Hugging Face's logo

ProbeX
/
Model-J__DINO__model_idx_0636

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Eliahu commited on
Commit
d495a07
·
verified ·
1 Parent(s): afb1c93

Upload folder using huggingface_hub

Browse files
Files changed (5) hide show
  1. config.json +128 -0
  2. model.safetensors +3 -0
  3. preprocessor_config.json +22 -0
  4. trainer_state.json +177 -0
  5. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,128 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/dino-vitb16",
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": "LABEL_0",
13
+ "1": "LABEL_1",
14
+ "2": "LABEL_2",
15
+ "3": "LABEL_3",
16
+ "4": "LABEL_4",
17
+ "5": "LABEL_5",
18
+ "6": "LABEL_6",
19
+ "7": "LABEL_7",
20
+ "8": "LABEL_8",
21
+ "9": "LABEL_9",
22
+ "10": "LABEL_10",
23
+ "11": "LABEL_11",
24
+ "12": "LABEL_12",
25
+ "13": "LABEL_13",
26
+ "14": "LABEL_14",
27
+ "15": "LABEL_15",
28
+ "16": "LABEL_16",
29
+ "17": "LABEL_17",
30
+ "18": "LABEL_18",
31
+ "19": "LABEL_19",
32
+ "20": "LABEL_20",
33
+ "21": "LABEL_21",
34
+ "22": "LABEL_22",
35
+ "23": "LABEL_23",
36
+ "24": "LABEL_24",
37
+ "25": "LABEL_25",
38
+ "26": "LABEL_26",
39
+ "27": "LABEL_27",
40
+ "28": "LABEL_28",
41
+ "29": "LABEL_29",
42
+ "30": "LABEL_30",
43
+ "31": "LABEL_31",
44
+ "32": "LABEL_32",
45
+ "33": "LABEL_33",
46
+ "34": "LABEL_34",
47
+ "35": "LABEL_35",
48
+ "36": "LABEL_36",
49
+ "37": "LABEL_37",
50
+ "38": "LABEL_38",
51
+ "39": "LABEL_39",
52
+ "40": "LABEL_40",
53
+ "41": "LABEL_41",
54
+ "42": "LABEL_42",
55
+ "43": "LABEL_43",
56
+ "44": "LABEL_44",
57
+ "45": "LABEL_45",
58
+ "46": "LABEL_46",
59
+ "47": "LABEL_47",
60
+ "48": "LABEL_48",
61
+ "49": "LABEL_49"
62
+ },
63
+ "image_size": 224,
64
+ "initializer_range": 0.02,
65
+ "intermediate_size": 3072,
66
+ "label2id": {
67
+ "LABEL_0": 0,
68
+ "LABEL_1": 1,
69
+ "LABEL_10": 10,
70
+ "LABEL_11": 11,
71
+ "LABEL_12": 12,
72
+ "LABEL_13": 13,
73
+ "LABEL_14": 14,
74
+ "LABEL_15": 15,
75
+ "LABEL_16": 16,
76
+ "LABEL_17": 17,
77
+ "LABEL_18": 18,
78
+ "LABEL_19": 19,
79
+ "LABEL_2": 2,
80
+ "LABEL_20": 20,
81
+ "LABEL_21": 21,
82
+ "LABEL_22": 22,
83
+ "LABEL_23": 23,
84
+ "LABEL_24": 24,
85
+ "LABEL_25": 25,
86
+ "LABEL_26": 26,
87
+ "LABEL_27": 27,
88
+ "LABEL_28": 28,
89
+ "LABEL_29": 29,
90
+ "LABEL_3": 3,
91
+ "LABEL_30": 30,
92
+ "LABEL_31": 31,
93
+ "LABEL_32": 32,
94
+ "LABEL_33": 33,
95
+ "LABEL_34": 34,
96
+ "LABEL_35": 35,
97
+ "LABEL_36": 36,
98
+ "LABEL_37": 37,
99
+ "LABEL_38": 38,
100
+ "LABEL_39": 39,
101
+ "LABEL_4": 4,
102
+ "LABEL_40": 40,
103
+ "LABEL_41": 41,
104
+ "LABEL_42": 42,
105
+ "LABEL_43": 43,
106
+ "LABEL_44": 44,
107
+ "LABEL_45": 45,
108
+ "LABEL_46": 46,
109
+ "LABEL_47": 47,
110
+ "LABEL_48": 48,
111
+ "LABEL_49": 49,
112
+ "LABEL_5": 5,
113
+ "LABEL_6": 6,
114
+ "LABEL_7": 7,
115
+ "LABEL_8": 8,
116
+ "LABEL_9": 9
117
+ },
118
+ "layer_norm_eps": 1e-12,
119
+ "model_type": "vit",
120
+ "num_attention_heads": 12,
121
+ "num_channels": 3,
122
+ "num_hidden_layers": 12,
123
+ "patch_size": 16,
124
+ "problem_type": "single_label_classification",
125
+ "qkv_bias": true,
126
+ "torch_dtype": "float32",
127
+ "transformers_version": "4.44.0"
128
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d8d9d1849a89938617c8f68b27630fc41b4762ecc41131d7cc72035dbc64c65
3
+ size 343372728
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
+ 0.485,
7
+ 0.456,
8
+ 0.406
9
+ ],
10
+ "image_processor_type": "ViTImageProcessor",
11
+ "image_std": [
12
+ 0.229,
13
+ 0.224,
14
+ 0.225
15
+ ],
16
+ "resample": 2,
17
+ "rescale_factor": 0.00392156862745098,
18
+ "size": {
19
+ "height": 224,
20
+ "width": 224
21
+ }
22
+ }
trainer_state.json ADDED
@@ -0,0 +1,177 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.34026666666666666,
3
+ "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0636/checkpoints/checkpoint-2997",
4
+ "epoch": 9.0,
5
+ "eval_steps": 500,
6
+ "global_step": 2997,
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
+ "grad_norm": 25.15431022644043,
14
+ "learning_rate": 0.0005,
15
+ "loss": 3.4452,
16
+ "step": 333
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.17466666666666666,
21
+ "eval_loss": 3.132124423980713,
22
+ "eval_runtime": 13.4229,
23
+ "eval_samples_per_second": 279.373,
24
+ "eval_steps_per_second": 4.395,
25
+ "step": 333
26
+ },
27
+ {
28
+ "epoch": 2.0,
29
+ "grad_norm": 23.65234375,
30
+ "learning_rate": 0.0005,
31
+ "loss": 2.9675,
32
+ "step": 666
33
+ },
34
+ {
35
+ "epoch": 2.0,
36
+ "eval_accuracy": 0.22426666666666667,
37
+ "eval_loss": 2.913943290710449,
38
+ "eval_runtime": 12.4633,
39
+ "eval_samples_per_second": 300.883,
40
+ "eval_steps_per_second": 4.734,
41
+ "step": 666
42
+ },
43
+ {
44
+ "epoch": 3.0,
45
+ "grad_norm": 21.702959060668945,
46
+ "learning_rate": 0.0005,
47
+ "loss": 2.8415,
48
+ "step": 999
49
+ },
50
+ {
51
+ "epoch": 3.0,
52
+ "eval_accuracy": 0.23066666666666666,
53
+ "eval_loss": 2.8593287467956543,
54
+ "eval_runtime": 12.426,
55
+ "eval_samples_per_second": 301.785,
56
+ "eval_steps_per_second": 4.748,
57
+ "step": 999
58
+ },
59
+ {
60
+ "epoch": 4.0,
61
+ "grad_norm": 18.083477020263672,
62
+ "learning_rate": 0.0005,
63
+ "loss": 2.7455,
64
+ "step": 1332
65
+ },
66
+ {
67
+ "epoch": 4.0,
68
+ "eval_accuracy": 0.27653333333333335,
69
+ "eval_loss": 2.6849989891052246,
70
+ "eval_runtime": 12.2484,
71
+ "eval_samples_per_second": 306.164,
72
+ "eval_steps_per_second": 4.817,
73
+ "step": 1332
74
+ },
75
+ {
76
+ "epoch": 5.0,
77
+ "grad_norm": 24.421483993530273,
78
+ "learning_rate": 0.0005,
79
+ "loss": 2.6459,
80
+ "step": 1665
81
+ },
82
+ {
83
+ "epoch": 5.0,
84
+ "eval_accuracy": 0.2848,
85
+ "eval_loss": 2.6264588832855225,
86
+ "eval_runtime": 11.4717,
87
+ "eval_samples_per_second": 326.891,
88
+ "eval_steps_per_second": 5.143,
89
+ "step": 1665
90
+ },
91
+ {
92
+ "epoch": 6.0,
93
+ "grad_norm": 27.10919189453125,
94
+ "learning_rate": 0.0005,
95
+ "loss": 2.5473,
96
+ "step": 1998
97
+ },
98
+ {
99
+ "epoch": 6.0,
100
+ "eval_accuracy": 0.3072,
101
+ "eval_loss": 2.569124460220337,
102
+ "eval_runtime": 11.3468,
103
+ "eval_samples_per_second": 330.489,
104
+ "eval_steps_per_second": 5.2,
105
+ "step": 1998
106
+ },
107
+ {
108
+ "epoch": 7.0,
109
+ "grad_norm": 16.007593154907227,
110
+ "learning_rate": 0.0005,
111
+ "loss": 2.4564,
112
+ "step": 2331
113
+ },
114
+ {
115
+ "epoch": 7.0,
116
+ "eval_accuracy": 0.3138666666666667,
117
+ "eval_loss": 2.5231592655181885,
118
+ "eval_runtime": 11.3042,
119
+ "eval_samples_per_second": 331.736,
120
+ "eval_steps_per_second": 5.219,
121
+ "step": 2331
122
+ },
123
+ {
124
+ "epoch": 8.0,
125
+ "grad_norm": Infinity,
126
+ "learning_rate": 0.0005,
127
+ "loss": 2.3686,
128
+ "step": 2664
129
+ },
130
+ {
131
+ "epoch": 8.0,
132
+ "eval_accuracy": 0.3184,
133
+ "eval_loss": 2.506213903427124,
134
+ "eval_runtime": 11.3724,
135
+ "eval_samples_per_second": 329.747,
136
+ "eval_steps_per_second": 5.188,
137
+ "step": 2664
138
+ },
139
+ {
140
+ "epoch": 9.0,
141
+ "grad_norm": 8.122834205627441,
142
+ "learning_rate": 0.0005,
143
+ "loss": 2.2757,
144
+ "step": 2997
145
+ },
146
+ {
147
+ "epoch": 9.0,
148
+ "eval_accuracy": 0.34026666666666666,
149
+ "eval_loss": 2.4242594242095947,
150
+ "eval_runtime": 11.6295,
151
+ "eval_samples_per_second": 322.455,
152
+ "eval_steps_per_second": 5.073,
153
+ "step": 2997
154
+ }
155
+ ],
156
+ "logging_steps": 500,
157
+ "max_steps": 2997,
158
+ "num_input_tokens_seen": 0,
159
+ "num_train_epochs": 9,
160
+ "save_steps": 500,
161
+ "stateful_callbacks": {
162
+ "TrainerControl": {
163
+ "args": {
164
+ "should_epoch_stop": false,
165
+ "should_evaluate": false,
166
+ "should_log": false,
167
+ "should_save": true,
168
+ "should_training_stop": true
169
+ },
170
+ "attributes": {}
171
+ }
172
+ },
173
+ "total_flos": 1.482671885603328e+19,
174
+ "train_batch_size": 64,
175
+ "trial_name": null,
176
+ "trial_params": null
177
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f19522a0f2e95e3d6bae9654fc861fb9988a58893bc49fb2dc299139b554f48
3
+ size 5368