Hugging Face's logo

amaye15
/
SwinV2-Base-Document-Classifier

Image Classification
Transformers
Safetensors
swinv2
Generated from Trainer
Inference Endpoints
Model card Files Community
amaye15 commited on
Commit
8a354ee
•
1 Parent(s): dde12b2

End of training

Browse files
Files changed (4) hide show
  1. .DS_Store +0 -0
  2. README.md +16 -16
  3. model.safetensors +1 -1
  4. training_args.bin +1 -1
.DS_Store ADDED
Binary file (8.2 kB). View file
 
README.md CHANGED
@@ -20,11 +20,11 @@ should probably proofread and complete it, then remove this comment. -->
20
 
21
  This model is a fine-tuned version of [microsoft/swinv2-base-patch4-window16-256](https://huggingface.co/microsoft/swinv2-base-patch4-window16-256) on the None dataset.
22
  It achieves the following results on the evaluation set:
23
- - Loss: 0.0191
24
- - Accuracy: 0.9946
25
- - F1: 0.9946
26
- - Precision: 0.9946
27
- - Recall: 0.9946
28
 
29
  ## Model description
30
 
@@ -57,20 +57,20 @@ The following hyperparameters were used during training:
57
 
58
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
59
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
60
- | 0.0794 | 0.2 | 160 | 0.0330 | 0.9899 | 0.9899 | 0.9899 | 0.9899 |
61
- | 0.0619 | 0.3 | 240 | 0.0278 | 0.9908 | 0.9908 | 0.9908 | 0.9909 |
62
- | 0.0499 | 0.4 | 320 | 0.0272 | 0.9914 | 0.9914 | 0.9914 | 0.9914 |
63
- | 0.0482 | 0.5 | 400 | 0.0275 | 0.9917 | 0.9917 | 0.9917 | 0.9917 |
64
- | 0.0416 | 1.1 | 480 | 0.0218 | 0.9931 | 0.9931 | 0.9931 | 0.9931 |
65
- | 0.0353 | 1.2 | 560 | 0.0208 | 0.9942 | 0.9942 | 0.9942 | 0.9942 |
66
- | 0.0306 | 1.3 | 640 | 0.0183 | 0.9949 | 0.9949 | 0.9949 | 0.9949 |
67
- | 0.0296 | 1.4 | 720 | 0.0198 | 0.9944 | 0.9944 | 0.9944 | 0.9944 |
68
- | 0.0305 | 1.5 | 800 | 0.0191 | 0.9946 | 0.9946 | 0.9946 | 0.9946 |
69
 
70
 
71
  ### Framework versions
72
 
73
  - Transformers 4.39.3
74
- - Pytorch 2.2.2
75
- - Datasets 2.18.0
76
  - Tokenizers 0.15.2
 
20
 
21
  This model is a fine-tuned version of [microsoft/swinv2-base-patch4-window16-256](https://huggingface.co/microsoft/swinv2-base-patch4-window16-256) on the None dataset.
22
  It achieves the following results on the evaluation set:
23
+ - Loss: 0.0365
24
+ - Accuracy: 0.9901
25
+ - F1: 0.9901
26
+ - Precision: 0.9902
27
+ - Recall: 0.9901
28
 
29
  ## Model description
30
 
 
57
 
58
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
59
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
60
+ | 0.0801 | 0.2 | 160 | 0.0489 | 0.9837 | 0.9838 | 0.9841 | 0.9837 |
61
+ | 0.0656 | 0.3 | 240 | 0.0436 | 0.9877 | 0.9878 | 0.9879 | 0.9878 |
62
+ | 0.058 | 0.4 | 320 | 0.0462 | 0.9884 | 0.9885 | 0.9886 | 0.9885 |
63
+ | 0.0462 | 0.5 | 400 | 0.0426 | 0.9881 | 0.9882 | 0.9883 | 0.9882 |
64
+ | 0.0632 | 1.1 | 480 | 0.0356 | 0.9896 | 0.9897 | 0.9897 | 0.9897 |
65
+ | 0.0307 | 1.2 | 560 | 0.0331 | 0.9912 | 0.9912 | 0.9913 | 0.9912 |
66
+ | 0.0314 | 1.3 | 640 | 0.0347 | 0.9902 | 0.9903 | 0.9903 | 0.9903 |
67
+ | 0.0315 | 1.4 | 720 | 0.0365 | 0.9898 | 0.9898 | 0.9899 | 0.9898 |
68
+ | 0.0301 | 1.5 | 800 | 0.0365 | 0.9901 | 0.9901 | 0.9902 | 0.9901 |
69
 
70
 
71
  ### Framework versions
72
 
73
  - Transformers 4.39.3
74
+ - Pytorch 2.3.1
75
+ - Datasets 2.19.2
76
  - Tokenizers 0.15.2
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:70c214f7529796e41d06693872910b6e9c70c950a6bff2e1dd832ffbd850bcf6
3
  size 347657788
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d45d5b7b4f548b578829ecae5a7c4daa0f2087f641604f35be39acb454296cfd
3
  size 347657788
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:85edbb24908afb517e69a64a4520221852132703b1a24815afc7c29da105a95a
3
  size 4984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dcbfb57cacfcd9a50e91bac3ce8665e74c5f13f7800f346da928dcadd83d4f50
3
  size 4984