Hugging Face's logo

Encore02
/
vit-weldclassifyv4

Image Classification
Transformers
TensorBoard
Safetensors
vit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
Encore02 commited on
Commit
fdfc589
•
1 Parent(s): 249aedd

Model save

Browse files
Files changed (3) hide show
  1. README.md +27 -20
  2. data/events.out.tfevents.1730619187.cf96de2eb818.233.0 +2 -2
  3. model.safetensors +1 -1
README.md CHANGED
@@ -3,7 +3,6 @@ library_name: transformers
3
  license: apache-2.0
4
  base_model: google/vit-base-patch16-224-in21k
5
  tags:
6
- - image-classification
7
  - generated_from_trainer
8
  datasets:
9
  - imagefolder
@@ -24,7 +23,7 @@ model-index:
24
  metrics:
25
  - name: Accuracy
26
  type: accuracy
27
- value: 0.6745283018867925
28
  ---
29
 
30
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -34,8 +33,8 @@ should probably proofread and complete it, then remove this comment. -->
34
 
35
  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.
36
  It achieves the following results on the evaluation set:
37
- - Loss: 0.7452
38
- - Accuracy: 0.6745
39
 
40
  ## Model description
41
 
@@ -60,28 +59,36 @@ The following hyperparameters were used during training:
60
  - seed: 42
61
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
62
  - lr_scheduler_type: linear
63
- - num_epochs: 13
64
  - mixed_precision_training: Native AMP
65
 
66
  ### Training results
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
  |:-------------:|:-------:|:----:|:---------------:|:--------:|
70
- | 1.2099 | 0.8403 | 100 | 1.1625 | 0.5047 |
71
- | 1.1066 | 1.6807 | 200 | 1.0892 | 0.4953 |
72
- | 1.0298 | 2.5210 | 300 | 0.8939 | 0.5896 |
73
- | 0.5798 | 3.3613 | 400 | 0.7452 | 0.6745 |
74
- | 0.4879 | 4.2017 | 500 | 0.8673 | 0.6557 |
75
- | 0.197 | 5.0420 | 600 | 1.0145 | 0.6557 |
76
- | 0.1368 | 5.8824 | 700 | 0.8305 | 0.7311 |
77
- | 0.0841 | 6.7227 | 800 | 0.8974 | 0.7736 |
78
- | 0.0942 | 7.5630 | 900 | 1.1262 | 0.7217 |
79
- | 0.0296 | 8.4034 | 1000 | 1.2890 | 0.7123 |
80
- | 0.0432 | 9.2437 | 1100 | 1.2428 | 0.7406 |
81
- | 0.0353 | 10.0840 | 1200 | 1.2506 | 0.7453 |
82
- | 0.0065 | 10.9244 | 1300 | 1.1232 | 0.7783 |
83
- | 0.0056 | 11.7647 | 1400 | 1.1349 | 0.7830 |
84
- | 0.0054 | 12.6050 | 1500 | 1.1463 | 0.7830 |
 
 
 
 
 
 
 
 
85
 
86
 
87
  ### Framework versions
 
3
  license: apache-2.0
4
  base_model: google/vit-base-patch16-224-in21k
5
  tags:
 
6
  - generated_from_trainer
7
  datasets:
8
  - imagefolder
 
23
  metrics:
24
  - name: Accuracy
25
  type: accuracy
26
+ value: 0.9280575539568345
27
  ---
28
 
29
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
33
 
34
  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.
35
  It achieves the following results on the evaluation set:
36
+ - Loss: 0.4136
37
+ - Accuracy: 0.9281
38
 
39
  ## Model description
40
 
 
59
  - seed: 42
60
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
61
  - lr_scheduler_type: linear
62
+ - num_epochs: 15
63
  - mixed_precision_training: Native AMP
64
 
65
  ### Training results
66
 
67
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
68
  |:-------------:|:-------:|:----:|:---------------:|:--------:|
69
+ | 0.8146 | 0.6410 | 100 | 0.7349 | 0.6835 |
70
+ | 0.6048 | 1.2821 | 200 | 0.6821 | 0.6978 |
71
+ | 0.4796 | 1.9231 | 300 | 0.4833 | 0.8129 |
72
+ | 0.4532 | 2.5641 | 400 | 0.5380 | 0.8022 |
73
+ | 0.1242 | 3.2051 | 500 | 0.3899 | 0.8741 |
74
+ | 0.124 | 3.8462 | 600 | 0.5237 | 0.8273 |
75
+ | 0.1239 | 4.4872 | 700 | 0.4221 | 0.8849 |
76
+ | 0.0785 | 5.1282 | 800 | 0.3683 | 0.9137 |
77
+ | 0.093 | 5.7692 | 900 | 0.6376 | 0.8597 |
78
+ | 0.0056 | 6.4103 | 1000 | 0.3162 | 0.9245 |
79
+ | 0.0472 | 7.0513 | 1100 | 0.5225 | 0.8885 |
80
+ | 0.0234 | 7.6923 | 1200 | 0.6096 | 0.8597 |
81
+ | 0.0354 | 8.3333 | 1300 | 0.5520 | 0.8777 |
82
+ | 0.026 | 8.9744 | 1400 | 0.4938 | 0.8993 |
83
+ | 0.002 | 9.6154 | 1500 | 0.4350 | 0.9173 |
84
+ | 0.0021 | 10.2564 | 1600 | 0.4224 | 0.9173 |
85
+ | 0.0016 | 10.8974 | 1700 | 0.3838 | 0.9281 |
86
+ | 0.0014 | 11.5385 | 1800 | 0.3943 | 0.9281 |
87
+ | 0.0013 | 12.1795 | 1900 | 0.4012 | 0.9281 |
88
+ | 0.0012 | 12.8205 | 2000 | 0.4067 | 0.9281 |
89
+ | 0.0011 | 13.4615 | 2100 | 0.4101 | 0.9281 |
90
+ | 0.0011 | 14.1026 | 2200 | 0.4124 | 0.9281 |
91
+ | 0.0012 | 14.7436 | 2300 | 0.4136 | 0.9281 |
92
 
93
 
94
  ### Framework versions
data/events.out.tfevents.1730619187.cf96de2eb818.233.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a4772e45e8e654fb5f299965d0279044f1aa1ecb663c9fe15110a088fdd78a88
3
- size 61655
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1f074810da8591db5305a9290f1a97d6ff70587c48818f0546e35e2a9e39997
3
+ size 62009
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3bd3d90a40e75b1aa70018f48ed8d6adeacd8a045c6adb7cebb9d07a870eff36
3
  size 343230128
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b6317f64e2681edc3ef5811da8d887ff1ec0a12fb3ce34479d83e2e0cbad22d
3
  size 343230128