Hugging Face's logo

polejowska
/
detr-r50-cd45rb-8ah-6l-gelu-corrected

Object Detection
Transformers
PyTorch
detr
Generated from Trainer
Inference Endpoints
Model card Files Community
2
polejowska commited on
Commit
d17d71f
•
1 Parent(s): cb0eea8

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": 1.639158010482788,
3
+ "best_model_checkpoint": "detr-r50-cd45rb-8ah-6l-gelu-corrected\\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": 9.00238818931828e-06,
13
+ "loss": 3.0438,
14
+ "step": 4606
15
+ },
16
+ {
17
+ "epoch": 1.0,
18
+ "eval_loss": 1.9413050413131714,
19
+ "eval_runtime": 201.9196,
20
+ "eval_samples_per_second": 8.82,
21
+ "eval_steps_per_second": 1.104,
22
+ "step": 4606
23
+ },
24
+ {
25
+ "epoch": 2.0,
26
+ "learning_rate": 8.002822405557968e-06,
27
+ "loss": 2.3933,
28
+ "step": 9212
29
+ },
30
+ {
31
+ "epoch": 2.0,
32
+ "eval_loss": 1.8238338232040405,
33
+ "eval_runtime": 202.1836,
34
+ "eval_samples_per_second": 8.809,
35
+ "eval_steps_per_second": 1.103,
36
+ "step": 9212
37
+ },
38
+ {
39
+ "epoch": 3.0,
40
+ "learning_rate": 7.003039513677812e-06,
41
+ "loss": 2.2782,
42
+ "step": 13818
43
+ },
44
+ {
45
+ "epoch": 3.0,
46
+ "eval_loss": 1.771848440170288,
47
+ "eval_runtime": 202.1516,
48
+ "eval_samples_per_second": 8.81,
49
+ "eval_steps_per_second": 1.103,
50
+ "step": 13818
51
+ },
52
+ {
53
+ "epoch": 4.0,
54
+ "learning_rate": 6.003473729917499e-06,
55
+ "loss": 2.2383,
56
+ "step": 18424
57
+ },
58
+ {
59
+ "epoch": 4.0,
60
+ "eval_loss": 1.752848505973816,
61
+ "eval_runtime": 202.2922,
62
+ "eval_samples_per_second": 8.804,
63
+ "eval_steps_per_second": 1.102,
64
+ "step": 18424
65
+ },
66
+ {
67
+ "epoch": 5.0,
68
+ "learning_rate": 5.003690838037343e-06,
69
+ "loss": 2.2046,
70
+ "step": 23030
71
+ },
72
+ {
73
+ "epoch": 5.0,
74
+ "eval_loss": 1.7264593839645386,
75
+ "eval_runtime": 201.788,
76
+ "eval_samples_per_second": 8.826,
77
+ "eval_steps_per_second": 1.105,
78
+ "step": 23030
79
+ },
80
+ {
81
+ "epoch": 6.0,
82
+ "learning_rate": 4.0041250542770305e-06,
83
+ "loss": 2.1659,
84
+ "step": 27636
85
+ },
86
+ {
87
+ "epoch": 6.0,
88
+ "eval_loss": 1.7125098705291748,
89
+ "eval_runtime": 202.0053,
90
+ "eval_samples_per_second": 8.817,
91
+ "eval_steps_per_second": 1.104,
92
+ "step": 27636
93
+ },
94
+ {
95
+ "epoch": 7.0,
96
+ "learning_rate": 3.0045592705167175e-06,
97
+ "loss": 2.1457,
98
+ "step": 32242
99
+ },
100
+ {
101
+ "epoch": 7.0,
102
+ "eval_loss": 1.6760411262512207,
103
+ "eval_runtime": 201.2859,
104
+ "eval_samples_per_second": 8.848,
105
+ "eval_steps_per_second": 1.108,
106
+ "step": 32242
107
+ },
108
+ {
109
+ "epoch": 8.0,
110
+ "learning_rate": 2.0047763786365613e-06,
111
+ "loss": 2.1111,
112
+ "step": 36848
113
+ },
114
+ {
115
+ "epoch": 8.0,
116
+ "eval_loss": 1.6621686220169067,
117
+ "eval_runtime": 201.2613,
118
+ "eval_samples_per_second": 8.849,
119
+ "eval_steps_per_second": 1.108,
120
+ "step": 36848
121
+ },
122
+ {
123
+ "epoch": 9.0,
124
+ "learning_rate": 1.0052105948762484e-06,
125
+ "loss": 2.0959,
126
+ "step": 41454
127
+ },
128
+ {
129
+ "epoch": 9.0,
130
+ "eval_loss": 1.6466784477233887,
131
+ "eval_runtime": 201.3173,
132
+ "eval_samples_per_second": 8.847,
133
+ "eval_steps_per_second": 1.108,
134
+ "step": 41454
135
+ },
136
+ {
137
+ "epoch": 10.0,
138
+ "learning_rate": 5.427702996092055e-09,
139
+ "loss": 2.0826,
140
+ "step": 46060
141
+ },
142
+ {
143
+ "epoch": 10.0,
144
+ "eval_loss": 1.639158010482788,
145
+ "eval_runtime": 201.0423,
146
+ "eval_samples_per_second": 8.859,
147
+ "eval_steps_per_second": 1.109,
148
+ "step": 46060
149
+ },
150
+ {
151
+ "epoch": 10.0,
152
+ "step": 46060,
153
+ "total_flos": 8.803256478082562e+19,
154
+ "train_loss": 2.275937762904364,
155
+ "train_runtime": 29381.2037,
156
+ "train_samples_per_second": 6.27,
157
+ "train_steps_per_second": 1.568
158
+ }
159
+ ],
160
+ "max_steps": 46060,
161
+ "num_train_epochs": 10,
162
+ "total_flos": 8.803256478082562e+19,
163
+ "trial_name": null,
164
+ "trial_params": null
165
+ }