Hugging Face's logo

dima806
/
fairface_age_image_detection

Image Classification
Transformers
Safetensors
vit
Inference Endpoints
Model card Files Community
dima806 commited on
Commit
ce928c3
·
verified ·
1 Parent(s): 4b642db

Upload folder using huggingface_hub

Browse files
Files changed (10) hide show
  1. checkpoint-9376/config.json +46 -0
  2. checkpoint-9376/model.safetensors +3 -0
  3. checkpoint-9376/optimizer.pt +3 -0
  4. checkpoint-9376/preprocessor_config.json +23 -0
  5. checkpoint-9376/rng_state.pth +3 -0
  6. checkpoint-9376/scheduler.pt +3 -0
  7. checkpoint-9376/trainer_state.json +199 -0
  8. checkpoint-9376/training_args.bin +3 -0
  9. model.safetensors +1 -1
  10. training_args.bin +1 -1
checkpoint-9376/config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/vit-base-patch16-224-in21k",
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": "0-2",
13
+ "1": "3-9",
14
+ "2": "10-19",
15
+ "3": "20-29",
16
+ "4": "30-39",
17
+ "5": "40-49",
18
+ "6": "50-59",
19
+ "7": "60-69",
20
+ "8": "more than 70"
21
+ },
22
+ "image_size": 224,
23
+ "initializer_range": 0.02,
24
+ "intermediate_size": 3072,
25
+ "label2id": {
26
+ "0-2": 0,
27
+ "10-19": 2,
28
+ "20-29": 3,
29
+ "3-9": 1,
30
+ "30-39": 4,
31
+ "40-49": 5,
32
+ "50-59": 6,
33
+ "60-69": 7,
34
+ "more than 70": 8
35
+ },
36
+ "layer_norm_eps": 1e-12,
37
+ "model_type": "vit",
38
+ "num_attention_heads": 12,
39
+ "num_channels": 3,
40
+ "num_hidden_layers": 12,
41
+ "patch_size": 16,
42
+ "problem_type": "single_label_classification",
43
+ "qkv_bias": true,
44
+ "torch_dtype": "float32",
45
+ "transformers_version": "4.47.0"
46
+ }
checkpoint-9376/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac667f9891e096b94eec6a038cc2967f2cd9d88254165edf42d05ba621ba1c7a
3
+ size 343245508
checkpoint-9376/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2297f022db5d3507731ee0645ef4ac9a9d0d10e51c904f9c64f2bb393f4d7fed
3
+ size 686611898
checkpoint-9376/preprocessor_config.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_convert_rgb": null,
3
+ "do_normalize": true,
4
+ "do_rescale": true,
5
+ "do_resize": true,
6
+ "image_mean": [
7
+ 0.5,
8
+ 0.5,
9
+ 0.5
10
+ ],
11
+ "image_processor_type": "ViTImageProcessor",
12
+ "image_std": [
13
+ 0.5,
14
+ 0.5,
15
+ 0.5
16
+ ],
17
+ "resample": 2,
18
+ "rescale_factor": 0.00392156862745098,
19
+ "size": {
20
+ "height": 224,
21
+ "width": 224
22
+ }
23
+ }
checkpoint-9376/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48ee9b73399c28d7e668360bf1d5a4d11095c4738bf96c13f7bb6fbff59f8ccb
3
+ size 14244
checkpoint-9376/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19ef57ca7ce01a08a3ddc4d19049becd27a3d4c36511ddeaa3a26bb44693aa91
3
+ size 1064
checkpoint-9376/trainer_state.json ADDED
@@ -0,0 +1,199 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 1.0641573667526245,
3
+ "best_model_checkpoint": "fairface_age_image_detection/checkpoint-9376",
4
+ "epoch": 4.0,
5
+ "eval_steps": 500,
6
+ "global_step": 9376,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.21331058020477817,
13
+ "grad_norm": 1.7275338172912598,
14
+ "learning_rate": 2.855243405532919e-06,
15
+ "loss": 1.8728,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 0.42662116040955633,
20
+ "grad_norm": 2.228030204772949,
21
+ "learning_rate": 2.6944027450139397e-06,
22
+ "loss": 1.4714,
23
+ "step": 1000
24
+ },
25
+ {
26
+ "epoch": 0.6399317406143344,
27
+ "grad_norm": 2.2512168884277344,
28
+ "learning_rate": 2.5335620844949606e-06,
29
+ "loss": 1.3358,
30
+ "step": 1500
31
+ },
32
+ {
33
+ "epoch": 0.8532423208191127,
34
+ "grad_norm": 3.124258279800415,
35
+ "learning_rate": 2.372721423975981e-06,
36
+ "loss": 1.264,
37
+ "step": 2000
38
+ },
39
+ {
40
+ "epoch": 1.0,
41
+ "eval_accuracy": 0.5423,
42
+ "eval_loss": 1.2151408195495605,
43
+ "eval_model_preparation_time": 0.0043,
44
+ "eval_runtime": 907.0206,
45
+ "eval_samples_per_second": 11.025,
46
+ "eval_steps_per_second": 1.378,
47
+ "step": 2344
48
+ },
49
+ {
50
+ "epoch": 1.0665529010238908,
51
+ "grad_norm": 5.8204874992370605,
52
+ "learning_rate": 2.211880763457002e-06,
53
+ "loss": 1.2174,
54
+ "step": 2500
55
+ },
56
+ {
57
+ "epoch": 1.2798634812286689,
58
+ "grad_norm": 5.175824165344238,
59
+ "learning_rate": 2.051040102938023e-06,
60
+ "loss": 1.171,
61
+ "step": 3000
62
+ },
63
+ {
64
+ "epoch": 1.493174061433447,
65
+ "grad_norm": 3.312744617462158,
66
+ "learning_rate": 1.8901994424190437e-06,
67
+ "loss": 1.1425,
68
+ "step": 3500
69
+ },
70
+ {
71
+ "epoch": 1.7064846416382253,
72
+ "grad_norm": 4.630620002746582,
73
+ "learning_rate": 1.7293587819000642e-06,
74
+ "loss": 1.1267,
75
+ "step": 4000
76
+ },
77
+ {
78
+ "epoch": 1.9197952218430034,
79
+ "grad_norm": 3.5600452423095703,
80
+ "learning_rate": 1.5685181213810853e-06,
81
+ "loss": 1.1051,
82
+ "step": 4500
83
+ },
84
+ {
85
+ "epoch": 2.0,
86
+ "eval_accuracy": 0.5688,
87
+ "eval_loss": 1.1124917268753052,
88
+ "eval_model_preparation_time": 0.0043,
89
+ "eval_runtime": 915.0894,
90
+ "eval_samples_per_second": 10.928,
91
+ "eval_steps_per_second": 1.366,
92
+ "step": 4688
93
+ },
94
+ {
95
+ "epoch": 2.1331058020477816,
96
+ "grad_norm": 7.453662395477295,
97
+ "learning_rate": 1.407677460862106e-06,
98
+ "loss": 1.0871,
99
+ "step": 5000
100
+ },
101
+ {
102
+ "epoch": 2.34641638225256,
103
+ "grad_norm": 8.157800674438477,
104
+ "learning_rate": 1.2468368003431269e-06,
105
+ "loss": 1.0696,
106
+ "step": 5500
107
+ },
108
+ {
109
+ "epoch": 2.5597269624573378,
110
+ "grad_norm": 3.6688616275787354,
111
+ "learning_rate": 1.0859961398241475e-06,
112
+ "loss": 1.0571,
113
+ "step": 6000
114
+ },
115
+ {
116
+ "epoch": 2.773037542662116,
117
+ "grad_norm": 3.1099190711975098,
118
+ "learning_rate": 9.251554793051683e-07,
119
+ "loss": 1.0476,
120
+ "step": 6500
121
+ },
122
+ {
123
+ "epoch": 2.986348122866894,
124
+ "grad_norm": 5.784822463989258,
125
+ "learning_rate": 7.643148187861893e-07,
126
+ "loss": 1.0407,
127
+ "step": 7000
128
+ },
129
+ {
130
+ "epoch": 3.0,
131
+ "eval_accuracy": 0.5756,
132
+ "eval_loss": 1.0761935710906982,
133
+ "eval_model_preparation_time": 0.0043,
134
+ "eval_runtime": 920.0161,
135
+ "eval_samples_per_second": 10.869,
136
+ "eval_steps_per_second": 1.359,
137
+ "step": 7032
138
+ },
139
+ {
140
+ "epoch": 3.1996587030716723,
141
+ "grad_norm": 5.856372833251953,
142
+ "learning_rate": 6.0347415826721e-07,
143
+ "loss": 1.0212,
144
+ "step": 7500
145
+ },
146
+ {
147
+ "epoch": 3.4129692832764507,
148
+ "grad_norm": 5.725022792816162,
149
+ "learning_rate": 4.426334977482307e-07,
150
+ "loss": 1.0253,
151
+ "step": 8000
152
+ },
153
+ {
154
+ "epoch": 3.6262798634812285,
155
+ "grad_norm": 4.74147891998291,
156
+ "learning_rate": 2.8179283722925154e-07,
157
+ "loss": 1.0232,
158
+ "step": 8500
159
+ },
160
+ {
161
+ "epoch": 3.839590443686007,
162
+ "grad_norm": 4.050413131713867,
163
+ "learning_rate": 1.2095217671027237e-07,
164
+ "loss": 1.0173,
165
+ "step": 9000
166
+ },
167
+ {
168
+ "epoch": 4.0,
169
+ "eval_accuracy": 0.5791,
170
+ "eval_loss": 1.0641573667526245,
171
+ "eval_model_preparation_time": 0.0043,
172
+ "eval_runtime": 919.3696,
173
+ "eval_samples_per_second": 10.877,
174
+ "eval_steps_per_second": 1.36,
175
+ "step": 9376
176
+ }
177
+ ],
178
+ "logging_steps": 500,
179
+ "max_steps": 9376,
180
+ "num_input_tokens_seen": 0,
181
+ "num_train_epochs": 4,
182
+ "save_steps": 500,
183
+ "stateful_callbacks": {
184
+ "TrainerControl": {
185
+ "args": {
186
+ "should_epoch_stop": false,
187
+ "should_evaluate": false,
188
+ "should_log": false,
189
+ "should_save": true,
190
+ "should_training_stop": true
191
+ },
192
+ "attributes": {}
193
+ }
194
+ },
195
+ "total_flos": 2.32490554103808e+19,
196
+ "train_batch_size": 32,
197
+ "trial_name": null,
198
+ "trial_params": null
199
+ }
checkpoint-9376/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50f7f93c67bf88403da8f77fa2109e270c1cad6076487c78154dcb74bbd014af
3
+ size 5304
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1f6f3b28c3de06bcedbae8b985363f2df21de98524d8165e2c6cc7f998d98c57
3
  size 343245508
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac667f9891e096b94eec6a038cc2967f2cd9d88254165edf42d05ba621ba1c7a
3
  size 343245508
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:28ebf2b6dbb08045128c07625eb89924fd949f0c3794edd35784a5c320305df8
3
  size 5304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50f7f93c67bf88403da8f77fa2109e270c1cad6076487c78154dcb74bbd014af
3
  size 5304