Hugging Face's logo

ongkn
/
attraction-classifier

Image Classification
Transformers
Safetensors
vit
Generated from Trainer
Eval Results (legacy)
Model card Files
xet
Community
5
ongkn commited on
Commit
d64505f
·
verified ·
1 Parent(s): ac36ef8

End of training

Browse files
Files changed (2) hide show
  1. README.md +12 -19
  2. model.safetensors +1 -1
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
- value: 0.8252212389380531
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -32,8 +32,8 @@ should probably proofread and complete it, then remove this comment. -->
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 imagefolder dataset.
34
  It achieves the following results on the evaluation set:
35
- - Loss: 0.5421
36
- - Accuracy: 0.8252
37
 
38
  ## Model description
39
 
@@ -57,7 +57,7 @@ The following hyperparameters were used during training:
57
  - eval_batch_size: 16
58
  - seed: 69
59
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
60
- - lr_scheduler_type: linear
61
  - lr_scheduler_warmup_ratio: 0.05
62
  - num_epochs: 10
63
 
@@ -65,21 +65,14 @@ The following hyperparameters were used during training:
65
 
66
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
67
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
68
- | 0.5852 | 0.59 | 150 | 0.5592 | 0.7035 |
69
- | 0.6115 | 1.18 | 300 | 0.6364 | 0.6704 |
70
- | 0.475 | 1.77 | 450 | 0.5351 | 0.7257 |
71
- | 0.4268 | 2.36 | 600 | 0.5552 | 0.7190 |
72
- | 0.4349 | 2.95 | 750 | 0.4939 | 0.7677 |
73
- | 0.364 | 3.54 | 900 | 0.4969 | 0.7611 |
74
- | 0.343 | 4.13 | 1050 | 0.5717 | 0.7721 |
75
- | 0.3516 | 4.72 | 1200 | 0.4815 | 0.7898 |
76
- | 0.3222 | 5.31 | 1350 | 0.4609 | 0.8142 |
77
- | 0.2444 | 5.91 | 1500 | 0.5285 | 0.7854 |
78
- | 0.2152 | 6.5 | 1650 | 0.4901 | 0.8097 |
79
- | 0.2318 | 7.09 | 1800 | 0.4804 | 0.8252 |
80
- | 0.1875 | 7.68 | 1950 | 0.5690 | 0.8119 |
81
- | 0.195 | 8.27 | 2100 | 0.5276 | 0.8031 |
82
- | 0.1409 | 8.86 | 2250 | 0.5421 | 0.8252 |
83
 
84
 
85
  ### Framework versions
 
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
+ value: 0.756043956043956
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
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 imagefolder dataset.
34
  It achieves the following results on the evaluation set:
35
+ - Loss: 0.5514
36
+ - Accuracy: 0.7560
37
 
38
  ## Model description
39
 
 
57
  - eval_batch_size: 16
58
  - seed: 69
59
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
60
+ - lr_scheduler_type: cosine
61
  - lr_scheduler_warmup_ratio: 0.05
62
  - num_epochs: 10
63
 
 
65
 
66
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
67
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
68
+ | 0.5592 | 0.59 | 150 | 0.7210 | 0.6 |
69
+ | 0.5506 | 1.17 | 300 | 0.5884 | 0.6703 |
70
+ | 0.4778 | 1.76 | 450 | 0.5711 | 0.6967 |
71
+ | 0.427 | 2.34 | 600 | 0.5350 | 0.7473 |
72
+ | 0.4146 | 2.93 | 750 | 0.4936 | 0.7626 |
73
+ | 0.3544 | 3.52 | 900 | 0.6238 | 0.7253 |
74
+ | 0.3431 | 4.1 | 1050 | 0.5962 | 0.7055 |
75
+ | 0.3273 | 4.69 | 1200 | 0.5514 | 0.7560 |
 
 
 
 
 
 
 
76
 
77
 
78
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:01b7862a664429b68e3750fa695e74082e3aafc2a865123787d4e0707f89580f
3
  size 343223968
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b3e70ea72ebc9bc51e79b3100cb508c38d074472d38b89237ed488a7dc0b992
3
  size 343223968