polejowska commited on
Commit
5571b11
1 Parent(s): 0cded09

End of training

Browse files
Files changed (1) hide show
  1. trainer_state.json +165 -0
trainer_state.json ADDED
@@ -0,0 +1,165 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.9491861462593079,
3
+ "best_model_checkpoint": "detr-r50-cd45rb-8ah-4l-f-c\\checkpoint-46060",
4
+ "epoch": 10.0,
5
+ "global_step": 46060,
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": 9.001519756838908e-06,
13
+ "loss": 1.9191,
14
+ "step": 4606
15
+ },
16
+ {
17
+ "epoch": 1.0,
18
+ "eval_loss": 1.2036592960357666,
19
+ "eval_runtime": 233.3951,
20
+ "eval_samples_per_second": 7.631,
21
+ "eval_steps_per_second": 0.955,
22
+ "step": 4606
23
+ },
24
+ {
25
+ "epoch": 2.0,
26
+ "learning_rate": 8.002171081198438e-06,
27
+ "loss": 1.5088,
28
+ "step": 9212
29
+ },
30
+ {
31
+ "epoch": 2.0,
32
+ "eval_loss": 1.09281587600708,
33
+ "eval_runtime": 232.4582,
34
+ "eval_samples_per_second": 7.662,
35
+ "eval_steps_per_second": 0.959,
36
+ "step": 9212
37
+ },
38
+ {
39
+ "epoch": 3.0,
40
+ "learning_rate": 7.0023881893182814e-06,
41
+ "loss": 1.4004,
42
+ "step": 13818
43
+ },
44
+ {
45
+ "epoch": 3.0,
46
+ "eval_loss": 1.0351686477661133,
47
+ "eval_runtime": 231.5449,
48
+ "eval_samples_per_second": 7.692,
49
+ "eval_steps_per_second": 0.963,
50
+ "step": 13818
51
+ },
52
+ {
53
+ "epoch": 4.0,
54
+ "learning_rate": 6.002822405557969e-06,
55
+ "loss": 1.3481,
56
+ "step": 18424
57
+ },
58
+ {
59
+ "epoch": 4.0,
60
+ "eval_loss": 1.0199804306030273,
61
+ "eval_runtime": 230.3809,
62
+ "eval_samples_per_second": 7.731,
63
+ "eval_steps_per_second": 0.968,
64
+ "step": 18424
65
+ },
66
+ {
67
+ "epoch": 5.0,
68
+ "learning_rate": 5.0034737299175e-06,
69
+ "loss": 1.3104,
70
+ "step": 23030
71
+ },
72
+ {
73
+ "epoch": 5.0,
74
+ "eval_loss": 1.0002790689468384,
75
+ "eval_runtime": 231.2382,
76
+ "eval_samples_per_second": 7.702,
77
+ "eval_steps_per_second": 0.964,
78
+ "step": 23030
79
+ },
80
+ {
81
+ "epoch": 6.0,
82
+ "learning_rate": 4.003907946157187e-06,
83
+ "loss": 1.2791,
84
+ "step": 27636
85
+ },
86
+ {
87
+ "epoch": 6.0,
88
+ "eval_loss": 1.0887064933776855,
89
+ "eval_runtime": 195.9195,
90
+ "eval_samples_per_second": 9.09,
91
+ "eval_steps_per_second": 1.138,
92
+ "step": 27636
93
+ },
94
+ {
95
+ "epoch": 7.0,
96
+ "learning_rate": 3.00412505427703e-06,
97
+ "loss": 1.2555,
98
+ "step": 32242
99
+ },
100
+ {
101
+ "epoch": 7.0,
102
+ "eval_loss": 0.9726870656013489,
103
+ "eval_runtime": 197.9362,
104
+ "eval_samples_per_second": 8.998,
105
+ "eval_steps_per_second": 1.127,
106
+ "step": 32242
107
+ },
108
+ {
109
+ "epoch": 8.0,
110
+ "learning_rate": 2.0045592705167173e-06,
111
+ "loss": 1.2354,
112
+ "step": 36848
113
+ },
114
+ {
115
+ "epoch": 8.0,
116
+ "eval_loss": 0.9574904441833496,
117
+ "eval_runtime": 198.5985,
118
+ "eval_samples_per_second": 8.968,
119
+ "eval_steps_per_second": 1.123,
120
+ "step": 36848
121
+ },
122
+ {
123
+ "epoch": 9.0,
124
+ "learning_rate": 1.0049934867564047e-06,
125
+ "loss": 1.2231,
126
+ "step": 41454
127
+ },
128
+ {
129
+ "epoch": 9.0,
130
+ "eval_loss": 0.9551559090614319,
131
+ "eval_runtime": 197.7002,
132
+ "eval_samples_per_second": 9.009,
133
+ "eval_steps_per_second": 1.128,
134
+ "step": 41454
135
+ },
136
+ {
137
+ "epoch": 10.0,
138
+ "learning_rate": 5.427702996092055e-09,
139
+ "loss": 1.212,
140
+ "step": 46060
141
+ },
142
+ {
143
+ "epoch": 10.0,
144
+ "eval_loss": 0.9491861462593079,
145
+ "eval_runtime": 216.4233,
146
+ "eval_samples_per_second": 8.229,
147
+ "eval_steps_per_second": 1.03,
148
+ "step": 46060
149
+ },
150
+ {
151
+ "epoch": 10.0,
152
+ "step": 46060,
153
+ "total_flos": 7.575060159014402e+19,
154
+ "train_loss": 1.3691692582535009,
155
+ "train_runtime": 30392.7009,
156
+ "train_samples_per_second": 6.061,
157
+ "train_steps_per_second": 1.515
158
+ }
159
+ ],
160
+ "max_steps": 46060,
161
+ "num_train_epochs": 10,
162
+ "total_flos": 7.575060159014402e+19,
163
+ "trial_name": null,
164
+ "trial_params": null
165
+ }