Hugging Face's logo

fullstuck
/
image_classification

Image Classification
Transformers
PyTorch
TensorBoard
Safetensors
vit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
fullstuck commited on
Commit
8e994a4
•
1 Parent(s): beee5a8

End of training

Browse files
Files changed (3) hide show
  1. README.md +78 -11
  2. model.safetensors +1 -1
  3. runs/Feb16_14-26-47_13e690524ef8/events.out.tfevents.1708095183.13e690524ef8.4038.1 +3 -0
README.md CHANGED
@@ -5,9 +5,24 @@ tags:
5
  - generated_from_trainer
6
  datasets:
7
  - imagefolder
 
 
8
  model-index:
9
  - name: image_classification
10
- results: []
 
 
 
 
 
 
 
 
 
 
 
 
 
11
  ---
12
 
13
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -17,12 +32,8 @@ should probably proofread and complete it, then remove this comment. -->
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
  It achieves the following results on the evaluation set:
20
- - eval_loss: 2.0725
21
- - eval_accuracy: 0.1437
22
- - eval_runtime: 142.7817
23
- - eval_samples_per_second: 1.121
24
- - eval_steps_per_second: 0.07
25
- - step: 0
26
 
27
  ## Model description
28
 
@@ -49,9 +60,65 @@ The following hyperparameters were used during training:
49
  - lr_scheduler_type: linear
50
  - num_epochs: 50
51
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
52
  ### Framework versions
53
 
54
- - Transformers 4.33.2
55
- - Pytorch 2.0.1+cu118
56
- - Datasets 2.14.5
57
- - Tokenizers 0.13.3
 
5
  - generated_from_trainer
6
  datasets:
7
  - imagefolder
8
+ metrics:
9
+ - accuracy
10
  model-index:
11
  - name: image_classification
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: train
21
+ args: default
22
+ metrics:
23
+ - name: Accuracy
24
+ type: accuracy
25
+ value: 0.4875
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 [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: 1.4148
36
+ - Accuracy: 0.4875
 
 
 
 
37
 
38
  ## Model description
39
 
 
60
  - lr_scheduler_type: linear
61
  - num_epochs: 50
62
 
63
+ ### Training results
64
+
65
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
66
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
67
+ | No log | 1.0 | 40 | 2.0788 | 0.1125 |
68
+ | No log | 2.0 | 80 | 2.0706 | 0.1688 |
69
+ | No log | 3.0 | 120 | 2.0465 | 0.2062 |
70
+ | No log | 4.0 | 160 | 2.0386 | 0.2 |
71
+ | No log | 5.0 | 200 | 2.0110 | 0.2188 |
72
+ | No log | 6.0 | 240 | 1.9815 | 0.225 |
73
+ | No log | 7.0 | 280 | 1.9430 | 0.2313 |
74
+ | No log | 8.0 | 320 | 1.8889 | 0.3312 |
75
+ | No log | 9.0 | 360 | 1.8283 | 0.3063 |
76
+ | No log | 10.0 | 400 | 1.7769 | 0.3438 |
77
+ | No log | 11.0 | 440 | 1.7292 | 0.325 |
78
+ | No log | 12.0 | 480 | 1.6966 | 0.3312 |
79
+ | 1.885 | 13.0 | 520 | 1.6708 | 0.375 |
80
+ | 1.885 | 14.0 | 560 | 1.6527 | 0.3937 |
81
+ | 1.885 | 15.0 | 600 | 1.6266 | 0.3937 |
82
+ | 1.885 | 16.0 | 640 | 1.6116 | 0.3937 |
83
+ | 1.885 | 17.0 | 680 | 1.5944 | 0.4188 |
84
+ | 1.885 | 18.0 | 720 | 1.5931 | 0.3688 |
85
+ | 1.885 | 19.0 | 760 | 1.5645 | 0.3937 |
86
+ | 1.885 | 20.0 | 800 | 1.5503 | 0.45 |
87
+ | 1.885 | 21.0 | 840 | 1.5550 | 0.425 |
88
+ | 1.885 | 22.0 | 880 | 1.5370 | 0.4375 |
89
+ | 1.885 | 23.0 | 920 | 1.5239 | 0.4688 |
90
+ | 1.885 | 24.0 | 960 | 1.5240 | 0.4437 |
91
+ | 1.4797 | 25.0 | 1000 | 1.5031 | 0.4688 |
92
+ | 1.4797 | 26.0 | 1040 | 1.5183 | 0.4188 |
93
+ | 1.4797 | 27.0 | 1080 | 1.4949 | 0.4062 |
94
+ | 1.4797 | 28.0 | 1120 | 1.5014 | 0.4437 |
95
+ | 1.4797 | 29.0 | 1160 | 1.4766 | 0.4625 |
96
+ | 1.4797 | 30.0 | 1200 | 1.4892 | 0.4375 |
97
+ | 1.4797 | 31.0 | 1240 | 1.4812 | 0.4938 |
98
+ | 1.4797 | 32.0 | 1280 | 1.4472 | 0.4688 |
99
+ | 1.4797 | 33.0 | 1320 | 1.4744 | 0.425 |
100
+ | 1.4797 | 34.0 | 1360 | 1.4563 | 0.4562 |
101
+ | 1.4797 | 35.0 | 1400 | 1.4785 | 0.4313 |
102
+ | 1.4797 | 36.0 | 1440 | 1.4331 | 0.5125 |
103
+ | 1.4797 | 37.0 | 1480 | 1.4551 | 0.45 |
104
+ | 1.293 | 38.0 | 1520 | 1.4470 | 0.4625 |
105
+ | 1.293 | 39.0 | 1560 | 1.4695 | 0.4375 |
106
+ | 1.293 | 40.0 | 1600 | 1.4366 | 0.4813 |
107
+ | 1.293 | 41.0 | 1640 | 1.4350 | 0.5 |
108
+ | 1.293 | 42.0 | 1680 | 1.4181 | 0.475 |
109
+ | 1.293 | 43.0 | 1720 | 1.4428 | 0.4875 |
110
+ | 1.293 | 44.0 | 1760 | 1.4067 | 0.5188 |
111
+ | 1.293 | 45.0 | 1800 | 1.4058 | 0.475 |
112
+ | 1.293 | 46.0 | 1840 | 1.4341 | 0.475 |
113
+ | 1.293 | 47.0 | 1880 | 1.4082 | 0.4813 |
114
+ | 1.293 | 48.0 | 1920 | 1.4461 | 0.4688 |
115
+ | 1.293 | 49.0 | 1960 | 1.4136 | 0.5062 |
116
+ | 1.1998 | 50.0 | 2000 | 1.4226 | 0.4938 |
117
+
118
+
119
  ### Framework versions
120
 
121
+ - Transformers 4.35.2
122
+ - Pytorch 2.1.0+cu121
123
+ - Datasets 2.17.0
124
+ - Tokenizers 0.15.2
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:13d3c593b63ec57246df5f91f044d3f0de8d31ec4e136396768c0dfbe50e7cb6
3
  size 343242432
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:482bec9f9a0e53f82db308ff3c8624209b14a6138f4f39423c8af831f645dc70
3
  size 343242432
runs/Feb16_14-26-47_13e690524ef8/events.out.tfevents.1708095183.13e690524ef8.4038.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9d7a0ecacdf08ccae84af1415b8de4c73a5602751f05f1c30c12d5d71125541
3
+ size 411