Hugging Face's logo

HorcruxNo13
/
vit-base-patch16-224

Image Classification
Transformers
PyTorch
vit
Generated from Trainer
Eval Results (legacy)
Model card Files
xet
Community
1
HorcruxNo13 commited on
Commit
61ee075
·
1 Parent(s): b26ac4e

Model save

Browse files
Files changed (2) hide show
  1. README.md +27 -22
  2. pytorch_model.bin +1 -1
README.md CHANGED
@@ -24,13 +24,13 @@ model-index:
24
  metrics:
25
  - name: Accuracy
26
  type: accuracy
27
- value: 0.8033333333333333
28
  - name: Precision
29
  type: precision
30
- value: 0.7988653846153846
31
  - name: Recall
32
  type: recall
33
- value: 0.8033333333333333
34
  ---
35
 
36
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -40,11 +40,11 @@ should probably proofread and complete it, then remove this comment. -->
40
 
41
  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.
42
  It achieves the following results on the evaluation set:
43
- - Loss: 0.4775
44
- - Accuracy: 0.8033
45
- - Precision: 0.7989
46
- - Recall: 0.8033
47
- - F1 Score: 0.7784
48
 
49
  ## Model description
50
 
@@ -64,30 +64,35 @@ More information needed
64
 
65
  The following hyperparameters were used during training:
66
  - learning_rate: 5e-05
67
- - train_batch_size: 32
68
- - eval_batch_size: 32
69
  - seed: 42
70
  - gradient_accumulation_steps: 4
71
- - total_train_batch_size: 128
72
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
73
  - lr_scheduler_type: linear
74
  - lr_scheduler_warmup_ratio: 0.1
75
- - num_epochs: 10
76
 
77
  ### Training results
78
 
79
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 Score |
80
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:--------:|
81
- | No log | 1.0 | 8 | 0.5941 | 0.7333 | 0.5378 | 0.7333 | 0.6205 |
82
- | 0.6385 | 2.0 | 16 | 0.5391 | 0.775 | 0.7830 | 0.775 | 0.7210 |
83
- | 0.546 | 3.0 | 24 | 0.5417 | 0.775 | 0.7658 | 0.775 | 0.7321 |
84
- | 0.481 | 4.0 | 32 | 0.5486 | 0.7833 | 0.8030 | 0.7833 | 0.7313 |
85
- | 0.3841 | 5.0 | 40 | 0.5420 | 0.7875 | 0.7825 | 0.7875 | 0.7515 |
86
- | 0.3841 | 6.0 | 48 | 0.5246 | 0.8292 | 0.8358 | 0.8292 | 0.8068 |
87
- | 0.2565 | 7.0 | 56 | 0.5763 | 0.8083 | 0.8070 | 0.8083 | 0.7821 |
88
- | 0.1605 | 8.0 | 64 | 0.5433 | 0.825 | 0.8180 | 0.825 | 0.8120 |
89
- | 0.0824 | 9.0 | 72 | 0.6010 | 0.8125 | 0.8027 | 0.8125 | 0.7994 |
90
- | 0.0489 | 10.0 | 80 | 0.6063 | 0.8125 | 0.8032 | 0.8125 | 0.7977 |
 
 
 
 
 
91
 
92
 
93
  ### Framework versions
 
24
  metrics:
25
  - name: Accuracy
26
  type: accuracy
27
+ value: 0.7066666666666667
28
  - name: Precision
29
  type: precision
30
+ value: 0.5034113712374582
31
  - name: Recall
32
  type: recall
33
+ value: 0.7066666666666667
34
  ---
35
 
36
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
40
 
41
  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.
42
  It achieves the following results on the evaluation set:
43
+ - Loss: 0.5891
44
+ - Accuracy: 0.7067
45
+ - Precision: 0.5034
46
+ - Recall: 0.7067
47
+ - F1 Score: 0.5880
48
 
49
  ## Model description
50
 
 
64
 
65
  The following hyperparameters were used during training:
66
  - learning_rate: 5e-05
67
+ - train_batch_size: 64
68
+ - eval_batch_size: 64
69
  - seed: 42
70
  - gradient_accumulation_steps: 4
71
+ - total_train_batch_size: 256
72
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
73
  - lr_scheduler_type: linear
74
  - lr_scheduler_warmup_ratio: 0.1
75
+ - num_epochs: 15
76
 
77
  ### Training results
78
 
79
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 Score |
80
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:--------:|
81
+ | No log | 1.0 | 4 | 0.5970 | 0.725 | 0.5256 | 0.725 | 0.6094 |
82
+ | No log | 2.0 | 8 | 0.5990 | 0.7292 | 0.8028 | 0.7292 | 0.6191 |
83
+ | No log | 3.0 | 12 | 0.5648 | 0.725 | 0.5256 | 0.725 | 0.6094 |
84
+ | 0.6217 | 4.0 | 16 | 0.6035 | 0.7042 | 0.6625 | 0.7042 | 0.6709 |
85
+ | 0.6217 | 5.0 | 20 | 0.5560 | 0.7333 | 0.8050 | 0.7333 | 0.6286 |
86
+ | 0.6217 | 6.0 | 24 | 0.5656 | 0.7167 | 0.6184 | 0.7167 | 0.6194 |
87
+ | 0.6217 | 7.0 | 28 | 0.5552 | 0.7292 | 0.8028 | 0.7292 | 0.6191 |
88
+ | 0.5729 | 8.0 | 32 | 0.5532 | 0.7292 | 0.7126 | 0.7292 | 0.6263 |
89
+ | 0.5729 | 9.0 | 36 | 0.5634 | 0.7292 | 0.6863 | 0.7292 | 0.6453 |
90
+ | 0.5729 | 10.0 | 40 | 0.5589 | 0.7333 | 0.7009 | 0.7333 | 0.6536 |
91
+ | 0.5729 | 11.0 | 44 | 0.5676 | 0.7292 | 0.6848 | 0.7292 | 0.6612 |
92
+ | 0.5599 | 12.0 | 48 | 0.5655 | 0.7333 | 0.6952 | 0.7333 | 0.6688 |
93
+ | 0.5599 | 13.0 | 52 | 0.5692 | 0.7333 | 0.6954 | 0.7333 | 0.6816 |
94
+ | 0.5599 | 14.0 | 56 | 0.5746 | 0.725 | 0.6864 | 0.725 | 0.6863 |
95
+ | 0.5382 | 15.0 | 60 | 0.5752 | 0.7208 | 0.6832 | 0.7208 | 0.6864 |
96
 
97
 
98
  ### Framework versions
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:42da0afb8ad3f6a1c3aa34bf6bff09f056fcd3c9332647bc4967138ffbda96ce
3
  size 343268717
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:359464a0dc2505507d708b4687ebf21f36e4398f3e2dd227b81ddee8beedee54
3
  size 343268717