Hugging Face's logo

dima806
/
facial_age_image_detection

Image Classification
Transformers
Safetensors
vit
Model card Files
xet
 Community
dima806 commited on
Commit
ffbe5c2
·
verified ·
1 Parent(s): 68e1908

Upload folder using huggingface_hub

Browse files
Files changed (10) hide show
  1. checkpoint-4560/config.json +74 -0
  2. checkpoint-4560/model.safetensors +3 -0
  3. checkpoint-4560/optimizer.pt +3 -0
  4. checkpoint-4560/preprocessor_config.json +22 -0
  5. checkpoint-4560/rng_state.pth +3 -0
  6. checkpoint-4560/scheduler.pt +3 -0
  7. checkpoint-4560/trainer_state.json +255 -0
  8. checkpoint-4560/training_args.bin +3 -0
  9. model.safetensors +1 -1
  10. training_args.bin +1 -1
checkpoint-4560/config.json ADDED
@@ -0,0 +1,74 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "dima806/facial_age_image_detection",
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": "01",
13
+ "1": "02",
14
+ "2": "03",
15
+ "3": "04",
16
+ "4": "05",
17
+ "5": "06-07",
18
+ "6": "08-09",
19
+ "7": "10-12",
20
+ "8": "13-15",
21
+ "9": "16-20",
22
+ "10": "21-25",
23
+ "11": "26-30",
24
+ "12": "31-35",
25
+ "13": "36-40",
26
+ "14": "41-45",
27
+ "15": "46-50",
28
+ "16": "51-55",
29
+ "17": "56-60",
30
+ "18": "61-65",
31
+ "19": "66-70",
32
+ "20": "71-80",
33
+ "21": "81-90",
34
+ "22": "90+"
35
+ },
36
+ "image_size": 224,
37
+ "initializer_range": 0.02,
38
+ "intermediate_size": 3072,
39
+ "label2id": {
40
+ "01": 0,
41
+ "02": 1,
42
+ "03": 2,
43
+ "04": 3,
44
+ "05": 4,
45
+ "06-07": 5,
46
+ "08-09": 6,
47
+ "10-12": 7,
48
+ "13-15": 8,
49
+ "16-20": 9,
50
+ "21-25": 10,
51
+ "26-30": 11,
52
+ "31-35": 12,
53
+ "36-40": 13,
54
+ "41-45": 14,
55
+ "46-50": 15,
56
+ "51-55": 16,
57
+ "56-60": 17,
58
+ "61-65": 18,
59
+ "66-70": 19,
60
+ "71-80": 20,
61
+ "81-90": 21,
62
+ "90+": 22
63
+ },
64
+ "layer_norm_eps": 1e-12,
65
+ "model_type": "vit",
66
+ "num_attention_heads": 12,
67
+ "num_channels": 3,
68
+ "num_hidden_layers": 12,
69
+ "patch_size": 16,
70
+ "problem_type": "single_label_classification",
71
+ "qkv_bias": true,
72
+ "torch_dtype": "float32",
73
+ "transformers_version": "4.38.2"
74
+ }
checkpoint-4560/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0cecd28b4d92743518c8f4fb11713818229a881dd452670d73ff23b062afd1f7
3
+ size 343288572
checkpoint-4560/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5f7399d19831d1ef6e68eb30c8293476e2eeb3519e06665fee27c97a26ee12d
3
+ size 686697605
checkpoint-4560/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-4560/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6c0c4148260c61af1a42d6dea9247f87d82d5366bc3a4b2215db8d70bae6b31
3
+ size 14575
checkpoint-4560/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:481698a62856c54221140971b2e4ad8c29d8b8579a0e38b6957e61736ba1b721
3
+ size 627
checkpoint-4560/trainer_state.json ADDED
@@ -0,0 +1,255 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 1.1997283697128296,
3
+ "best_model_checkpoint": "facial_age_image_detection/checkpoint-4560",
4
+ "epoch": 19.0,
5
+ "eval_steps": 500,
6
+ "global_step": 4560,
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": 0.5973023164891017,
14
+ "eval_loss": 1.2148407697677612,
15
+ "eval_runtime": 107.0191,
16
+ "eval_samples_per_second": 95.6,
17
+ "eval_steps_per_second": 2.99,
18
+ "step": 240
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_accuracy": 0.6003323233310527,
23
+ "eval_loss": 1.2124874591827393,
24
+ "eval_runtime": 108.7931,
25
+ "eval_samples_per_second": 94.041,
26
+ "eval_steps_per_second": 2.941,
27
+ "step": 480
28
+ },
29
+ {
30
+ "epoch": 2.08,
31
+ "grad_norm": 10.869218826293945,
32
+ "learning_rate": 4.526315789473684e-07,
33
+ "loss": 0.7792,
34
+ "step": 500
35
+ },
36
+ {
37
+ "epoch": 3.0,
38
+ "eval_accuracy": 0.6001368390186688,
39
+ "eval_loss": 1.2103016376495361,
40
+ "eval_runtime": 108.2046,
41
+ "eval_samples_per_second": 94.552,
42
+ "eval_steps_per_second": 2.957,
43
+ "step": 720
44
+ },
45
+ {
46
+ "epoch": 4.0,
47
+ "eval_accuracy": 0.5932948880852311,
48
+ "eval_loss": 1.2177255153656006,
49
+ "eval_runtime": 108.1913,
50
+ "eval_samples_per_second": 94.564,
51
+ "eval_steps_per_second": 2.958,
52
+ "step": 960
53
+ },
54
+ {
55
+ "epoch": 4.17,
56
+ "grad_norm": 7.94642972946167,
57
+ "learning_rate": 4e-07,
58
+ "loss": 0.7693,
59
+ "step": 1000
60
+ },
61
+ {
62
+ "epoch": 5.0,
63
+ "eval_accuracy": 0.5987684488319812,
64
+ "eval_loss": 1.2087459564208984,
65
+ "eval_runtime": 108.1422,
66
+ "eval_samples_per_second": 94.607,
67
+ "eval_steps_per_second": 2.959,
68
+ "step": 1200
69
+ },
70
+ {
71
+ "epoch": 6.0,
72
+ "eval_accuracy": 0.5989639331443651,
73
+ "eval_loss": 1.2106623649597168,
74
+ "eval_runtime": 108.6434,
75
+ "eval_samples_per_second": 94.17,
76
+ "eval_steps_per_second": 2.945,
77
+ "step": 1440
78
+ },
79
+ {
80
+ "epoch": 6.25,
81
+ "grad_norm": 12.206405639648438,
82
+ "learning_rate": 3.4736842105263157e-07,
83
+ "loss": 0.7579,
84
+ "step": 1500
85
+ },
86
+ {
87
+ "epoch": 7.0,
88
+ "eval_accuracy": 0.5941745674909589,
89
+ "eval_loss": 1.2116234302520752,
90
+ "eval_runtime": 110.2341,
91
+ "eval_samples_per_second": 92.812,
92
+ "eval_steps_per_second": 2.903,
93
+ "step": 1680
94
+ },
95
+ {
96
+ "epoch": 8.0,
97
+ "eval_accuracy": 0.596520379239566,
98
+ "eval_loss": 1.209428071975708,
99
+ "eval_runtime": 109.2117,
100
+ "eval_samples_per_second": 93.68,
101
+ "eval_steps_per_second": 2.93,
102
+ "step": 1920
103
+ },
104
+ {
105
+ "epoch": 8.33,
106
+ "grad_norm": 13.978309631347656,
107
+ "learning_rate": 2.947368421052631e-07,
108
+ "loss": 0.7564,
109
+ "step": 2000
110
+ },
111
+ {
112
+ "epoch": 9.0,
113
+ "eval_accuracy": 0.5945655361157267,
114
+ "eval_loss": 1.207972764968872,
115
+ "eval_runtime": 109.0595,
116
+ "eval_samples_per_second": 93.811,
117
+ "eval_steps_per_second": 2.934,
118
+ "step": 2160
119
+ },
120
+ {
121
+ "epoch": 10.0,
122
+ "eval_accuracy": 0.5972045743329097,
123
+ "eval_loss": 1.2053894996643066,
124
+ "eval_runtime": 108.2001,
125
+ "eval_samples_per_second": 94.556,
126
+ "eval_steps_per_second": 2.957,
127
+ "step": 2400
128
+ },
129
+ {
130
+ "epoch": 10.42,
131
+ "grad_norm": 13.184745788574219,
132
+ "learning_rate": 2.4210526315789473e-07,
133
+ "loss": 0.7462,
134
+ "step": 2500
135
+ },
136
+ {
137
+ "epoch": 11.0,
138
+ "eval_accuracy": 0.596520379239566,
139
+ "eval_loss": 1.2063862085342407,
140
+ "eval_runtime": 109.0351,
141
+ "eval_samples_per_second": 93.832,
142
+ "eval_steps_per_second": 2.935,
143
+ "step": 2640
144
+ },
145
+ {
146
+ "epoch": 12.0,
147
+ "eval_accuracy": 0.5967158635519499,
148
+ "eval_loss": 1.205006718635559,
149
+ "eval_runtime": 107.7737,
150
+ "eval_samples_per_second": 94.93,
151
+ "eval_steps_per_second": 2.969,
152
+ "step": 2880
153
+ },
154
+ {
155
+ "epoch": 12.5,
156
+ "grad_norm": 13.500107765197754,
157
+ "learning_rate": 1.8947368421052632e-07,
158
+ "loss": 0.7444,
159
+ "step": 3000
160
+ },
161
+ {
162
+ "epoch": 13.0,
163
+ "eval_accuracy": 0.5974000586452937,
164
+ "eval_loss": 1.2029664516448975,
165
+ "eval_runtime": 108.3584,
166
+ "eval_samples_per_second": 94.418,
167
+ "eval_steps_per_second": 2.953,
168
+ "step": 3120
169
+ },
170
+ {
171
+ "epoch": 14.0,
172
+ "eval_accuracy": 0.5982797380510214,
173
+ "eval_loss": 1.2019948959350586,
174
+ "eval_runtime": 108.2177,
175
+ "eval_samples_per_second": 94.541,
176
+ "eval_steps_per_second": 2.957,
177
+ "step": 3360
178
+ },
179
+ {
180
+ "epoch": 14.58,
181
+ "grad_norm": 12.818633079528809,
182
+ "learning_rate": 1.368421052631579e-07,
183
+ "loss": 0.7402,
184
+ "step": 3500
185
+ },
186
+ {
187
+ "epoch": 15.0,
188
+ "eval_accuracy": 0.5969113478643339,
189
+ "eval_loss": 1.2034169435501099,
190
+ "eval_runtime": 107.9426,
191
+ "eval_samples_per_second": 94.782,
192
+ "eval_steps_per_second": 2.965,
193
+ "step": 3600
194
+ },
195
+ {
196
+ "epoch": 16.0,
197
+ "eval_accuracy": 0.5980842537386375,
198
+ "eval_loss": 1.2004482746124268,
199
+ "eval_runtime": 108.7494,
200
+ "eval_samples_per_second": 94.079,
201
+ "eval_steps_per_second": 2.943,
202
+ "step": 3840
203
+ },
204
+ {
205
+ "epoch": 16.67,
206
+ "grad_norm": 10.575230598449707,
207
+ "learning_rate": 8.421052631578947e-08,
208
+ "loss": 0.7357,
209
+ "step": 4000
210
+ },
211
+ {
212
+ "epoch": 17.0,
213
+ "eval_accuracy": 0.5988661909881732,
214
+ "eval_loss": 1.2010480165481567,
215
+ "eval_runtime": 108.3609,
216
+ "eval_samples_per_second": 94.416,
217
+ "eval_steps_per_second": 2.953,
218
+ "step": 4080
219
+ },
220
+ {
221
+ "epoch": 18.0,
222
+ "eval_accuracy": 0.5970090900205258,
223
+ "eval_loss": 1.2006783485412598,
224
+ "eval_runtime": 108.1842,
225
+ "eval_samples_per_second": 94.57,
226
+ "eval_steps_per_second": 2.958,
227
+ "step": 4320
228
+ },
229
+ {
230
+ "epoch": 18.75,
231
+ "grad_norm": 10.900801658630371,
232
+ "learning_rate": 3.157894736842105e-08,
233
+ "loss": 0.7376,
234
+ "step": 4500
235
+ },
236
+ {
237
+ "epoch": 19.0,
238
+ "eval_accuracy": 0.5974000586452937,
239
+ "eval_loss": 1.1997283697128296,
240
+ "eval_runtime": 108.4624,
241
+ "eval_samples_per_second": 94.328,
242
+ "eval_steps_per_second": 2.95,
243
+ "step": 4560
244
+ }
245
+ ],
246
+ "logging_steps": 500,
247
+ "max_steps": 4800,
248
+ "num_input_tokens_seen": 0,
249
+ "num_train_epochs": 20,
250
+ "save_steps": 500,
251
+ "total_flos": 2.2597429437571006e+19,
252
+ "train_batch_size": 64,
253
+ "trial_name": null,
254
+ "trial_params": null
255
+ }
checkpoint-4560/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1720d13f8074df3fb08ee60b875a9df5a8b4161f2f31054e04a3b9fdc006e59a
3
+ size 4411
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8d052f8d13109aaca6992c41e105e8137d68f28772bd1e17c922d876b6978559
3
  size 343288572
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0cecd28b4d92743518c8f4fb11713818229a881dd452670d73ff23b062afd1f7
3
  size 343288572
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ae77cac5ba4aa1a550d83b9efd041272a8a03cde4495bce42f5d0c2a0f9fce17
3
  size 4411
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1720d13f8074df3fb08ee60b875a9df5a8b4161f2f31054e04a3b9fdc006e59a
3
  size 4411