Hugging Face's logo

nemik
/
frost-vision-v2-google_vit-base-patch16-384-v2024-11-10

Image Classification
Transformers
TensorBoard
Safetensors
vit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
nemik commited on
Commit
db80b82
•
1 Parent(s): 1c8a19e

Model save

Browse files
Files changed (2) hide show
  1. README.md +113 -0
  2. model.safetensors +1 -1
README.md ADDED
@@ -0,0 +1,113 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: apache-2.0
4
+ base_model: google/vit-base-patch16-384
5
+ tags:
6
+ - generated_from_trainer
7
+ datasets:
8
+ - webdataset
9
+ metrics:
10
+ - accuracy
11
+ - f1
12
+ - precision
13
+ - recall
14
+ model-index:
15
+ - name: frost-vision-v2-google_vit-base-patch16-384-v2024-11-10
16
+ results:
17
+ - task:
18
+ name: Image Classification
19
+ type: image-classification
20
+ dataset:
21
+ name: webdataset
22
+ type: webdataset
23
+ config: default
24
+ split: train
25
+ args: default
26
+ metrics:
27
+ - name: Accuracy
28
+ type: accuracy
29
+ value: 0.9376760563380282
30
+ - name: F1
31
+ type: f1
32
+ value: 0.8415398388540735
33
+ - name: Precision
34
+ type: precision
35
+ value: 0.8545454545454545
36
+ - name: Recall
37
+ type: recall
38
+ value: 0.8289241622574955
39
+ ---
40
+
41
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
42
+ should probably proofread and complete it, then remove this comment. -->
43
+
44
+ # frost-vision-v2-google_vit-base-patch16-384-v2024-11-10
45
+
46
+ This model is a fine-tuned version of [google/vit-base-patch16-384](https://huggingface.co/google/vit-base-patch16-384) on the webdataset dataset.
47
+ It achieves the following results on the evaluation set:
48
+ - Loss: 0.2101
49
+ - Accuracy: 0.9377
50
+ - F1: 0.8415
51
+ - Precision: 0.8545
52
+ - Recall: 0.8289
53
+
54
+ ## Model description
55
+
56
+ More information needed
57
+
58
+ ## Intended uses & limitations
59
+
60
+ More information needed
61
+
62
+ ## Training and evaluation data
63
+
64
+ More information needed
65
+
66
+ ## Training procedure
67
+
68
+ ### Training hyperparameters
69
+
70
+ The following hyperparameters were used during training:
71
+ - learning_rate: 0.0002
72
+ - train_batch_size: 16
73
+ - eval_batch_size: 8
74
+ - seed: 42
75
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
76
+ - lr_scheduler_type: linear
77
+ - lr_scheduler_warmup_ratio: 0.1
78
+ - num_epochs: 30
79
+ - mixed_precision_training: Native AMP
80
+
81
+ ### Training results
82
+
83
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
84
+ |:-------------:|:-------:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
85
+ | 0.2243 | 1.4085 | 100 | 0.2088 | 0.9243 | 0.7981 | 0.8534 | 0.7496 |
86
+ | 0.2438 | 2.8169 | 200 | 0.1819 | 0.9299 | 0.8103 | 0.8817 | 0.7496 |
87
+ | 0.1338 | 4.2254 | 300 | 0.1608 | 0.9377 | 0.8449 | 0.8397 | 0.8501 |
88
+ | 0.1224 | 5.6338 | 400 | 0.1735 | 0.9271 | 0.8179 | 0.8158 | 0.8201 |
89
+ | 0.1065 | 7.0423 | 500 | 0.1847 | 0.9275 | 0.8187 | 0.8172 | 0.8201 |
90
+ | 0.1008 | 8.4507 | 600 | 0.1710 | 0.9405 | 0.8506 | 0.8528 | 0.8483 |
91
+ | 0.1005 | 9.8592 | 700 | 0.1823 | 0.9384 | 0.8405 | 0.8698 | 0.8131 |
92
+ | 0.0756 | 11.2676 | 800 | 0.1771 | 0.9415 | 0.8520 | 0.8613 | 0.8430 |
93
+ | 0.0653 | 12.6761 | 900 | 0.1971 | 0.9324 | 0.8310 | 0.8295 | 0.8325 |
94
+ | 0.0367 | 14.0845 | 1000 | 0.2123 | 0.9296 | 0.8221 | 0.8294 | 0.8148 |
95
+ | 0.0459 | 15.4930 | 1100 | 0.2006 | 0.9335 | 0.832 | 0.8387 | 0.8254 |
96
+ | 0.0559 | 16.9014 | 1200 | 0.2097 | 0.9313 | 0.8232 | 0.8470 | 0.8007 |
97
+ | 0.0382 | 18.3099 | 1300 | 0.2055 | 0.9352 | 0.8372 | 0.8401 | 0.8342 |
98
+ | 0.0361 | 19.7183 | 1400 | 0.2070 | 0.9335 | 0.8305 | 0.8449 | 0.8166 |
99
+ | 0.0358 | 21.1268 | 1500 | 0.1959 | 0.9398 | 0.8458 | 0.8653 | 0.8272 |
100
+ | 0.0382 | 22.5352 | 1600 | 0.2097 | 0.9320 | 0.8269 | 0.8412 | 0.8131 |
101
+ | 0.0285 | 23.9437 | 1700 | 0.2016 | 0.9415 | 0.8515 | 0.8639 | 0.8395 |
102
+ | 0.0141 | 25.3521 | 1800 | 0.2161 | 0.9366 | 0.8384 | 0.8537 | 0.8236 |
103
+ | 0.0179 | 26.7606 | 1900 | 0.2073 | 0.9377 | 0.8427 | 0.8495 | 0.8360 |
104
+ | 0.0263 | 28.1690 | 2000 | 0.2097 | 0.9391 | 0.8457 | 0.8556 | 0.8360 |
105
+ | 0.0191 | 29.5775 | 2100 | 0.2101 | 0.9377 | 0.8415 | 0.8545 | 0.8289 |
106
+
107
+
108
+ ### Framework versions
109
+
110
+ - Transformers 4.44.2
111
+ - Pytorch 2.5.0+cu121
112
+ - Datasets 3.1.0
113
+ - Tokenizers 0.19.1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3b9470df6f11db19ee43901092cc4958f1ea75f9c174387147c939b202514212
3
  size 344415944
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3cabc559423b45550befb870507744874ceb594e6c71241a9e3ed6cf33f0311c
3
  size 344415944