision': 1.0} | {'recall': 1.0} |
136
+ | 0.0 | 48.0 | 18852 | 0.0000 | {'accuracy': 1.0} | {'f1': 1.0} | {'precision': 1.0} | {'recall': 1.0} |
137
+ | 0.0 | 48.9981 | 19244 | 0.0000 | {'accuracy': 1.0} | {'f1': 1.0} | {'precision': 1.0} | {'recall': 1.0} |
138
+ | 0.0 | 49.9045 | 19600 | 0.0000 | {'accuracy': 1.0} | {'f1': 1.0} | {'precision': 1.0} | {'recall': 1.0} |
139
+
140
+
141
+ ### Framework versions
142
+
143
+ - Transformers 4.43.3
144
+ - Pytorch 2.3.1
145
+ - Datasets 2.20.0
146
+ - Tokenizers 0.19.1