Hugging Face's logo

anaghasavit
/
beit-base-patch16-224-pt22k-ft22k-finetunedt

Image Classification
Transformers
PyTorch
TensorBoard
beit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
anaghasavit commited on
Commit
c90fc57
•
1 Parent(s): 4c9a873

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +12 -17
README.md CHANGED
@@ -31,7 +31,7 @@ should probably proofread and complete it, then remove this comment. -->
31
 
32
  This model is a fine-tuned version of [microsoft/beit-base-patch16-224-pt22k-ft22k](https://huggingface.co/microsoft/beit-base-patch16-224-pt22k-ft22k) on the imagefolder dataset.
33
  It achieves the following results on the evaluation set:
34
- - Loss: 0.0000
35
  - Accuracy: 1.0
36
 
37
  ## Model description
@@ -60,27 +60,22 @@ The following hyperparameters were used during training:
60
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
61
  - lr_scheduler_type: linear
62
  - lr_scheduler_warmup_ratio: 0.1
63
- - num_epochs: 15
64
 
65
  ### Training results
66
 
67
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
68
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
69
- | 0.7369 | 1.0 | 25 | 0.0425 | 0.9972 |
70
- | 0.007 | 2.0 | 50 | 0.0005 | 1.0 |
71
- | 0.0041 | 3.0 | 75 | 0.0003 | 1.0 |
72
- | 0.0011 | 4.0 | 100 | 0.0002 | 1.0 |
73
- | 0.0008 | 5.0 | 125 | 0.0001 | 1.0 |
74
- | 0.0055 | 6.0 | 150 | 0.0002 | 1.0 |
75
- | 0.0007 | 7.0 | 175 | 0.0001 | 1.0 |
76
- | 0.0047 | 8.0 | 200 | 0.0001 | 1.0 |
77
- | 0.0005 | 9.0 | 225 | 0.0001 | 1.0 |
78
- | 0.006 | 10.0 | 250 | 0.0001 | 1.0 |
79
- | 0.0065 | 11.0 | 275 | 0.0001 | 1.0 |
80
- | 0.0023 | 12.0 | 300 | 0.0001 | 1.0 |
81
- | 0.0003 | 13.0 | 325 | 0.0001 | 1.0 |
82
- | 0.0011 | 14.0 | 350 | 0.0000 | 1.0 |
83
- | 0.0003 | 15.0 | 375 | 0.0000 | 1.0 |
84
 
85
 
86
  ### Framework versions
 
31
 
32
  This model is a fine-tuned version of [microsoft/beit-base-patch16-224-pt22k-ft22k](https://huggingface.co/microsoft/beit-base-patch16-224-pt22k-ft22k) on the imagefolder dataset.
33
  It achieves the following results on the evaluation set:
34
+ - Loss: 0.0001
35
  - Accuracy: 1.0
36
 
37
  ## Model description
 
60
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
61
  - lr_scheduler_type: linear
62
  - lr_scheduler_warmup_ratio: 0.1
63
+ - num_epochs: 10
64
 
65
  ### Training results
66
 
67
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
68
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
69
+ | 0.4714 | 1.0 | 25 | 0.0147 | 1.0 |
70
+ | 0.0089 | 2.0 | 50 | 0.0008 | 1.0 |
71
+ | 0.0101 | 3.0 | 75 | 0.0003 | 1.0 |
72
+ | 0.0021 | 4.0 | 100 | 0.0002 | 1.0 |
73
+ | 0.0028 | 5.0 | 125 | 0.0001 | 1.0 |
74
+ | 0.0016 | 6.0 | 150 | 0.0001 | 1.0 |
75
+ | 0.0044 | 7.0 | 175 | 0.0001 | 1.0 |
76
+ | 0.0007 | 8.0 | 200 | 0.0001 | 1.0 |
77
+ | 0.0013 | 9.0 | 225 | 0.0001 | 1.0 |
78
+ | 0.0004 | 10.0 | 250 | 0.0001 | 1.0 |
 
 
 
 
 
79
 
80
 
81
  ### Framework versions