Hugging Face's logo

onizukal
/
Boya1_RMSProp_1-e5_20Epoch_09Momentum_Beit-base-patch16_fold1

Image Classification
Transformers
Safetensors
beit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
onizukal commited on
Commit
ed05cbb
•
1 Parent(s): 5cc43bf

End of training

Browse files
Files changed (3) hide show
  1. README.md +27 -17
  2. model.safetensors +1 -1
  3. training_args.bin +1 -1
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
- value: 0.6692913385826772
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-base-patch16-224-pt22k-ft22k](https://huggingface.co/microsoft/beit-base-patch16-224-pt22k-ft22k) on the imagefolder dataset.
34
  It achieves the following results on the evaluation set:
35
- - Loss: 1.6421
36
- - Accuracy: 0.6693
37
 
38
  ## Model description
39
 
@@ -52,29 +52,39 @@ More information needed
52
  ### Training hyperparameters
53
 
54
  The following hyperparameters were used during training:
55
- - learning_rate: 1e-05
56
  - train_batch_size: 16
57
  - eval_batch_size: 16
58
  - seed: 42
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
- | 1.0907 | 1.0 | 924 | 1.0851 | 0.6296 |
69
- | 0.945 | 2.0 | 1848 | 1.0698 | 0.6340 |
70
- | 0.7725 | 3.0 | 2772 | 0.9959 | 0.6687 |
71
- | 0.4807 | 4.0 | 3696 | 1.0700 | 0.6677 |
72
- | 0.5152 | 5.0 | 4620 | 1.1856 | 0.6579 |
73
- | 0.264 | 6.0 | 5544 | 1.2952 | 0.6647 |
74
- | 0.1403 | 7.0 | 6468 | 1.4304 | 0.6655 |
75
- | 0.1127 | 8.0 | 7392 | 1.5557 | 0.6679 |
76
- | 0.1072 | 9.0 | 8316 | 1.6120 | 0.6685 |
77
- | 0.1138 | 10.0 | 9240 | 1.6421 | 0.6693 |
 
 
 
 
 
 
 
 
 
 
78
 
79
 
80
  ### Framework versions
 
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
+ value: 0.6532717893021993
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-base-patch16-224-pt22k-ft22k](https://huggingface.co/microsoft/beit-base-patch16-224-pt22k-ft22k) on the imagefolder dataset.
34
  It achieves the following results on the evaluation set:
35
+ - Loss: 3.0645
36
+ - Accuracy: 0.6533
37
 
38
  ## Model description
39
 
 
52
  ### Training hyperparameters
53
 
54
  The following hyperparameters were used during training:
55
+ - learning_rate: 0.0001
56
  - train_batch_size: 16
57
  - eval_batch_size: 16
58
  - seed: 42
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: 20
63
 
64
  ### Training results
65
 
66
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
67
+ |:-------------:|:-----:|:-----:|:---------------:|:--------:|
68
+ | 1.1014 | 1.0 | 924 | 1.1155 | 0.6131 |
69
+ | 0.917 | 2.0 | 1848 | 1.0767 | 0.6242 |
70
+ | 0.7533 | 3.0 | 2772 | 1.0565 | 0.6473 |
71
+ | 0.493 | 4.0 | 3696 | 1.1952 | 0.6530 |
72
+ | 0.482 | 5.0 | 4620 | 1.3688 | 0.6473 |
73
+ | 0.1989 | 6.0 | 5544 | 1.6284 | 0.6435 |
74
+ | 0.1622 | 7.0 | 6468 | 2.0114 | 0.6373 |
75
+ | 0.0666 | 8.0 | 7392 | 2.2124 | 0.6541 |
76
+ | 0.0417 | 9.0 | 8316 | 2.4424 | 0.6389 |
77
+ | 0.0196 | 10.0 | 9240 | 2.5614 | 0.6397 |
78
+ | 0.0323 | 11.0 | 10164 | 2.8070 | 0.6443 |
79
+ | 0.0014 | 12.0 | 11088 | 2.8503 | 0.6506 |
80
+ | 0.001 | 13.0 | 12012 | 2.8885 | 0.6497 |
81
+ | 0.0706 | 14.0 | 12936 | 3.0224 | 0.6462 |
82
+ | 0.0003 | 15.0 | 13860 | 3.0064 | 0.6465 |
83
+ | 0.0013 | 16.0 | 14784 | 3.0115 | 0.6552 |
84
+ | 0.0316 | 17.0 | 15708 | 3.0514 | 0.6563 |
85
+ | 0.0002 | 18.0 | 16632 | 3.0348 | 0.6568 |
86
+ | 0.0 | 19.0 | 17556 | 3.0737 | 0.6508 |
87
+ | 0.0494 | 20.0 | 18480 | 3.0645 | 0.6533 |
88
 
89
 
90
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:08c64cca68c8fe48ab7bf203aad1a2e384786b8da9cb34a6a52c7417cdad88aa
3
  size 343129544
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03b47859f778ecb58e65217fa7104237ebbbfea3d987cefb004d3e9e4e32b04d
3
  size 343129544
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8a22b617296dee1b6eb4886e7a0a0e1984d2f915d0ddd6fcbb7c46b40489c5d6
3
  size 4704
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:372e21b3f66c823bccf323c9bd7bbc52d9d39c6f6cf82b9008319f0e011e91ec
3
  size 4704