Upload folder using huggingface_hub
Browse files- checkpoint-5320/config.json +74 -0
- checkpoint-5320/model.safetensors +3 -0
- checkpoint-5320/optimizer.pt +3 -0
- checkpoint-5320/preprocessor_config.json +22 -0
- checkpoint-5320/rng_state.pth +3 -0
- checkpoint-5320/scheduler.pt +3 -0
- checkpoint-5320/trainer_state.json +262 -0
- checkpoint-5320/training_args.bin +3 -0
- model.safetensors +1 -1
checkpoint-5320/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-5320/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7303e59f72b028ddf2798e9fcc38f9ac9f1df9e3333dbae5f4d59dc288cef8da
|
3 |
+
size 343288572
|
checkpoint-5320/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:40034ea547b49afdc94c78f4d0271b2b05fe48dd72218175ab5bd07e1c743ddd
|
3 |
+
size 686697605
|
checkpoint-5320/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-5320/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f2535ee43cb0bb37233af37de834c1e7079b7f75f6fb44a9e6b167c602d5c761
|
3 |
+
size 14575
|
checkpoint-5320/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:72378befdc66ee6fca960f722919978c9617b5b60e0e8713021ad0c504c9991f
|
3 |
+
size 627
|
checkpoint-5320/trainer_state.json
ADDED
@@ -0,0 +1,262 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 1.257996678352356,
|
3 |
+
"best_model_checkpoint": "facial_age_image_detection/checkpoint-5320",
|
4 |
+
"epoch": 19.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 5320,
|
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": 0.5756548937833963,
|
14 |
+
"eval_loss": 1.3048689365386963,
|
15 |
+
"eval_runtime": 87.7602,
|
16 |
+
"eval_samples_per_second": 87.431,
|
17 |
+
"eval_steps_per_second": 2.735,
|
18 |
+
"step": 280
|
19 |
+
},
|
20 |
+
{
|
21 |
+
"epoch": 1.79,
|
22 |
+
"grad_norm": 11.91701889038086,
|
23 |
+
"learning_rate": 9.18918918918919e-07,
|
24 |
+
"loss": 0.9042,
|
25 |
+
"step": 500
|
26 |
+
},
|
27 |
+
{
|
28 |
+
"epoch": 2.0,
|
29 |
+
"eval_accuracy": 0.5678352665189625,
|
30 |
+
"eval_loss": 1.306204080581665,
|
31 |
+
"eval_runtime": 81.8404,
|
32 |
+
"eval_samples_per_second": 93.756,
|
33 |
+
"eval_steps_per_second": 2.933,
|
34 |
+
"step": 560
|
35 |
+
},
|
36 |
+
{
|
37 |
+
"epoch": 3.0,
|
38 |
+
"eval_accuracy": 0.576176202267692,
|
39 |
+
"eval_loss": 1.300585150718689,
|
40 |
+
"eval_runtime": 81.0324,
|
41 |
+
"eval_samples_per_second": 94.691,
|
42 |
+
"eval_steps_per_second": 2.962,
|
43 |
+
"step": 840
|
44 |
+
},
|
45 |
+
{
|
46 |
+
"epoch": 3.57,
|
47 |
+
"grad_norm": 12.9658784866333,
|
48 |
+
"learning_rate": 8.288288288288288e-07,
|
49 |
+
"loss": 0.8924,
|
50 |
+
"step": 1000
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 4.0,
|
54 |
+
"eval_accuracy": 0.5730483513619185,
|
55 |
+
"eval_loss": 1.2988545894622803,
|
56 |
+
"eval_runtime": 82.0516,
|
57 |
+
"eval_samples_per_second": 93.514,
|
58 |
+
"eval_steps_per_second": 2.925,
|
59 |
+
"step": 1120
|
60 |
+
},
|
61 |
+
{
|
62 |
+
"epoch": 5.0,
|
63 |
+
"eval_accuracy": 0.5746122768148052,
|
64 |
+
"eval_loss": 1.2918657064437866,
|
65 |
+
"eval_runtime": 85.7442,
|
66 |
+
"eval_samples_per_second": 89.487,
|
67 |
+
"eval_steps_per_second": 2.799,
|
68 |
+
"step": 1400
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 5.36,
|
72 |
+
"grad_norm": 11.397974014282227,
|
73 |
+
"learning_rate": 7.387387387387387e-07,
|
74 |
+
"loss": 0.8708,
|
75 |
+
"step": 1500
|
76 |
+
},
|
77 |
+
{
|
78 |
+
"epoch": 6.0,
|
79 |
+
"eval_accuracy": 0.5765671836309136,
|
80 |
+
"eval_loss": 1.2833993434906006,
|
81 |
+
"eval_runtime": 80.6066,
|
82 |
+
"eval_samples_per_second": 95.191,
|
83 |
+
"eval_steps_per_second": 2.977,
|
84 |
+
"step": 1680
|
85 |
+
},
|
86 |
+
{
|
87 |
+
"epoch": 7.0,
|
88 |
+
"eval_accuracy": 0.5842564837742734,
|
89 |
+
"eval_loss": 1.276853322982788,
|
90 |
+
"eval_runtime": 82.4272,
|
91 |
+
"eval_samples_per_second": 93.088,
|
92 |
+
"eval_steps_per_second": 2.912,
|
93 |
+
"step": 1960
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 7.14,
|
97 |
+
"grad_norm": 7.821016311645508,
|
98 |
+
"learning_rate": 6.486486486486486e-07,
|
99 |
+
"loss": 0.8563,
|
100 |
+
"step": 2000
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 8.0,
|
104 |
+
"eval_accuracy": 0.5781311090838004,
|
105 |
+
"eval_loss": 1.2758774757385254,
|
106 |
+
"eval_runtime": 81.3168,
|
107 |
+
"eval_samples_per_second": 94.359,
|
108 |
+
"eval_steps_per_second": 2.951,
|
109 |
+
"step": 2240
|
110 |
+
},
|
111 |
+
{
|
112 |
+
"epoch": 8.93,
|
113 |
+
"grad_norm": 9.624176025390625,
|
114 |
+
"learning_rate": 5.585585585585585e-07,
|
115 |
+
"loss": 0.8478,
|
116 |
+
"step": 2500
|
117 |
+
},
|
118 |
+
{
|
119 |
+
"epoch": 9.0,
|
120 |
+
"eval_accuracy": 0.5789130718102438,
|
121 |
+
"eval_loss": 1.2749879360198975,
|
122 |
+
"eval_runtime": 80.8906,
|
123 |
+
"eval_samples_per_second": 94.856,
|
124 |
+
"eval_steps_per_second": 2.967,
|
125 |
+
"step": 2520
|
126 |
+
},
|
127 |
+
{
|
128 |
+
"epoch": 10.0,
|
129 |
+
"eval_accuracy": 0.582301576958165,
|
130 |
+
"eval_loss": 1.270504355430603,
|
131 |
+
"eval_runtime": 83.0139,
|
132 |
+
"eval_samples_per_second": 92.43,
|
133 |
+
"eval_steps_per_second": 2.891,
|
134 |
+
"step": 2800
|
135 |
+
},
|
136 |
+
{
|
137 |
+
"epoch": 10.71,
|
138 |
+
"grad_norm": 7.522056579589844,
|
139 |
+
"learning_rate": 4.684684684684684e-07,
|
140 |
+
"loss": 0.8341,
|
141 |
+
"step": 3000
|
142 |
+
},
|
143 |
+
{
|
144 |
+
"epoch": 11.0,
|
145 |
+
"eval_accuracy": 0.5815196142317216,
|
146 |
+
"eval_loss": 1.2686316967010498,
|
147 |
+
"eval_runtime": 81.0469,
|
148 |
+
"eval_samples_per_second": 94.674,
|
149 |
+
"eval_steps_per_second": 2.961,
|
150 |
+
"step": 3080
|
151 |
+
},
|
152 |
+
{
|
153 |
+
"epoch": 12.0,
|
154 |
+
"eval_accuracy": 0.5804769972631305,
|
155 |
+
"eval_loss": 1.2680425643920898,
|
156 |
+
"eval_runtime": 80.5295,
|
157 |
+
"eval_samples_per_second": 95.282,
|
158 |
+
"eval_steps_per_second": 2.98,
|
159 |
+
"step": 3360
|
160 |
+
},
|
161 |
+
{
|
162 |
+
"epoch": 12.5,
|
163 |
+
"grad_norm": 14.59212589263916,
|
164 |
+
"learning_rate": 3.783783783783784e-07,
|
165 |
+
"loss": 0.8298,
|
166 |
+
"step": 3500
|
167 |
+
},
|
168 |
+
{
|
169 |
+
"epoch": 13.0,
|
170 |
+
"eval_accuracy": 0.5786524175680959,
|
171 |
+
"eval_loss": 1.2673722505569458,
|
172 |
+
"eval_runtime": 84.1895,
|
173 |
+
"eval_samples_per_second": 91.14,
|
174 |
+
"eval_steps_per_second": 2.851,
|
175 |
+
"step": 3640
|
176 |
+
},
|
177 |
+
{
|
178 |
+
"epoch": 14.0,
|
179 |
+
"eval_accuracy": 0.5802163430209827,
|
180 |
+
"eval_loss": 1.2637258768081665,
|
181 |
+
"eval_runtime": 82.7707,
|
182 |
+
"eval_samples_per_second": 92.702,
|
183 |
+
"eval_steps_per_second": 2.9,
|
184 |
+
"step": 3920
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 14.29,
|
188 |
+
"grad_norm": 11.842473030090332,
|
189 |
+
"learning_rate": 2.882882882882883e-07,
|
190 |
+
"loss": 0.8226,
|
191 |
+
"step": 4000
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 15.0,
|
195 |
+
"eval_accuracy": 0.5813892871106477,
|
196 |
+
"eval_loss": 1.2624099254608154,
|
197 |
+
"eval_runtime": 82.4012,
|
198 |
+
"eval_samples_per_second": 93.118,
|
199 |
+
"eval_steps_per_second": 2.913,
|
200 |
+
"step": 4200
|
201 |
+
},
|
202 |
+
{
|
203 |
+
"epoch": 16.0,
|
204 |
+
"eval_accuracy": 0.5829532125635345,
|
205 |
+
"eval_loss": 1.2608647346496582,
|
206 |
+
"eval_runtime": 82.9157,
|
207 |
+
"eval_samples_per_second": 92.54,
|
208 |
+
"eval_steps_per_second": 2.895,
|
209 |
+
"step": 4480
|
210 |
+
},
|
211 |
+
{
|
212 |
+
"epoch": 16.07,
|
213 |
+
"grad_norm": 7.111355304718018,
|
214 |
+
"learning_rate": 1.9819819819819818e-07,
|
215 |
+
"loss": 0.8104,
|
216 |
+
"step": 4500
|
217 |
+
},
|
218 |
+
{
|
219 |
+
"epoch": 17.0,
|
220 |
+
"eval_accuracy": 0.5825622312003128,
|
221 |
+
"eval_loss": 1.2595696449279785,
|
222 |
+
"eval_runtime": 87.9608,
|
223 |
+
"eval_samples_per_second": 87.232,
|
224 |
+
"eval_steps_per_second": 2.728,
|
225 |
+
"step": 4760
|
226 |
+
},
|
227 |
+
{
|
228 |
+
"epoch": 17.86,
|
229 |
+
"grad_norm": 10.99641227722168,
|
230 |
+
"learning_rate": 1.0810810810810811e-07,
|
231 |
+
"loss": 0.8098,
|
232 |
+
"step": 5000
|
233 |
+
},
|
234 |
+
{
|
235 |
+
"epoch": 18.0,
|
236 |
+
"eval_accuracy": 0.5826925583213867,
|
237 |
+
"eval_loss": 1.2582371234893799,
|
238 |
+
"eval_runtime": 83.3175,
|
239 |
+
"eval_samples_per_second": 92.093,
|
240 |
+
"eval_steps_per_second": 2.881,
|
241 |
+
"step": 5040
|
242 |
+
},
|
243 |
+
{
|
244 |
+
"epoch": 19.0,
|
245 |
+
"eval_accuracy": 0.5821712498370911,
|
246 |
+
"eval_loss": 1.257996678352356,
|
247 |
+
"eval_runtime": 83.5381,
|
248 |
+
"eval_samples_per_second": 91.85,
|
249 |
+
"eval_steps_per_second": 2.873,
|
250 |
+
"step": 5320
|
251 |
+
}
|
252 |
+
],
|
253 |
+
"logging_steps": 500,
|
254 |
+
"max_steps": 5600,
|
255 |
+
"num_input_tokens_seen": 0,
|
256 |
+
"num_train_epochs": 20,
|
257 |
+
"save_steps": 500,
|
258 |
+
"total_flos": 2.636440398962747e+19,
|
259 |
+
"train_batch_size": 64,
|
260 |
+
"trial_name": null,
|
261 |
+
"trial_params": null
|
262 |
+
}
|
checkpoint-5320/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9f6a197bb61538af9105ff3f98f5f8f19f1a1b0dc25898782642a1539f61d8e6
|
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 sha256:7303e59f72b028ddf2798e9fcc38f9ac9f1df9e3333dbae5f4d59dc288cef8da
|
3 |
size 343288572
|