Hugging Face's logo

zeenfts
/
output_dir

Image Classification
Transformers
PyTorch
vit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
2
zeenfts commited on
Commit
6e115f9
•
1 Parent(s): 6fa3e6d

End of training

Browse files
Files changed (1) hide show
  1. README.md +39 -32
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
- value: 0.575
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: 1.2775
36
- - Accuracy: 0.575
37
 
38
  ## Model description
39
 
@@ -52,46 +52,53 @@ More information needed
52
  ### Training hyperparameters
53
 
54
  The following hyperparameters were used during training:
55
- - learning_rate: 0.0007
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: 0.1
64
- - num_epochs: 31
65
 
66
  ### Training results
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
- | No log | 0.8 | 2 | 2.0745 | 0.1125 |
71
- | No log | 2.0 | 5 | 1.9646 | 0.1875 |
72
- | No log | 2.8 | 7 | 1.8686 | 0.325 |
73
- | 1.9551 | 4.0 | 10 | 1.7196 | 0.3937 |
74
- | 1.9551 | 4.8 | 12 | 1.5011 | 0.4813 |
75
- | 1.9551 | 6.0 | 15 | 1.3693 | 0.4938 |
76
- | 1.9551 | 6.8 | 17 | 1.4287 | 0.4625 |
77
- | 1.3855 | 8.0 | 20 | 1.2961 | 0.5188 |
78
- | 1.3855 | 8.8 | 22 | 1.2534 | 0.5312 |
79
- | 1.3855 | 10.0 | 25 | 1.2544 | 0.5 |
80
- | 1.3855 | 10.8 | 27 | 1.2417 | 0.5437 |
81
- | 0.8352 | 12.0 | 30 | 1.1863 | 0.5437 |
82
- | 0.8352 | 12.8 | 32 | 1.2524 | 0.5437 |
83
- | 0.8352 | 14.0 | 35 | 1.3570 | 0.5062 |
84
- | 0.8352 | 14.8 | 37 | 1.3046 | 0.5687 |
85
- | 0.4513 | 16.0 | 40 | 1.3582 | 0.4688 |
86
- | 0.4513 | 16.8 | 42 | 1.3063 | 0.5625 |
87
- | 0.4513 | 18.0 | 45 | 1.3494 | 0.5312 |
88
- | 0.4513 | 18.8 | 47 | 1.2484 | 0.5938 |
89
- | 0.282 | 20.0 | 50 | 1.3694 | 0.5437 |
90
- | 0.282 | 20.8 | 52 | 1.4651 | 0.5375 |
91
- | 0.282 | 22.0 | 55 | 1.3577 | 0.5563 |
92
- | 0.282 | 22.8 | 57 | 1.2522 | 0.5625 |
93
- | 0.2038 | 24.0 | 60 | 1.4027 | 0.5813 |
94
- | 0.2038 | 24.8 | 62 | 1.2445 | 0.5938 |
 
 
 
 
 
 
 
 
95
 
96
 
97
  ### Framework versions
 
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
+ value: 0.5875
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: 1.2119
36
+ - Accuracy: 0.5875
37
 
38
  ## Model description
39
 
 
52
  ### Training hyperparameters
53
 
54
  The following hyperparameters were used during training:
55
+ - learning_rate: 5e-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: reduce_lr_on_plateau
63
+ - num_epochs: 41
 
64
 
65
  ### Training results
66
 
67
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
68
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
69
+ | No log | 0.8 | 2 | 2.0638 | 0.1562 |
70
+ | No log | 2.0 | 5 | 2.0353 | 0.2 |
71
+ | No log | 2.8 | 7 | 1.9965 | 0.2687 |
72
+ | 1.9968 | 4.0 | 10 | 1.9289 | 0.3937 |
73
+ | 1.9968 | 4.8 | 12 | 1.8942 | 0.3125 |
74
+ | 1.9968 | 6.0 | 15 | 1.8054 | 0.4562 |
75
+ | 1.9968 | 6.8 | 17 | 1.7626 | 0.4313 |
76
+ | 1.7555 | 8.0 | 20 | 1.7078 | 0.4562 |
77
+ | 1.7555 | 8.8 | 22 | 1.6608 | 0.45 |
78
+ | 1.7555 | 10.0 | 25 | 1.6121 | 0.425 |
79
+ | 1.7555 | 10.8 | 27 | 1.5759 | 0.4813 |
80
+ | 1.5214 | 12.0 | 30 | 1.5340 | 0.4562 |
81
+ | 1.5214 | 12.8 | 32 | 1.5006 | 0.5062 |
82
+ | 1.5214 | 14.0 | 35 | 1.4956 | 0.4313 |
83
+ | 1.5214 | 14.8 | 37 | 1.4418 | 0.5125 |
84
+ | 1.3342 | 16.0 | 40 | 1.4236 | 0.525 |
85
+ | 1.3342 | 16.8 | 42 | 1.3784 | 0.55 |
86
+ | 1.3342 | 18.0 | 45 | 1.4367 | 0.4938 |
87
+ | 1.3342 | 18.8 | 47 | 1.3665 | 0.525 |
88
+ | 1.1553 | 20.0 | 50 | 1.3867 | 0.4813 |
89
+ | 1.1553 | 20.8 | 52 | 1.3536 | 0.5312 |
90
+ | 1.1553 | 22.0 | 55 | 1.3391 | 0.5125 |
91
+ | 1.1553 | 22.8 | 57 | 1.2930 | 0.5563 |
92
+ | 0.9972 | 24.0 | 60 | 1.2894 | 0.5375 |
93
+ | 0.9972 | 24.8 | 62 | 1.2802 | 0.5625 |
94
+ | 0.9972 | 26.0 | 65 | 1.2671 | 0.5687 |
95
+ | 0.9972 | 26.8 | 67 | 1.2491 | 0.5625 |
96
+ | 0.838 | 28.0 | 70 | 1.2907 | 0.5437 |
97
+ | 0.838 | 28.8 | 72 | 1.2806 | 0.5563 |
98
+ | 0.838 | 30.0 | 75 | 1.2228 | 0.5687 |
99
+ | 0.838 | 30.8 | 77 | 1.2485 | 0.575 |
100
+ | 0.7226 | 32.0 | 80 | 1.2777 | 0.5437 |
101
+ | 0.7226 | 32.8 | 82 | 1.2106 | 0.6 |
102
 
103
 
104
  ### Framework versions