Riyagarg01 commited on
Commit
fa736c0
1 Parent(s): ccf6834

Upload trainer_state.json

Browse files
Files changed (1) hide show
  1. trainer_state.json +136 -0
trainer_state.json ADDED
@@ -0,0 +1,136 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 45.45454545454545,
5
+ "global_step": 1000,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 2.27,
12
+ "learning_rate": 3e-06,
13
+ "loss": 7.7644,
14
+ "step": 50
15
+ },
16
+ {
17
+ "epoch": 4.55,
18
+ "learning_rate": 6e-06,
19
+ "loss": 4.0219,
20
+ "step": 100
21
+ },
22
+ {
23
+ "epoch": 6.82,
24
+ "learning_rate": 9e-06,
25
+ "loss": 2.3865,
26
+ "step": 150
27
+ },
28
+ {
29
+ "epoch": 9.09,
30
+ "learning_rate": 1.2e-05,
31
+ "loss": 2.0278,
32
+ "step": 200
33
+ },
34
+ {
35
+ "epoch": 11.36,
36
+ "learning_rate": 1.5e-05,
37
+ "loss": 1.8286,
38
+ "step": 250
39
+ },
40
+ {
41
+ "epoch": 13.64,
42
+ "learning_rate": 1.8e-05,
43
+ "loss": 1.721,
44
+ "step": 300
45
+ },
46
+ {
47
+ "epoch": 15.91,
48
+ "learning_rate": 2.1e-05,
49
+ "loss": 1.6587,
50
+ "step": 350
51
+ },
52
+ {
53
+ "epoch": 18.18,
54
+ "learning_rate": 2.4e-05,
55
+ "loss": 1.6102,
56
+ "step": 400
57
+ },
58
+ {
59
+ "epoch": 20.45,
60
+ "learning_rate": 2.7000000000000002e-05,
61
+ "loss": 1.5738,
62
+ "step": 450
63
+ },
64
+ {
65
+ "epoch": 22.73,
66
+ "learning_rate": 3e-05,
67
+ "loss": 1.5536,
68
+ "step": 500
69
+ },
70
+ {
71
+ "epoch": 25.0,
72
+ "learning_rate": 2.911764705882353e-05,
73
+ "loss": 1.5398,
74
+ "step": 550
75
+ },
76
+ {
77
+ "epoch": 27.27,
78
+ "learning_rate": 2.823529411764706e-05,
79
+ "loss": 1.5346,
80
+ "step": 600
81
+ },
82
+ {
83
+ "epoch": 29.55,
84
+ "learning_rate": 2.735294117647059e-05,
85
+ "loss": 1.5068,
86
+ "step": 650
87
+ },
88
+ {
89
+ "epoch": 31.82,
90
+ "learning_rate": 2.647058823529412e-05,
91
+ "loss": 1.5084,
92
+ "step": 700
93
+ },
94
+ {
95
+ "epoch": 34.09,
96
+ "learning_rate": 2.5588235294117648e-05,
97
+ "loss": 1.497,
98
+ "step": 750
99
+ },
100
+ {
101
+ "epoch": 36.36,
102
+ "learning_rate": 2.4705882352941174e-05,
103
+ "loss": 1.4906,
104
+ "step": 800
105
+ },
106
+ {
107
+ "epoch": 38.64,
108
+ "learning_rate": 2.3823529411764704e-05,
109
+ "loss": 1.4887,
110
+ "step": 850
111
+ },
112
+ {
113
+ "epoch": 40.91,
114
+ "learning_rate": 2.2941176470588233e-05,
115
+ "loss": 1.4765,
116
+ "step": 900
117
+ },
118
+ {
119
+ "epoch": 43.18,
120
+ "learning_rate": 2.2058823529411766e-05,
121
+ "loss": 1.4792,
122
+ "step": 950
123
+ },
124
+ {
125
+ "epoch": 45.45,
126
+ "learning_rate": 2.1176470588235296e-05,
127
+ "loss": 1.473,
128
+ "step": 1000
129
+ }
130
+ ],
131
+ "max_steps": 2200,
132
+ "num_train_epochs": 100,
133
+ "total_flos": 2356631411097600.0,
134
+ "trial_name": null,
135
+ "trial_params": null
136
+ }