Hugging Face's logo

djbp
/
swin-tiny-patch4-window7-224-Mid-NonMidMarket-Classification

Image Classification
Transformers
PyTorch
TensorBoard
Safetensors
swin
Generated from Trainer
Eval Results (legacy)
Model card Files
xet
Metrics Community
djbp commited on
Commit
71e1f17
·
verified ·
1 Parent(s): 2b6cd58

Model save

Browse files
Files changed (2) hide show
  1. README.md +16 -17
  2. model.safetensors +1 -1
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
- value: 0.8425624321389794
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/swin-tiny-patch4-window7-224](https://huggingface.co/microsoft/swin-tiny-patch4-window7-224) on the imagefolder dataset.
34
  It achieves the following results on the evaluation set:
35
- - Loss: 0.4046
36
- - Accuracy: 0.8426
37
 
38
  ## Model description
39
 
@@ -53,11 +53,11 @@ More information needed
53
 
54
  The following hyperparameters were used during training:
55
  - learning_rate: 5e-05
56
- - train_batch_size: 32
57
- - eval_batch_size: 32
58
  - seed: 42
59
  - gradient_accumulation_steps: 4
60
- - total_train_batch_size: 128
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
@@ -67,21 +67,20 @@ The following hyperparameters were used during training:
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
  |:-------------:|:------:|:----:|:---------------:|:--------:|
70
- | 0.5809 | 0.9884 | 64 | 0.5024 | 0.7937 |
71
- | 0.5326 | 1.9923 | 129 | 0.4402 | 0.8132 |
72
- | 0.4626 | 2.9961 | 194 | 0.4244 | 0.8284 |
73
- | 0.4778 | 4.0 | 259 | 0.4234 | 0.8274 |
74
- | 0.4109 | 4.9884 | 323 | 0.4197 | 0.8306 |
75
- | 0.3764 | 5.9923 | 388 | 0.4095 | 0.8295 |
76
- | 0.3725 | 6.9961 | 453 | 0.4046 | 0.8426 |
77
- | 0.3583 | 8.0 | 518 | 0.4109 | 0.8371 |
78
- | 0.3451 | 8.9884 | 582 | 0.4171 | 0.8350 |
79
- | 0.3351 | 9.8842 | 640 | 0.4153 | 0.8404 |
80
 
81
 
82
  ### Framework versions
83
 
84
  - Transformers 4.41.2
85
- - Pytorch 2.3.0+cu121
86
  - Datasets 2.19.2
87
  - Tokenizers 0.19.1
 
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
+ value: 0.3763440860215054
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/swin-tiny-patch4-window7-224](https://huggingface.co/microsoft/swin-tiny-patch4-window7-224) on the imagefolder dataset.
34
  It achieves the following results on the evaluation set:
35
+ - Loss: 2.0368
36
+ - Accuracy: 0.3763
37
 
38
  ## Model description
39
 
 
53
 
54
  The following hyperparameters were used during training:
55
  - learning_rate: 5e-05
56
+ - train_batch_size: 64
57
+ - eval_batch_size: 64
58
  - seed: 42
59
  - gradient_accumulation_steps: 4
60
+ - total_train_batch_size: 256
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
 
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
  |:-------------:|:------:|:----:|:---------------:|:--------:|
70
+ | No log | 0.8889 | 6 | 2.8975 | 0.1398 |
71
+ | 2.9658 | 1.9259 | 13 | 2.6866 | 0.2204 |
72
+ | 2.6529 | 2.9630 | 20 | 2.4370 | 0.3011 |
73
+ | 2.6529 | 4.0 | 27 | 2.2516 | 0.3495 |
74
+ | 2.3311 | 4.8889 | 33 | 2.1685 | 0.3710 |
75
+ | 2.1441 | 5.9259 | 40 | 2.0987 | 0.3656 |
76
+ | 2.1441 | 6.9630 | 47 | 2.0567 | 0.3925 |
77
+ | 2.0507 | 8.0 | 54 | 2.0416 | 0.3871 |
78
+ | 1.988 | 8.8889 | 60 | 2.0368 | 0.3763 |
 
79
 
80
 
81
  ### Framework versions
82
 
83
  - Transformers 4.41.2
84
+ - Pytorch 1.13.1+cu117
85
  - Datasets 2.19.2
86
  - Tokenizers 0.19.1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:090b7723d551154d9a4f98820d373b4593412c9f56ddcd61fc01e98704a38c06
3
  size 110398208
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b89a6e3f2ef68912b0214c90af89c534c6aab552210fad7164f072a2e2a85810
3
  size 110398208