Hugging Face's logo

HZhang729
/
nike_image_classification

Image Classification
Transformers
Safetensors
vit
Model card Files
xet
Community
HZhang729 commited on
Commit
e414c31
·
verified ·
1 Parent(s): 605e6b2

Upload folder using huggingface_hub

Browse files
Files changed (20) hide show
  1. checkpoint-522/config.json +38 -0
  2. checkpoint-522/model.safetensors +3 -0
  3. checkpoint-522/optimizer.pt +3 -0
  4. checkpoint-522/preprocessor_config.json +36 -0
  5. checkpoint-522/rng_state.pth +3 -0
  6. checkpoint-522/scheduler.pt +3 -0
  7. checkpoint-522/trainer_state.json +109 -0
  8. checkpoint-522/training_args.bin +3 -0
  9. checkpoint-580/config.json +38 -0
  10. checkpoint-580/model.safetensors +3 -0
  11. checkpoint-580/optimizer.pt +3 -0
  12. checkpoint-580/preprocessor_config.json +36 -0
  13. checkpoint-580/rng_state.pth +3 -0
  14. checkpoint-580/scheduler.pt +3 -0
  15. checkpoint-580/trainer_state.json +118 -0
  16. checkpoint-580/training_args.bin +3 -0
  17. config.json +38 -0
  18. model.safetensors +3 -0
  19. preprocessor_config.json +36 -0
  20. training_args.bin +3 -0
checkpoint-522/config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "Nike Air Forces",
13
+ "1": "Nike Air Jordans",
14
+ "2": "Nike Dunks",
15
+ "3": "Nike Air Maxes",
16
+ "4": "Nike Cleats"
17
+ },
18
+ "image_size": 224,
19
+ "initializer_range": 0.02,
20
+ "intermediate_size": 3072,
21
+ "label2id": {
22
+ "Nike Air Forces": 0,
23
+ "Nike Air Jordans": 1,
24
+ "Nike Air Maxes": 3,
25
+ "Nike Cleats": 4,
26
+ "Nike Dunks": 2
27
+ },
28
+ "layer_norm_eps": 1e-12,
29
+ "model_type": "vit",
30
+ "num_attention_heads": 12,
31
+ "num_channels": 3,
32
+ "num_hidden_layers": 12,
33
+ "patch_size": 16,
34
+ "problem_type": "single_label_classification",
35
+ "qkv_bias": true,
36
+ "torch_dtype": "float32",
37
+ "transformers_version": "4.40.1"
38
+ }
checkpoint-522/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19eca277d73b542ef0fbfc68f9a559a1ee064af209bb22d68c99ebcb8a29b5c8
3
+ size 343233204
checkpoint-522/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16bbb9953b01bd37dc587ed829984ed882decac2df752f29b7efcbe25f88e2bd
3
+ size 686587322
checkpoint-522/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
+ }
checkpoint-522/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e297de999ef2cb0b7fd240a4b1952731b100739de8f0b301f84cc672131bfc10
3
+ size 14244
checkpoint-522/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6cbf7f1c36f73e0b0d9424f669545469e81bf6560cb400793ff4c35d3fc6e360
3
+ size 1064
checkpoint-522/trainer_state.json ADDED
@@ -0,0 +1,109 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.09288685023784637,
3
+ "best_model_checkpoint": "nike_image_classification/checkpoint-522",
4
+ "epoch": 9.0,
5
+ "eval_steps": 500,
6
+ "global_step": 522,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 1.0,
13
+ "eval_accuracy": 0.8836206896551724,
14
+ "eval_loss": 1.1449412107467651,
15
+ "eval_runtime": 3.1799,
16
+ "eval_samples_per_second": 72.959,
17
+ "eval_steps_per_second": 9.12,
18
+ "step": 58
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_accuracy": 0.9525862068965517,
23
+ "eval_loss": 0.5601115226745605,
24
+ "eval_runtime": 3.0442,
25
+ "eval_samples_per_second": 76.21,
26
+ "eval_steps_per_second": 9.526,
27
+ "step": 116
28
+ },
29
+ {
30
+ "epoch": 3.0,
31
+ "eval_accuracy": 0.9870689655172413,
32
+ "eval_loss": 0.2682268023490906,
33
+ "eval_runtime": 3.0991,
34
+ "eval_samples_per_second": 74.861,
35
+ "eval_steps_per_second": 9.358,
36
+ "step": 174
37
+ },
38
+ {
39
+ "epoch": 4.0,
40
+ "eval_accuracy": 0.9827586206896551,
41
+ "eval_loss": 0.1728191375732422,
42
+ "eval_runtime": 3.0728,
43
+ "eval_samples_per_second": 75.5,
44
+ "eval_steps_per_second": 9.438,
45
+ "step": 232
46
+ },
47
+ {
48
+ "epoch": 5.0,
49
+ "eval_accuracy": 0.9913793103448276,
50
+ "eval_loss": 0.1280447393655777,
51
+ "eval_runtime": 3.062,
52
+ "eval_samples_per_second": 75.768,
53
+ "eval_steps_per_second": 9.471,
54
+ "step": 290
55
+ },
56
+ {
57
+ "epoch": 6.0,
58
+ "eval_accuracy": 0.9913793103448276,
59
+ "eval_loss": 0.11126421391963959,
60
+ "eval_runtime": 3.0781,
61
+ "eval_samples_per_second": 75.371,
62
+ "eval_steps_per_second": 9.421,
63
+ "step": 348
64
+ },
65
+ {
66
+ "epoch": 7.0,
67
+ "eval_accuracy": 0.9956896551724138,
68
+ "eval_loss": 0.10203886032104492,
69
+ "eval_runtime": 3.0495,
70
+ "eval_samples_per_second": 76.077,
71
+ "eval_steps_per_second": 9.51,
72
+ "step": 406
73
+ },
74
+ {
75
+ "epoch": 8.0,
76
+ "eval_accuracy": 0.9913793103448276,
77
+ "eval_loss": 0.09709906578063965,
78
+ "eval_runtime": 3.0724,
79
+ "eval_samples_per_second": 75.512,
80
+ "eval_steps_per_second": 9.439,
81
+ "step": 464
82
+ },
83
+ {
84
+ "epoch": 8.620689655172415,
85
+ "grad_norm": 0.23432303965091705,
86
+ "learning_rate": 4.444444444444444e-06,
87
+ "loss": 0.3676,
88
+ "step": 500
89
+ },
90
+ {
91
+ "epoch": 9.0,
92
+ "eval_accuracy": 0.9913793103448276,
93
+ "eval_loss": 0.09288685023784637,
94
+ "eval_runtime": 3.0773,
95
+ "eval_samples_per_second": 75.391,
96
+ "eval_steps_per_second": 9.424,
97
+ "step": 522
98
+ }
99
+ ],
100
+ "logging_steps": 500,
101
+ "max_steps": 580,
102
+ "num_input_tokens_seen": 0,
103
+ "num_train_epochs": 10,
104
+ "save_steps": 500,
105
+ "total_flos": 6.472304995598991e+17,
106
+ "train_batch_size": 16,
107
+ "trial_name": null,
108
+ "trial_params": null
109
+ }
checkpoint-522/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:565d9e81bfa8a84cbe2fc9cdb8b217927d3174dd2f7030edb93ca20322fc9a0c
3
+ size 4984
checkpoint-580/config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "Nike Air Forces",
13
+ "1": "Nike Air Jordans",
14
+ "2": "Nike Dunks",
15
+ "3": "Nike Air Maxes",
16
+ "4": "Nike Cleats"
17
+ },
18
+ "image_size": 224,
19
+ "initializer_range": 0.02,
20
+ "intermediate_size": 3072,
21
+ "label2id": {
22
+ "Nike Air Forces": 0,
23
+ "Nike Air Jordans": 1,
24
+ "Nike Air Maxes": 3,
25
+ "Nike Cleats": 4,
26
+ "Nike Dunks": 2
27
+ },
28
+ "layer_norm_eps": 1e-12,
29
+ "model_type": "vit",
30
+ "num_attention_heads": 12,
31
+ "num_channels": 3,
32
+ "num_hidden_layers": 12,
33
+ "patch_size": 16,
34
+ "problem_type": "single_label_classification",
35
+ "qkv_bias": true,
36
+ "torch_dtype": "float32",
37
+ "transformers_version": "4.40.1"
38
+ }
checkpoint-580/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79840cee9ba528901f5a74fd6fc306958217671eccbe080c1948576217ff77ec
3
+ size 343233204
checkpoint-580/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30bb9329db878839e888907963b6160ad4d8b7f8b3b5dd6c739de2b005b09350
3
+ size 686587322
checkpoint-580/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
+ }
checkpoint-580/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:976a381961ba57622c9a4731010cc9b3a75dbbd58ca475b58fcacbe5098305c0
3
+ size 14244
checkpoint-580/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:055f5cb46ece048c04c34aff9c03c1f9b7eb75ce77eb2abde77f409358674264
3
+ size 1064
checkpoint-580/trainer_state.json ADDED
@@ -0,0 +1,118 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.09262324869632721,
3
+ "best_model_checkpoint": "nike_image_classification/checkpoint-580",
4
+ "epoch": 10.0,
5
+ "eval_steps": 500,
6
+ "global_step": 580,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 1.0,
13
+ "eval_accuracy": 0.8836206896551724,
14
+ "eval_loss": 1.1449412107467651,
15
+ "eval_runtime": 3.1799,
16
+ "eval_samples_per_second": 72.959,
17
+ "eval_steps_per_second": 9.12,
18
+ "step": 58
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_accuracy": 0.9525862068965517,
23
+ "eval_loss": 0.5601115226745605,
24
+ "eval_runtime": 3.0442,
25
+ "eval_samples_per_second": 76.21,
26
+ "eval_steps_per_second": 9.526,
27
+ "step": 116
28
+ },
29
+ {
30
+ "epoch": 3.0,
31
+ "eval_accuracy": 0.9870689655172413,
32
+ "eval_loss": 0.2682268023490906,
33
+ "eval_runtime": 3.0991,
34
+ "eval_samples_per_second": 74.861,
35
+ "eval_steps_per_second": 9.358,
36
+ "step": 174
37
+ },
38
+ {
39
+ "epoch": 4.0,
40
+ "eval_accuracy": 0.9827586206896551,
41
+ "eval_loss": 0.1728191375732422,
42
+ "eval_runtime": 3.0728,
43
+ "eval_samples_per_second": 75.5,
44
+ "eval_steps_per_second": 9.438,
45
+ "step": 232
46
+ },
47
+ {
48
+ "epoch": 5.0,
49
+ "eval_accuracy": 0.9913793103448276,
50
+ "eval_loss": 0.1280447393655777,
51
+ "eval_runtime": 3.062,
52
+ "eval_samples_per_second": 75.768,
53
+ "eval_steps_per_second": 9.471,
54
+ "step": 290
55
+ },
56
+ {
57
+ "epoch": 6.0,
58
+ "eval_accuracy": 0.9913793103448276,
59
+ "eval_loss": 0.11126421391963959,
60
+ "eval_runtime": 3.0781,
61
+ "eval_samples_per_second": 75.371,
62
+ "eval_steps_per_second": 9.421,
63
+ "step": 348
64
+ },
65
+ {
66
+ "epoch": 7.0,
67
+ "eval_accuracy": 0.9956896551724138,
68
+ "eval_loss": 0.10203886032104492,
69
+ "eval_runtime": 3.0495,
70
+ "eval_samples_per_second": 76.077,
71
+ "eval_steps_per_second": 9.51,
72
+ "step": 406
73
+ },
74
+ {
75
+ "epoch": 8.0,
76
+ "eval_accuracy": 0.9913793103448276,
77
+ "eval_loss": 0.09709906578063965,
78
+ "eval_runtime": 3.0724,
79
+ "eval_samples_per_second": 75.512,
80
+ "eval_steps_per_second": 9.439,
81
+ "step": 464
82
+ },
83
+ {
84
+ "epoch": 8.620689655172415,
85
+ "grad_norm": 0.23432303965091705,
86
+ "learning_rate": 4.444444444444444e-06,
87
+ "loss": 0.3676,
88
+ "step": 500
89
+ },
90
+ {
91
+ "epoch": 9.0,
92
+ "eval_accuracy": 0.9913793103448276,
93
+ "eval_loss": 0.09288685023784637,
94
+ "eval_runtime": 3.0773,
95
+ "eval_samples_per_second": 75.391,
96
+ "eval_steps_per_second": 9.424,
97
+ "step": 522
98
+ },
99
+ {
100
+ "epoch": 10.0,
101
+ "eval_accuracy": 0.9913793103448276,
102
+ "eval_loss": 0.09262324869632721,
103
+ "eval_runtime": 3.0557,
104
+ "eval_samples_per_second": 75.923,
105
+ "eval_steps_per_second": 9.49,
106
+ "step": 580
107
+ }
108
+ ],
109
+ "logging_steps": 500,
110
+ "max_steps": 580,
111
+ "num_input_tokens_seen": 0,
112
+ "num_train_epochs": 10,
113
+ "save_steps": 500,
114
+ "total_flos": 7.19144999510999e+17,
115
+ "train_batch_size": 16,
116
+ "trial_name": null,
117
+ "trial_params": null
118
+ }
checkpoint-580/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:565d9e81bfa8a84cbe2fc9cdb8b217927d3174dd2f7030edb93ca20322fc9a0c
3
+ size 4984
config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "Nike Air Forces",
13
+ "1": "Nike Air Jordans",
14
+ "2": "Nike Dunks",
15
+ "3": "Nike Air Maxes",
16
+ "4": "Nike Cleats"
17
+ },
18
+ "image_size": 224,
19
+ "initializer_range": 0.02,
20
+ "intermediate_size": 3072,
21
+ "label2id": {
22
+ "Nike Air Forces": 0,
23
+ "Nike Air Jordans": 1,
24
+ "Nike Air Maxes": 3,
25
+ "Nike Cleats": 4,
26
+ "Nike Dunks": 2
27
+ },
28
+ "layer_norm_eps": 1e-12,
29
+ "model_type": "vit",
30
+ "num_attention_heads": 12,
31
+ "num_channels": 3,
32
+ "num_hidden_layers": 12,
33
+ "patch_size": 16,
34
+ "problem_type": "single_label_classification",
35
+ "qkv_bias": true,
36
+ "torch_dtype": "float32",
37
+ "transformers_version": "4.40.1"
38
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79840cee9ba528901f5a74fd6fc306958217671eccbe080c1948576217ff77ec
3
+ size 343233204
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
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:565d9e81bfa8a84cbe2fc9cdb8b217927d3174dd2f7030edb93ca20322fc9a0c
3
+ size 4984