End of training
Browse files
all_results.json
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 2.97,
|
3 |
+
"eval_accuracy": 0.9965277777777778,
|
4 |
+
"eval_loss": 0.007796453312039375,
|
5 |
+
"eval_runtime": 5.2724,
|
6 |
+
"eval_samples_per_second": 54.624,
|
7 |
+
"eval_steps_per_second": 6.828,
|
8 |
+
"total_flos": 1.9084428343340237e+17,
|
9 |
+
"train_loss": 0.11689412463456392,
|
10 |
+
"train_runtime": 178.3666,
|
11 |
+
"train_samples_per_second": 43.444,
|
12 |
+
"train_steps_per_second": 1.346
|
13 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 2.97,
|
3 |
+
"eval_accuracy": 0.9965277777777778,
|
4 |
+
"eval_loss": 0.007796453312039375,
|
5 |
+
"eval_runtime": 5.2724,
|
6 |
+
"eval_samples_per_second": 54.624,
|
7 |
+
"eval_steps_per_second": 6.828
|
8 |
+
}
|
runs/Apr16_00-37-59_e141a17aebe5/events.out.tfevents.1681605741.e141a17aebe5.1112.6
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9d035c071576469a7101fb297e6bc062f278f341c204e87404674b8407cf3c97
|
3 |
+
size 411
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 2.97,
|
3 |
+
"total_flos": 1.9084428343340237e+17,
|
4 |
+
"train_loss": 0.11689412463456392,
|
5 |
+
"train_runtime": 178.3666,
|
6 |
+
"train_samples_per_second": 43.444,
|
7 |
+
"train_steps_per_second": 1.346
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,196 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.9965277777777778,
|
3 |
+
"best_model_checkpoint": "swin-tiny-patch4-window7-224-long_sleeve/checkpoint-80",
|
4 |
+
"epoch": 2.972136222910217,
|
5 |
+
"global_step": 240,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.12,
|
12 |
+
"learning_rate": 2.0833333333333336e-05,
|
13 |
+
"loss": 0.7149,
|
14 |
+
"step": 10
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.25,
|
18 |
+
"learning_rate": 4.166666666666667e-05,
|
19 |
+
"loss": 0.5408,
|
20 |
+
"step": 20
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.37,
|
24 |
+
"learning_rate": 4.8611111111111115e-05,
|
25 |
+
"loss": 0.2349,
|
26 |
+
"step": 30
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 0.5,
|
30 |
+
"learning_rate": 4.62962962962963e-05,
|
31 |
+
"loss": 0.1318,
|
32 |
+
"step": 40
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 0.62,
|
36 |
+
"learning_rate": 4.3981481481481486e-05,
|
37 |
+
"loss": 0.1089,
|
38 |
+
"step": 50
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.74,
|
42 |
+
"learning_rate": 4.166666666666667e-05,
|
43 |
+
"loss": 0.0902,
|
44 |
+
"step": 60
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.87,
|
48 |
+
"learning_rate": 3.935185185185186e-05,
|
49 |
+
"loss": 0.0907,
|
50 |
+
"step": 70
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 0.99,
|
54 |
+
"learning_rate": 3.7037037037037037e-05,
|
55 |
+
"loss": 0.07,
|
56 |
+
"step": 80
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 0.99,
|
60 |
+
"eval_accuracy": 0.9965277777777778,
|
61 |
+
"eval_loss": 0.007796453312039375,
|
62 |
+
"eval_runtime": 2.8498,
|
63 |
+
"eval_samples_per_second": 101.06,
|
64 |
+
"eval_steps_per_second": 12.632,
|
65 |
+
"step": 80
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 1.11,
|
69 |
+
"learning_rate": 3.472222222222222e-05,
|
70 |
+
"loss": 0.0976,
|
71 |
+
"step": 90
|
72 |
+
},
|
73 |
+
{
|
74 |
+
"epoch": 1.24,
|
75 |
+
"learning_rate": 3.240740740740741e-05,
|
76 |
+
"loss": 0.0694,
|
77 |
+
"step": 100
|
78 |
+
},
|
79 |
+
{
|
80 |
+
"epoch": 1.36,
|
81 |
+
"learning_rate": 3.0092592592592593e-05,
|
82 |
+
"loss": 0.064,
|
83 |
+
"step": 110
|
84 |
+
},
|
85 |
+
{
|
86 |
+
"epoch": 1.49,
|
87 |
+
"learning_rate": 2.777777777777778e-05,
|
88 |
+
"loss": 0.0384,
|
89 |
+
"step": 120
|
90 |
+
},
|
91 |
+
{
|
92 |
+
"epoch": 1.61,
|
93 |
+
"learning_rate": 2.5462962962962965e-05,
|
94 |
+
"loss": 0.0645,
|
95 |
+
"step": 130
|
96 |
+
},
|
97 |
+
{
|
98 |
+
"epoch": 1.73,
|
99 |
+
"learning_rate": 2.314814814814815e-05,
|
100 |
+
"loss": 0.0789,
|
101 |
+
"step": 140
|
102 |
+
},
|
103 |
+
{
|
104 |
+
"epoch": 1.86,
|
105 |
+
"learning_rate": 2.0833333333333336e-05,
|
106 |
+
"loss": 0.0315,
|
107 |
+
"step": 150
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 1.98,
|
111 |
+
"learning_rate": 1.8518518518518518e-05,
|
112 |
+
"loss": 0.0402,
|
113 |
+
"step": 160
|
114 |
+
},
|
115 |
+
{
|
116 |
+
"epoch": 1.99,
|
117 |
+
"eval_accuracy": 0.9965277777777778,
|
118 |
+
"eval_loss": 0.007359893061220646,
|
119 |
+
"eval_runtime": 2.2966,
|
120 |
+
"eval_samples_per_second": 125.405,
|
121 |
+
"eval_steps_per_second": 15.676,
|
122 |
+
"step": 161
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 2.11,
|
126 |
+
"learning_rate": 1.6203703703703704e-05,
|
127 |
+
"loss": 0.0434,
|
128 |
+
"step": 170
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 2.23,
|
132 |
+
"learning_rate": 1.388888888888889e-05,
|
133 |
+
"loss": 0.049,
|
134 |
+
"step": 180
|
135 |
+
},
|
136 |
+
{
|
137 |
+
"epoch": 2.35,
|
138 |
+
"learning_rate": 1.1574074074074075e-05,
|
139 |
+
"loss": 0.0571,
|
140 |
+
"step": 190
|
141 |
+
},
|
142 |
+
{
|
143 |
+
"epoch": 2.48,
|
144 |
+
"learning_rate": 9.259259259259259e-06,
|
145 |
+
"loss": 0.0526,
|
146 |
+
"step": 200
|
147 |
+
},
|
148 |
+
{
|
149 |
+
"epoch": 2.6,
|
150 |
+
"learning_rate": 6.944444444444445e-06,
|
151 |
+
"loss": 0.0285,
|
152 |
+
"step": 210
|
153 |
+
},
|
154 |
+
{
|
155 |
+
"epoch": 2.72,
|
156 |
+
"learning_rate": 4.6296296296296296e-06,
|
157 |
+
"loss": 0.0646,
|
158 |
+
"step": 220
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 2.85,
|
162 |
+
"learning_rate": 2.3148148148148148e-06,
|
163 |
+
"loss": 0.0149,
|
164 |
+
"step": 230
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"epoch": 2.97,
|
168 |
+
"learning_rate": 0.0,
|
169 |
+
"loss": 0.0288,
|
170 |
+
"step": 240
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 2.97,
|
174 |
+
"eval_accuracy": 0.9965277777777778,
|
175 |
+
"eval_loss": 0.00683227414265275,
|
176 |
+
"eval_runtime": 2.3219,
|
177 |
+
"eval_samples_per_second": 124.035,
|
178 |
+
"eval_steps_per_second": 15.504,
|
179 |
+
"step": 240
|
180 |
+
},
|
181 |
+
{
|
182 |
+
"epoch": 2.97,
|
183 |
+
"step": 240,
|
184 |
+
"total_flos": 1.9084428343340237e+17,
|
185 |
+
"train_loss": 0.11689412463456392,
|
186 |
+
"train_runtime": 178.3666,
|
187 |
+
"train_samples_per_second": 43.444,
|
188 |
+
"train_steps_per_second": 1.346
|
189 |
+
}
|
190 |
+
],
|
191 |
+
"max_steps": 240,
|
192 |
+
"num_train_epochs": 3,
|
193 |
+
"total_flos": 1.9084428343340237e+17,
|
194 |
+
"trial_name": null,
|
195 |
+
"trial_params": null
|
196 |
+
}
|