Hugging Face's logo

SonishMaharjan
/
ditmodel

Image Classification
Transformers
TensorBoard
Safetensors
beit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
SonishMaharjan commited on
Commit
b1069a7
•
1 Parent(s): 18e7565

Model save

Browse files
Files changed (1) hide show
  1. README.md +16 -17
README.md CHANGED
@@ -1,5 +1,4 @@
1
  ---
2
- base_model: microsoft/dit-base
3
  tags:
4
  - generated_from_trainer
5
  datasets:
@@ -21,7 +20,7 @@ model-index:
21
  metrics:
22
  - name: Accuracy
23
  type: accuracy
24
- value: 0.8741148701809599
25
  ---
26
 
27
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -29,19 +28,19 @@ should probably proofread and complete it, then remove this comment. -->
29
 
30
  # ditmodel
31
 
32
- This model is a fine-tuned version of [microsoft/dit-base](https://huggingface.co/microsoft/dit-base) on the imagefolder dataset.
33
  It achieves the following results on the evaluation set:
34
- - Loss: 0.2285
35
- - Accuracy: 0.8741
36
- - Weighted f1: 0.8720
37
- - Micro f1: 0.8741
38
- - Macro f1: 0.8640
39
- - Weighted recall: 0.8741
40
- - Micro recall: 0.8741
41
- - Macro recall: 0.8626
42
- - Weighted precision: 0.8780
43
- - Micro precision: 0.8741
44
- - Macro precision: 0.8745
45
 
46
  ## Model description
47
 
@@ -75,9 +74,9 @@ The following hyperparameters were used during training:
75
 
76
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | Weighted f1 | Micro f1 | Macro f1 | Weighted recall | Micro recall | Macro recall | Weighted precision | Micro precision | Macro precision |
77
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:-----------:|:--------:|:--------:|:---------------:|:------------:|:------------:|:------------------:|:---------------:|:---------------:|
78
- | 0.8637 | 0.98 | 38 | 0.5986 | 0.6778 | 0.5949 | 0.6778 | 0.5662 | 0.6778 | 0.6778 | 0.6474 | 0.7506 | 0.6778 | 0.7511 |
79
- | 0.5018 | 1.99 | 77 | 0.2707 | 0.8517 | 0.8453 | 0.8517 | 0.8377 | 0.8517 | 0.8517 | 0.8345 | 0.8588 | 0.8517 | 0.8623 |
80
- | 0.3761 | 2.94 | 114 | 0.2285 | 0.8741 | 0.8720 | 0.8741 | 0.8640 | 0.8741 | 0.8741 | 0.8626 | 0.8780 | 0.8741 | 0.8745 |
81
 
82
 
83
  ### Framework versions
 
1
  ---
 
2
  tags:
3
  - generated_from_trainer
4
  datasets:
 
20
  metrics:
21
  - name: Accuracy
22
  type: accuracy
23
+ value: 0.9425649095200629
24
  ---
25
 
26
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
28
 
29
  # ditmodel
30
 
31
+ This model was trained from scratch on the imagefolder dataset.
32
  It achieves the following results on the evaluation set:
33
+ - Loss: 0.1359
34
+ - Accuracy: 0.9426
35
+ - Weighted f1: 0.9426
36
+ - Micro f1: 0.9426
37
+ - Macro f1: 0.9386
38
+ - Weighted recall: 0.9426
39
+ - Micro recall: 0.9426
40
+ - Macro recall: 0.9404
41
+ - Weighted precision: 0.9440
42
+ - Micro precision: 0.9426
43
+ - Macro precision: 0.9382
44
 
45
  ## Model description
46
 
 
74
 
75
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | Weighted f1 | Micro f1 | Macro f1 | Weighted recall | Micro recall | Macro recall | Weighted precision | Micro precision | Macro precision |
76
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:-----------:|:--------:|:--------:|:---------------:|:------------:|:------------:|:------------------:|:---------------:|:---------------:|
77
+ | 0.3093 | 0.98 | 38 | 0.2252 | 0.8891 | 0.8879 | 0.8891 | 0.8820 | 0.8891 | 0.8891 | 0.8738 | 0.8952 | 0.8891 | 0.8994 |
78
+ | 0.2278 | 1.99 | 77 | 0.1648 | 0.9292 | 0.9292 | 0.9292 | 0.9220 | 0.9292 | 0.9292 | 0.9221 | 0.9310 | 0.9292 | 0.9241 |
79
+ | 0.2066 | 2.94 | 114 | 0.1359 | 0.9426 | 0.9426 | 0.9426 | 0.9386 | 0.9426 | 0.9426 | 0.9404 | 0.9440 | 0.9426 | 0.9382 |
80
 
81
 
82
  ### Framework versions