arpanl commited on
Commit
c0826fa
1 Parent(s): 344fd21

Model save

Browse files
Files changed (1) hide show
  1. README.md +15 -13
README.md CHANGED
@@ -2,7 +2,6 @@
2
  license: apache-2.0
3
  base_model: google/vit-base-patch16-224
4
  tags:
5
- - image-classification
6
  - generated_from_trainer
7
  datasets:
8
  - imagefolder
@@ -16,7 +15,7 @@ model-index:
16
  name: Image Classification
17
  type: image-classification
18
  dataset:
19
- name: custom
20
  type: imagefolder
21
  config: default
22
  split: train
@@ -24,10 +23,10 @@ model-index:
24
  metrics:
25
  - name: Accuracy
26
  type: accuracy
27
- value: 0.42857142857142855
28
  - name: F1
29
  type: f1
30
- value: 0.3151515151515151
31
  ---
32
 
33
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -35,11 +34,11 @@ should probably proofread and complete it, then remove this comment. -->
35
 
36
  # Model
37
 
38
- This model is a fine-tuned version of [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224) on the custom dataset.
39
  It achieves the following results on the evaluation set:
40
- - Loss: 1.3328
41
- - Accuracy: 0.4286
42
- - F1: 0.3152
43
 
44
  ## Model description
45
 
@@ -64,15 +63,18 @@ The following hyperparameters were used during training:
64
  - seed: 42
65
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
66
  - lr_scheduler_type: linear
67
- - num_epochs: 3
68
 
69
  ### Training results
70
 
 
 
 
71
 
72
 
73
  ### Framework versions
74
 
75
- - Transformers 4.37.2
76
- - Pytorch 2.1.0+cu121
77
- - Datasets 2.16.1
78
- - Tokenizers 0.15.1
 
2
  license: apache-2.0
3
  base_model: google/vit-base-patch16-224
4
  tags:
 
5
  - generated_from_trainer
6
  datasets:
7
  - imagefolder
 
15
  name: Image Classification
16
  type: image-classification
17
  dataset:
18
+ name: imagefolder
19
  type: imagefolder
20
  config: default
21
  split: train
 
23
  metrics:
24
  - name: Accuracy
25
  type: accuracy
26
+ value: 0.3333333333333333
27
  - name: F1
28
  type: f1
29
+ value: 0.16666666666666666
30
  ---
31
 
32
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
34
 
35
  # Model
36
 
37
+ This model is a fine-tuned version of [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224) on the imagefolder dataset.
38
  It achieves the following results on the evaluation set:
39
+ - Loss: 4.2752
40
+ - Accuracy: 0.3333
41
+ - F1: 0.1667
42
 
43
  ## Model description
44
 
 
63
  - seed: 42
64
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
65
  - lr_scheduler_type: linear
66
+ - num_epochs: 50
67
 
68
  ### Training results
69
 
70
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
71
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
72
+ | 2.1596 | 50.0 | 50 | 4.2752 | 0.3333 | 0.1667 |
73
 
74
 
75
  ### Framework versions
76
 
77
+ - Transformers 4.39.0
78
+ - Pytorch 2.2.1+cu121
79
+ - Datasets 2.18.0
80
+ - Tokenizers 0.15.2