moooji commited on
Commit
7d6da1a
1 Parent(s): 047904f

End of training

Browse files
Files changed (5) hide show
  1. README.md +4 -2
  2. all_results.json +12 -0
  3. eval_results.json +8 -0
  4. train_results.json +7 -0
  5. 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: imagefolder
18
  type: imagefolder
19
  config: default
20
  split: train
@@ -30,7 +32,7 @@ should probably proofread and complete it, then remove this comment. -->
30
 
31
  # fashion-images-gender-age-vit-large-patch16-224-in21k
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 imagefolder dataset.
34
  It achieves the following results on the evaluation set:
35
  - Loss: 0.0276
36
  - Accuracy: 0.9944
 
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
 
32
 
33
  # fashion-images-gender-age-vit-large-patch16-224-in21k
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: 0.0276
38
  - Accuracy: 0.9944
all_results.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.0,
3
+ "eval_accuracy": 0.9944444444444445,
4
+ "eval_loss": 0.027647286653518677,
5
+ "eval_runtime": 252.7502,
6
+ "eval_samples_per_second": 13.531,
7
+ "eval_steps_per_second": 1.693,
8
+ "train_loss": 0.10462298566501659,
9
+ "train_runtime": 9666.7071,
10
+ "train_samples_per_second": 10.021,
11
+ "train_steps_per_second": 1.253
12
+ }
eval_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.0,
3
+ "eval_accuracy": 0.9944444444444445,
4
+ "eval_loss": 0.027647286653518677,
5
+ "eval_runtime": 252.7502,
6
+ "eval_samples_per_second": 13.531,
7
+ "eval_steps_per_second": 1.693
8
+ }
train_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.0,
3
+ "train_loss": 0.10462298566501659,
4
+ "train_runtime": 9666.7071,
5
+ "train_samples_per_second": 10.021,
6
+ "train_steps_per_second": 1.253
7
+ }
trainer_state.json ADDED
@@ -0,0 +1,217 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.027647286653518677,
3
+ "best_model_checkpoint": "/workspace/training_output/age-gender-vit-large-patch16-224-in21k/checkpoint-12110",
4
+ "epoch": 5.0,
5
+ "eval_steps": 500,
6
+ "global_step": 12110,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.21,
13
+ "learning_rate": 1.9174236168455824e-05,
14
+ "loss": 0.2922,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 0.41,
19
+ "learning_rate": 1.8348472336911643e-05,
20
+ "loss": 0.2144,
21
+ "step": 1000
22
+ },
23
+ {
24
+ "epoch": 0.62,
25
+ "learning_rate": 1.752270850536747e-05,
26
+ "loss": 0.1678,
27
+ "step": 1500
28
+ },
29
+ {
30
+ "epoch": 0.83,
31
+ "learning_rate": 1.6696944673823288e-05,
32
+ "loss": 0.1615,
33
+ "step": 2000
34
+ },
35
+ {
36
+ "epoch": 1.0,
37
+ "eval_accuracy": 0.9847953216374269,
38
+ "eval_loss": 0.05505400523543358,
39
+ "eval_runtime": 258.103,
40
+ "eval_samples_per_second": 13.251,
41
+ "eval_steps_per_second": 1.658,
42
+ "step": 2422
43
+ },
44
+ {
45
+ "epoch": 1.03,
46
+ "learning_rate": 1.587118084227911e-05,
47
+ "loss": 0.1614,
48
+ "step": 2500
49
+ },
50
+ {
51
+ "epoch": 1.24,
52
+ "learning_rate": 1.5045417010734931e-05,
53
+ "loss": 0.1273,
54
+ "step": 3000
55
+ },
56
+ {
57
+ "epoch": 1.45,
58
+ "learning_rate": 1.4219653179190754e-05,
59
+ "loss": 0.1361,
60
+ "step": 3500
61
+ },
62
+ {
63
+ "epoch": 1.65,
64
+ "learning_rate": 1.3393889347646574e-05,
65
+ "loss": 0.1256,
66
+ "step": 4000
67
+ },
68
+ {
69
+ "epoch": 1.86,
70
+ "learning_rate": 1.2568125516102397e-05,
71
+ "loss": 0.1032,
72
+ "step": 4500
73
+ },
74
+ {
75
+ "epoch": 2.0,
76
+ "eval_accuracy": 0.9903508771929824,
77
+ "eval_loss": 0.040435414761304855,
78
+ "eval_runtime": 263.0983,
79
+ "eval_samples_per_second": 12.999,
80
+ "eval_steps_per_second": 1.627,
81
+ "step": 4844
82
+ },
83
+ {
84
+ "epoch": 2.06,
85
+ "learning_rate": 1.1742361684558218e-05,
86
+ "loss": 0.1154,
87
+ "step": 5000
88
+ },
89
+ {
90
+ "epoch": 2.27,
91
+ "learning_rate": 1.091659785301404e-05,
92
+ "loss": 0.0984,
93
+ "step": 5500
94
+ },
95
+ {
96
+ "epoch": 2.48,
97
+ "learning_rate": 1.0090834021469859e-05,
98
+ "loss": 0.087,
99
+ "step": 6000
100
+ },
101
+ {
102
+ "epoch": 2.68,
103
+ "learning_rate": 9.265070189925683e-06,
104
+ "loss": 0.0889,
105
+ "step": 6500
106
+ },
107
+ {
108
+ "epoch": 2.89,
109
+ "learning_rate": 8.439306358381504e-06,
110
+ "loss": 0.095,
111
+ "step": 7000
112
+ },
113
+ {
114
+ "epoch": 3.0,
115
+ "eval_accuracy": 0.9903508771929824,
116
+ "eval_loss": 0.04800451546907425,
117
+ "eval_runtime": 255.5823,
118
+ "eval_samples_per_second": 13.381,
119
+ "eval_steps_per_second": 1.675,
120
+ "step": 7266
121
+ },
122
+ {
123
+ "epoch": 3.1,
124
+ "learning_rate": 7.6135425268373255e-06,
125
+ "loss": 0.0604,
126
+ "step": 7500
127
+ },
128
+ {
129
+ "epoch": 3.3,
130
+ "learning_rate": 6.787778695293147e-06,
131
+ "loss": 0.0647,
132
+ "step": 8000
133
+ },
134
+ {
135
+ "epoch": 3.51,
136
+ "learning_rate": 5.962014863748969e-06,
137
+ "loss": 0.0585,
138
+ "step": 8500
139
+ },
140
+ {
141
+ "epoch": 3.72,
142
+ "learning_rate": 5.13625103220479e-06,
143
+ "loss": 0.0746,
144
+ "step": 9000
145
+ },
146
+ {
147
+ "epoch": 3.92,
148
+ "learning_rate": 4.310487200660611e-06,
149
+ "loss": 0.0599,
150
+ "step": 9500
151
+ },
152
+ {
153
+ "epoch": 4.0,
154
+ "eval_accuracy": 0.9923976608187135,
155
+ "eval_loss": 0.03288862109184265,
156
+ "eval_runtime": 256.4303,
157
+ "eval_samples_per_second": 13.337,
158
+ "eval_steps_per_second": 1.669,
159
+ "step": 9688
160
+ },
161
+ {
162
+ "epoch": 4.13,
163
+ "learning_rate": 3.484723369116433e-06,
164
+ "loss": 0.0452,
165
+ "step": 10000
166
+ },
167
+ {
168
+ "epoch": 4.34,
169
+ "learning_rate": 2.658959537572254e-06,
170
+ "loss": 0.0528,
171
+ "step": 10500
172
+ },
173
+ {
174
+ "epoch": 4.54,
175
+ "learning_rate": 1.8331957060280761e-06,
176
+ "loss": 0.045,
177
+ "step": 11000
178
+ },
179
+ {
180
+ "epoch": 4.75,
181
+ "learning_rate": 1.0074318744838975e-06,
182
+ "loss": 0.0504,
183
+ "step": 11500
184
+ },
185
+ {
186
+ "epoch": 4.95,
187
+ "learning_rate": 1.8166804293971927e-07,
188
+ "loss": 0.0386,
189
+ "step": 12000
190
+ },
191
+ {
192
+ "epoch": 5.0,
193
+ "eval_accuracy": 0.9944444444444445,
194
+ "eval_loss": 0.027647286653518677,
195
+ "eval_runtime": 295.0164,
196
+ "eval_samples_per_second": 11.593,
197
+ "eval_steps_per_second": 1.451,
198
+ "step": 12110
199
+ },
200
+ {
201
+ "epoch": 5.0,
202
+ "step": 12110,
203
+ "total_flos": 2.653627303487527e+19,
204
+ "train_loss": 0.10462298566501659,
205
+ "train_runtime": 9666.7071,
206
+ "train_samples_per_second": 10.021,
207
+ "train_steps_per_second": 1.253
208
+ }
209
+ ],
210
+ "logging_steps": 500,
211
+ "max_steps": 12110,
212
+ "num_train_epochs": 5,
213
+ "save_steps": 500,
214
+ "total_flos": 2.653627303487527e+19,
215
+ "trial_name": null,
216
+ "trial_params": null
217
+ }