Hugging Face's logo

habibi26
/
ktp-kk-crop

Image Classification
Transformers
TensorBoard
Safetensors
clip
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
habibi26 commited on
Commit
f94313c
·
verified ·
1 Parent(s): ef26ea2

Model save

Browse files
Files changed (2) hide show
  1. README.md +30 -30
  2. model.safetensors +1 -1
README.md CHANGED
@@ -21,7 +21,7 @@ model-index:
21
  metrics:
22
  - name: Accuracy
23
  type: accuracy
24
- value: 0.8021978021978022
25
  ---
26
 
27
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -31,8 +31,8 @@ should probably proofread and complete it, then remove this comment. -->
31
 
32
  This model is a fine-tuned version of [openai/clip-vit-base-patch32](https://huggingface.co/openai/clip-vit-base-patch32) on the imagefolder dataset.
33
  It achieves the following results on the evaluation set:
34
- - Loss: 2.5306
35
- - Accuracy: 0.8022
36
 
37
  ## Model description
38
 
@@ -64,33 +64,33 @@ The following hyperparameters were used during training:
64
 
65
  ### Training results
66
 
67
- | Training Loss | Epoch | Step | Validation Loss | Accuracy |
68
- |:-------------:|:-----:|:----:|:---------------:|:--------:|
69
- | No log | 1.0 | 2 | 0.6707 | 0.6154 |
70
- | No log | 2.0 | 4 | 0.6923 | 0.6154 |
71
- | No log | 3.0 | 6 | 0.7209 | 0.7033 |
72
- | No log | 4.0 | 8 | 0.4789 | 0.8022 |
73
- | No log | 5.0 | 10 | 0.3554 | 0.9011 |
74
- | No log | 6.0 | 12 | 0.8338 | 0.8242 |
75
- | No log | 7.0 | 14 | 1.0734 | 0.7912 |
76
- | 0.2476 | 8.0 | 16 | 1.0161 | 0.8242 |
77
- | 0.2476 | 9.0 | 18 | 0.8967 | 0.8571 |
78
- | 0.2476 | 10.0 | 20 | 0.8477 | 0.8681 |
79
- | 0.2476 | 11.0 | 22 | 1.3332 | 0.8352 |
80
- | 0.2476 | 12.0 | 24 | 3.4776 | 0.7253 |
81
- | 0.2476 | 13.0 | 26 | 6.0098 | 0.6374 |
82
- | 0.2476 | 14.0 | 28 | 3.8650 | 0.7253 |
83
- | 0.0277 | 15.0 | 30 | 2.2410 | 0.8132 |
84
- | 0.0277 | 16.0 | 32 | 1.4585 | 0.8132 |
85
- | 0.0277 | 17.0 | 34 | 1.4790 | 0.8022 |
86
- | 0.0277 | 18.0 | 36 | 1.8427 | 0.8242 |
87
- | 0.0277 | 19.0 | 38 | 2.0874 | 0.8242 |
88
- | 0.0277 | 20.0 | 40 | 2.2456 | 0.8132 |
89
- | 0.0277 | 21.0 | 42 | 2.3663 | 0.8022 |
90
- | 0.0277 | 22.0 | 44 | 2.4484 | 0.8022 |
91
- | 0.0001 | 23.0 | 46 | 2.4974 | 0.8022 |
92
- | 0.0001 | 24.0 | 48 | 2.5221 | 0.8022 |
93
- | 0.0001 | 25.0 | 50 | 2.5306 | 0.8022 |
94
 
95
 
96
  ### Framework versions
 
21
  metrics:
22
  - name: Accuracy
23
  type: accuracy
24
+ value: 0.967032967032967
25
  ---
26
 
27
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
31
 
32
  This model is a fine-tuned version of [openai/clip-vit-base-patch32](https://huggingface.co/openai/clip-vit-base-patch32) on the imagefolder dataset.
33
  It achieves the following results on the evaluation set:
34
+ - Loss: 0.1497
35
+ - Accuracy: 0.9670
36
 
37
  ## Model description
38
 
 
64
 
65
  ### Training results
66
 
67
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
68
+ |:-------------:|:-------:|:----:|:---------------:|:--------:|
69
+ | No log | 0.9655 | 7 | 0.6506 | 0.5824 |
70
+ | No log | 1.9310 | 14 | 0.3689 | 0.8352 |
71
+ | 0.5439 | 2.8966 | 21 | 0.1940 | 0.9341 |
72
+ | 0.5439 | 4.0 | 29 | 0.1185 | 0.9780 |
73
+ | 0.0961 | 4.9655 | 36 | 0.1345 | 0.9780 |
74
+ | 0.0961 | 5.9310 | 43 | 0.0828 | 0.9670 |
75
+ | 0.114 | 6.8966 | 50 | 0.3337 | 0.9451 |
76
+ | 0.114 | 8.0 | 58 | 0.1176 | 0.9670 |
77
+ | 0.0106 | 8.9655 | 65 | 0.1484 | 0.9670 |
78
+ | 0.0106 | 9.9310 | 72 | 0.0991 | 0.9780 |
79
+ | 0.0609 | 10.8966 | 79 | 0.2071 | 0.9670 |
80
+ | 0.0609 | 12.0 | 87 | 0.2575 | 0.9341 |
81
+ | 0.0112 | 12.9655 | 94 | 0.1714 | 0.9451 |
82
+ | 0.0112 | 13.9310 | 101 | 0.1918 | 0.9451 |
83
+ | 0.0147 | 14.8966 | 108 | 0.1829 | 0.9670 |
84
+ | 0.0147 | 16.0 | 116 | 0.3227 | 0.9341 |
85
+ | 0.0025 | 16.9655 | 123 | 0.1287 | 0.9780 |
86
+ | 0.0025 | 17.9310 | 130 | 0.1364 | 0.9780 |
87
+ | 0.0 | 18.8966 | 137 | 0.1446 | 0.9670 |
88
+ | 0.0 | 20.0 | 145 | 0.1487 | 0.9670 |
89
+ | 0.0 | 20.9655 | 152 | 0.1499 | 0.9670 |
90
+ | 0.0 | 21.9310 | 159 | 0.1501 | 0.9670 |
91
+ | 0.0 | 22.8966 | 166 | 0.1498 | 0.9670 |
92
+ | 0.0 | 24.0 | 174 | 0.1497 | 0.9670 |
93
+ | 0.0 | 24.1379 | 175 | 0.1497 | 0.9670 |
94
 
95
 
96
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dc19d445406ecf22b049d0a730fac54a5c2bd71e43aca109884ef65197b2396a
3
  size 349854120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0930d3d00a0f8440842fc8e9adace12a20d1d1e5ca7904fe7df8ab9ec3630d63
3
  size 349854120