Hugging Face's logo

barten
/
vit-base-patch16-224-type

Image Classification
Transformers
PyTorch
TensorBoard
Safetensors
vit
Generated from Trainer
Eval Results (legacy)
Model card Files
xet
Metrics Community
barten commited on
Commit
e6c682e
·
1 Parent(s): 1d04c2b

Model save

Browse files
Files changed (3) hide show
  1. README.md +24 -19
  2. model.safetensors +1 -1
  3. runs/Nov15_14-54-12_28f7839165a4/events.out.tfevents.1700060053.28f7839165a4.1395.1 +2 -2
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
- value: 0.7570422535211268
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](https://huggingface.co/google/vit-base-patch16-224) on the imagefolder dataset.
34
  It achieves the following results on the evaluation set:
35
- - Loss: 0.6881
36
- - Accuracy: 0.7570
37
 
38
  ## Model description
39
 
@@ -53,35 +53,40 @@ More information needed
53
 
54
  The following hyperparameters were used during training:
55
  - learning_rate: 5e-05
56
- - train_batch_size: 32
57
- - eval_batch_size: 32
58
  - seed: 42
59
  - gradient_accumulation_steps: 4
60
- - total_train_batch_size: 128
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: 10
65
 
66
  ### Training results
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
- | 1.3494 | 1.0 | 62 | 1.1001 | 0.6350 |
71
- | 0.9612 | 1.99 | 124 | 0.8708 | 0.6772 |
72
- | 0.8817 | 2.99 | 186 | 0.7898 | 0.7265 |
73
- | 0.8362 | 4.0 | 249 | 0.7643 | 0.7277 |
74
- | 0.7959 | 5.0 | 311 | 0.7310 | 0.7383 |
75
- | 0.6765 | 5.99 | 373 | 0.7247 | 0.7471 |
76
- | 0.6504 | 6.99 | 435 | 0.6939 | 0.7576 |
77
- | 0.5846 | 8.0 | 498 | 0.6983 | 0.7576 |
78
- | 0.5774 | 9.0 | 560 | 0.6935 | 0.7594 |
79
- | 0.5749 | 9.96 | 620 | 0.6881 | 0.7570 |
 
 
 
 
 
80
 
81
 
82
  ### Framework versions
83
 
84
- - Transformers 4.35.0
85
  - Pytorch 2.1.0+cu118
86
- - Datasets 2.14.6
87
  - Tokenizers 0.14.1
 
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
+ value: 0.7541079812206573
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](https://huggingface.co/google/vit-base-patch16-224) on the imagefolder dataset.
34
  It achieves the following results on the evaluation set:
35
+ - Loss: 0.7622
36
+ - Accuracy: 0.7541
37
 
38
  ## Model description
39
 
 
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: 15
65
 
66
  ### Training results
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
+ | 1.2477 | 1.0 | 124 | 1.0873 | 0.6262 |
71
+ | 0.9863 | 2.0 | 249 | 0.8378 | 0.6984 |
72
+ | 0.9532 | 3.0 | 373 | 0.7864 | 0.7295 |
73
+ | 0.758 | 4.0 | 498 | 0.7582 | 0.7342 |
74
+ | 0.6702 | 5.0 | 622 | 0.7462 | 0.7330 |
75
+ | 0.6304 | 6.0 | 747 | 0.7100 | 0.7482 |
76
+ | 0.518 | 7.0 | 871 | 0.7437 | 0.7506 |
77
+ | 0.5636 | 8.0 | 996 | 0.7337 | 0.7541 |
78
+ | 0.4993 | 9.0 | 1120 | 0.7356 | 0.7535 |
79
+ | 0.5118 | 10.0 | 1245 | 0.7427 | 0.7582 |
80
+ | 0.393 | 11.0 | 1369 | 0.7663 | 0.7494 |
81
+ | 0.3634 | 12.0 | 1494 | 0.7718 | 0.7488 |
82
+ | 0.3514 | 13.0 | 1618 | 0.7588 | 0.7553 |
83
+ | 0.3273 | 14.0 | 1743 | 0.7616 | 0.7541 |
84
+ | 0.3782 | 14.94 | 1860 | 0.7622 | 0.7541 |
85
 
86
 
87
  ### Framework versions
88
 
89
+ - Transformers 4.35.1
90
  - Pytorch 2.1.0+cu118
91
+ - Datasets 2.14.7
92
  - Tokenizers 0.14.1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fb922b9da425162872a21435143f61abb44d0cb5215f7896eac99e4a9478ec01
3
  size 343245508
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca3670d6ef787cafce0a9a922fb52a643c7188cef0a9a4fc4eb83322480d4494
3
  size 343245508
runs/Nov15_14-54-12_28f7839165a4/events.out.tfevents.1700060053.28f7839165a4.1395.1 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f9df4870e85ed5915f9517828ba89090cd760dcaeb628ede7e612753e31a41ad
3
- size 36818
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2d7d5aa9163669e83c3889b5d92a262bfce502f9ae9c11fef8fd8a388f47264
3
+ size 39379