rshrott commited on
Commit
ab52a27
1 Parent(s): 8f2aeca

Model save

Browse files
README.md ADDED
@@ -0,0 +1,94 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: google/vit-base-patch16-224-in21k
4
+ tags:
5
+ - generated_from_trainer
6
+ datasets:
7
+ - renovation
8
+ metrics:
9
+ - accuracy
10
+ model-index:
11
+ - name: vit-base-renovation2
12
+ results:
13
+ - task:
14
+ name: Image Classification
15
+ type: image-classification
16
+ dataset:
17
+ name: renovation
18
+ type: renovation
19
+ config: default
20
+ split: validation
21
+ args: default
22
+ metrics:
23
+ - name: Accuracy
24
+ type: accuracy
25
+ value: 0.6529680365296804
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-base-renovation2
32
+
33
+ This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the renovation dataset.
34
+ It achieves the following results on the evaluation set:
35
+ - Loss: 1.6878
36
+ - Accuracy: 0.6530
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: 16
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: 4
62
+ - mixed_precision_training: Native AMP
63
+
64
+ ### Training results
65
+
66
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
67
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
68
+ | 0.273 | 0.2 | 25 | 1.2384 | 0.6027 |
69
+ | 0.5153 | 0.4 | 50 | 1.4060 | 0.5845 |
70
+ | 0.2792 | 0.6 | 75 | 1.3026 | 0.5936 |
71
+ | 0.5516 | 0.81 | 100 | 1.3999 | 0.6027 |
72
+ | 0.4247 | 1.01 | 125 | 1.2621 | 0.5982 |
73
+ | 0.1556 | 1.21 | 150 | 1.5661 | 0.5571 |
74
+ | 0.1458 | 1.41 | 175 | 1.3459 | 0.6347 |
75
+ | 0.1595 | 1.61 | 200 | 1.5278 | 0.5982 |
76
+ | 0.1195 | 1.81 | 225 | 1.5303 | 0.6256 |
77
+ | 0.1507 | 2.02 | 250 | 1.7701 | 0.5845 |
78
+ | 0.023 | 2.22 | 275 | 1.5354 | 0.6301 |
79
+ | 0.028 | 2.42 | 300 | 1.6535 | 0.6301 |
80
+ | 0.0698 | 2.62 | 325 | 1.6772 | 0.6438 |
81
+ | 0.0516 | 2.82 | 350 | 1.4380 | 0.6804 |
82
+ | 0.0136 | 3.02 | 375 | 1.6561 | 0.6484 |
83
+ | 0.0325 | 3.23 | 400 | 1.6028 | 0.6621 |
84
+ | 0.0149 | 3.43 | 425 | 1.6261 | 0.6621 |
85
+ | 0.0082 | 3.63 | 450 | 1.6615 | 0.6621 |
86
+ | 0.0093 | 3.83 | 475 | 1.6878 | 0.6530 |
87
+
88
+
89
+ ### Framework versions
90
+
91
+ - Transformers 4.38.2
92
+ - Pytorch 2.2.1+cu121
93
+ - Datasets 2.18.0
94
+ - Tokenizers 0.15.2
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:38c1b7bf5946e613fc0860474980e31910c0f0a3ed700e3e3b22e551f6880b95
3
  size 343239356
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e08605b429cfd98e5ebd8261cc022718a079b20f40424fad5fafb701a94315f
3
  size 343239356
runs/Mar20_02-51-07_afa5dd1e3938/events.out.tfevents.1710903080.afa5dd1e3938.399.3 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f8add397f0d1dedc1673ccb6d9aaf285ce470f16a2624809909b6dfee01a36c4
3
- size 15751
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a468e951662830b4ee1b18e7e6f03ac3c9b9f90696ad4860631ba7d61548d6b9
3
+ size 21630