Hugging Face's logo

ProbeX
/
Model-J__MAE__model_idx_0399

Image Classification
Transformers
Safetensors
vit
probex
model-j
weight-space-learning
Model card Files
xet
Community
Eliahu commited on
Commit
f8ffad4
·
verified ·
1 Parent(s): 9d237d7

Upload folder using huggingface_hub

Browse files
Files changed (5) hide show
  1. config.json +134 -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 +1,134 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/vit-mae-base",
3
+ "architectures": [
4
+ "ViTForImageClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.0,
7
+ "decoder_hidden_size": 512,
8
+ "decoder_intermediate_size": 2048,
9
+ "decoder_num_attention_heads": 16,
10
+ "decoder_num_hidden_layers": 8,
11
+ "encoder_stride": 16,
12
+ "hidden_act": "gelu",
13
+ "hidden_dropout_prob": 0.0,
14
+ "hidden_size": 768,
15
+ "id2label": {
16
+ "0": "LABEL_0",
17
+ "1": "LABEL_1",
18
+ "2": "LABEL_2",
19
+ "3": "LABEL_3",
20
+ "4": "LABEL_4",
21
+ "5": "LABEL_5",
22
+ "6": "LABEL_6",
23
+ "7": "LABEL_7",
24
+ "8": "LABEL_8",
25
+ "9": "LABEL_9",
26
+ "10": "LABEL_10",
27
+ "11": "LABEL_11",
28
+ "12": "LABEL_12",
29
+ "13": "LABEL_13",
30
+ "14": "LABEL_14",
31
+ "15": "LABEL_15",
32
+ "16": "LABEL_16",
33
+ "17": "LABEL_17",
34
+ "18": "LABEL_18",
35
+ "19": "LABEL_19",
36
+ "20": "LABEL_20",
37
+ "21": "LABEL_21",
38
+ "22": "LABEL_22",
39
+ "23": "LABEL_23",
40
+ "24": "LABEL_24",
41
+ "25": "LABEL_25",
42
+ "26": "LABEL_26",
43
+ "27": "LABEL_27",
44
+ "28": "LABEL_28",
45
+ "29": "LABEL_29",
46
+ "30": "LABEL_30",
47
+ "31": "LABEL_31",
48
+ "32": "LABEL_32",
49
+ "33": "LABEL_33",
50
+ "34": "LABEL_34",
51
+ "35": "LABEL_35",
52
+ "36": "LABEL_36",
53
+ "37": "LABEL_37",
54
+ "38": "LABEL_38",
55
+ "39": "LABEL_39",
56
+ "40": "LABEL_40",
57
+ "41": "LABEL_41",
58
+ "42": "LABEL_42",
59
+ "43": "LABEL_43",
60
+ "44": "LABEL_44",
61
+ "45": "LABEL_45",
62
+ "46": "LABEL_46",
63
+ "47": "LABEL_47",
64
+ "48": "LABEL_48",
65
+ "49": "LABEL_49"
66
+ },
67
+ "image_size": 224,
68
+ "initializer_range": 0.02,
69
+ "intermediate_size": 3072,
70
+ "label2id": {
71
+ "LABEL_0": 0,
72
+ "LABEL_1": 1,
73
+ "LABEL_10": 10,
74
+ "LABEL_11": 11,
75
+ "LABEL_12": 12,
76
+ "LABEL_13": 13,
77
+ "LABEL_14": 14,
78
+ "LABEL_15": 15,
79
+ "LABEL_16": 16,
80
+ "LABEL_17": 17,
81
+ "LABEL_18": 18,
82
+ "LABEL_19": 19,
83
+ "LABEL_2": 2,
84
+ "LABEL_20": 20,
85
+ "LABEL_21": 21,
86
+ "LABEL_22": 22,
87
+ "LABEL_23": 23,
88
+ "LABEL_24": 24,
89
+ "LABEL_25": 25,
90
+ "LABEL_26": 26,
91
+ "LABEL_27": 27,
92
+ "LABEL_28": 28,
93
+ "LABEL_29": 29,
94
+ "LABEL_3": 3,
95
+ "LABEL_30": 30,
96
+ "LABEL_31": 31,
97
+ "LABEL_32": 32,
98
+ "LABEL_33": 33,
99
+ "LABEL_34": 34,
100
+ "LABEL_35": 35,
101
+ "LABEL_36": 36,
102
+ "LABEL_37": 37,
103
+ "LABEL_38": 38,
104
+ "LABEL_39": 39,
105
+ "LABEL_4": 4,
106
+ "LABEL_40": 40,
107
+ "LABEL_41": 41,
108
+ "LABEL_42": 42,
109
+ "LABEL_43": 43,
110
+ "LABEL_44": 44,
111
+ "LABEL_45": 45,
112
+ "LABEL_46": 46,
113
+ "LABEL_47": 47,
114
+ "LABEL_48": 48,
115
+ "LABEL_49": 49,
116
+ "LABEL_5": 5,
117
+ "LABEL_6": 6,
118
+ "LABEL_7": 7,
119
+ "LABEL_8": 8,
120
+ "LABEL_9": 9
121
+ },
122
+ "layer_norm_eps": 1e-12,
123
+ "mask_ratio": 0.75,
124
+ "model_type": "vit",
125
+ "norm_pix_loss": false,
126
+ "num_attention_heads": 12,
127
+ "num_channels": 3,
128
+ "num_hidden_layers": 12,
129
+ "patch_size": 16,
130
+ "problem_type": "single_label_classification",
131
+ "qkv_bias": true,
132
+ "torch_dtype": "float32",
133
+ "transformers_version": "4.44.0"
134
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0b09e890325efd47ed2d564d6efe8e82387567b0fb5318b9cb0737cd838d7d5
3
+ size 343372760
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": 0.7930666666666667,
3
+ "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0399/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": 4.108035564422607,
14
+ "learning_rate": 0.0003,
15
+ "loss": 1.8467,
16
+ "step": 333
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.6957333333333333,
21
+ "eval_loss": 0.9857635498046875,
22
+ "eval_runtime": 5.7486,
23
+ "eval_samples_per_second": 652.337,
24
+ "eval_steps_per_second": 10.263,
25
+ "step": 333
26
+ },
27
+ {
28
+ "epoch": 2.0,
29
+ "grad_norm": Infinity,
30
+ "learning_rate": 0.0003,
31
+ "loss": 0.7187,
32
+ "step": 666
33
+ },
34
+ {
35
+ "epoch": 2.0,
36
+ "eval_accuracy": 0.7898666666666667,
37
+ "eval_loss": 0.6947962045669556,
38
+ "eval_runtime": 5.7935,
39
+ "eval_samples_per_second": 647.276,
40
+ "eval_steps_per_second": 10.184,
41
+ "step": 666
42
+ },
43
+ {
44
+ "epoch": 3.0,
45
+ "grad_norm": 6.667613983154297,
46
+ "learning_rate": 0.0003,
47
+ "loss": 0.431,
48
+ "step": 999
49
+ },
50
+ {
51
+ "epoch": 3.0,
52
+ "eval_accuracy": 0.7885333333333333,
53
+ "eval_loss": 0.6893866658210754,
54
+ "eval_runtime": 6.1522,
55
+ "eval_samples_per_second": 609.539,
56
+ "eval_steps_per_second": 9.59,
57
+ "step": 999
58
+ },
59
+ {
60
+ "epoch": 4.0,
61
+ "grad_norm": 17.746402740478516,
62
+ "learning_rate": 0.0003,
63
+ "loss": 0.299,
64
+ "step": 1332
65
+ },
66
+ {
67
+ "epoch": 4.0,
68
+ "eval_accuracy": 0.7549333333333333,
69
+ "eval_loss": 0.8416933417320251,
70
+ "eval_runtime": 5.7497,
71
+ "eval_samples_per_second": 652.204,
72
+ "eval_steps_per_second": 10.261,
73
+ "step": 1332
74
+ },
75
+ {
76
+ "epoch": 5.0,
77
+ "grad_norm": 0.4448702335357666,
78
+ "learning_rate": 0.0003,
79
+ "loss": 0.228,
80
+ "step": 1665
81
+ },
82
+ {
83
+ "epoch": 5.0,
84
+ "eval_accuracy": 0.7858666666666667,
85
+ "eval_loss": 0.7561094760894775,
86
+ "eval_runtime": 5.6552,
87
+ "eval_samples_per_second": 663.109,
88
+ "eval_steps_per_second": 10.433,
89
+ "step": 1665
90
+ },
91
+ {
92
+ "epoch": 6.0,
93
+ "grad_norm": 4.781618595123291,
94
+ "learning_rate": 0.0003,
95
+ "loss": 0.1924,
96
+ "step": 1998
97
+ },
98
+ {
99
+ "epoch": 6.0,
100
+ "eval_accuracy": 0.7909333333333334,
101
+ "eval_loss": 0.7749009728431702,
102
+ "eval_runtime": 5.7554,
103
+ "eval_samples_per_second": 651.563,
104
+ "eval_steps_per_second": 10.251,
105
+ "step": 1998
106
+ },
107
+ {
108
+ "epoch": 7.0,
109
+ "grad_norm": 33.57717514038086,
110
+ "learning_rate": 0.0003,
111
+ "loss": 0.1637,
112
+ "step": 2331
113
+ },
114
+ {
115
+ "epoch": 7.0,
116
+ "eval_accuracy": 0.7850666666666667,
117
+ "eval_loss": 0.8349209427833557,
118
+ "eval_runtime": 6.1206,
119
+ "eval_samples_per_second": 612.683,
120
+ "eval_steps_per_second": 9.64,
121
+ "step": 2331
122
+ },
123
+ {
124
+ "epoch": 8.0,
125
+ "grad_norm": 0.02094506472349167,
126
+ "learning_rate": 0.0003,
127
+ "loss": 0.1418,
128
+ "step": 2664
129
+ },
130
+ {
131
+ "epoch": 8.0,
132
+ "eval_accuracy": 0.7682666666666667,
133
+ "eval_loss": 0.9396815896034241,
134
+ "eval_runtime": 5.9164,
135
+ "eval_samples_per_second": 633.835,
136
+ "eval_steps_per_second": 9.972,
137
+ "step": 2664
138
+ },
139
+ {
140
+ "epoch": 9.0,
141
+ "grad_norm": 0.03026556596159935,
142
+ "learning_rate": 0.0003,
143
+ "loss": 0.1295,
144
+ "step": 2997
145
+ },
146
+ {
147
+ "epoch": 9.0,
148
+ "eval_accuracy": 0.7930666666666667,
149
+ "eval_loss": 0.8031014204025269,
150
+ "eval_runtime": 5.9717,
151
+ "eval_samples_per_second": 627.967,
152
+ "eval_steps_per_second": 9.88,
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 sha256:2926281022d9a61ddba0118984c567db530720b174db312aeb56bbb04dfbdda5
3
+ size 5368