Hugging Face's logo

Melo1512
/
vit-msn-small-beta-fia-equally-enhanced_test_1

Image Classification
Transformers
TensorBoard
Safetensors
vit_msn
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
Melo1512 commited on
Commit
da4e843
·
verified ·
1 Parent(s): 564dbf0

Model save

Browse files
Files changed (2) hide show
  1. README.md +137 -0
  2. model.safetensors +1 -1
README.md ADDED
@@ -0,0 +1,137 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: apache-2.0
4
+ base_model: facebook/vit-msn-small
5
+ tags:
6
+ - generated_from_trainer
7
+ datasets:
8
+ - imagefolder
9
+ metrics:
10
+ - accuracy
11
+ model-index:
12
+ - name: vit-msn-small-beta-fia-equally-enhanced_test_1
13
+ results:
14
+ - task:
15
+ name: Image Classification
16
+ type: image-classification
17
+ dataset:
18
+ name: imagefolder
19
+ type: imagefolder
20
+ config: default
21
+ split: test
22
+ args: default
23
+ metrics:
24
+ - name: Accuracy
25
+ type: accuracy
26
+ value: 0.8591549295774648
27
+ ---
28
+
29
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
30
+ should probably proofread and complete it, then remove this comment. -->
31
+
32
+ # vit-msn-small-beta-fia-equally-enhanced_test_1
33
+
34
+ This model is a fine-tuned version of [facebook/vit-msn-small](https://huggingface.co/facebook/vit-msn-small) on the imagefolder dataset.
35
+ It achieves the following results on the evaluation set:
36
+ - Loss: 0.6194
37
+ - Accuracy: 0.8592
38
+
39
+ ## Model description
40
+
41
+ More information needed
42
+
43
+ ## Intended uses & limitations
44
+
45
+ More information needed
46
+
47
+ ## Training and evaluation data
48
+
49
+ More information needed
50
+
51
+ ## Training procedure
52
+
53
+ ### Training hyperparameters
54
+
55
+ The following hyperparameters were used during training:
56
+ - learning_rate: 1e-05
57
+ - train_batch_size: 64
58
+ - eval_batch_size: 64
59
+ - seed: 42
60
+ - gradient_accumulation_steps: 4
61
+ - total_train_batch_size: 256
62
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
63
+ - lr_scheduler_type: linear
64
+ - lr_scheduler_warmup_ratio: 0.2
65
+ - num_epochs: 100
66
+ - label_smoothing_factor: 0.1
67
+
68
+ ### Training results
69
+
70
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
71
+ |:-------------:|:-------:|:----:|:---------------:|:--------:|
72
+ | No log | 0.5714 | 1 | 1.5578 | 0.0704 |
73
+ | No log | 1.7143 | 3 | 1.4950 | 0.0634 |
74
+ | No log | 2.8571 | 5 | 1.3574 | 0.0634 |
75
+ | No log | 4.0 | 7 | 1.1698 | 0.1268 |
76
+ | No log | 4.5714 | 8 | 1.0682 | 0.3169 |
77
+ | 1.5036 | 5.7143 | 10 | 0.8754 | 0.7958 |
78
+ | 1.5036 | 6.8571 | 12 | 0.7359 | 0.8239 |
79
+ | 1.5036 | 8.0 | 14 | 0.6782 | 0.8169 |
80
+ | 1.5036 | 8.5714 | 15 | 0.6718 | 0.8169 |
81
+ | 1.5036 | 9.7143 | 17 | 0.6821 | 0.8099 |
82
+ | 1.5036 | 10.8571 | 19 | 0.7157 | 0.8028 |
83
+ | 0.7486 | 12.0 | 21 | 0.7173 | 0.8099 |
84
+ | 0.7486 | 12.5714 | 22 | 0.6967 | 0.8169 |
85
+ | 0.7486 | 13.7143 | 24 | 0.6847 | 0.8169 |
86
+ | 0.7486 | 14.8571 | 26 | 0.6827 | 0.8239 |
87
+ | 0.7486 | 16.0 | 28 | 0.6959 | 0.8380 |
88
+ | 0.7486 | 16.5714 | 29 | 0.6826 | 0.8521 |
89
+ | 0.6547 | 17.7143 | 31 | 0.6360 | 0.8310 |
90
+ | 0.6547 | 18.8571 | 33 | 0.6257 | 0.8521 |
91
+ | 0.6547 | 20.0 | 35 | 0.6594 | 0.8732 |
92
+ | 0.6547 | 20.5714 | 36 | 0.6784 | 0.8380 |
93
+ | 0.6547 | 21.7143 | 38 | 0.6578 | 0.8521 |
94
+ | 0.5817 | 22.8571 | 40 | 0.6146 | 0.8592 |
95
+ | 0.5817 | 24.0 | 42 | 0.6212 | 0.8732 |
96
+ | 0.5817 | 24.5714 | 43 | 0.6395 | 0.8732 |
97
+ | 0.5817 | 25.7143 | 45 | 0.6452 | 0.8732 |
98
+ | 0.5817 | 26.8571 | 47 | 0.6317 | 0.8803 |
99
+ | 0.5817 | 28.0 | 49 | 0.6332 | 0.8803 |
100
+ | 0.5632 | 28.5714 | 50 | 0.6418 | 0.8732 |
101
+ | 0.5632 | 29.7143 | 52 | 0.6383 | 0.8803 |
102
+ | 0.5632 | 30.8571 | 54 | 0.6367 | 0.8592 |
103
+ | 0.5632 | 32.0 | 56 | 0.6253 | 0.8732 |
104
+ | 0.5632 | 32.5714 | 57 | 0.6268 | 0.8592 |
105
+ | 0.5632 | 33.7143 | 59 | 0.6234 | 0.8662 |
106
+ | 0.5328 | 34.8571 | 61 | 0.6368 | 0.8521 |
107
+ | 0.5328 | 36.0 | 63 | 0.6251 | 0.8592 |
108
+ | 0.5328 | 36.5714 | 64 | 0.6184 | 0.8732 |
109
+ | 0.5328 | 37.7143 | 66 | 0.6067 | 0.8732 |
110
+ | 0.5328 | 38.8571 | 68 | 0.6182 | 0.8662 |
111
+ | 0.5272 | 40.0 | 70 | 0.6398 | 0.8451 |
112
+ | 0.5272 | 40.5714 | 71 | 0.6440 | 0.8310 |
113
+ | 0.5272 | 41.7143 | 73 | 0.6318 | 0.8451 |
114
+ | 0.5272 | 42.8571 | 75 | 0.6111 | 0.8732 |
115
+ | 0.5272 | 44.0 | 77 | 0.6061 | 0.8732 |
116
+ | 0.5272 | 44.5714 | 78 | 0.6116 | 0.8732 |
117
+ | 0.5255 | 45.7143 | 80 | 0.6320 | 0.8451 |
118
+ | 0.5255 | 46.8571 | 82 | 0.6394 | 0.8310 |
119
+ | 0.5255 | 48.0 | 84 | 0.6379 | 0.8310 |
120
+ | 0.5255 | 48.5714 | 85 | 0.6363 | 0.8310 |
121
+ | 0.5255 | 49.7143 | 87 | 0.6282 | 0.8521 |
122
+ | 0.5255 | 50.8571 | 89 | 0.6214 | 0.8592 |
123
+ | 0.52 | 52.0 | 91 | 0.6195 | 0.8592 |
124
+ | 0.52 | 52.5714 | 92 | 0.6170 | 0.8662 |
125
+ | 0.52 | 53.7143 | 94 | 0.6169 | 0.8592 |
126
+ | 0.52 | 54.8571 | 96 | 0.6174 | 0.8592 |
127
+ | 0.52 | 56.0 | 98 | 0.6187 | 0.8592 |
128
+ | 0.52 | 56.5714 | 99 | 0.6193 | 0.8592 |
129
+ | 0.504 | 57.1429 | 100 | 0.6194 | 0.8592 |
130
+
131
+
132
+ ### Framework versions
133
+
134
+ - Transformers 4.44.2
135
+ - Pytorch 2.4.1+cu121
136
+ - Datasets 3.2.0
137
+ - Tokenizers 0.19.1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f3881e8f2cb9556b16be259588fc755e18590f1cf2f6288001da0e8f63a2a935
3
  size 86690164
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:15e446859656a5f7714c509729af0b360a24b80baedb6281e1bc2e18e516ffaf
3
  size 86690164