Hugging Face's logo

habibi26
/
ktp-crop-clip

Image Classification
Transformers
TensorBoard
Safetensors
clip
Generated from Trainer
Eval Results (legacy)
Model card Files
xet
 Metrics Community
habibi26 commited on
Commit
c4a213b
·
verified ·
1 Parent(s): 7a70e87

Model save

Browse files
Files changed (3) hide show
  1. README.md +96 -0
  2. model.safetensors +1 -1
  3. runs/Jul03_08-10-40_199eb666e01e/events.out.tfevents.1719994251.199eb666e01e.34.4 +2 -2
README.md ADDED
@@ -0,0 +1,96 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: openai/clip-vit-base-patch32
3
+ tags:
4
+ - generated_from_trainer
5
+ datasets:
6
+ - imagefolder
7
+ metrics:
8
+ - accuracy
9
+ model-index:
10
+ - name: ktp-crop-clip
11
+ results:
12
+ - task:
13
+ name: Image Classification
14
+ type: image-classification
15
+ dataset:
16
+ name: imagefolder
17
+ type: imagefolder
18
+ config: default
19
+ split: validation
20
+ args: default
21
+ metrics:
22
+ - name: Accuracy
23
+ type: accuracy
24
+ value: 0.9864864864864865
25
+ ---
26
+
27
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
28
+ should probably proofread and complete it, then remove this comment. -->
29
+
30
+ # ktp-crop-clip
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: 0.1223
35
+ - Accuracy: 0.9865
36
+
37
+ ## Model description
38
+
39
+ More information needed
40
+
41
+ ## Intended uses & limitations
42
+
43
+ More information needed
44
+
45
+ ## Training and evaluation data
46
+
47
+ More information needed
48
+
49
+ ## Training procedure
50
+
51
+ ### Training hyperparameters
52
+
53
+ The following hyperparameters were used during training:
54
+ - learning_rate: 5e-05
55
+ - train_batch_size: 16
56
+ - eval_batch_size: 16
57
+ - seed: 42
58
+ - gradient_accumulation_steps: 4
59
+ - total_train_batch_size: 64
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 | 0.96 | 6 | 0.8954 | 0.5270 |
70
+ | 0.7112 | 1.92 | 12 | 0.6729 | 0.5405 |
71
+ | 0.7112 | 2.88 | 18 | 0.6407 | 0.7297 |
72
+ | 0.4413 | 4.0 | 25 | 0.1279 | 0.9459 |
73
+ | 0.0935 | 4.96 | 31 | 0.1436 | 0.9730 |
74
+ | 0.0935 | 5.92 | 37 | 0.0021 | 1.0 |
75
+ | 0.0697 | 6.88 | 43 | 0.2862 | 0.9459 |
76
+ | 0.161 | 8.0 | 50 | 0.0843 | 0.9595 |
77
+ | 0.161 | 8.96 | 56 | 0.2255 | 0.9459 |
78
+ | 0.0061 | 9.92 | 62 | 0.4678 | 0.9054 |
79
+ | 0.0061 | 10.88 | 68 | 0.3299 | 0.9189 |
80
+ | 0.0309 | 12.0 | 75 | 0.5189 | 0.9189 |
81
+ | 0.0025 | 12.96 | 81 | 0.0850 | 0.9865 |
82
+ | 0.0025 | 13.92 | 87 | 0.0720 | 0.9865 |
83
+ | 0.0042 | 14.88 | 93 | 0.0745 | 0.9865 |
84
+ | 0.0002 | 16.0 | 100 | 0.0869 | 0.9865 |
85
+ | 0.0002 | 16.96 | 106 | 0.0895 | 0.9865 |
86
+ | 0.0001 | 17.92 | 112 | 0.1127 | 0.9865 |
87
+ | 0.0001 | 18.88 | 118 | 0.1219 | 0.9865 |
88
+ | 0.0 | 19.2 | 120 | 0.1223 | 0.9865 |
89
+
90
+
91
+ ### Framework versions
92
+
93
+ - Transformers 4.41.2
94
+ - Pytorch 2.1.2
95
+ - Datasets 2.19.2
96
+ - Tokenizers 0.19.1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:766c8f07618f6042af8b1083cbb05a35e0f6d7f5429ec68dcfc5e58789f1f2cb
3
  size 349854120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aee1030481d1f60449a2e5e484ff6178f7b619c02597b243357a5b3eef02fd5f
3
  size 349854120
runs/Jul03_08-10-40_199eb666e01e/events.out.tfevents.1719994251.199eb666e01e.34.4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8877714b100a1994c1cdef76120b650df3f3c6ed7a5e73375ed58a94d87b1fe0
3
- size 13026
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cca1e6b0da2d601e556924bc4efaed20b11a13e55bfeecacadfdfed3958a4683
3
+ size 13898