Hugging Face's logo

onizukal
/
Boya3_3Class_RMSprop_1e5_20Epoch_Beit-large-224_fold2

Image Classification
Transformers
PyTorch
beit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
onizukal commited on
Commit
bfd949f
•
1 Parent(s): 9111f40

End of training

Browse files
Files changed (2) hide show
  1. README.md +14 -9
  2. pytorch_model.bin +1 -1
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
- value: 0.8262929332806949
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 [microsoft/beit-large-patch16-224](https://huggingface.co/microsoft/beit-large-patch16-224) on the imagefolder dataset.
34
  It achieves the following results on the evaluation set:
35
- - Loss: 0.9056
36
- - Accuracy: 0.8263
37
 
38
  ## Model description
39
 
@@ -59,17 +59,22 @@ The following hyperparameters were used during training:
59
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
60
  - lr_scheduler_type: linear
61
  - lr_scheduler_warmup_ratio: 0.1
62
- - num_epochs: 5
63
 
64
  ### Training results
65
 
66
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
67
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
68
- | 0.421 | 1.0 | 631 | 0.5376 | 0.7505 |
69
- | 0.3189 | 2.0 | 1262 | 0.4039 | 0.8393 |
70
- | 0.1316 | 3.0 | 1893 | 0.5225 | 0.8346 |
71
- | 0.0717 | 4.0 | 2524 | 0.7629 | 0.8318 |
72
- | 0.0963 | 5.0 | 3155 | 0.9056 | 0.8263 |
 
 
 
 
 
73
 
74
 
75
  ### Framework versions
 
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
+ value: 0.8322147651006712
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 [microsoft/beit-large-patch16-224](https://huggingface.co/microsoft/beit-large-patch16-224) on the imagefolder dataset.
34
  It achieves the following results on the evaluation set:
35
+ - Loss: 1.8357
36
+ - Accuracy: 0.8322
37
 
38
  ## Model description
39
 
 
59
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
60
  - lr_scheduler_type: linear
61
  - lr_scheduler_warmup_ratio: 0.1
62
+ - num_epochs: 10
63
 
64
  ### Training results
65
 
66
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
67
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
68
+ | 0.4181 | 1.0 | 631 | 0.4865 | 0.7722 |
69
+ | 0.3391 | 2.0 | 1262 | 0.4494 | 0.8314 |
70
+ | 0.1276 | 3.0 | 1893 | 0.5148 | 0.8393 |
71
+ | 0.1436 | 4.0 | 2524 | 0.7474 | 0.8302 |
72
+ | 0.1404 | 5.0 | 3155 | 1.1243 | 0.8287 |
73
+ | 0.0742 | 6.0 | 3786 | 1.4178 | 0.8401 |
74
+ | 0.0155 | 7.0 | 4417 | 1.6465 | 0.8247 |
75
+ | 0.0 | 8.0 | 5048 | 1.7427 | 0.8239 |
76
+ | 0.0 | 9.0 | 5679 | 1.8000 | 0.8346 |
77
+ | 0.0 | 10.0 | 6310 | 1.8357 | 0.8322 |
78
 
79
 
80
  ### Framework versions
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f4699c1834643d4071190b83444e1fb74bdf370367c2c25b5045662c9bd6db60
3
  size 1213789289
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:751483bf67ff68e9153b11c0a76496e4e1d513aa44e233588934b38543e38719
3
  size 1213789289