End of training
Browse files- README.md +7 -5
- all_results.json +12 -0
- eval_results.json +8 -0
- train_results.json +7 -0
- trainer_state.json +217 -0
README.md
CHANGED
@@ -2,6 +2,8 @@
|
|
2 |
license: apache-2.0
|
3 |
base_model: google/vit-large-patch16-224-in21k
|
4 |
tags:
|
|
|
|
|
5 |
- generated_from_trainer
|
6 |
datasets:
|
7 |
- imagefolder
|
@@ -14,7 +16,7 @@ model-index:
|
|
14 |
name: Image Classification
|
15 |
type: image-classification
|
16 |
dataset:
|
17 |
-
name:
|
18 |
type: imagefolder
|
19 |
config: default
|
20 |
split: train
|
@@ -22,7 +24,7 @@ model-index:
|
|
22 |
metrics:
|
23 |
- name: Accuracy
|
24 |
type: accuracy
|
25 |
-
value: 0.
|
26 |
---
|
27 |
|
28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -30,10 +32,10 @@ should probably proofread and complete it, then remove this comment. -->
|
|
30 |
|
31 |
# fashion-images-gender-age-vit-large-patch16-224-in21k-v2
|
32 |
|
33 |
-
This model is a fine-tuned version of [google/vit-large-patch16-224-in21k](https://huggingface.co/google/vit-large-patch16-224-in21k) on the
|
34 |
It achieves the following results on the evaluation set:
|
35 |
-
- Loss: 0.
|
36 |
-
- Accuracy: 0.
|
37 |
|
38 |
## Model description
|
39 |
|
|
|
2 |
license: apache-2.0
|
3 |
base_model: google/vit-large-patch16-224-in21k
|
4 |
tags:
|
5 |
+
- image-classification
|
6 |
+
- vision
|
7 |
- generated_from_trainer
|
8 |
datasets:
|
9 |
- imagefolder
|
|
|
16 |
name: Image Classification
|
17 |
type: image-classification
|
18 |
dataset:
|
19 |
+
name: touchtech/fashion-images-gender-age
|
20 |
type: imagefolder
|
21 |
config: default
|
22 |
split: train
|
|
|
24 |
metrics:
|
25 |
- name: Accuracy
|
26 |
type: accuracy
|
27 |
+
value: 0.9939200926462073
|
28 |
---
|
29 |
|
30 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
32 |
|
33 |
# fashion-images-gender-age-vit-large-patch16-224-in21k-v2
|
34 |
|
35 |
+
This model is a fine-tuned version of [google/vit-large-patch16-224-in21k](https://huggingface.co/google/vit-large-patch16-224-in21k) on the touchtech/fashion-images-gender-age dataset.
|
36 |
It achieves the following results on the evaluation set:
|
37 |
+
- Loss: 0.0213
|
38 |
+
- Accuracy: 0.9939
|
39 |
|
40 |
## Model description
|
41 |
|
all_results.json
ADDED
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 5.0,
|
3 |
+
"eval_accuracy": 0.9939200926462073,
|
4 |
+
"eval_loss": 0.021338362246751785,
|
5 |
+
"eval_runtime": 239.8687,
|
6 |
+
"eval_samples_per_second": 14.4,
|
7 |
+
"eval_steps_per_second": 1.801,
|
8 |
+
"train_loss": 0.11058193139753197,
|
9 |
+
"train_runtime": 9068.2818,
|
10 |
+
"train_samples_per_second": 10.791,
|
11 |
+
"train_steps_per_second": 1.349
|
12 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 5.0,
|
3 |
+
"eval_accuracy": 0.9939200926462073,
|
4 |
+
"eval_loss": 0.021338362246751785,
|
5 |
+
"eval_runtime": 239.8687,
|
6 |
+
"eval_samples_per_second": 14.4,
|
7 |
+
"eval_steps_per_second": 1.801
|
8 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 5.0,
|
3 |
+
"train_loss": 0.11058193139753197,
|
4 |
+
"train_runtime": 9068.2818,
|
5 |
+
"train_samples_per_second": 10.791,
|
6 |
+
"train_steps_per_second": 1.349
|
7 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,217 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.021338362246751785,
|
3 |
+
"best_model_checkpoint": "/workspace/training_output/age-gender-vit-large-patch16-224-in21k-v2/checkpoint-9788",
|
4 |
+
"epoch": 5.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 12235,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.2,
|
13 |
+
"learning_rate": 1.918267266040049e-05,
|
14 |
+
"loss": 0.3012,
|
15 |
+
"step": 500
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 0.41,
|
19 |
+
"learning_rate": 1.836534532080098e-05,
|
20 |
+
"loss": 0.2093,
|
21 |
+
"step": 1000
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"epoch": 0.61,
|
25 |
+
"learning_rate": 1.7548017981201474e-05,
|
26 |
+
"loss": 0.1836,
|
27 |
+
"step": 1500
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 0.82,
|
31 |
+
"learning_rate": 1.6730690641601963e-05,
|
32 |
+
"loss": 0.1758,
|
33 |
+
"step": 2000
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 1.0,
|
37 |
+
"eval_accuracy": 0.9863925883034164,
|
38 |
+
"eval_loss": 0.04839900881052017,
|
39 |
+
"eval_runtime": 252.348,
|
40 |
+
"eval_samples_per_second": 13.687,
|
41 |
+
"eval_steps_per_second": 1.712,
|
42 |
+
"step": 2447
|
43 |
+
},
|
44 |
+
{
|
45 |
+
"epoch": 1.02,
|
46 |
+
"learning_rate": 1.5913363302002453e-05,
|
47 |
+
"loss": 0.157,
|
48 |
+
"step": 2500
|
49 |
+
},
|
50 |
+
{
|
51 |
+
"epoch": 1.23,
|
52 |
+
"learning_rate": 1.5096035962402944e-05,
|
53 |
+
"loss": 0.1331,
|
54 |
+
"step": 3000
|
55 |
+
},
|
56 |
+
{
|
57 |
+
"epoch": 1.43,
|
58 |
+
"learning_rate": 1.4278708622803434e-05,
|
59 |
+
"loss": 0.1351,
|
60 |
+
"step": 3500
|
61 |
+
},
|
62 |
+
{
|
63 |
+
"epoch": 1.63,
|
64 |
+
"learning_rate": 1.3461381283203925e-05,
|
65 |
+
"loss": 0.1333,
|
66 |
+
"step": 4000
|
67 |
+
},
|
68 |
+
{
|
69 |
+
"epoch": 1.84,
|
70 |
+
"learning_rate": 1.2644053943604415e-05,
|
71 |
+
"loss": 0.1123,
|
72 |
+
"step": 4500
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 2.0,
|
76 |
+
"eval_accuracy": 0.980023161551824,
|
77 |
+
"eval_loss": 0.0850570872426033,
|
78 |
+
"eval_runtime": 231.2388,
|
79 |
+
"eval_samples_per_second": 14.937,
|
80 |
+
"eval_steps_per_second": 1.868,
|
81 |
+
"step": 4894
|
82 |
+
},
|
83 |
+
{
|
84 |
+
"epoch": 2.04,
|
85 |
+
"learning_rate": 1.1826726604004906e-05,
|
86 |
+
"loss": 0.1151,
|
87 |
+
"step": 5000
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 2.25,
|
91 |
+
"learning_rate": 1.1009399264405396e-05,
|
92 |
+
"loss": 0.0985,
|
93 |
+
"step": 5500
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 2.45,
|
97 |
+
"learning_rate": 1.0192071924805887e-05,
|
98 |
+
"loss": 0.0941,
|
99 |
+
"step": 6000
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 2.66,
|
103 |
+
"learning_rate": 9.374744585206375e-06,
|
104 |
+
"loss": 0.1066,
|
105 |
+
"step": 6500
|
106 |
+
},
|
107 |
+
{
|
108 |
+
"epoch": 2.86,
|
109 |
+
"learning_rate": 8.557417245606866e-06,
|
110 |
+
"loss": 0.0922,
|
111 |
+
"step": 7000
|
112 |
+
},
|
113 |
+
{
|
114 |
+
"epoch": 3.0,
|
115 |
+
"eval_accuracy": 0.9910248986682108,
|
116 |
+
"eval_loss": 0.034099191427230835,
|
117 |
+
"eval_runtime": 239.3405,
|
118 |
+
"eval_samples_per_second": 14.431,
|
119 |
+
"eval_steps_per_second": 1.805,
|
120 |
+
"step": 7341
|
121 |
+
},
|
122 |
+
{
|
123 |
+
"epoch": 3.06,
|
124 |
+
"learning_rate": 7.740089906007356e-06,
|
125 |
+
"loss": 0.091,
|
126 |
+
"step": 7500
|
127 |
+
},
|
128 |
+
{
|
129 |
+
"epoch": 3.27,
|
130 |
+
"learning_rate": 6.922762566407847e-06,
|
131 |
+
"loss": 0.0666,
|
132 |
+
"step": 8000
|
133 |
+
},
|
134 |
+
{
|
135 |
+
"epoch": 3.47,
|
136 |
+
"learning_rate": 6.105435226808338e-06,
|
137 |
+
"loss": 0.0667,
|
138 |
+
"step": 8500
|
139 |
+
},
|
140 |
+
{
|
141 |
+
"epoch": 3.68,
|
142 |
+
"learning_rate": 5.288107887208827e-06,
|
143 |
+
"loss": 0.0727,
|
144 |
+
"step": 9000
|
145 |
+
},
|
146 |
+
{
|
147 |
+
"epoch": 3.88,
|
148 |
+
"learning_rate": 4.470780547609318e-06,
|
149 |
+
"loss": 0.0592,
|
150 |
+
"step": 9500
|
151 |
+
},
|
152 |
+
{
|
153 |
+
"epoch": 4.0,
|
154 |
+
"eval_accuracy": 0.9939200926462073,
|
155 |
+
"eval_loss": 0.021338362246751785,
|
156 |
+
"eval_runtime": 246.6506,
|
157 |
+
"eval_samples_per_second": 14.004,
|
158 |
+
"eval_steps_per_second": 1.751,
|
159 |
+
"step": 9788
|
160 |
+
},
|
161 |
+
{
|
162 |
+
"epoch": 4.09,
|
163 |
+
"learning_rate": 3.6534532080098086e-06,
|
164 |
+
"loss": 0.0646,
|
165 |
+
"step": 10000
|
166 |
+
},
|
167 |
+
{
|
168 |
+
"epoch": 4.29,
|
169 |
+
"learning_rate": 2.8361258684102986e-06,
|
170 |
+
"loss": 0.0601,
|
171 |
+
"step": 10500
|
172 |
+
},
|
173 |
+
{
|
174 |
+
"epoch": 4.5,
|
175 |
+
"learning_rate": 2.018798528810789e-06,
|
176 |
+
"loss": 0.0556,
|
177 |
+
"step": 11000
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 4.7,
|
181 |
+
"learning_rate": 1.201471189211279e-06,
|
182 |
+
"loss": 0.0506,
|
183 |
+
"step": 11500
|
184 |
+
},
|
185 |
+
{
|
186 |
+
"epoch": 4.9,
|
187 |
+
"learning_rate": 3.841438496117696e-07,
|
188 |
+
"loss": 0.053,
|
189 |
+
"step": 12000
|
190 |
+
},
|
191 |
+
{
|
192 |
+
"epoch": 5.0,
|
193 |
+
"eval_accuracy": 0.9942096120440069,
|
194 |
+
"eval_loss": 0.02587772160768509,
|
195 |
+
"eval_runtime": 241.5304,
|
196 |
+
"eval_samples_per_second": 14.3,
|
197 |
+
"eval_steps_per_second": 1.789,
|
198 |
+
"step": 12235
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 5.0,
|
202 |
+
"step": 12235,
|
203 |
+
"total_flos": 2.6807470622410383e+19,
|
204 |
+
"train_loss": 0.11058193139753197,
|
205 |
+
"train_runtime": 9068.2818,
|
206 |
+
"train_samples_per_second": 10.791,
|
207 |
+
"train_steps_per_second": 1.349
|
208 |
+
}
|
209 |
+
],
|
210 |
+
"logging_steps": 500,
|
211 |
+
"max_steps": 12235,
|
212 |
+
"num_train_epochs": 5,
|
213 |
+
"save_steps": 500,
|
214 |
+
"total_flos": 2.6807470622410383e+19,
|
215 |
+
"trial_name": null,
|
216 |
+
"trial_params": null
|
217 |
+
}
|