Hugging Face's logo

Melo1512
/
vit-msn-small-beta-fia-manually-enhanced-HSV_test_3

Image Classification
Transformers
TensorBoard
Safetensors
vit_msn
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
Melo1512 commited on
Commit
8a29e0c
·
verified ·
1 Parent(s): 56b0ffb

Model save

Browse files
Files changed (3) hide show
  1. README.md +107 -0
  2. model.safetensors +1 -1
  3. runs/Jan27_17-12-41_db1093ce036b/events.out.tfevents.1737997967.db1093ce036b.224.4 +2 -2
README.md ADDED
@@ -0,0 +1,107 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ base_model: Melo1512/vit-msn-small-beta-fia-manually-enhanced-HSV_test_2
4
+ tags:
5
+ - generated_from_trainer
6
+ datasets:
7
+ - imagefolder
8
+ metrics:
9
+ - accuracy
10
+ model-index:
11
+ - name: vit-msn-small-beta-fia-manually-enhanced-HSV_test_3
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: test
21
+ args: default
22
+ metrics:
23
+ - name: Accuracy
24
+ type: accuracy
25
+ value: 0.8732394366197183
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-msn-small-beta-fia-manually-enhanced-HSV_test_3
32
+
33
+ This model is a fine-tuned version of [Melo1512/vit-msn-small-beta-fia-manually-enhanced-HSV_test_2](https://huggingface.co/Melo1512/vit-msn-small-beta-fia-manually-enhanced-HSV_test_2) on the imagefolder dataset.
34
+ It achieves the following results on the evaluation set:
35
+ - Loss: 0.5473
36
+ - Accuracy: 0.8732
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: 1e-05
56
+ - train_batch_size: 64
57
+ - eval_batch_size: 64
58
+ - seed: 42
59
+ - gradient_accumulation_steps: 4
60
+ - total_train_batch_size: 256
61
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
62
+ - lr_scheduler_type: linear
63
+ - lr_scheduler_warmup_ratio: 0.33
64
+ - num_epochs: 50
65
+ - label_smoothing_factor: 0.1
66
+
67
+ ### Training results
68
+
69
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
70
+ |:-------------:|:-------:|:----:|:---------------:|:--------:|
71
+ | No log | 0.5714 | 1 | 0.5374 | 0.8873 |
72
+ | No log | 1.7143 | 3 | 0.5290 | 0.8873 |
73
+ | No log | 2.8571 | 5 | 0.5365 | 0.8873 |
74
+ | No log | 4.0 | 7 | 0.5444 | 0.8803 |
75
+ | No log | 4.5714 | 8 | 0.5448 | 0.8803 |
76
+ | 0.4449 | 5.7143 | 10 | 0.5698 | 0.8592 |
77
+ | 0.4449 | 6.8571 | 12 | 0.5765 | 0.8662 |
78
+ | 0.4449 | 8.0 | 14 | 0.5411 | 0.8662 |
79
+ | 0.4449 | 8.5714 | 15 | 0.5283 | 0.8803 |
80
+ | 0.4449 | 9.7143 | 17 | 0.5272 | 0.8803 |
81
+ | 0.4449 | 10.8571 | 19 | 0.5337 | 0.8732 |
82
+ | 0.4343 | 12.0 | 21 | 0.5400 | 0.8732 |
83
+ | 0.4343 | 12.5714 | 22 | 0.5317 | 0.8803 |
84
+ | 0.4343 | 13.7143 | 24 | 0.5167 | 0.8803 |
85
+ | 0.4343 | 14.8571 | 26 | 0.5272 | 0.8732 |
86
+ | 0.4343 | 16.0 | 28 | 0.5362 | 0.8803 |
87
+ | 0.4343 | 16.5714 | 29 | 0.5354 | 0.8732 |
88
+ | 0.4389 | 17.7143 | 31 | 0.5263 | 0.8803 |
89
+ | 0.4389 | 18.8571 | 33 | 0.5342 | 0.8732 |
90
+ | 0.4389 | 20.0 | 35 | 0.5446 | 0.8803 |
91
+ | 0.4389 | 20.5714 | 36 | 0.5495 | 0.8803 |
92
+ | 0.4389 | 21.7143 | 38 | 0.5442 | 0.8803 |
93
+ | 0.423 | 22.8571 | 40 | 0.5322 | 0.8803 |
94
+ | 0.423 | 24.0 | 42 | 0.5274 | 0.8803 |
95
+ | 0.423 | 24.5714 | 43 | 0.5296 | 0.8803 |
96
+ | 0.423 | 25.7143 | 45 | 0.5363 | 0.8803 |
97
+ | 0.423 | 26.8571 | 47 | 0.5421 | 0.8732 |
98
+ | 0.423 | 28.0 | 49 | 0.5467 | 0.8732 |
99
+ | 0.4254 | 28.5714 | 50 | 0.5473 | 0.8732 |
100
+
101
+
102
+ ### Framework versions
103
+
104
+ - Transformers 4.44.2
105
+ - Pytorch 2.4.1+cu121
106
+ - Datasets 3.2.0
107
+ - Tokenizers 0.19.1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b15f61efd248d5214ad0966753f66a3d2841420c5e9263fa5786afbddba0acd2
3
  size 86690164
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7e50faa37c550f2aabfc854b385bbef4c8a5ea0a15023bcd3265f167eca1601
3
  size 86690164
runs/Jan27_17-12-41_db1093ce036b/events.out.tfevents.1737997967.db1093ce036b.224.4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e7ee09810d53c10b631cdc4192a25608047f816ee383854612e60b525018d4cc
3
- size 15063
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2cad62cdff43ddcecc9c3151c902ca4c36880b0749534b7b542e83b1f5ba1ed
3
+ size 15728