Hugging Face's logo

Alimuddin
/
amazon_fish_classification

Image Classification
Transformers
PyTorch
convnext
Generated from Trainer
Eval Results (legacy)
Model card Files
xet
Community
1
Alimuddin commited on
Commit
7970ad1
·
1 Parent(s): 2285615

End of training

Browse files
Files changed (2) hide show
  1. README.md +34 -10
  2. pytorch_model.bin +1 -1
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
- value: 0.3875
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: 1.5900
36
- - Accuracy: 0.3875
37
 
38
  ## Model description
39
 
@@ -52,21 +52,45 @@ More information needed
52
  ### Training hyperparameters
53
 
54
  The following hyperparameters were used during training:
55
- - learning_rate: 5e-05
56
- - train_batch_size: 16
57
- - eval_batch_size: 16
58
  - seed: 42
59
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
60
  - lr_scheduler_type: linear
61
- - num_epochs: 3
62
 
63
  ### Training results
64
 
65
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
66
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
67
- | No log | 1.0 | 40 | 1.8194 | 0.3187 |
68
- | No log | 2.0 | 80 | 1.6244 | 0.375 |
69
- | No log | 3.0 | 120 | 1.5811 | 0.425 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
70
 
71
 
72
  ### Framework versions
 
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
+ value: 0.53125
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: 1.3935
36
+ - Accuracy: 0.5312
37
 
38
  ## Model description
39
 
 
52
  ### Training hyperparameters
53
 
54
  The following hyperparameters were used during training:
55
+ - learning_rate: 1e-07
56
+ - train_batch_size: 27
57
+ - eval_batch_size: 27
58
  - seed: 42
59
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
60
  - lr_scheduler_type: linear
61
+ - num_epochs: 27
62
 
63
  ### Training results
64
 
65
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
66
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
67
+ | No log | 1.0 | 24 | 1.3599 | 0.5188 |
68
+ | No log | 2.0 | 48 | 1.4076 | 0.475 |
69
+ | No log | 3.0 | 72 | 1.3638 | 0.5375 |
70
+ | No log | 4.0 | 96 | 1.4062 | 0.5375 |
71
+ | No log | 5.0 | 120 | 1.3665 | 0.5563 |
72
+ | No log | 6.0 | 144 | 1.3475 | 0.575 |
73
+ | No log | 7.0 | 168 | 1.3814 | 0.525 |
74
+ | No log | 8.0 | 192 | 1.3791 | 0.5437 |
75
+ | No log | 9.0 | 216 | 1.3692 | 0.5125 |
76
+ | No log | 10.0 | 240 | 1.4024 | 0.5188 |
77
+ | No log | 11.0 | 264 | 1.3544 | 0.5687 |
78
+ | No log | 12.0 | 288 | 1.4049 | 0.5375 |
79
+ | No log | 13.0 | 312 | 1.3539 | 0.5687 |
80
+ | No log | 14.0 | 336 | 1.3936 | 0.5062 |
81
+ | No log | 15.0 | 360 | 1.3643 | 0.5375 |
82
+ | No log | 16.0 | 384 | 1.3618 | 0.5563 |
83
+ | No log | 17.0 | 408 | 1.3669 | 0.5687 |
84
+ | No log | 18.0 | 432 | 1.4041 | 0.5188 |
85
+ | No log | 19.0 | 456 | 1.3679 | 0.5312 |
86
+ | No log | 20.0 | 480 | 1.3489 | 0.5563 |
87
+ | 1.1227 | 21.0 | 504 | 1.3575 | 0.575 |
88
+ | 1.1227 | 22.0 | 528 | 1.3721 | 0.55 |
89
+ | 1.1227 | 23.0 | 552 | 1.3985 | 0.4938 |
90
+ | 1.1227 | 24.0 | 576 | 1.3924 | 0.5062 |
91
+ | 1.1227 | 25.0 | 600 | 1.3760 | 0.55 |
92
+ | 1.1227 | 26.0 | 624 | 1.3767 | 0.5125 |
93
+ | 1.1227 | 27.0 | 648 | 1.3627 | 0.5563 |
94
 
95
 
96
  ### Framework versions
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b9618a4873812dcdd3f8c3db63123373422a5e87deda4da86b5a35ce2287bef4
3
  size 343287149
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50efe9ad943ac4060f9c34c22db646e5ae81a1929a40404b81ab6495c3240f55
3
  size 343287149