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
674b20b
·
verified ·
1 Parent(s): e0fe8b5

End of training

Browse files
Files changed (2) hide show
  1. README.md +27 -37
  2. model.safetensors +1 -1
README.md CHANGED
@@ -23,7 +23,7 @@ model-index:
23
  metrics:
24
  - name: Accuracy
25
  type: accuracy
26
- value: 0.6701570749282837
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: 1.6095
37
- - Accuracy: 0.6702
38
 
39
  ## Model description
40
 
@@ -54,51 +54,41 @@ More information needed
54
 
55
  The following hyperparameters were used during training:
56
  - learning_rate: 5e-05
57
- - train_batch_size: 16
58
- - eval_batch_size: 16
59
  - seed: 42
60
  - gradient_accumulation_steps: 4
61
- - total_train_batch_size: 64
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: 30
66
  - mixed_precision_training: Native AMP
67
 
68
  ### Training results
69
 
70
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
71
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
72
- | 2.0582 | 1.0 | 34 | 1.8348 | 0.3351 |
73
- | 1.2969 | 2.0 | 68 | 1.2586 | 0.5288 |
74
- | 0.9759 | 3.0 | 102 | 1.0590 | 0.6047 |
75
- | 0.8705 | 4.0 | 136 | 0.9122 | 0.6466 |
76
- | 0.6166 | 5.0 | 170 | 0.9506 | 0.6597 |
77
- | 0.5408 | 6.0 | 204 | 0.9137 | 0.6623 |
78
- | 0.3518 | 7.0 | 238 | 1.1081 | 0.6440 |
79
- | 0.3488 | 8.0 | 272 | 1.0060 | 0.6545 |
80
- | 0.3068 | 9.0 | 306 | 1.0221 | 0.6780 |
81
- | 0.2824 | 10.0 | 340 | 1.1638 | 0.6283 |
82
- | 0.2048 | 11.0 | 374 | 1.2044 | 0.6518 |
83
- | 0.1972 | 12.0 | 408 | 1.2988 | 0.6440 |
84
- | 0.1818 | 13.0 | 442 | 1.1882 | 0.6728 |
85
- | 0.1316 | 14.0 | 476 | 1.2993 | 0.6518 |
86
- | 0.12 | 15.0 | 510 | 1.2681 | 0.6754 |
87
- | 0.0997 | 16.0 | 544 | 1.3582 | 0.6780 |
88
- | 0.1069 | 17.0 | 578 | 1.3963 | 0.6571 |
89
- | 0.078 | 18.0 | 612 | 1.4492 | 0.6675 |
90
- | 0.0783 | 19.0 | 646 | 1.4504 | 0.6545 |
91
- | 0.0765 | 20.0 | 680 | 1.5165 | 0.6675 |
92
- | 0.068 | 21.0 | 714 | 1.4972 | 0.6649 |
93
- | 0.0768 | 22.0 | 748 | 1.4949 | 0.6492 |
94
- | 0.0631 | 23.0 | 782 | 1.5874 | 0.6754 |
95
- | 0.0425 | 24.0 | 816 | 1.5859 | 0.6675 |
96
- | 0.0503 | 25.0 | 850 | 1.5003 | 0.6702 |
97
- | 0.0486 | 26.0 | 884 | 1.5484 | 0.6675 |
98
- | 0.0383 | 27.0 | 918 | 1.5526 | 0.6780 |
99
- | 0.036 | 28.0 | 952 | 1.6089 | 0.6623 |
100
- | 0.0212 | 29.0 | 986 | 1.5983 | 0.6754 |
101
- | 0.0269 | 30.0 | 1020 | 1.6095 | 0.6702 |
102
 
103
 
104
  ### Framework versions
 
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
 
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
 
 
54
 
55
  The following hyperparameters were used during training:
56
  - learning_rate: 5e-05
57
+ - train_batch_size: 8
58
+ - eval_batch_size: 8
59
  - seed: 42
60
  - gradient_accumulation_steps: 4
61
+ - total_train_batch_size: 32
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
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:74190b68f227ff03c4d9ff45f776fd05e41b96228ef525bc8446c813e9d215b3
3
  size 347519316
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce509c3972c17705268df89238398902adfe7a857601e7a889a519f52258530c
3
  size 347519316