Hugging Face's logo

GGital
/
vit-SUPER02

Image Classification
Transformers
TensorBoard
Safetensors
vit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
GGital commited on
Commit
ec367a4
·
verified ·
1 Parent(s): 472d502

Model save

Browse files
Files changed (3) hide show
  1. README.md +108 -0
  2. model.safetensors +1 -1
  3. runs/Feb02_18-14-56_b70c9f2dbb4e/events.out.tfevents.1706897703.b70c9f2dbb4e.2923.0 +2 -2
README.md ADDED
@@ -0,0 +1,108 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ base_model: laion/CLIP-ViT-H-14-laion2B-s32B-b79K
4
+ tags:
5
+ - generated_from_trainer
6
+ datasets:
7
+ - imagefolder
8
+ metrics:
9
+ - f1
10
+ model-index:
11
+ - name: vit-SUPER02
12
+ results:
13
+ - task:
14
+ name: Image Classification
15
+ type: image-classification
16
+ dataset:
17
+ name: imagefolder
18
+ type: imagefolder
19
+ config: default
20
+ split: train
21
+ args: default
22
+ metrics:
23
+ - name: F1
24
+ type: f1
25
+ value: 0.9434741496133529
26
+ ---
27
+
28
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
29
+ should probably proofread and complete it, then remove this comment. -->
30
+
31
+ # vit-SUPER02
32
+
33
+ This model is a fine-tuned version of [laion/CLIP-ViT-H-14-laion2B-s32B-b79K](https://huggingface.co/laion/CLIP-ViT-H-14-laion2B-s32B-b79K) on the imagefolder dataset.
34
+ It achieves the following results on the evaluation set:
35
+ - Loss: 0.2246
36
+ - F1: 0.9435
37
+
38
+ ## Model description
39
+
40
+ More information needed
41
+
42
+ ## Intended uses & limitations
43
+
44
+ More information needed
45
+
46
+ ## Training and evaluation data
47
+
48
+ More information needed
49
+
50
+ ## Training procedure
51
+
52
+ ### Training hyperparameters
53
+
54
+ The following hyperparameters were used during training:
55
+ - learning_rate: 0.0002
56
+ - train_batch_size: 64
57
+ - eval_batch_size: 8
58
+ - seed: 42
59
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
60
+ - lr_scheduler_type: linear
61
+ - num_epochs: 10
62
+ - mixed_precision_training: Native AMP
63
+
64
+ ### Training results
65
+
66
+ | Training Loss | Epoch | Step | Validation Loss | F1 |
67
+ |:-------------:|:-----:|:----:|:---------------:|:------:|
68
+ | 4.2088 | 0.3 | 50 | 4.0561 | 0.0670 |
69
+ | 2.9768 | 0.6 | 100 | 2.8147 | 0.2790 |
70
+ | 1.9733 | 0.9 | 150 | 1.7144 | 0.5560 |
71
+ | 1.1587 | 1.2 | 200 | 1.0544 | 0.7479 |
72
+ | 0.7738 | 1.5 | 250 | 0.6839 | 0.8392 |
73
+ | 0.5944 | 1.8 | 300 | 0.5771 | 0.8660 |
74
+ | 0.3746 | 2.1 | 350 | 0.5237 | 0.8636 |
75
+ | 0.4313 | 2.4 | 400 | 0.4649 | 0.8927 |
76
+ | 0.3874 | 2.69 | 450 | 0.3890 | 0.9015 |
77
+ | 0.346 | 2.99 | 500 | 0.3728 | 0.9072 |
78
+ | 0.3123 | 3.29 | 550 | 0.3296 | 0.9113 |
79
+ | 0.2976 | 3.59 | 600 | 0.3369 | 0.9166 |
80
+ | 0.2371 | 3.89 | 650 | 0.3207 | 0.9139 |
81
+ | 0.1462 | 4.19 | 700 | 0.2997 | 0.9195 |
82
+ | 0.178 | 4.49 | 750 | 0.2870 | 0.9317 |
83
+ | 0.1489 | 4.79 | 800 | 0.3048 | 0.9216 |
84
+ | 0.1135 | 5.09 | 850 | 0.2626 | 0.9364 |
85
+ | 0.0992 | 5.39 | 900 | 0.2920 | 0.9291 |
86
+ | 0.0879 | 5.69 | 950 | 0.2536 | 0.9365 |
87
+ | 0.0908 | 5.99 | 1000 | 0.2315 | 0.9435 |
88
+ | 0.071 | 6.29 | 1050 | 0.2542 | 0.9378 |
89
+ | 0.047 | 6.59 | 1100 | 0.2517 | 0.9426 |
90
+ | 0.0565 | 6.89 | 1150 | 0.2513 | 0.9365 |
91
+ | 0.0119 | 7.19 | 1200 | 0.2293 | 0.9431 |
92
+ | 0.0142 | 7.49 | 1250 | 0.2454 | 0.9414 |
93
+ | 0.0124 | 7.78 | 1300 | 0.2391 | 0.9432 |
94
+ | 0.0057 | 8.08 | 1350 | 0.2355 | 0.9446 |
95
+ | 0.0041 | 8.38 | 1400 | 0.2242 | 0.9520 |
96
+ | 0.0107 | 8.68 | 1450 | 0.2230 | 0.9466 |
97
+ | 0.009 | 8.98 | 1500 | 0.2236 | 0.9495 |
98
+ | 0.0027 | 9.28 | 1550 | 0.2274 | 0.9466 |
99
+ | 0.0027 | 9.58 | 1600 | 0.2241 | 0.9454 |
100
+ | 0.0022 | 9.88 | 1650 | 0.2246 | 0.9435 |
101
+
102
+
103
+ ### Framework versions
104
+
105
+ - Transformers 4.38.0.dev0
106
+ - Pytorch 2.1.0+cu121
107
+ - Datasets 2.16.1
108
+ - Tokenizers 0.15.1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3e94a462cc9facd0b0d165114fb84c7fb3fe4cf96a9816fcf2a4240edc41dcb1
3
  size 343817652
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26ad21aab0ab20c9546c7ebcf585b4deceb7113ef35f75bd8aa22d597aa84a67
3
  size 343817652
runs/Feb02_18-14-56_b70c9f2dbb4e/events.out.tfevents.1706897703.b70c9f2dbb4e.2923.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f17c5f97970d87598b8543b8eb1792c5ccac8b06a6f8c641b340112e605edceb
3
- size 52213
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96ca0f24cf52f9eddb6e0b4949f8fe2cb694e8b60d2c953e09e25cc8f2bb416e
3
+ size 52881