Upload folder using huggingface_hub
Browse files- checkpoint-3120/config.json +74 -0
- checkpoint-3120/model.safetensors +3 -0
- checkpoint-3120/optimizer.pt +3 -0
- checkpoint-3120/preprocessor_config.json +22 -0
- checkpoint-3120/rng_state.pth +3 -0
- checkpoint-3120/scheduler.pt +3 -0
- checkpoint-3120/trainer_state.json +180 -0
- checkpoint-3120/training_args.bin +3 -0
- model.safetensors +1 -1
- training_args.bin +1 -1
checkpoint-3120/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-3120/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8d052f8d13109aaca6992c41e105e8137d68f28772bd1e17c922d876b6978559
|
3 |
+
size 343288572
|
checkpoint-3120/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b46252046f1561bd1c4885f50566e0ee1beec9eeb4deae5166dc523dd64c786c
|
3 |
+
size 686697605
|
checkpoint-3120/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-3120/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b35d8037ff1536b893cff3157c05725f0ec623a81032cfa1a2644d8e0f6acd6f
|
3 |
+
size 14575
|
checkpoint-3120/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b6c627908da33f0bacb0545deae40dd9ee03d7851921b19d61d0f28acc936066
|
3 |
+
size 627
|
checkpoint-3120/trainer_state.json
ADDED
@@ -0,0 +1,180 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 1.2208830118179321,
|
3 |
+
"best_model_checkpoint": "facial_age_image_detection/checkpoint-3120",
|
4 |
+
"epoch": 13.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 3120,
|
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": 0.5914377871175838,
|
14 |
+
"eval_loss": 1.247507929801941,
|
15 |
+
"eval_runtime": 105.4075,
|
16 |
+
"eval_samples_per_second": 97.061,
|
17 |
+
"eval_steps_per_second": 3.036,
|
18 |
+
"step": 240
|
19 |
+
},
|
20 |
+
{
|
21 |
+
"epoch": 2.0,
|
22 |
+
"eval_accuracy": 0.599159417456749,
|
23 |
+
"eval_loss": 1.2387152910232544,
|
24 |
+
"eval_runtime": 105.6722,
|
25 |
+
"eval_samples_per_second": 96.818,
|
26 |
+
"eval_steps_per_second": 3.028,
|
27 |
+
"step": 480
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 2.08,
|
31 |
+
"grad_norm": 16.16035270690918,
|
32 |
+
"learning_rate": 6.112676056338028e-07,
|
33 |
+
"loss": 0.8178,
|
34 |
+
"step": 500
|
35 |
+
},
|
36 |
+
{
|
37 |
+
"epoch": 3.0,
|
38 |
+
"eval_accuracy": 0.593979083178575,
|
39 |
+
"eval_loss": 1.240220069885254,
|
40 |
+
"eval_runtime": 106.9319,
|
41 |
+
"eval_samples_per_second": 95.678,
|
42 |
+
"eval_steps_per_second": 2.993,
|
43 |
+
"step": 720
|
44 |
+
},
|
45 |
+
{
|
46 |
+
"epoch": 4.0,
|
47 |
+
"eval_accuracy": 0.5982797380510214,
|
48 |
+
"eval_loss": 1.2350324392318726,
|
49 |
+
"eval_runtime": 105.7769,
|
50 |
+
"eval_samples_per_second": 96.722,
|
51 |
+
"eval_steps_per_second": 3.025,
|
52 |
+
"step": 960
|
53 |
+
},
|
54 |
+
{
|
55 |
+
"epoch": 4.17,
|
56 |
+
"grad_norm": 12.192686080932617,
|
57 |
+
"learning_rate": 5.126760563380281e-07,
|
58 |
+
"loss": 0.8038,
|
59 |
+
"step": 1000
|
60 |
+
},
|
61 |
+
{
|
62 |
+
"epoch": 5.0,
|
63 |
+
"eval_accuracy": 0.5962271527709901,
|
64 |
+
"eval_loss": 1.2324706315994263,
|
65 |
+
"eval_runtime": 105.7457,
|
66 |
+
"eval_samples_per_second": 96.751,
|
67 |
+
"eval_steps_per_second": 3.026,
|
68 |
+
"step": 1200
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 6.0,
|
72 |
+
"eval_accuracy": 0.5964226370833741,
|
73 |
+
"eval_loss": 1.2318035364151,
|
74 |
+
"eval_runtime": 105.5068,
|
75 |
+
"eval_samples_per_second": 96.97,
|
76 |
+
"eval_steps_per_second": 3.033,
|
77 |
+
"step": 1440
|
78 |
+
},
|
79 |
+
{
|
80 |
+
"epoch": 6.25,
|
81 |
+
"grad_norm": 12.383950233459473,
|
82 |
+
"learning_rate": 4.140845070422535e-07,
|
83 |
+
"loss": 0.7976,
|
84 |
+
"step": 1500
|
85 |
+
},
|
86 |
+
{
|
87 |
+
"epoch": 7.0,
|
88 |
+
"eval_accuracy": 0.5976932851138697,
|
89 |
+
"eval_loss": 1.2295589447021484,
|
90 |
+
"eval_runtime": 106.676,
|
91 |
+
"eval_samples_per_second": 95.907,
|
92 |
+
"eval_steps_per_second": 3.0,
|
93 |
+
"step": 1680
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 8.0,
|
97 |
+
"eval_accuracy": 0.5974978008014857,
|
98 |
+
"eval_loss": 1.2282449007034302,
|
99 |
+
"eval_runtime": 105.9543,
|
100 |
+
"eval_samples_per_second": 96.561,
|
101 |
+
"eval_steps_per_second": 3.02,
|
102 |
+
"step": 1920
|
103 |
+
},
|
104 |
+
{
|
105 |
+
"epoch": 8.33,
|
106 |
+
"grad_norm": 12.568708419799805,
|
107 |
+
"learning_rate": 3.1549295774647887e-07,
|
108 |
+
"loss": 0.7888,
|
109 |
+
"step": 2000
|
110 |
+
},
|
111 |
+
{
|
112 |
+
"epoch": 9.0,
|
113 |
+
"eval_accuracy": 0.6013097448929723,
|
114 |
+
"eval_loss": 1.2256407737731934,
|
115 |
+
"eval_runtime": 105.7499,
|
116 |
+
"eval_samples_per_second": 96.747,
|
117 |
+
"eval_steps_per_second": 3.026,
|
118 |
+
"step": 2160
|
119 |
+
},
|
120 |
+
{
|
121 |
+
"epoch": 10.0,
|
122 |
+
"eval_accuracy": 0.6001368390186688,
|
123 |
+
"eval_loss": 1.2228951454162598,
|
124 |
+
"eval_runtime": 106.2182,
|
125 |
+
"eval_samples_per_second": 96.321,
|
126 |
+
"eval_steps_per_second": 3.013,
|
127 |
+
"step": 2400
|
128 |
+
},
|
129 |
+
{
|
130 |
+
"epoch": 10.42,
|
131 |
+
"grad_norm": 10.32869815826416,
|
132 |
+
"learning_rate": 2.169014084507042e-07,
|
133 |
+
"loss": 0.7785,
|
134 |
+
"step": 2500
|
135 |
+
},
|
136 |
+
{
|
137 |
+
"epoch": 11.0,
|
138 |
+
"eval_accuracy": 0.5989639331443651,
|
139 |
+
"eval_loss": 1.223892331123352,
|
140 |
+
"eval_runtime": 105.6089,
|
141 |
+
"eval_samples_per_second": 96.876,
|
142 |
+
"eval_steps_per_second": 3.03,
|
143 |
+
"step": 2640
|
144 |
+
},
|
145 |
+
{
|
146 |
+
"epoch": 12.0,
|
147 |
+
"eval_accuracy": 0.599452643925325,
|
148 |
+
"eval_loss": 1.2233675718307495,
|
149 |
+
"eval_runtime": 105.2752,
|
150 |
+
"eval_samples_per_second": 97.183,
|
151 |
+
"eval_steps_per_second": 3.04,
|
152 |
+
"step": 2880
|
153 |
+
},
|
154 |
+
{
|
155 |
+
"epoch": 12.5,
|
156 |
+
"grad_norm": 10.018258094787598,
|
157 |
+
"learning_rate": 1.1830985915492958e-07,
|
158 |
+
"loss": 0.7763,
|
159 |
+
"step": 3000
|
160 |
+
},
|
161 |
+
{
|
162 |
+
"epoch": 13.0,
|
163 |
+
"eval_accuracy": 0.5997458703939009,
|
164 |
+
"eval_loss": 1.2208830118179321,
|
165 |
+
"eval_runtime": 106.4062,
|
166 |
+
"eval_samples_per_second": 96.15,
|
167 |
+
"eval_steps_per_second": 3.007,
|
168 |
+
"step": 3120
|
169 |
+
}
|
170 |
+
],
|
171 |
+
"logging_steps": 500,
|
172 |
+
"max_steps": 3600,
|
173 |
+
"num_input_tokens_seen": 0,
|
174 |
+
"num_train_epochs": 15,
|
175 |
+
"save_steps": 500,
|
176 |
+
"total_flos": 1.5461399088864369e+19,
|
177 |
+
"train_batch_size": 64,
|
178 |
+
"trial_name": null,
|
179 |
+
"trial_params": null
|
180 |
+
}
|
checkpoint-3120/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ae77cac5ba4aa1a550d83b9efd041272a8a03cde4495bce42f5d0c2a0f9fce17
|
3 |
+
size 4411
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 343288572
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8d052f8d13109aaca6992c41e105e8137d68f28772bd1e17c922d876b6978559
|
3 |
size 343288572
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4411
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ae77cac5ba4aa1a550d83b9efd041272a8a03cde4495bce42f5d0c2a0f9fce17
|
3 |
size 4411
|