Hugging Face's logo

Danung
/
image_classification

Image Classification
Transformers
TensorBoard
Safetensors
vit
Generated from Trainer
Eval Results
Model card Files
xet
Metrics Community
Danung commited on
Commit
8546d9e
·
verified ·
1 Parent(s): af08b06

End of training

Browse files
Files changed (2) hide show
  1. README.md +12 -11
  2. model.safetensors +1 -1
README.md CHANGED
@@ -17,12 +17,12 @@ model-index:
17
  name: imagefolder
18
  type: imagefolder
19
  config: default
20
- split: train[:800]
21
  args: default
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
- value: 0.525
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -32,8 +32,8 @@ should probably proofread and complete it, then remove this comment. -->
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: 1.2522
36
- - Accuracy: 0.525
37
 
38
  ## Model description
39
 
@@ -58,21 +58,22 @@ The following hyperparameters were used during training:
58
  - seed: 42
59
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
60
  - lr_scheduler_type: linear
61
- - num_epochs: 4
62
 
63
  ### Training results
64
 
65
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
66
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
67
- | No log | 1.0 | 40 | 1.4900 | 0.4313 |
68
- | No log | 2.0 | 80 | 1.3787 | 0.4875 |
69
- | No log | 3.0 | 120 | 1.2962 | 0.5188 |
70
- | No log | 4.0 | 160 | 1.2553 | 0.5312 |
 
71
 
72
 
73
  ### Framework versions
74
 
75
- - Transformers 4.35.2
76
- - Pytorch 2.1.0+cu121
77
  - Datasets 2.17.0
78
  - Tokenizers 0.15.2
 
17
  name: imagefolder
18
  type: imagefolder
19
  config: default
20
+ split: train[:5000]
21
  args: default
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
+ value: 0.55
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: 1.2286
36
+ - Accuracy: 0.55
37
 
38
  ## Model description
39
 
 
58
  - seed: 42
59
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
60
  - lr_scheduler_type: linear
61
+ - num_epochs: 5
62
 
63
  ### Training results
64
 
65
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
66
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
67
+ | No log | 1.0 | 40 | 1.7112 | 0.3812 |
68
+ | No log | 2.0 | 80 | 1.4054 | 0.475 |
69
+ | No log | 3.0 | 120 | 1.3190 | 0.5437 |
70
+ | No log | 4.0 | 160 | 1.2331 | 0.55 |
71
+ | No log | 5.0 | 200 | 1.1892 | 0.5938 |
72
 
73
 
74
  ### Framework versions
75
 
76
+ - Transformers 4.37.2
77
+ - Pytorch 2.2.0+cu118
78
  - Datasets 2.17.0
79
  - Tokenizers 0.15.2
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e17a412c373b8fe22c5f34c9d3a8b5232b8e75c57e75d471d14d122305c8a88e
3
  size 343242432
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:222c32e629baaa928630ea9ea26b9673b6aeca0200b3e010a555e73bc5fa1ecc
3
  size 343242432