Hugging Face's logo

Lalith47
/
custom-cloud-model

Image Classification
Transformers
TensorBoard
Safetensors
swin
Generated from Trainer
Eval Results (legacy)
Model card Files
xet
Metrics Community
Lalith47 commited on
Commit
7445254
·
verified ·
1 Parent(s): 58600ba

End of training

Browse files
Files changed (2) hide show
  1. README.md +29 -24
  2. model.safetensors +1 -1
README.md CHANGED
@@ -23,7 +23,7 @@ model-index:
23
  metrics:
24
  - name: Accuracy
25
  type: accuracy
26
- value: 0.9423868060112
27
  ---
28
 
29
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -33,8 +33,8 @@ should probably proofread and complete it, then remove this comment. -->
33
 
34
  This model is a fine-tuned version of [microsoft/swin-base-patch4-window7-224](https://huggingface.co/microsoft/swin-base-patch4-window7-224) on the imagefolder dataset.
35
  It achieves the following results on the evaluation set:
36
- - Loss: 0.2205
37
- - Accuracy: 0.9424
38
 
39
  ## Model description
40
 
@@ -62,33 +62,38 @@ The following hyperparameters were used during training:
62
  - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
63
  - lr_scheduler_type: cosine
64
  - lr_scheduler_warmup_ratio: 0.1
65
- - num_epochs: 20
66
  - mixed_precision_training: Native AMP
67
 
68
  ### Training results
69
 
70
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
71
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
72
- | 0.9957 | 1.0 | 80 | 0.8805 | 0.7675 |
73
- | 0.829 | 2.0 | 160 | 0.3883 | 0.8539 |
74
- | 0.7625 | 3.0 | 240 | 0.3983 | 0.8868 |
75
- | 0.6964 | 4.0 | 320 | 0.2094 | 0.9300 |
76
- | 0.422 | 5.0 | 400 | 0.2364 | 0.9259 |
77
- | 0.3852 | 6.0 | 480 | 0.1997 | 0.9321 |
78
- | 0.3882 | 7.0 | 560 | 0.2917 | 0.9136 |
79
- | 0.2866 | 8.0 | 640 | 0.2616 | 0.9383 |
80
- | 0.2217 | 9.0 | 720 | 0.2164 | 0.9424 |
81
- | 0.1768 | 10.0 | 800 | 0.2873 | 0.9321 |
82
- | 0.1724 | 11.0 | 880 | 0.3396 | 0.9239 |
83
- | 0.1415 | 12.0 | 960 | 0.2368 | 0.9486 |
84
- | 0.1551 | 13.0 | 1040 | 0.2600 | 0.9342 |
85
- | 0.0656 | 14.0 | 1120 | 0.2325 | 0.9362 |
86
- | 0.0751 | 15.0 | 1200 | 0.1522 | 0.9527 |
87
- | 0.0712 | 16.0 | 1280 | 0.1996 | 0.9424 |
88
- | 0.0907 | 17.0 | 1360 | 0.2027 | 0.9444 |
89
- | 0.0609 | 18.0 | 1440 | 0.1956 | 0.9465 |
90
- | 0.0816 | 19.0 | 1520 | 0.2157 | 0.9486 |
91
- | 0.0359 | 20.0 | 1600 | 0.2205 | 0.9424 |
 
 
 
 
 
92
 
93
 
94
  ### Framework versions
 
23
  metrics:
24
  - name: Accuracy
25
  type: accuracy
26
+ value: 0.9506173133850098
27
  ---
28
 
29
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
33
 
34
  This model is a fine-tuned version of [microsoft/swin-base-patch4-window7-224](https://huggingface.co/microsoft/swin-base-patch4-window7-224) on the imagefolder dataset.
35
  It achieves the following results on the evaluation set:
36
+ - Loss: 0.2242
37
+ - Accuracy: 0.9506
38
 
39
  ## Model description
40
 
 
62
  - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
63
  - lr_scheduler_type: cosine
64
  - lr_scheduler_warmup_ratio: 0.1
65
+ - num_epochs: 25
66
  - mixed_precision_training: Native AMP
67
 
68
  ### Training results
69
 
70
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
71
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
72
+ | 1.153 | 1.0 | 80 | 0.9964 | 0.7510 |
73
+ | 0.8046 | 2.0 | 160 | 0.4400 | 0.8477 |
74
+ | 0.7706 | 3.0 | 240 | 0.5513 | 0.8107 |
75
+ | 0.6695 | 4.0 | 320 | 0.2639 | 0.9136 |
76
+ | 0.4697 | 5.0 | 400 | 0.2199 | 0.9300 |
77
+ | 0.4564 | 6.0 | 480 | 0.1808 | 0.9321 |
78
+ | 0.4094 | 7.0 | 560 | 0.2471 | 0.9239 |
79
+ | 0.2445 | 8.0 | 640 | 0.1998 | 0.9424 |
80
+ | 0.3153 | 9.0 | 720 | 0.2600 | 0.9136 |
81
+ | 0.1994 | 10.0 | 800 | 0.3160 | 0.9259 |
82
+ | 0.2205 | 11.0 | 880 | 0.2486 | 0.9239 |
83
+ | 0.2312 | 12.0 | 960 | 0.2131 | 0.9486 |
84
+ | 0.2382 | 13.0 | 1040 | 0.2487 | 0.9239 |
85
+ | 0.1158 | 14.0 | 1120 | 0.2153 | 0.9506 |
86
+ | 0.1 | 15.0 | 1200 | 0.2271 | 0.9486 |
87
+ | 0.0916 | 16.0 | 1280 | 0.2626 | 0.9259 |
88
+ | 0.1021 | 17.0 | 1360 | 0.2130 | 0.9403 |
89
+ | 0.0991 | 18.0 | 1440 | 0.2240 | 0.9444 |
90
+ | 0.0526 | 19.0 | 1520 | 0.2353 | 0.9506 |
91
+ | 0.0461 | 20.0 | 1600 | 0.2137 | 0.9506 |
92
+ | 0.0832 | 21.0 | 1680 | 0.2215 | 0.9444 |
93
+ | 0.0708 | 22.0 | 1760 | 0.2114 | 0.9506 |
94
+ | 0.1027 | 23.0 | 1840 | 0.2104 | 0.9527 |
95
+ | 0.0292 | 24.0 | 1920 | 0.2346 | 0.9547 |
96
+ | 0.033 | 25.0 | 2000 | 0.2242 | 0.9506 |
97
 
98
 
99
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:70171d1b1d5a7b8e014f4ee85c1bf29052420dea9ab52a21832363aac3a349ce
3
  size 347519316
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e013f8f9173e11dda8fc89126bf5c1bb098ccf8ff47935f8c606b6552df8bade
3
  size 347519316