Hugging Face's logo

pkr7098
/
only-lora-beans-vit-base-patch16-224-in21k

Image Classification
PEFT
Safetensors
vit
vision
Generated from Trainer
Model card Files Community
pkr7098 commited on
Commit
5320145
•
1 Parent(s): 0dabf2c

Model save

Browse files
Files changed (1) hide show
  1. README.md +15 -17
README.md CHANGED
@@ -5,8 +5,6 @@ license: apache-2.0
5
  metrics:
6
  - accuracy
7
  tags:
8
- - image-classification
9
- - vision
10
  - generated_from_trainer
11
  model-index:
12
  - name: only-lora-beans-vit-base-patch16-224-in21k
@@ -18,10 +16,10 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  # only-lora-beans-vit-base-patch16-224-in21k
20
 
21
- 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 beans dataset.
22
  It achieves the following results on the evaluation set:
23
- - Loss: 0.0752
24
- - Accuracy: 0.9624
25
 
26
  ## Model description
27
 
@@ -40,7 +38,7 @@ More information needed
40
  ### Training hyperparameters
41
 
42
  The following hyperparameters were used during training:
43
- - learning_rate: 0.005
44
  - train_batch_size: 8
45
  - eval_batch_size: 8
46
  - seed: 1337
@@ -52,21 +50,21 @@ The following hyperparameters were used during training:
52
 
53
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
54
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
55
- | 0.4846 | 1.0 | 130 | 0.0752 | 0.9624 |
56
- | 0.3473 | 2.0 | 260 | 0.1599 | 0.9549 |
57
- | 0.2953 | 3.0 | 390 | 0.1192 | 0.9549 |
58
- | 0.2653 | 4.0 | 520 | 0.1393 | 0.9398 |
59
- | 0.2344 | 5.0 | 650 | 0.1001 | 0.9624 |
60
- | 0.21 | 6.0 | 780 | 0.0893 | 0.9624 |
61
- | 0.3117 | 7.0 | 910 | 0.1933 | 0.9248 |
62
- | 0.2459 | 8.0 | 1040 | 0.1901 | 0.9248 |
63
- | 0.25 | 9.0 | 1170 | 0.0868 | 0.9699 |
64
- | 0.2038 | 10.0 | 1300 | 0.1528 | 0.9474 |
65
 
66
 
67
  ### Framework versions
68
 
69
- - PEFT 0.12.0
70
  - Transformers 4.44.0
71
  - Pytorch 2.4.0+cu121
72
  - Datasets 2.20.0
 
5
  metrics:
6
  - accuracy
7
  tags:
 
 
8
  - generated_from_trainer
9
  model-index:
10
  - name: only-lora-beans-vit-base-patch16-224-in21k
 
16
 
17
  # only-lora-beans-vit-base-patch16-224-in21k
18
 
19
+ This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.7512
22
+ - Accuracy: 0.6541
23
 
24
  ## Model description
25
 
 
38
  ### Training hyperparameters
39
 
40
  The following hyperparameters were used during training:
41
+ - learning_rate: 5e-05
42
  - train_batch_size: 8
43
  - eval_batch_size: 8
44
  - seed: 1337
 
50
 
51
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
52
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
53
+ | 1.1019 | 1.0 | 130 | 1.0947 | 0.4135 |
54
+ | 1.091 | 2.0 | 260 | 1.0027 | 0.5188 |
55
+ | 1.0433 | 3.0 | 390 | 0.9840 | 0.5188 |
56
+ | 0.9823 | 4.0 | 520 | 0.9470 | 0.5639 |
57
+ | 0.9523 | 5.0 | 650 | 0.9246 | 0.5789 |
58
+ | 0.9431 | 6.0 | 780 | 0.8905 | 0.5564 |
59
+ | 0.8587 | 7.0 | 910 | 0.8434 | 0.5940 |
60
+ | 0.834 | 8.0 | 1040 | 0.8319 | 0.5714 |
61
+ | 0.8149 | 9.0 | 1170 | 0.7831 | 0.6767 |
62
+ | 0.729 | 10.0 | 1300 | 0.7512 | 0.6541 |
63
 
64
 
65
  ### Framework versions
66
 
67
+ - PEFT 0.12.1.dev0
68
  - Transformers 4.44.0
69
  - Pytorch 2.4.0+cu121
70
  - Datasets 2.20.0