polejowska
commited on
Commit
•
3c80d68
1
Parent(s):
cd2b39a
End of training
Browse files- trainer_state.json +165 -0
trainer_state.json
ADDED
@@ -0,0 +1,165 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 1.8343534469604492,
|
3 |
+
"best_model_checkpoint": "cdetr-r50-cd45rb-all-4ah\\checkpoint-23030",
|
4 |
+
"epoch": 10.0,
|
5 |
+
"global_step": 23030,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 1.0,
|
12 |
+
"learning_rate": 9.003039513677813e-06,
|
13 |
+
"loss": 2.165,
|
14 |
+
"step": 2303
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 1.0,
|
18 |
+
"eval_loss": 2.0256807804107666,
|
19 |
+
"eval_runtime": 417.1917,
|
20 |
+
"eval_samples_per_second": 4.269,
|
21 |
+
"eval_steps_per_second": 0.535,
|
22 |
+
"step": 2303
|
23 |
+
},
|
24 |
+
{
|
25 |
+
"epoch": 2.0,
|
26 |
+
"learning_rate": 8.003907946157187e-06,
|
27 |
+
"loss": 1.9843,
|
28 |
+
"step": 4606
|
29 |
+
},
|
30 |
+
{
|
31 |
+
"epoch": 2.0,
|
32 |
+
"eval_loss": 1.9741652011871338,
|
33 |
+
"eval_runtime": 403.5768,
|
34 |
+
"eval_samples_per_second": 4.413,
|
35 |
+
"eval_steps_per_second": 0.553,
|
36 |
+
"step": 4606
|
37 |
+
},
|
38 |
+
{
|
39 |
+
"epoch": 3.0,
|
40 |
+
"learning_rate": 7.003907946157187e-06,
|
41 |
+
"loss": 1.9296,
|
42 |
+
"step": 6909
|
43 |
+
},
|
44 |
+
{
|
45 |
+
"epoch": 3.0,
|
46 |
+
"eval_loss": 1.9122804403305054,
|
47 |
+
"eval_runtime": 401.3575,
|
48 |
+
"eval_samples_per_second": 4.437,
|
49 |
+
"eval_steps_per_second": 0.556,
|
50 |
+
"step": 6909
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 4.0,
|
54 |
+
"learning_rate": 6.0043421623968744e-06,
|
55 |
+
"loss": 1.8949,
|
56 |
+
"step": 9212
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 4.0,
|
60 |
+
"eval_loss": 1.8927873373031616,
|
61 |
+
"eval_runtime": 408.1494,
|
62 |
+
"eval_samples_per_second": 4.364,
|
63 |
+
"eval_steps_per_second": 0.546,
|
64 |
+
"step": 9212
|
65 |
+
},
|
66 |
+
{
|
67 |
+
"epoch": 5.0,
|
68 |
+
"learning_rate": 5.005210594876249e-06,
|
69 |
+
"loss": 1.8751,
|
70 |
+
"step": 11515
|
71 |
+
},
|
72 |
+
{
|
73 |
+
"epoch": 5.0,
|
74 |
+
"eval_loss": 1.9116449356079102,
|
75 |
+
"eval_runtime": 406.0082,
|
76 |
+
"eval_samples_per_second": 4.387,
|
77 |
+
"eval_steps_per_second": 0.549,
|
78 |
+
"step": 11515
|
79 |
+
},
|
80 |
+
{
|
81 |
+
"epoch": 6.0,
|
82 |
+
"learning_rate": 4.005210594876249e-06,
|
83 |
+
"loss": 1.854,
|
84 |
+
"step": 13818
|
85 |
+
},
|
86 |
+
{
|
87 |
+
"epoch": 6.0,
|
88 |
+
"eval_loss": 1.8909248113632202,
|
89 |
+
"eval_runtime": 396.4567,
|
90 |
+
"eval_samples_per_second": 4.492,
|
91 |
+
"eval_steps_per_second": 0.562,
|
92 |
+
"step": 13818
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 7.0,
|
96 |
+
"learning_rate": 3.005644811115936e-06,
|
97 |
+
"loss": 1.8354,
|
98 |
+
"step": 16121
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 7.0,
|
102 |
+
"eval_loss": 1.8532779216766357,
|
103 |
+
"eval_runtime": 390.3322,
|
104 |
+
"eval_samples_per_second": 4.563,
|
105 |
+
"eval_steps_per_second": 0.571,
|
106 |
+
"step": 16121
|
107 |
+
},
|
108 |
+
{
|
109 |
+
"epoch": 8.0,
|
110 |
+
"learning_rate": 2.0060790273556234e-06,
|
111 |
+
"loss": 1.8257,
|
112 |
+
"step": 18424
|
113 |
+
},
|
114 |
+
{
|
115 |
+
"epoch": 8.0,
|
116 |
+
"eval_loss": 1.8406795263290405,
|
117 |
+
"eval_runtime": 388.3033,
|
118 |
+
"eval_samples_per_second": 4.587,
|
119 |
+
"eval_steps_per_second": 0.574,
|
120 |
+
"step": 18424
|
121 |
+
},
|
122 |
+
{
|
123 |
+
"epoch": 9.0,
|
124 |
+
"learning_rate": 1.0060790273556232e-06,
|
125 |
+
"loss": 1.8101,
|
126 |
+
"step": 20727
|
127 |
+
},
|
128 |
+
{
|
129 |
+
"epoch": 9.0,
|
130 |
+
"eval_loss": 1.8452762365341187,
|
131 |
+
"eval_runtime": 395.2037,
|
132 |
+
"eval_samples_per_second": 4.507,
|
133 |
+
"eval_steps_per_second": 0.564,
|
134 |
+
"step": 20727
|
135 |
+
},
|
136 |
+
{
|
137 |
+
"epoch": 10.0,
|
138 |
+
"learning_rate": 6.947459834997829e-09,
|
139 |
+
"loss": 1.8025,
|
140 |
+
"step": 23030
|
141 |
+
},
|
142 |
+
{
|
143 |
+
"epoch": 10.0,
|
144 |
+
"eval_loss": 1.8343534469604492,
|
145 |
+
"eval_runtime": 390.5312,
|
146 |
+
"eval_samples_per_second": 4.56,
|
147 |
+
"eval_steps_per_second": 0.571,
|
148 |
+
"step": 23030
|
149 |
+
},
|
150 |
+
{
|
151 |
+
"epoch": 10.0,
|
152 |
+
"step": 23030,
|
153 |
+
"total_flos": 9.19423903761792e+19,
|
154 |
+
"train_loss": 1.8976711761832392,
|
155 |
+
"train_runtime": 56257.2381,
|
156 |
+
"train_samples_per_second": 3.274,
|
157 |
+
"train_steps_per_second": 0.409
|
158 |
+
}
|
159 |
+
],
|
160 |
+
"max_steps": 23030,
|
161 |
+
"num_train_epochs": 10,
|
162 |
+
"total_flos": 9.19423903761792e+19,
|
163 |
+
"trial_name": null,
|
164 |
+
"trial_params": null
|
165 |
+
}
|