Hugging Face's logo

jayanthspratap
/
swinv2-base-patch4-window8-256

TensorBoard
Safetensors
swinv2
Generated from Trainer
Eval Results (legacy)
Model card Files
xet
Metrics Community
jayanthspratap commited on
Commit
1e069dc
·
verified ·
1 Parent(s): 3096fe2

Model save

Browse files
Files changed (2) hide show
  1. README.md +40 -20
  2. model.safetensors +1 -1
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
- value: 0.813953488372093
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/swinv2-base-patch4-window8-256](https://huggingface.co/microsoft/swinv2-base-patch4-window8-256) on the imagefolder dataset.
34
  It achieves the following results on the evaluation set:
35
- - Loss: 0.5212
36
- - Accuracy: 0.8140
37
 
38
  ## Model description
39
 
@@ -52,31 +52,51 @@ More information needed
52
  ### Training hyperparameters
53
 
54
  The following hyperparameters were used during training:
55
- - learning_rate: 5e-06
56
- - train_batch_size: 4
57
- - eval_batch_size: 4
58
  - seed: 42
59
  - gradient_accumulation_steps: 4
60
- - total_train_batch_size: 16
61
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
62
  - lr_scheduler_type: linear
63
  - lr_scheduler_warmup_ratio: 0.1
64
- - num_epochs: 10
65
 
66
  ### Training results
67
 
68
- | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
- |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
- | No log | 0.96 | 6 | 0.6027 | 0.7907 |
71
- | 0.6492 | 1.92 | 12 | 0.5212 | 0.8140 |
72
- | 0.6492 | 2.88 | 18 | 0.4939 | 0.8140 |
73
- | 0.5773 | 4.0 | 25 | 0.4829 | 0.8140 |
74
- | 0.6313 | 4.96 | 31 | 0.4833 | 0.8140 |
75
- | 0.6313 | 5.92 | 37 | 0.4873 | 0.8140 |
76
- | 0.5665 | 6.88 | 43 | 0.4876 | 0.8140 |
77
- | 0.5615 | 8.0 | 50 | 0.4861 | 0.8140 |
78
- | 0.5615 | 8.96 | 56 | 0.4873 | 0.8140 |
79
- | 0.5712 | 9.6 | 60 | 0.4871 | 0.8140 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
80
 
81
 
82
  ### Framework versions
 
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
+ value: 0.7241379310344828
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/swinv2-base-patch4-window8-256](https://huggingface.co/microsoft/swinv2-base-patch4-window8-256) on the imagefolder dataset.
34
  It achieves the following results on the evaluation set:
35
+ - Loss: 0.5995
36
+ - Accuracy: 0.7241
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: 1
57
+ - eval_batch_size: 1
58
  - seed: 42
59
  - gradient_accumulation_steps: 4
60
+ - total_train_batch_size: 4
61
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
62
  - lr_scheduler_type: linear
63
  - lr_scheduler_warmup_ratio: 0.1
64
+ - num_epochs: 30
65
 
66
  ### Training results
67
 
68
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
+ |:-------------:|:-------:|:----:|:---------------:|:--------:|
70
+ | 0.5428 | 0.9912 | 28 | 0.6211 | 0.7241 |
71
+ | 0.6494 | 1.9823 | 56 | 0.6130 | 0.7241 |
72
+ | 0.5752 | 2.9735 | 84 | 0.6846 | 0.7241 |
73
+ | 0.7165 | 4.0 | 113 | 0.9642 | 0.7241 |
74
+ | 0.5699 | 4.9912 | 141 | 0.6072 | 0.7241 |
75
+ | 0.5517 | 5.9823 | 169 | 0.6231 | 0.7241 |
76
+ | 0.5268 | 6.9735 | 197 | 0.6098 | 0.7241 |
77
+ | 0.672 | 8.0 | 226 | 0.5891 | 0.7241 |
78
+ | 0.5448 | 8.9912 | 254 | 0.6023 | 0.7241 |
79
+ | 0.555 | 9.9823 | 282 | 0.5917 | 0.7241 |
80
+ | 0.5818 | 10.9735 | 310 | 0.5940 | 0.7241 |
81
+ | 0.6556 | 12.0 | 339 | 0.5966 | 0.7241 |
82
+ | 0.716 | 12.9912 | 367 | 0.5904 | 0.7241 |
83
+ | 0.6104 | 13.9823 | 395 | 0.5938 | 0.7241 |
84
+ | 0.5046 | 14.9735 | 423 | 0.5921 | 0.7241 |
85
+ | 0.5871 | 16.0 | 452 | 0.6027 | 0.7241 |
86
+ | 0.5222 | 16.9912 | 480 | 0.5921 | 0.7241 |
87
+ | 0.5511 | 17.9823 | 508 | 0.5948 | 0.7241 |
88
+ | 0.6394 | 18.9735 | 536 | 0.5969 | 0.7241 |
89
+ | 0.566 | 20.0 | 565 | 0.6005 | 0.7241 |
90
+ | 0.6032 | 20.9912 | 593 | 0.5968 | 0.7241 |
91
+ | 0.4824 | 21.9823 | 621 | 0.5934 | 0.7241 |
92
+ | 0.4975 | 22.9735 | 649 | 0.5979 | 0.7241 |
93
+ | 0.4976 | 24.0 | 678 | 0.6034 | 0.7241 |
94
+ | 0.5355 | 24.9912 | 706 | 0.6033 | 0.7241 |
95
+ | 0.4323 | 25.9823 | 734 | 0.6015 | 0.7241 |
96
+ | 0.5579 | 26.9735 | 762 | 0.6043 | 0.7241 |
97
+ | 0.5639 | 28.0 | 791 | 0.6023 | 0.7241 |
98
+ | 0.5595 | 28.9912 | 819 | 0.5996 | 0.7241 |
99
+ | 0.4372 | 29.7345 | 840 | 0.5995 | 0.7241 |
100
 
101
 
102
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2c2d5f7b5676d641ae7f4537cc10f86a799caa079b6a02018a04c0991e5c8c72
3
  size 347645480
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f96dcb87333eb1bdcaea4b6b9ce7360fd42d417c79f02039c219f8de201f742
3
  size 347645480