dima806 commited on
Commit
e18389c
·
verified ·
1 Parent(s): 9b1c2f4

Upload folder using huggingface_hub

Browse files
checkpoint-4864/config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "dima806/faces_age_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": "MIDDLE",
13
+ "1": "YOUNG",
14
+ "2": "OLD"
15
+ },
16
+ "image_size": 224,
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 3072,
19
+ "label2id": {
20
+ "MIDDLE": 0,
21
+ "OLD": 2,
22
+ "YOUNG": 1
23
+ },
24
+ "layer_norm_eps": 1e-12,
25
+ "model_type": "vit",
26
+ "num_attention_heads": 12,
27
+ "num_channels": 3,
28
+ "num_hidden_layers": 12,
29
+ "patch_size": 16,
30
+ "problem_type": "single_label_classification",
31
+ "qkv_bias": true,
32
+ "torch_dtype": "float32",
33
+ "transformers_version": "4.45.1"
34
+ }
checkpoint-4864/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26c28313dbb1eb8f18c833f6aba6ced089f26f9a25213fb8d05d327640ffdabf
3
+ size 343227052
checkpoint-4864/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35282da004d78edba232363539fe1bdb077c5b1a859ee439802412a571ccc457
3
+ size 686574597
checkpoint-4864/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-4864/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:712e11ff275c7225840824c1b03f9f295abe58b55b4a1802347c3838edb541fa
3
+ size 14575
checkpoint-4864/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:839b1d5952e4aabae478801a4d5ebcbea9ab53163616c6bec1416baefaa6f6c4
3
+ size 627
checkpoint-4864/trainer_state.json ADDED
@@ -0,0 +1,256 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.24626319110393524,
3
+ "best_model_checkpoint": "faces_age_detection/checkpoint-4864",
4
+ "epoch": 16.0,
5
+ "eval_steps": 500,
6
+ "global_step": 4864,
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": 0.9048206710374084,
14
+ "eval_loss": 0.25544658303260803,
15
+ "eval_model_preparation_time": 0.0056,
16
+ "eval_runtime": 115.8575,
17
+ "eval_samples_per_second": 111.905,
18
+ "eval_steps_per_second": 3.504,
19
+ "step": 304
20
+ },
21
+ {
22
+ "epoch": 1.6447368421052633,
23
+ "grad_norm": 9.665897369384766,
24
+ "learning_rate": 9.253731343283582e-07,
25
+ "loss": 0.1128,
26
+ "step": 500
27
+ },
28
+ {
29
+ "epoch": 2.0,
30
+ "eval_accuracy": 0.9051291939838025,
31
+ "eval_loss": 0.25322863459587097,
32
+ "eval_model_preparation_time": 0.0056,
33
+ "eval_runtime": 116.0042,
34
+ "eval_samples_per_second": 111.763,
35
+ "eval_steps_per_second": 3.5,
36
+ "step": 608
37
+ },
38
+ {
39
+ "epoch": 3.0,
40
+ "eval_accuracy": 0.909371384496722,
41
+ "eval_loss": 0.24770796298980713,
42
+ "eval_model_preparation_time": 0.0056,
43
+ "eval_runtime": 115.4652,
44
+ "eval_samples_per_second": 112.285,
45
+ "eval_steps_per_second": 3.516,
46
+ "step": 912
47
+ },
48
+ {
49
+ "epoch": 3.2894736842105265,
50
+ "grad_norm": 5.963768482208252,
51
+ "learning_rate": 8.424543946932007e-07,
52
+ "loss": 0.1092,
53
+ "step": 1000
54
+ },
55
+ {
56
+ "epoch": 4.0,
57
+ "eval_accuracy": 0.9075973775549556,
58
+ "eval_loss": 0.2508331835269928,
59
+ "eval_model_preparation_time": 0.0056,
60
+ "eval_runtime": 110.7185,
61
+ "eval_samples_per_second": 117.099,
62
+ "eval_steps_per_second": 3.667,
63
+ "step": 1216
64
+ },
65
+ {
66
+ "epoch": 4.934210526315789,
67
+ "grad_norm": 6.369262218475342,
68
+ "learning_rate": 7.595356550580431e-07,
69
+ "loss": 0.1013,
70
+ "step": 1500
71
+ },
72
+ {
73
+ "epoch": 5.0,
74
+ "eval_accuracy": 0.9069803316621674,
75
+ "eval_loss": 0.24949955940246582,
76
+ "eval_model_preparation_time": 0.0056,
77
+ "eval_runtime": 114.7896,
78
+ "eval_samples_per_second": 112.946,
79
+ "eval_steps_per_second": 3.537,
80
+ "step": 1520
81
+ },
82
+ {
83
+ "epoch": 6.0,
84
+ "eval_accuracy": 0.9052834554569996,
85
+ "eval_loss": 0.2557480037212372,
86
+ "eval_model_preparation_time": 0.0056,
87
+ "eval_runtime": 117.3931,
88
+ "eval_samples_per_second": 110.441,
89
+ "eval_steps_per_second": 3.458,
90
+ "step": 1824
91
+ },
92
+ {
93
+ "epoch": 6.578947368421053,
94
+ "grad_norm": 8.901986122131348,
95
+ "learning_rate": 6.766169154228856e-07,
96
+ "loss": 0.097,
97
+ "step": 2000
98
+ },
99
+ {
100
+ "epoch": 7.0,
101
+ "eval_accuracy": 0.9085229463941381,
102
+ "eval_loss": 0.2521224617958069,
103
+ "eval_model_preparation_time": 0.0056,
104
+ "eval_runtime": 116.8685,
105
+ "eval_samples_per_second": 110.937,
106
+ "eval_steps_per_second": 3.474,
107
+ "step": 2128
108
+ },
109
+ {
110
+ "epoch": 8.0,
111
+ "eval_accuracy": 0.9035865792518318,
112
+ "eval_loss": 0.2614166736602783,
113
+ "eval_model_preparation_time": 0.0056,
114
+ "eval_runtime": 117.7658,
115
+ "eval_samples_per_second": 110.091,
116
+ "eval_steps_per_second": 3.448,
117
+ "step": 2432
118
+ },
119
+ {
120
+ "epoch": 8.223684210526315,
121
+ "grad_norm": 9.241392135620117,
122
+ "learning_rate": 5.93698175787728e-07,
123
+ "loss": 0.0981,
124
+ "step": 2500
125
+ },
126
+ {
127
+ "epoch": 9.0,
128
+ "eval_accuracy": 0.9066718087157732,
129
+ "eval_loss": 0.25424298644065857,
130
+ "eval_model_preparation_time": 0.0056,
131
+ "eval_runtime": 117.1049,
132
+ "eval_samples_per_second": 110.713,
133
+ "eval_steps_per_second": 3.467,
134
+ "step": 2736
135
+ },
136
+ {
137
+ "epoch": 9.868421052631579,
138
+ "grad_norm": 15.468152046203613,
139
+ "learning_rate": 5.107794361525704e-07,
140
+ "loss": 0.0928,
141
+ "step": 3000
142
+ },
143
+ {
144
+ "epoch": 10.0,
145
+ "eval_accuracy": 0.9087543386039336,
146
+ "eval_loss": 0.2496512234210968,
147
+ "eval_model_preparation_time": 0.0056,
148
+ "eval_runtime": 117.518,
149
+ "eval_samples_per_second": 110.324,
150
+ "eval_steps_per_second": 3.455,
151
+ "step": 3040
152
+ },
153
+ {
154
+ "epoch": 11.0,
155
+ "eval_accuracy": 0.9098341689163132,
156
+ "eval_loss": 0.2480880618095398,
157
+ "eval_model_preparation_time": 0.0056,
158
+ "eval_runtime": 119.13,
159
+ "eval_samples_per_second": 108.831,
160
+ "eval_steps_per_second": 3.408,
161
+ "step": 3344
162
+ },
163
+ {
164
+ "epoch": 11.513157894736842,
165
+ "grad_norm": 9.02236557006836,
166
+ "learning_rate": 4.278606965174129e-07,
167
+ "loss": 0.088,
168
+ "step": 3500
169
+ },
170
+ {
171
+ "epoch": 12.0,
172
+ "eval_accuracy": 0.9090628615503278,
173
+ "eval_loss": 0.2512376010417938,
174
+ "eval_model_preparation_time": 0.0056,
175
+ "eval_runtime": 117.373,
176
+ "eval_samples_per_second": 110.46,
177
+ "eval_steps_per_second": 3.459,
178
+ "step": 3648
179
+ },
180
+ {
181
+ "epoch": 13.0,
182
+ "eval_accuracy": 0.9090628615503278,
183
+ "eval_loss": 0.2498735636472702,
184
+ "eval_model_preparation_time": 0.0056,
185
+ "eval_runtime": 116.0104,
186
+ "eval_samples_per_second": 111.757,
187
+ "eval_steps_per_second": 3.5,
188
+ "step": 3952
189
+ },
190
+ {
191
+ "epoch": 13.157894736842104,
192
+ "grad_norm": 10.029730796813965,
193
+ "learning_rate": 3.4494195688225535e-07,
194
+ "loss": 0.0855,
195
+ "step": 4000
196
+ },
197
+ {
198
+ "epoch": 14.0,
199
+ "eval_accuracy": 0.9099112996529117,
200
+ "eval_loss": 0.24805885553359985,
201
+ "eval_model_preparation_time": 0.0056,
202
+ "eval_runtime": 116.2889,
203
+ "eval_samples_per_second": 111.49,
204
+ "eval_steps_per_second": 3.491,
205
+ "step": 4256
206
+ },
207
+ {
208
+ "epoch": 14.802631578947368,
209
+ "grad_norm": 7.256553649902344,
210
+ "learning_rate": 2.620232172470978e-07,
211
+ "loss": 0.0847,
212
+ "step": 4500
213
+ },
214
+ {
215
+ "epoch": 15.0,
216
+ "eval_accuracy": 0.9097570381797146,
217
+ "eval_loss": 0.24851545691490173,
218
+ "eval_model_preparation_time": 0.0056,
219
+ "eval_runtime": 115.2188,
220
+ "eval_samples_per_second": 112.525,
221
+ "eval_steps_per_second": 3.524,
222
+ "step": 4560
223
+ },
224
+ {
225
+ "epoch": 16.0,
226
+ "eval_accuracy": 0.9106054762822985,
227
+ "eval_loss": 0.24626319110393524,
228
+ "eval_model_preparation_time": 0.0056,
229
+ "eval_runtime": 114.9847,
230
+ "eval_samples_per_second": 112.754,
231
+ "eval_steps_per_second": 3.531,
232
+ "step": 4864
233
+ }
234
+ ],
235
+ "logging_steps": 500,
236
+ "max_steps": 6080,
237
+ "num_input_tokens_seen": 0,
238
+ "num_train_epochs": 20,
239
+ "save_steps": 500,
240
+ "stateful_callbacks": {
241
+ "TrainerControl": {
242
+ "args": {
243
+ "should_epoch_stop": false,
244
+ "should_evaluate": false,
245
+ "should_log": false,
246
+ "should_save": true,
247
+ "should_training_stop": false
248
+ },
249
+ "attributes": {}
250
+ }
251
+ },
252
+ "total_flos": 2.4112003658884735e+19,
253
+ "train_batch_size": 64,
254
+ "trial_name": null,
255
+ "trial_params": null
256
+ }
checkpoint-4864/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96f4804d79a52c4c7cdc8b0f335cb99905741b776f69b39ee053f7cf04592ee6
3
+ size 4731
config.json CHANGED
@@ -30,5 +30,5 @@
30
  "problem_type": "single_label_classification",
31
  "qkv_bias": true,
32
  "torch_dtype": "float32",
33
- "transformers_version": "4.38.2"
34
  }
 
30
  "problem_type": "single_label_classification",
31
  "qkv_bias": true,
32
  "torch_dtype": "float32",
33
+ "transformers_version": "4.45.1"
34
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:daecfa46675787b1707ed8ee020c8ada43c783d760c6e8ac8b638e873803193b
3
  size 343227052
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26c28313dbb1eb8f18c833f6aba6ced089f26f9a25213fb8d05d327640ffdabf
3
  size 343227052
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3c29334dc4de288a7c3f093e596c8e19c0643c2ab9b32aa95c2c7e1069ebc8f5
3
- size 4411
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96f4804d79a52c4c7cdc8b0f335cb99905741b776f69b39ee053f7cf04592ee6
3
+ size 4731