dima806 commited on
Commit
fe992d9
1 Parent(s): 53d0034

Upload folder using huggingface_hub

Browse files
checkpoint-7200/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-7200/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d3d446592a8713ec044baca3f10db07d050d0d63c2dcc0af7e90747c2f711873
3
+ size 343288572
checkpoint-7200/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8166380427e225d52a205db74850bc04dbc22e556214e6b4de05b871df229f2d
3
+ size 686697605
checkpoint-7200/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-7200/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cee3f1199a3a7440359065ef545267762f93d938a90762d6c726ff979fe42003
3
+ size 14575
checkpoint-7200/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4fe9b776ccb005d02cf74cee0e0dbb014831873780c48de9e65b51be3cae5a84
3
+ size 627
checkpoint-7200/trainer_state.json ADDED
@@ -0,0 +1,389 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 1.143545389175415,
3
+ "best_model_checkpoint": "facial_age_image_detection/checkpoint-7200",
4
+ "epoch": 30.0,
5
+ "eval_steps": 500,
6
+ "global_step": 7200,
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": 0.6146026781350796,
14
+ "eval_loss": 1.1694062948226929,
15
+ "eval_runtime": 105.8046,
16
+ "eval_samples_per_second": 96.697,
17
+ "eval_steps_per_second": 3.024,
18
+ "step": 240
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_accuracy": 0.6155800996969993,
23
+ "eval_loss": 1.168785572052002,
24
+ "eval_runtime": 110.1471,
25
+ "eval_samples_per_second": 92.885,
26
+ "eval_steps_per_second": 2.905,
27
+ "step": 480
28
+ },
29
+ {
30
+ "epoch": 2.08,
31
+ "grad_norm": 8.204376220703125,
32
+ "learning_rate": 4.685314685314685e-07,
33
+ "loss": 0.7138,
34
+ "step": 500
35
+ },
36
+ {
37
+ "epoch": 3.0,
38
+ "eval_accuracy": 0.6099110546378653,
39
+ "eval_loss": 1.1679891347885132,
40
+ "eval_runtime": 102.9363,
41
+ "eval_samples_per_second": 99.392,
42
+ "eval_steps_per_second": 3.109,
43
+ "step": 720
44
+ },
45
+ {
46
+ "epoch": 4.0,
47
+ "eval_accuracy": 0.6177304271332226,
48
+ "eval_loss": 1.1608326435089111,
49
+ "eval_runtime": 101.8768,
50
+ "eval_samples_per_second": 100.425,
51
+ "eval_steps_per_second": 3.141,
52
+ "step": 960
53
+ },
54
+ {
55
+ "epoch": 4.17,
56
+ "grad_norm": 14.190340042114258,
57
+ "learning_rate": 4.335664335664335e-07,
58
+ "loss": 0.7034,
59
+ "step": 1000
60
+ },
61
+ {
62
+ "epoch": 5.0,
63
+ "eval_accuracy": 0.6098133124816734,
64
+ "eval_loss": 1.1647840738296509,
65
+ "eval_runtime": 103.2275,
66
+ "eval_samples_per_second": 99.111,
67
+ "eval_steps_per_second": 3.1,
68
+ "step": 1200
69
+ },
70
+ {
71
+ "epoch": 6.0,
72
+ "eval_accuracy": 0.6123546085426644,
73
+ "eval_loss": 1.1614784002304077,
74
+ "eval_runtime": 106.5014,
75
+ "eval_samples_per_second": 96.064,
76
+ "eval_steps_per_second": 3.005,
77
+ "step": 1440
78
+ },
79
+ {
80
+ "epoch": 6.25,
81
+ "grad_norm": 18.558853149414062,
82
+ "learning_rate": 3.9860139860139855e-07,
83
+ "loss": 0.6951,
84
+ "step": 1500
85
+ },
86
+ {
87
+ "epoch": 7.0,
88
+ "eval_accuracy": 0.6186101065389502,
89
+ "eval_loss": 1.160543441772461,
90
+ "eval_runtime": 105.023,
91
+ "eval_samples_per_second": 97.417,
92
+ "eval_steps_per_second": 3.047,
93
+ "step": 1680
94
+ },
95
+ {
96
+ "epoch": 8.0,
97
+ "eval_accuracy": 0.6172417163522628,
98
+ "eval_loss": 1.1572130918502808,
99
+ "eval_runtime": 105.5204,
100
+ "eval_samples_per_second": 96.958,
101
+ "eval_steps_per_second": 3.033,
102
+ "step": 1920
103
+ },
104
+ {
105
+ "epoch": 8.33,
106
+ "grad_norm": 9.678888320922852,
107
+ "learning_rate": 3.636363636363636e-07,
108
+ "loss": 0.6885,
109
+ "step": 2000
110
+ },
111
+ {
112
+ "epoch": 9.0,
113
+ "eval_accuracy": 0.6171439741960708,
114
+ "eval_loss": 1.1544899940490723,
115
+ "eval_runtime": 102.6064,
116
+ "eval_samples_per_second": 99.711,
117
+ "eval_steps_per_second": 3.119,
118
+ "step": 2160
119
+ },
120
+ {
121
+ "epoch": 10.0,
122
+ "eval_accuracy": 0.6179259114456065,
123
+ "eval_loss": 1.155420184135437,
124
+ "eval_runtime": 104.82,
125
+ "eval_samples_per_second": 97.605,
126
+ "eval_steps_per_second": 3.053,
127
+ "step": 2400
128
+ },
129
+ {
130
+ "epoch": 10.42,
131
+ "grad_norm": 13.007719039916992,
132
+ "learning_rate": 3.286713286713286e-07,
133
+ "loss": 0.6806,
134
+ "step": 2500
135
+ },
136
+ {
137
+ "epoch": 11.0,
138
+ "eval_accuracy": 0.6176326849770306,
139
+ "eval_loss": 1.1572375297546387,
140
+ "eval_runtime": 103.6156,
141
+ "eval_samples_per_second": 98.74,
142
+ "eval_steps_per_second": 3.088,
143
+ "step": 2640
144
+ },
145
+ {
146
+ "epoch": 12.0,
147
+ "eval_accuracy": 0.6146026781350796,
148
+ "eval_loss": 1.1544034481048584,
149
+ "eval_runtime": 102.3651,
150
+ "eval_samples_per_second": 99.946,
151
+ "eval_steps_per_second": 3.126,
152
+ "step": 2880
153
+ },
154
+ {
155
+ "epoch": 12.5,
156
+ "grad_norm": 12.4281005859375,
157
+ "learning_rate": 2.9370629370629366e-07,
158
+ "loss": 0.6767,
159
+ "step": 3000
160
+ },
161
+ {
162
+ "epoch": 13.0,
163
+ "eval_accuracy": 0.6182191379141824,
164
+ "eval_loss": 1.1541900634765625,
165
+ "eval_runtime": 105.249,
166
+ "eval_samples_per_second": 97.208,
167
+ "eval_steps_per_second": 3.04,
168
+ "step": 3120
169
+ },
170
+ {
171
+ "epoch": 14.0,
172
+ "eval_accuracy": 0.6143094516665037,
173
+ "eval_loss": 1.1535159349441528,
174
+ "eval_runtime": 106.0372,
175
+ "eval_samples_per_second": 96.485,
176
+ "eval_steps_per_second": 3.018,
177
+ "step": 3360
178
+ },
179
+ {
180
+ "epoch": 14.58,
181
+ "grad_norm": 7.5727410316467285,
182
+ "learning_rate": 2.5874125874125877e-07,
183
+ "loss": 0.667,
184
+ "step": 3500
185
+ },
186
+ {
187
+ "epoch": 15.0,
188
+ "eval_accuracy": 0.6190988173199101,
189
+ "eval_loss": 1.1515381336212158,
190
+ "eval_runtime": 102.4541,
191
+ "eval_samples_per_second": 99.859,
192
+ "eval_steps_per_second": 3.123,
193
+ "step": 3600
194
+ },
195
+ {
196
+ "epoch": 16.0,
197
+ "eval_accuracy": 0.6183168800703743,
198
+ "eval_loss": 1.1484887599945068,
199
+ "eval_runtime": 111.0745,
200
+ "eval_samples_per_second": 92.109,
201
+ "eval_steps_per_second": 2.881,
202
+ "step": 3840
203
+ },
204
+ {
205
+ "epoch": 16.67,
206
+ "grad_norm": 10.47463607788086,
207
+ "learning_rate": 2.2377622377622377e-07,
208
+ "loss": 0.6652,
209
+ "step": 4000
210
+ },
211
+ {
212
+ "epoch": 17.0,
213
+ "eval_accuracy": 0.6168507477274948,
214
+ "eval_loss": 1.1494479179382324,
215
+ "eval_runtime": 104.2245,
216
+ "eval_samples_per_second": 98.163,
217
+ "eval_steps_per_second": 3.07,
218
+ "step": 4080
219
+ },
220
+ {
221
+ "epoch": 18.0,
222
+ "eval_accuracy": 0.6195875281008699,
223
+ "eval_loss": 1.1498117446899414,
224
+ "eval_runtime": 103.8649,
225
+ "eval_samples_per_second": 98.503,
226
+ "eval_steps_per_second": 3.081,
227
+ "step": 4320
228
+ },
229
+ {
230
+ "epoch": 18.75,
231
+ "grad_norm": 15.560189247131348,
232
+ "learning_rate": 1.888111888111888e-07,
233
+ "loss": 0.6619,
234
+ "step": 4500
235
+ },
236
+ {
237
+ "epoch": 19.0,
238
+ "eval_accuracy": 0.619489785944678,
239
+ "eval_loss": 1.1467111110687256,
240
+ "eval_runtime": 104.6948,
241
+ "eval_samples_per_second": 97.722,
242
+ "eval_steps_per_second": 3.057,
243
+ "step": 4560
244
+ },
245
+ {
246
+ "epoch": 20.0,
247
+ "eval_accuracy": 0.6170462320398789,
248
+ "eval_loss": 1.1486930847167969,
249
+ "eval_runtime": 105.6513,
250
+ "eval_samples_per_second": 96.837,
251
+ "eval_steps_per_second": 3.029,
252
+ "step": 4800
253
+ },
254
+ {
255
+ "epoch": 20.83,
256
+ "grad_norm": 10.84726333618164,
257
+ "learning_rate": 1.5384615384615385e-07,
258
+ "loss": 0.6586,
259
+ "step": 5000
260
+ },
261
+ {
262
+ "epoch": 21.0,
263
+ "eval_accuracy": 0.6190988173199101,
264
+ "eval_loss": 1.1456117630004883,
265
+ "eval_runtime": 102.8016,
266
+ "eval_samples_per_second": 99.522,
267
+ "eval_steps_per_second": 3.113,
268
+ "step": 5040
269
+ },
270
+ {
271
+ "epoch": 22.0,
272
+ "eval_accuracy": 0.6169484898836868,
273
+ "eval_loss": 1.145732045173645,
274
+ "eval_runtime": 103.7561,
275
+ "eval_samples_per_second": 98.606,
276
+ "eval_steps_per_second": 3.084,
277
+ "step": 5280
278
+ },
279
+ {
280
+ "epoch": 22.92,
281
+ "grad_norm": 10.03998851776123,
282
+ "learning_rate": 1.1888111888111887e-07,
283
+ "loss": 0.652,
284
+ "step": 5500
285
+ },
286
+ {
287
+ "epoch": 23.0,
288
+ "eval_accuracy": 0.6170462320398789,
289
+ "eval_loss": 1.145518183708191,
290
+ "eval_runtime": 102.871,
291
+ "eval_samples_per_second": 99.455,
292
+ "eval_steps_per_second": 3.111,
293
+ "step": 5520
294
+ },
295
+ {
296
+ "epoch": 24.0,
297
+ "eval_accuracy": 0.6180236536017985,
298
+ "eval_loss": 1.1446188688278198,
299
+ "eval_runtime": 101.7602,
300
+ "eval_samples_per_second": 100.54,
301
+ "eval_steps_per_second": 3.145,
302
+ "step": 5760
303
+ },
304
+ {
305
+ "epoch": 25.0,
306
+ "grad_norm": 13.074454307556152,
307
+ "learning_rate": 8.391608391608391e-08,
308
+ "loss": 0.6536,
309
+ "step": 6000
310
+ },
311
+ {
312
+ "epoch": 25.0,
313
+ "eval_accuracy": 0.619489785944678,
314
+ "eval_loss": 1.1448231935501099,
315
+ "eval_runtime": 101.7751,
316
+ "eval_samples_per_second": 100.526,
317
+ "eval_steps_per_second": 3.144,
318
+ "step": 6000
319
+ },
320
+ {
321
+ "epoch": 26.0,
322
+ "eval_accuracy": 0.6186101065389502,
323
+ "eval_loss": 1.1442244052886963,
324
+ "eval_runtime": 102.0024,
325
+ "eval_samples_per_second": 100.302,
326
+ "eval_steps_per_second": 3.137,
327
+ "step": 6240
328
+ },
329
+ {
330
+ "epoch": 27.0,
331
+ "eval_accuracy": 0.6180236536017985,
332
+ "eval_loss": 1.1441760063171387,
333
+ "eval_runtime": 102.5718,
334
+ "eval_samples_per_second": 99.745,
335
+ "eval_steps_per_second": 3.12,
336
+ "step": 6480
337
+ },
338
+ {
339
+ "epoch": 27.08,
340
+ "grad_norm": 12.248133659362793,
341
+ "learning_rate": 4.895104895104895e-08,
342
+ "loss": 0.6512,
343
+ "step": 6500
344
+ },
345
+ {
346
+ "epoch": 28.0,
347
+ "eval_accuracy": 0.6179259114456065,
348
+ "eval_loss": 1.1439582109451294,
349
+ "eval_runtime": 103.381,
350
+ "eval_samples_per_second": 98.964,
351
+ "eval_steps_per_second": 3.095,
352
+ "step": 6720
353
+ },
354
+ {
355
+ "epoch": 29.0,
356
+ "eval_accuracy": 0.6181213957579904,
357
+ "eval_loss": 1.1439974308013916,
358
+ "eval_runtime": 102.6407,
359
+ "eval_samples_per_second": 99.678,
360
+ "eval_steps_per_second": 3.118,
361
+ "step": 6960
362
+ },
363
+ {
364
+ "epoch": 29.17,
365
+ "grad_norm": 7.591431617736816,
366
+ "learning_rate": 1.3986013986013985e-08,
367
+ "loss": 0.6473,
368
+ "step": 7000
369
+ },
370
+ {
371
+ "epoch": 30.0,
372
+ "eval_accuracy": 0.6190010751637182,
373
+ "eval_loss": 1.143545389175415,
374
+ "eval_runtime": 105.5925,
375
+ "eval_samples_per_second": 96.891,
376
+ "eval_steps_per_second": 3.031,
377
+ "step": 7200
378
+ }
379
+ ],
380
+ "logging_steps": 500,
381
+ "max_steps": 7200,
382
+ "num_input_tokens_seen": 0,
383
+ "num_train_epochs": 30,
384
+ "save_steps": 500,
385
+ "total_flos": 3.5680151743533187e+19,
386
+ "train_batch_size": 64,
387
+ "trial_name": null,
388
+ "trial_params": null
389
+ }
checkpoint-7200/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d3cbd7e961f520d4cc073622bb190f62bb0989c97e9a4850106ebdbeddcce186
3
+ size 4411
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1ca355e4ab0436bd1f28b1391a4d956b8e70f091a4970fe45a99bd0c57eb8d48
3
  size 343288572
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d3d446592a8713ec044baca3f10db07d050d0d63c2dcc0af7e90747c2f711873
3
  size 343288572
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1720d13f8074df3fb08ee60b875a9df5a8b4161f2f31054e04a3b9fdc006e59a
3
  size 4411
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d3cbd7e961f520d4cc073622bb190f62bb0989c97e9a4850106ebdbeddcce186
3
  size 4411