Hugging Face's logo

onizukal
/
Boya1_3Class_Adamax_1e4_20Epoch_Beit-large-224_fold4

Image Classification
Transformers
PyTorch
beit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
onizukal commited on
Commit
677c930
•
1 Parent(s): 296116a

End of training

Browse files
Files changed (1) hide show
  1. README.md +9 -14
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
- value: 0.8420054200542005
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: 1.7296
36
- - Accuracy: 0.8420
37
 
38
  ## Model description
39
 
@@ -59,22 +59,17 @@ 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: 10
63
 
64
  ### Training results
65
 
66
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
67
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
68
- | 0.3707 | 1.0 | 923 | 0.4482 | 0.8136 |
69
- | 0.3226 | 2.0 | 1846 | 0.4118 | 0.8336 |
70
- | 0.1875 | 3.0 | 2769 | 0.5879 | 0.8344 |
71
- | 0.1605 | 4.0 | 3692 | 0.7513 | 0.8304 |
72
- | 0.1167 | 5.0 | 4615 | 1.2298 | 0.8396 |
73
- | 0.0003 | 6.0 | 5538 | 1.5337 | 0.8331 |
74
- | 0.0635 | 7.0 | 6461 | 1.5787 | 0.8377 |
75
- | 0.0071 | 8.0 | 7384 | 1.6914 | 0.8350 |
76
- | 0.0 | 9.0 | 8307 | 1.7195 | 0.8404 |
77
- | 0.0 | 10.0 | 9230 | 1.7296 | 0.8420 |
78
 
79
 
80
  ### Framework versions
 
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
+ value: 0.8406504065040651
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: 1.2276
36
+ - Accuracy: 0.8407
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: 5
63
 
64
  ### Training results
65
 
66
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
67
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
68
+ | 0.3425 | 1.0 | 923 | 0.4401 | 0.8230 |
69
+ | 0.2611 | 2.0 | 1846 | 0.4241 | 0.8314 |
70
+ | 0.1595 | 3.0 | 2769 | 0.5720 | 0.8363 |
71
+ | 0.1001 | 4.0 | 3692 | 0.9325 | 0.8344 |
72
+ | 0.0096 | 5.0 | 4615 | 1.2276 | 0.8407 |
 
 
 
 
 
73
 
74
 
75
  ### Framework versions