Hugging Face's logo

Alan1402
/
vit-base-cifar10

Image Classification
Transformers
TensorBoard
Safetensors
vit
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
Alan1402 commited on
Commit
cee8d8b
•
1 Parent(s): ec4fec6

Model save

Browse files
Files changed (11) hide show
  1. README.md +103 -0
  2. all_results.json +8 -0
  3. config.json +48 -0
  4. eval_results.json +8 -0
  5. model.safetensors +3 -0
  6. preprocessor_config.json +36 -0
  7. runs/Jul11_03-32-16_68a81de322cb/events.out.tfevents.1720668846.68a81de322cb.2308.0 +3 -0
  8. runs/Jul11_04-21-03_68a81de322cb/events.out.tfevents.1720671694.68a81de322cb.2308.1 +3 -0
  9. runs/Jul11_04-24-19_68a81de322cb/events.out.tfevents.1720671864.68a81de322cb.2308.2 +3 -0
  10. runs/Jul11_04-24-19_68a81de322cb/events.out.tfevents.1720676901.68a81de322cb.2308.3 +3 -0
  11. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,103 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: google/vit-base-patch16-224-in21k
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - accuracy
8
+ model-index:
9
+ - name: vit-base-cifar10
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ # vit-base-cifar10
17
+
18
+ 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.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 0.0803
21
+ - Accuracy: 0.9773
22
+
23
+ ## Model description
24
+
25
+ More information needed
26
+
27
+ ## Intended uses & limitations
28
+
29
+ More information needed
30
+
31
+ ## Training and evaluation data
32
+
33
+ More information needed
34
+
35
+ ## Training procedure
36
+
37
+ ### Training hyperparameters
38
+
39
+ The following hyperparameters were used during training:
40
+ - learning_rate: 0.0002
41
+ - train_batch_size: 16
42
+ - eval_batch_size: 16
43
+ - seed: 42
44
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
+ - lr_scheduler_type: linear
46
+ - num_epochs: 2
47
+ - mixed_precision_training: Native AMP
48
+
49
+ ### Training results
50
+
51
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
52
+ |:-------------:|:------:|:----:|:---------------:|:--------:|
53
+ | 0.1043 | 0.0457 | 100 | 0.2855 | 0.919 |
54
+ | 0.2671 | 0.0914 | 200 | 0.3650 | 0.9015 |
55
+ | 0.2935 | 0.1371 | 300 | 0.3167 | 0.9067 |
56
+ | 0.27 | 0.1828 | 400 | 0.3518 | 0.8922 |
57
+ | 0.3634 | 0.2285 | 500 | 0.3660 | 0.8953 |
58
+ | 0.2559 | 0.2742 | 600 | 0.3964 | 0.8901 |
59
+ | 0.197 | 0.3199 | 700 | 0.2481 | 0.9253 |
60
+ | 0.2594 | 0.3656 | 800 | 0.2486 | 0.923 |
61
+ | 0.4545 | 0.4113 | 900 | 0.3271 | 0.9 |
62
+ | 0.1243 | 0.4570 | 1000 | 0.2448 | 0.9269 |
63
+ | 0.3593 | 0.5027 | 1100 | 0.2118 | 0.9354 |
64
+ | 0.1375 | 0.5484 | 1200 | 0.2205 | 0.9349 |
65
+ | 0.1521 | 0.5941 | 1300 | 0.2009 | 0.9376 |
66
+ | 0.1237 | 0.6399 | 1400 | 0.1803 | 0.9445 |
67
+ | 0.2214 | 0.6856 | 1500 | 0.2026 | 0.9395 |
68
+ | 0.1324 | 0.7313 | 1600 | 0.1635 | 0.9493 |
69
+ | 0.1864 | 0.7770 | 1700 | 0.1672 | 0.9493 |
70
+ | 0.128 | 0.8227 | 1800 | 0.2015 | 0.9409 |
71
+ | 0.121 | 0.8684 | 1900 | 0.1753 | 0.9451 |
72
+ | 0.1918 | 0.9141 | 2000 | 0.1370 | 0.9588 |
73
+ | 0.1658 | 0.9598 | 2100 | 0.1543 | 0.9535 |
74
+ | 0.1088 | 1.0055 | 2200 | 0.1361 | 0.9577 |
75
+ | 0.0916 | 1.0512 | 2300 | 0.1393 | 0.9597 |
76
+ | 0.005 | 1.0969 | 2400 | 0.1295 | 0.9621 |
77
+ | 0.0294 | 1.1426 | 2500 | 0.1327 | 0.9639 |
78
+ | 0.0939 | 1.1883 | 2600 | 0.1409 | 0.9621 |
79
+ | 0.0756 | 1.2340 | 2700 | 0.1202 | 0.9682 |
80
+ | 0.0466 | 1.2797 | 2800 | 0.1274 | 0.964 |
81
+ | 0.0565 | 1.3254 | 2900 | 0.1250 | 0.9663 |
82
+ | 0.0609 | 1.3711 | 3000 | 0.1299 | 0.9657 |
83
+ | 0.0201 | 1.4168 | 3100 | 0.1203 | 0.9685 |
84
+ | 0.0258 | 1.4625 | 3200 | 0.1166 | 0.9693 |
85
+ | 0.0913 | 1.5082 | 3300 | 0.1009 | 0.9736 |
86
+ | 0.0235 | 1.5539 | 3400 | 0.0964 | 0.9732 |
87
+ | 0.0089 | 1.5996 | 3500 | 0.0966 | 0.9747 |
88
+ | 0.0455 | 1.6453 | 3600 | 0.0963 | 0.9748 |
89
+ | 0.0271 | 1.6910 | 3700 | 0.0874 | 0.9763 |
90
+ | 0.0407 | 1.7367 | 3800 | 0.0898 | 0.9761 |
91
+ | 0.1095 | 1.7824 | 3900 | 0.0849 | 0.976 |
92
+ | 0.0327 | 1.8282 | 4000 | 0.0926 | 0.9745 |
93
+ | 0.0427 | 1.8739 | 4100 | 0.0811 | 0.9769 |
94
+ | 0.003 | 1.9196 | 4200 | 0.0821 | 0.9761 |
95
+ | 0.0182 | 1.9653 | 4300 | 0.0803 | 0.9773 |
96
+
97
+
98
+ ### Framework versions
99
+
100
+ - Transformers 4.41.2
101
+ - Pytorch 2.3.0+cu121
102
+ - Datasets 2.20.0
103
+ - Tokenizers 0.19.1
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.0,
3
+ "eval_accuracy": 0.9772666666666666,
4
+ "eval_loss": 0.08026164770126343,
5
+ "eval_runtime": 73.8075,
6
+ "eval_samples_per_second": 203.231,
7
+ "eval_steps_per_second": 12.709
8
+ }
config.json ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/vit-base-patch16-224-in21k",
3
+ "architectures": [
4
+ "ViTForImageClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.0,
7
+ "encoder_stride": 16,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.0,
10
+ "hidden_size": 768,
11
+ "id2label": {
12
+ "0": "airplane",
13
+ "1": "automobile",
14
+ "2": "bird",
15
+ "3": "cat",
16
+ "4": "deer",
17
+ "5": "dog",
18
+ "6": "frog",
19
+ "7": "horse",
20
+ "8": "ship",
21
+ "9": "truck"
22
+ },
23
+ "image_size": 224,
24
+ "initializer_range": 0.02,
25
+ "intermediate_size": 3072,
26
+ "label2id": {
27
+ "airplane": "0",
28
+ "automobile": "1",
29
+ "bird": "2",
30
+ "cat": "3",
31
+ "deer": "4",
32
+ "dog": "5",
33
+ "frog": "6",
34
+ "horse": "7",
35
+ "ship": "8",
36
+ "truck": "9"
37
+ },
38
+ "layer_norm_eps": 1e-12,
39
+ "model_type": "vit",
40
+ "num_attention_heads": 12,
41
+ "num_channels": 3,
42
+ "num_hidden_layers": 12,
43
+ "patch_size": 16,
44
+ "problem_type": "single_label_classification",
45
+ "qkv_bias": true,
46
+ "torch_dtype": "float32",
47
+ "transformers_version": "4.41.2"
48
+ }
eval_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.0,
3
+ "eval_accuracy": 0.9772666666666666,
4
+ "eval_loss": 0.08026164770126343,
5
+ "eval_runtime": 73.8075,
6
+ "eval_samples_per_second": 203.231,
7
+ "eval_steps_per_second": 12.709
8
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c975f5c180d9530fa4dd36efb68a0dcf4a2cc0c4e987022f8213bfa3078ff425
3
+ size 343248584
preprocessor_config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_valid_processor_keys": [
3
+ "images",
4
+ "do_resize",
5
+ "size",
6
+ "resample",
7
+ "do_rescale",
8
+ "rescale_factor",
9
+ "do_normalize",
10
+ "image_mean",
11
+ "image_std",
12
+ "return_tensors",
13
+ "data_format",
14
+ "input_data_format"
15
+ ],
16
+ "do_normalize": true,
17
+ "do_rescale": true,
18
+ "do_resize": true,
19
+ "image_mean": [
20
+ 0.5,
21
+ 0.5,
22
+ 0.5
23
+ ],
24
+ "image_processor_type": "ViTImageProcessor",
25
+ "image_std": [
26
+ 0.5,
27
+ 0.5,
28
+ 0.5
29
+ ],
30
+ "resample": 2,
31
+ "rescale_factor": 0.00392156862745098,
32
+ "size": {
33
+ "height": 224,
34
+ "width": 224
35
+ }
36
+ }
runs/Jul11_03-32-16_68a81de322cb/events.out.tfevents.1720668846.68a81de322cb.2308.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6552ba20fc317ca496530faea387b19e4b792dd8354c125a5c61008671ba671
3
+ size 26609
runs/Jul11_04-21-03_68a81de322cb/events.out.tfevents.1720671694.68a81de322cb.2308.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3208881b3215da52a29830cfaf2796a00a504f095ee4ee9d82a386c85af10c3a
3
+ size 9578
runs/Jul11_04-24-19_68a81de322cb/events.out.tfevents.1720671864.68a81de322cb.2308.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c29be2489d38b5fbdfb5e6d44a64c82e2e43c70d343474872e5fc366611c4c2d
3
+ size 111580
runs/Jul11_04-24-19_68a81de322cb/events.out.tfevents.1720676901.68a81de322cb.2308.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99d9915b08810dc0b2179a4702e0c1e43d582c4abc61ccae3758a2a829195f65
3
+ size 411
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12137f9c2609cda8061eb814fba14714946fd9509a99f4e2d72db5e34f673c18
3
+ size 5112