dukenmarga commited on
Commit
57458a3
·
verified ·
1 Parent(s): 7a01c1d

End of training

Browse files
README.md CHANGED
@@ -1,6 +1,6 @@
1
  ---
2
  license: apache-2.0
3
- base_model: google/vit-base-patch16-224-in21k
4
  tags:
5
  - generated_from_trainer
6
  datasets:
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
- value: 0.5375
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -30,10 +30,10 @@ should probably proofread and complete it, then remove this comment. -->
30
 
31
  # image_classification
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: 1.2847
36
- - Accuracy: 0.5375
37
 
38
  ## Model description
39
 
@@ -52,51 +52,23 @@ 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
  - gradient_accumulation_steps: 4
60
- - total_train_batch_size: 64
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: 30
65
 
66
  ### Training results
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
- | 1.856 | 1.0 | 10 | 1.9048 | 0.3063 |
71
- | 1.81 | 2.0 | 20 | 1.8399 | 0.3063 |
72
- | 1.7131 | 3.0 | 30 | 1.7206 | 0.3375 |
73
- | 1.5894 | 4.0 | 40 | 1.6192 | 0.375 |
74
- | 1.4919 | 5.0 | 50 | 1.5405 | 0.4688 |
75
- | 1.4037 | 6.0 | 60 | 1.4735 | 0.4625 |
76
- | 1.2923 | 7.0 | 70 | 1.4350 | 0.4688 |
77
- | 1.2228 | 8.0 | 80 | 1.4562 | 0.4188 |
78
- | 1.1275 | 9.0 | 90 | 1.3757 | 0.4875 |
79
- | 1.0461 | 10.0 | 100 | 1.3880 | 0.45 |
80
- | 0.9891 | 11.0 | 110 | 1.3440 | 0.5 |
81
- | 0.9058 | 12.0 | 120 | 1.3576 | 0.4813 |
82
- | 0.8835 | 13.0 | 130 | 1.3420 | 0.5188 |
83
- | 0.8274 | 14.0 | 140 | 1.3294 | 0.4938 |
84
- | 0.7686 | 15.0 | 150 | 1.2996 | 0.525 |
85
- | 0.7181 | 16.0 | 160 | 1.2817 | 0.5437 |
86
- | 0.6822 | 17.0 | 170 | 1.2726 | 0.5312 |
87
- | 0.6398 | 18.0 | 180 | 1.3250 | 0.5062 |
88
- | 0.6009 | 19.0 | 190 | 1.3224 | 0.5312 |
89
- | 0.5892 | 20.0 | 200 | 1.3125 | 0.4875 |
90
- | 0.5528 | 21.0 | 210 | 1.3334 | 0.4938 |
91
- | 0.5699 | 22.0 | 220 | 1.2408 | 0.5563 |
92
- | 0.5209 | 23.0 | 230 | 1.3150 | 0.525 |
93
- | 0.5011 | 24.0 | 240 | 1.3601 | 0.4938 |
94
- | 0.5123 | 25.0 | 250 | 1.2566 | 0.5563 |
95
- | 0.4768 | 26.0 | 260 | 1.2542 | 0.5188 |
96
- | 0.4812 | 27.0 | 270 | 1.2753 | 0.525 |
97
- | 0.474 | 28.0 | 280 | 1.2961 | 0.5125 |
98
- | 0.5015 | 29.0 | 290 | 1.2658 | 0.5437 |
99
- | 0.4685 | 30.0 | 300 | 1.2562 | 0.55 |
100
 
101
 
102
  ### Framework versions
 
1
  ---
2
  license: apache-2.0
3
+ base_model: google/vit-large-patch16-224-in21k
4
  tags:
5
  - generated_from_trainer
6
  datasets:
 
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
+ value: 0.375
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
30
 
31
  # image_classification
32
 
33
+ This model is a fine-tuned version of [google/vit-large-patch16-224-in21k](https://huggingface.co/google/vit-large-patch16-224-in21k) on the imagefolder dataset.
34
  It achieves the following results on the evaluation set:
35
+ - Loss: 1.5119
36
+ - Accuracy: 0.375
37
 
38
  ## Model description
39
 
 
52
  ### Training hyperparameters
53
 
54
  The following hyperparameters were used during training:
55
+ - learning_rate: 2e-05
56
+ - train_batch_size: 4
57
+ - eval_batch_size: 4
58
  - seed: 42
59
  - gradient_accumulation_steps: 4
60
+ - total_train_batch_size: 16
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: 2
65
 
66
  ### Training results
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
+ | 1.691 | 1.0 | 40 | 1.7336 | 0.3 |
71
+ | 1.41 | 2.0 | 80 | 1.4853 | 0.4562 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
72
 
73
 
74
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5544aaf741433b6ff94b1340796f3ee58eecd01504b3634b250d933ce2191db7
3
  size 1213285872
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2bb57949556a600070447416ef5b375219118506fe348b41c1cf7d3c0ee59622
3
  size 1213285872
runs/Sep04_10-45-47_256b260ffd87/events.out.tfevents.1725446761.256b260ffd87.1415.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:881a6fb349a5afe76b3a83a93e880759de2fd910d83d4f07bcbcd7c7124fa011
3
- size 14095
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ebbe568343219c942514234eeb2719b479f749636f9235c5951450d1854d5ed
3
+ size 22626
runs/Sep04_10-45-47_256b260ffd87/events.out.tfevents.1725447094.256b260ffd87.1415.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21bed670db7e500b81823f9563be7f30aee606041e4223d6d097d1cf9805ae6f
3
+ size 405