Hugging Face's logo

nemik
/
mobilevitv2-1.0-imagenet1k-256-finetuned_v2024-7-25-frost

Image Classification
Transformers
TensorBoard
Safetensors
mobilevitv2
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
nemik commited on
Commit
6e14f3f
·
verified ·
1 Parent(s): 53bad07

Model save

Browse files
Files changed (2) hide show
  1. README.md +110 -0
  2. model.safetensors +1 -1
README.md ADDED
@@ -0,0 +1,110 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: other
3
+ base_model: apple/mobilevitv2-1.0-imagenet1k-256
4
+ tags:
5
+ - generated_from_trainer
6
+ datasets:
7
+ - webdataset
8
+ metrics:
9
+ - accuracy
10
+ - f1
11
+ - precision
12
+ - recall
13
+ model-index:
14
+ - name: mobilevitv2-1.0-imagenet1k-256-finetuned_v2024-7-25-frost
15
+ results:
16
+ - task:
17
+ name: Image Classification
18
+ type: image-classification
19
+ dataset:
20
+ name: webdataset
21
+ type: webdataset
22
+ config: default
23
+ split: train
24
+ args: default
25
+ metrics:
26
+ - name: Accuracy
27
+ type: accuracy
28
+ value: 0.9283185840707965
29
+ - name: F1
30
+ type: f1
31
+ value: 0.8171557562076749
32
+ - name: Precision
33
+ type: precision
34
+ value: 0.8341013824884793
35
+ - name: Recall
36
+ type: recall
37
+ value: 0.8008849557522124
38
+ ---
39
+
40
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
41
+ should probably proofread and complete it, then remove this comment. -->
42
+
43
+ # mobilevitv2-1.0-imagenet1k-256-finetuned_v2024-7-25-frost
44
+
45
+ This model is a fine-tuned version of [apple/mobilevitv2-1.0-imagenet1k-256](https://huggingface.co/apple/mobilevitv2-1.0-imagenet1k-256) on the webdataset dataset.
46
+ It achieves the following results on the evaluation set:
47
+ - Loss: 0.1955
48
+ - Accuracy: 0.9283
49
+ - F1: 0.8172
50
+ - Precision: 0.8341
51
+ - Recall: 0.8009
52
+
53
+ ## Model description
54
+
55
+ More information needed
56
+
57
+ ## Intended uses & limitations
58
+
59
+ More information needed
60
+
61
+ ## Training and evaluation data
62
+
63
+ More information needed
64
+
65
+ ## Training procedure
66
+
67
+ ### Training hyperparameters
68
+
69
+ The following hyperparameters were used during training:
70
+ - learning_rate: 0.0002
71
+ - train_batch_size: 16
72
+ - eval_batch_size: 8
73
+ - seed: 42
74
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
75
+ - lr_scheduler_type: linear
76
+ - lr_scheduler_warmup_ratio: 0.1
77
+ - num_epochs: 30
78
+ - mixed_precision_training: Native AMP
79
+
80
+ ### Training results
81
+
82
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
83
+ |:-------------:|:-------:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
84
+ | 0.6687 | 1.5625 | 100 | 0.6623 | 0.7230 | 0.5335 | 0.4022 | 0.7920 |
85
+ | 0.4454 | 3.125 | 200 | 0.4152 | 0.8832 | 0.7490 | 0.6567 | 0.8717 |
86
+ | 0.2835 | 4.6875 | 300 | 0.2661 | 0.9097 | 0.7661 | 0.7952 | 0.7389 |
87
+ | 0.2197 | 6.25 | 400 | 0.2151 | 0.9195 | 0.7869 | 0.8358 | 0.7434 |
88
+ | 0.1613 | 7.8125 | 500 | 0.2007 | 0.9292 | 0.8140 | 0.8578 | 0.7743 |
89
+ | 0.1655 | 9.375 | 600 | 0.1935 | 0.9310 | 0.8227 | 0.8458 | 0.8009 |
90
+ | 0.1815 | 10.9375 | 700 | 0.1883 | 0.9265 | 0.8074 | 0.8488 | 0.7699 |
91
+ | 0.1316 | 12.5 | 800 | 0.1825 | 0.9327 | 0.8273 | 0.8505 | 0.8053 |
92
+ | 0.1612 | 14.0625 | 900 | 0.1837 | 0.9257 | 0.8100 | 0.8287 | 0.7920 |
93
+ | 0.118 | 15.625 | 1000 | 0.1896 | 0.9310 | 0.8227 | 0.8458 | 0.8009 |
94
+ | 0.1178 | 17.1875 | 1100 | 0.1937 | 0.9239 | 0.8028 | 0.8333 | 0.7743 |
95
+ | 0.1248 | 18.75 | 1200 | 0.1913 | 0.9301 | 0.8192 | 0.8483 | 0.7920 |
96
+ | 0.1169 | 20.3125 | 1300 | 0.1916 | 0.9301 | 0.8167 | 0.8585 | 0.7788 |
97
+ | 0.1094 | 21.875 | 1400 | 0.1925 | 0.9292 | 0.8182 | 0.8411 | 0.7965 |
98
+ | 0.1108 | 23.4375 | 1500 | 0.1961 | 0.9345 | 0.8333 | 0.8486 | 0.8186 |
99
+ | 0.1089 | 25.0 | 1600 | 0.1993 | 0.9283 | 0.8172 | 0.8341 | 0.8009 |
100
+ | 0.0919 | 26.5625 | 1700 | 0.1936 | 0.9319 | 0.8262 | 0.8433 | 0.8097 |
101
+ | 0.0969 | 28.125 | 1800 | 0.1978 | 0.9310 | 0.8227 | 0.8458 | 0.8009 |
102
+ | 0.1093 | 29.6875 | 1900 | 0.1955 | 0.9283 | 0.8172 | 0.8341 | 0.8009 |
103
+
104
+
105
+ ### Framework versions
106
+
107
+ - Transformers 4.42.4
108
+ - Pytorch 2.3.1+cu121
109
+ - Datasets 2.20.0
110
+ - Tokenizers 0.19.1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f4db72ae6ef55736ca25d77676d66b240d7f6719e46867997d6f491ff15f0641
3
  size 17675500
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c4f9d9f42e1a00e0bfdba1bc9e3f9c74ea07e57d58c6dac341ebaffe7716668
3
  size 17675500