Hugging Face's logo

habibi26
/
ktp-not-ktp-clip

Image Classification
Transformers
TensorBoard
Safetensors
clip
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
habibi26 commited on
Commit
73a156e
•
1 Parent(s): 82a43a2

Model save

Browse files
Files changed (3) hide show
  1. README.md +28 -23
  2. model.safetensors +1 -1
  3. runs/Jul03_12-38-35_e0133a370a2e/events.out.tfevents.1720010332.e0133a370a2e.34.2 +2 -2
README.md CHANGED
@@ -21,7 +21,7 @@ model-index:
21
  metrics:
22
  - name: Accuracy
23
  type: accuracy
24
- value: 0.9953271028037384
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: 0.0245
35
- - Accuracy: 0.9953
36
 
37
  ## Model description
38
 
@@ -60,31 +60,36 @@ The following hyperparameters were used during training:
60
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
61
  - lr_scheduler_type: linear
62
  - lr_scheduler_warmup_ratio: 0.1
63
- - num_epochs: 20
64
 
65
  ### Training results
66
 
67
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
68
  |:-------------:|:-------:|:----:|:---------------:|:--------:|
69
- | No log | 0.9231 | 6 | 0.4883 | 0.8972 |
70
- | 0.6748 | 2.0 | 13 | 0.0755 | 0.9720 |
71
- | 0.6748 | 2.9231 | 19 | 0.1373 | 0.9346 |
72
- | 0.1779 | 4.0 | 26 | 0.0682 | 0.9720 |
73
- | 0.1511 | 4.9231 | 32 | 0.0399 | 0.9766 |
74
- | 0.1511 | 6.0 | 39 | 0.0112 | 0.9953 |
75
- | 0.0248 | 6.9231 | 45 | 0.0555 | 0.9766 |
76
- | 0.057 | 8.0 | 52 | 0.0051 | 1.0 |
77
- | 0.057 | 8.9231 | 58 | 0.0293 | 0.9860 |
78
- | 0.0361 | 10.0 | 65 | 0.0272 | 0.9860 |
79
- | 0.011 | 10.9231 | 71 | 0.0170 | 0.9907 |
80
- | 0.011 | 12.0 | 78 | 0.0710 | 0.9860 |
81
- | 0.0006 | 12.9231 | 84 | 0.0721 | 0.9813 |
82
- | 0.0001 | 14.0 | 91 | 0.0277 | 0.9907 |
83
- | 0.0001 | 14.9231 | 97 | 0.0224 | 0.9953 |
84
- | 0.0001 | 16.0 | 104 | 0.0202 | 0.9953 |
85
- | 0.0 | 16.9231 | 110 | 0.0234 | 0.9953 |
86
- | 0.0 | 18.0 | 117 | 0.0245 | 0.9953 |
87
- | 0.0 | 18.4615 | 120 | 0.0245 | 0.9953 |
 
 
 
 
 
88
 
89
 
90
  ### Framework versions
 
21
  metrics:
22
  - name: Accuracy
23
  type: accuracy
24
+ value: 1.0
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: 0.0000
35
+ - Accuracy: 1.0
36
 
37
  ## Model description
38
 
 
60
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
61
  - lr_scheduler_type: linear
62
  - lr_scheduler_warmup_ratio: 0.1
63
+ - num_epochs: 25
64
 
65
  ### Training results
66
 
67
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
68
  |:-------------:|:-------:|:----:|:---------------:|:--------:|
69
+ | No log | 0.9231 | 6 | 0.2212 | 0.9533 |
70
+ | No log | 2.0 | 13 | 0.1671 | 0.9579 |
71
+ | 0.0031 | 2.9231 | 19 | 0.1645 | 0.9626 |
72
+ | 0.0031 | 4.0 | 26 | 0.0958 | 0.9766 |
73
+ | 0.1018 | 4.9231 | 32 | 0.0468 | 0.9860 |
74
+ | 0.1018 | 6.0 | 39 | 0.0092 | 0.9953 |
75
+ | 0.0279 | 6.9231 | 45 | 0.0505 | 0.9813 |
76
+ | 0.0279 | 8.0 | 52 | 0.0798 | 0.9860 |
77
+ | 0.0279 | 8.9231 | 58 | 0.0083 | 0.9953 |
78
+ | 0.0261 | 10.0 | 65 | 0.2501 | 0.9626 |
79
+ | 0.0261 | 10.9231 | 71 | 0.1456 | 0.9579 |
80
+ | 0.0007 | 12.0 | 78 | 0.0000 | 1.0 |
81
+ | 0.0007 | 12.9231 | 84 | 0.0011 | 1.0 |
82
+ | 0.0077 | 14.0 | 91 | 0.0233 | 0.9953 |
83
+ | 0.0077 | 14.9231 | 97 | 0.0463 | 0.9953 |
84
+ | 0.0077 | 16.0 | 104 | 0.0000 | 1.0 |
85
+ | 0.0033 | 16.9231 | 110 | 0.0003 | 1.0 |
86
+ | 0.0033 | 18.0 | 117 | 0.0022 | 1.0 |
87
+ | 0.0 | 18.9231 | 123 | 0.0004 | 1.0 |
88
+ | 0.0 | 20.0 | 130 | 0.0000 | 1.0 |
89
+ | 0.0001 | 20.9231 | 136 | 0.0000 | 1.0 |
90
+ | 0.0001 | 22.0 | 143 | 0.0000 | 1.0 |
91
+ | 0.0001 | 22.9231 | 149 | 0.0000 | 1.0 |
92
+ | 0.0 | 23.0769 | 150 | 0.0000 | 1.0 |
93
 
94
 
95
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c45043c5571c626426e80a570f24ac607f177ea9d24ec6afe2feaa4d21662e07
3
  size 349857196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5f036a6878f16c60039825387cb6c54988756420dc85360e9938d1f3a661fa9
3
  size 349857196
runs/Jul03_12-38-35_e0133a370a2e/events.out.tfevents.1720010332.e0133a370a2e.34.2 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4a542f243e4a610209139511a4815ccac32b8ac25b8412a410b73e6b59d75a58
3
- size 14035
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b739fc6edac054c0cb3a2fe93184daa74b485dba23acfc01126250095142d09
3
+ size 14923