Hugging Face's logo

dima806
/
asl_alphabet_image_detection

Image Classification
Transformers
PyTorch
Safetensors
vit
Inference Endpoints
Model card Files Community
1
dima806 commited on
Commit
7ef33c5
•
1 Parent(s): 3af295f

Upload folder using huggingface_hub

Browse files
Files changed (12) hide show
  1. checkpoint-6525/config.json +86 -0
  2. checkpoint-6525/optimizer.pt +3 -0
  3. checkpoint-6525/preprocessor_config.json +22 -0
  4. checkpoint-6525/pytorch_model.bin +3 -0
  5. checkpoint-6525/rng_state.pth +3 -0
  6. checkpoint-6525/scheduler.pt +3 -0
  7. checkpoint-6525/trainer_state.json +124 -0
  8. checkpoint-6525/training_args.bin +3 -0
  9. config.json +86 -0
  10. preprocessor_config.json +22 -0
  11. pytorch_model.bin +3 -0
  12. training_args.bin +3 -0
checkpoint-6525/config.json ADDED
@@ -0,0 +1,86 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "H",
13
+ "1": "Z",
14
+ "2": "D",
15
+ "3": "X",
16
+ "4": "K",
17
+ "5": "V",
18
+ "6": "I",
19
+ "7": "J",
20
+ "8": "T",
21
+ "9": "W",
22
+ "10": "E",
23
+ "11": "M",
24
+ "12": "G",
25
+ "13": "nothing",
26
+ "14": "del",
27
+ "15": "C",
28
+ "16": "F",
29
+ "17": "L",
30
+ "18": "U",
31
+ "19": "O",
32
+ "20": "space",
33
+ "21": "Y",
34
+ "22": "A",
35
+ "23": "B",
36
+ "24": "R",
37
+ "25": "Q",
38
+ "26": "N",
39
+ "27": "S",
40
+ "28": "P"
41
+ },
42
+ "image_size": 224,
43
+ "initializer_range": 0.02,
44
+ "intermediate_size": 3072,
45
+ "label2id": {
46
+ "A": 22,
47
+ "B": 23,
48
+ "C": 15,
49
+ "D": 2,
50
+ "E": 10,
51
+ "F": 16,
52
+ "G": 12,
53
+ "H": 0,
54
+ "I": 6,
55
+ "J": 7,
56
+ "K": 4,
57
+ "L": 17,
58
+ "M": 11,
59
+ "N": 26,
60
+ "O": 19,
61
+ "P": 28,
62
+ "Q": 25,
63
+ "R": 24,
64
+ "S": 27,
65
+ "T": 8,
66
+ "U": 18,
67
+ "V": 5,
68
+ "W": 9,
69
+ "X": 3,
70
+ "Y": 21,
71
+ "Z": 1,
72
+ "del": 14,
73
+ "nothing": 13,
74
+ "space": 20
75
+ },
76
+ "layer_norm_eps": 1e-12,
77
+ "model_type": "vit",
78
+ "num_attention_heads": 12,
79
+ "num_channels": 3,
80
+ "num_hidden_layers": 12,
81
+ "patch_size": 16,
82
+ "problem_type": "single_label_classification",
83
+ "qkv_bias": true,
84
+ "torch_dtype": "float32",
85
+ "transformers_version": "4.33.0"
86
+ }
checkpoint-6525/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6487fb928614c51494131641afe4cecca5a0a067a8ec1129271a10de5f8eac3a
3
+ size 686734469
checkpoint-6525/preprocessor_config.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_normalize": true,
3
+ "do_rescale": true,
4
+ "do_resize": true,
5
+ "image_mean": [
6
+ 0.5,
7
+ 0.5,
8
+ 0.5
9
+ ],
10
+ "image_processor_type": "ViTImageProcessor",
11
+ "image_std": [
12
+ 0.5,
13
+ 0.5,
14
+ 0.5
15
+ ],
16
+ "resample": 2,
17
+ "rescale_factor": 0.00392156862745098,
18
+ "size": {
19
+ "height": 224,
20
+ "width": 224
21
+ }
22
+ }
checkpoint-6525/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13d1c79457949ca681c82d1343381da9f0753f2bfe22940fcdf11d1297be75b9
3
+ size 343351725
checkpoint-6525/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa96537221eaa2bd8801be815d067f48c6af04437ff3ec34045d278e34e645fc
3
+ size 14575
checkpoint-6525/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f6ded57350838be39f4c3d139de6f7933111085d5f7246631735ba8033af504
3
+ size 627
checkpoint-6525/trainer_state.json ADDED
@@ -0,0 +1,124 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.0647471621632576,
3
+ "best_model_checkpoint": "asl_alphabet_image_detection/checkpoint-6525",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 6525,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.23,
13
+ "learning_rate": 9.305019305019305e-06,
14
+ "loss": 2.5567,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 0.46,
19
+ "learning_rate": 8.532818532818533e-06,
20
+ "loss": 1.116,
21
+ "step": 1000
22
+ },
23
+ {
24
+ "epoch": 0.69,
25
+ "learning_rate": 7.760617760617761e-06,
26
+ "loss": 0.5592,
27
+ "step": 1500
28
+ },
29
+ {
30
+ "epoch": 0.92,
31
+ "learning_rate": 6.988416988416989e-06,
32
+ "loss": 0.3304,
33
+ "step": 2000
34
+ },
35
+ {
36
+ "epoch": 1.0,
37
+ "eval_accuracy": 0.9991954022988506,
38
+ "eval_loss": 0.2387184053659439,
39
+ "eval_runtime": 184.9784,
40
+ "eval_samples_per_second": 94.065,
41
+ "eval_steps_per_second": 11.758,
42
+ "step": 2175
43
+ },
44
+ {
45
+ "epoch": 1.15,
46
+ "learning_rate": 6.2162162162162164e-06,
47
+ "loss": 0.2285,
48
+ "step": 2500
49
+ },
50
+ {
51
+ "epoch": 1.38,
52
+ "learning_rate": 5.444015444015444e-06,
53
+ "loss": 0.1713,
54
+ "step": 3000
55
+ },
56
+ {
57
+ "epoch": 1.61,
58
+ "learning_rate": 4.671814671814672e-06,
59
+ "loss": 0.1359,
60
+ "step": 3500
61
+ },
62
+ {
63
+ "epoch": 1.84,
64
+ "learning_rate": 3.8996138996139e-06,
65
+ "loss": 0.1108,
66
+ "step": 4000
67
+ },
68
+ {
69
+ "epoch": 2.0,
70
+ "eval_accuracy": 0.9997126436781609,
71
+ "eval_loss": 0.09148428589105606,
72
+ "eval_runtime": 182.2169,
73
+ "eval_samples_per_second": 95.491,
74
+ "eval_steps_per_second": 11.936,
75
+ "step": 4350
76
+ },
77
+ {
78
+ "epoch": 2.07,
79
+ "learning_rate": 3.1274131274131274e-06,
80
+ "loss": 0.0934,
81
+ "step": 4500
82
+ },
83
+ {
84
+ "epoch": 2.3,
85
+ "learning_rate": 2.3552123552123553e-06,
86
+ "loss": 0.0813,
87
+ "step": 5000
88
+ },
89
+ {
90
+ "epoch": 2.53,
91
+ "learning_rate": 1.583011583011583e-06,
92
+ "loss": 0.0733,
93
+ "step": 5500
94
+ },
95
+ {
96
+ "epoch": 2.76,
97
+ "learning_rate": 8.108108108108109e-07,
98
+ "loss": 0.0679,
99
+ "step": 6000
100
+ },
101
+ {
102
+ "epoch": 2.99,
103
+ "learning_rate": 3.861003861003861e-08,
104
+ "loss": 0.0647,
105
+ "step": 6500
106
+ },
107
+ {
108
+ "epoch": 3.0,
109
+ "eval_accuracy": 0.9997701149425288,
110
+ "eval_loss": 0.0647471621632576,
111
+ "eval_runtime": 184.0798,
112
+ "eval_samples_per_second": 94.524,
113
+ "eval_steps_per_second": 11.816,
114
+ "step": 6525
115
+ }
116
+ ],
117
+ "logging_steps": 500,
118
+ "max_steps": 6525,
119
+ "num_train_epochs": 3,
120
+ "save_steps": 500,
121
+ "total_flos": 1.6184242948762829e+19,
122
+ "trial_name": null,
123
+ "trial_params": null
124
+ }
checkpoint-6525/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7951844a95980b8b5c6a8ed6e5720b223e30c8a20f870af7d12a101fa197e693
3
+ size 4027
config.json ADDED
@@ -0,0 +1,86 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "H",
13
+ "1": "Z",
14
+ "2": "D",
15
+ "3": "X",
16
+ "4": "K",
17
+ "5": "V",
18
+ "6": "I",
19
+ "7": "J",
20
+ "8": "T",
21
+ "9": "W",
22
+ "10": "E",
23
+ "11": "M",
24
+ "12": "G",
25
+ "13": "nothing",
26
+ "14": "del",
27
+ "15": "C",
28
+ "16": "F",
29
+ "17": "L",
30
+ "18": "U",
31
+ "19": "O",
32
+ "20": "space",
33
+ "21": "Y",
34
+ "22": "A",
35
+ "23": "B",
36
+ "24": "R",
37
+ "25": "Q",
38
+ "26": "N",
39
+ "27": "S",
40
+ "28": "P"
41
+ },
42
+ "image_size": 224,
43
+ "initializer_range": 0.02,
44
+ "intermediate_size": 3072,
45
+ "label2id": {
46
+ "A": 22,
47
+ "B": 23,
48
+ "C": 15,
49
+ "D": 2,
50
+ "E": 10,
51
+ "F": 16,
52
+ "G": 12,
53
+ "H": 0,
54
+ "I": 6,
55
+ "J": 7,
56
+ "K": 4,
57
+ "L": 17,
58
+ "M": 11,
59
+ "N": 26,
60
+ "O": 19,
61
+ "P": 28,
62
+ "Q": 25,
63
+ "R": 24,
64
+ "S": 27,
65
+ "T": 8,
66
+ "U": 18,
67
+ "V": 5,
68
+ "W": 9,
69
+ "X": 3,
70
+ "Y": 21,
71
+ "Z": 1,
72
+ "del": 14,
73
+ "nothing": 13,
74
+ "space": 20
75
+ },
76
+ "layer_norm_eps": 1e-12,
77
+ "model_type": "vit",
78
+ "num_attention_heads": 12,
79
+ "num_channels": 3,
80
+ "num_hidden_layers": 12,
81
+ "patch_size": 16,
82
+ "problem_type": "single_label_classification",
83
+ "qkv_bias": true,
84
+ "torch_dtype": "float32",
85
+ "transformers_version": "4.33.0"
86
+ }
preprocessor_config.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_normalize": true,
3
+ "do_rescale": true,
4
+ "do_resize": true,
5
+ "image_mean": [
6
+ 0.5,
7
+ 0.5,
8
+ 0.5
9
+ ],
10
+ "image_processor_type": "ViTImageProcessor",
11
+ "image_std": [
12
+ 0.5,
13
+ 0.5,
14
+ 0.5
15
+ ],
16
+ "resample": 2,
17
+ "rescale_factor": 0.00392156862745098,
18
+ "size": {
19
+ "height": 224,
20
+ "width": 224
21
+ }
22
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13d1c79457949ca681c82d1343381da9f0753f2bfe22940fcdf11d1297be75b9
3
+ size 343351725
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7951844a95980b8b5c6a8ed6e5720b223e30c8a20f870af7d12a101fa197e693
3
+ size 4027