XiaoY1 commited on
Commit
8f83a17
·
verified ·
1 Parent(s): 957fc8c

Upload trainer_state.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. trainer_state.json +2970 -0
trainer_state.json ADDED
@@ -0,0 +1,2970 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 4.962025316455696,
5
+ "eval_steps": 500,
6
+ "global_step": 490,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.01,
13
+ "learning_rate": 0.0,
14
+ "loss": 2.2689,
15
+ "step": 1
16
+ },
17
+ {
18
+ "epoch": 0.02,
19
+ "learning_rate": 4.306765580733931e-06,
20
+ "loss": 1.9111,
21
+ "step": 2
22
+ },
23
+ {
24
+ "epoch": 0.03,
25
+ "learning_rate": 6.826061944859854e-06,
26
+ "loss": 2.0757,
27
+ "step": 3
28
+ },
29
+ {
30
+ "epoch": 0.04,
31
+ "learning_rate": 8.613531161467863e-06,
32
+ "loss": 1.8188,
33
+ "step": 4
34
+ },
35
+ {
36
+ "epoch": 0.05,
37
+ "learning_rate": 1e-05,
38
+ "loss": 1.7535,
39
+ "step": 5
40
+ },
41
+ {
42
+ "epoch": 0.06,
43
+ "learning_rate": 1.1132827525593786e-05,
44
+ "loss": 1.6784,
45
+ "step": 6
46
+ },
47
+ {
48
+ "epoch": 0.07,
49
+ "learning_rate": 1.2090619551221676e-05,
50
+ "loss": 1.8318,
51
+ "step": 7
52
+ },
53
+ {
54
+ "epoch": 0.08,
55
+ "learning_rate": 1.2920296742201793e-05,
56
+ "loss": 1.7084,
57
+ "step": 8
58
+ },
59
+ {
60
+ "epoch": 0.09,
61
+ "learning_rate": 1.3652123889719709e-05,
62
+ "loss": 1.6416,
63
+ "step": 9
64
+ },
65
+ {
66
+ "epoch": 0.1,
67
+ "learning_rate": 1.4306765580733935e-05,
68
+ "loss": 1.6962,
69
+ "step": 10
70
+ },
71
+ {
72
+ "epoch": 0.11,
73
+ "learning_rate": 1.4898961024049785e-05,
74
+ "loss": 1.5732,
75
+ "step": 11
76
+ },
77
+ {
78
+ "epoch": 0.12,
79
+ "learning_rate": 1.543959310632772e-05,
80
+ "loss": 1.6528,
81
+ "step": 12
82
+ },
83
+ {
84
+ "epoch": 0.13,
85
+ "learning_rate": 1.5936926411670824e-05,
86
+ "loss": 1.716,
87
+ "step": 13
88
+ },
89
+ {
90
+ "epoch": 0.14,
91
+ "learning_rate": 1.639738513195561e-05,
92
+ "loss": 1.5802,
93
+ "step": 14
94
+ },
95
+ {
96
+ "epoch": 0.15,
97
+ "learning_rate": 1.6826061944859853e-05,
98
+ "loss": 1.6403,
99
+ "step": 15
100
+ },
101
+ {
102
+ "epoch": 0.16,
103
+ "learning_rate": 1.7227062322935725e-05,
104
+ "loss": 1.5923,
105
+ "step": 16
106
+ },
107
+ {
108
+ "epoch": 0.17,
109
+ "learning_rate": 1.7603744277225883e-05,
110
+ "loss": 1.6141,
111
+ "step": 17
112
+ },
113
+ {
114
+ "epoch": 0.18,
115
+ "learning_rate": 1.7958889470453637e-05,
116
+ "loss": 1.6916,
117
+ "step": 18
118
+ },
119
+ {
120
+ "epoch": 0.19,
121
+ "learning_rate": 1.8294828004351506e-05,
122
+ "loss": 1.5832,
123
+ "step": 19
124
+ },
125
+ {
126
+ "epoch": 0.2,
127
+ "learning_rate": 1.8613531161467863e-05,
128
+ "loss": 1.6152,
129
+ "step": 20
130
+ },
131
+ {
132
+ "epoch": 0.21,
133
+ "learning_rate": 1.891668149608153e-05,
134
+ "loss": 1.6234,
135
+ "step": 21
136
+ },
137
+ {
138
+ "epoch": 0.22,
139
+ "learning_rate": 1.9205726604783716e-05,
140
+ "loss": 1.6703,
141
+ "step": 22
142
+ },
143
+ {
144
+ "epoch": 0.23,
145
+ "learning_rate": 1.94819209346638e-05,
146
+ "loss": 1.6648,
147
+ "step": 23
148
+ },
149
+ {
150
+ "epoch": 0.24,
151
+ "learning_rate": 1.9746358687061647e-05,
152
+ "loss": 1.7037,
153
+ "step": 24
154
+ },
155
+ {
156
+ "epoch": 0.25,
157
+ "learning_rate": 2e-05,
158
+ "loss": 1.6608,
159
+ "step": 25
160
+ },
161
+ {
162
+ "epoch": 0.26,
163
+ "learning_rate": 2e-05,
164
+ "loss": 1.5428,
165
+ "step": 26
166
+ },
167
+ {
168
+ "epoch": 0.27,
169
+ "learning_rate": 1.995698924731183e-05,
170
+ "loss": 1.6165,
171
+ "step": 27
172
+ },
173
+ {
174
+ "epoch": 0.28,
175
+ "learning_rate": 1.991397849462366e-05,
176
+ "loss": 1.5947,
177
+ "step": 28
178
+ },
179
+ {
180
+ "epoch": 0.29,
181
+ "learning_rate": 1.9870967741935484e-05,
182
+ "loss": 1.6807,
183
+ "step": 29
184
+ },
185
+ {
186
+ "epoch": 0.3,
187
+ "learning_rate": 1.9827956989247316e-05,
188
+ "loss": 1.4922,
189
+ "step": 30
190
+ },
191
+ {
192
+ "epoch": 0.31,
193
+ "learning_rate": 1.978494623655914e-05,
194
+ "loss": 1.5233,
195
+ "step": 31
196
+ },
197
+ {
198
+ "epoch": 0.32,
199
+ "learning_rate": 1.974193548387097e-05,
200
+ "loss": 1.6164,
201
+ "step": 32
202
+ },
203
+ {
204
+ "epoch": 0.33,
205
+ "learning_rate": 1.96989247311828e-05,
206
+ "loss": 1.4448,
207
+ "step": 33
208
+ },
209
+ {
210
+ "epoch": 0.34,
211
+ "learning_rate": 1.9655913978494624e-05,
212
+ "loss": 1.7434,
213
+ "step": 34
214
+ },
215
+ {
216
+ "epoch": 0.35,
217
+ "learning_rate": 1.9612903225806452e-05,
218
+ "loss": 1.596,
219
+ "step": 35
220
+ },
221
+ {
222
+ "epoch": 0.36,
223
+ "learning_rate": 1.956989247311828e-05,
224
+ "loss": 1.7181,
225
+ "step": 36
226
+ },
227
+ {
228
+ "epoch": 0.37,
229
+ "learning_rate": 1.952688172043011e-05,
230
+ "loss": 1.5812,
231
+ "step": 37
232
+ },
233
+ {
234
+ "epoch": 0.38,
235
+ "learning_rate": 1.948387096774194e-05,
236
+ "loss": 1.6811,
237
+ "step": 38
238
+ },
239
+ {
240
+ "epoch": 0.39,
241
+ "learning_rate": 1.9440860215053764e-05,
242
+ "loss": 1.5775,
243
+ "step": 39
244
+ },
245
+ {
246
+ "epoch": 0.41,
247
+ "learning_rate": 1.9397849462365592e-05,
248
+ "loss": 1.6463,
249
+ "step": 40
250
+ },
251
+ {
252
+ "epoch": 0.42,
253
+ "learning_rate": 1.935483870967742e-05,
254
+ "loss": 1.5282,
255
+ "step": 41
256
+ },
257
+ {
258
+ "epoch": 0.43,
259
+ "learning_rate": 1.931182795698925e-05,
260
+ "loss": 1.6476,
261
+ "step": 42
262
+ },
263
+ {
264
+ "epoch": 0.44,
265
+ "learning_rate": 1.9268817204301078e-05,
266
+ "loss": 1.4159,
267
+ "step": 43
268
+ },
269
+ {
270
+ "epoch": 0.45,
271
+ "learning_rate": 1.9225806451612907e-05,
272
+ "loss": 1.51,
273
+ "step": 44
274
+ },
275
+ {
276
+ "epoch": 0.46,
277
+ "learning_rate": 1.9182795698924732e-05,
278
+ "loss": 1.5285,
279
+ "step": 45
280
+ },
281
+ {
282
+ "epoch": 0.47,
283
+ "learning_rate": 1.913978494623656e-05,
284
+ "loss": 1.7255,
285
+ "step": 46
286
+ },
287
+ {
288
+ "epoch": 0.48,
289
+ "learning_rate": 1.909677419354839e-05,
290
+ "loss": 1.6362,
291
+ "step": 47
292
+ },
293
+ {
294
+ "epoch": 0.49,
295
+ "learning_rate": 1.9053763440860214e-05,
296
+ "loss": 1.5058,
297
+ "step": 48
298
+ },
299
+ {
300
+ "epoch": 0.5,
301
+ "learning_rate": 1.9010752688172046e-05,
302
+ "loss": 1.6969,
303
+ "step": 49
304
+ },
305
+ {
306
+ "epoch": 0.51,
307
+ "learning_rate": 1.896774193548387e-05,
308
+ "loss": 1.7406,
309
+ "step": 50
310
+ },
311
+ {
312
+ "epoch": 0.52,
313
+ "learning_rate": 1.89247311827957e-05,
314
+ "loss": 1.595,
315
+ "step": 51
316
+ },
317
+ {
318
+ "epoch": 0.53,
319
+ "learning_rate": 1.888172043010753e-05,
320
+ "loss": 1.6272,
321
+ "step": 52
322
+ },
323
+ {
324
+ "epoch": 0.54,
325
+ "learning_rate": 1.8838709677419354e-05,
326
+ "loss": 1.6688,
327
+ "step": 53
328
+ },
329
+ {
330
+ "epoch": 0.55,
331
+ "learning_rate": 1.8795698924731186e-05,
332
+ "loss": 1.4956,
333
+ "step": 54
334
+ },
335
+ {
336
+ "epoch": 0.56,
337
+ "learning_rate": 1.875268817204301e-05,
338
+ "loss": 1.6564,
339
+ "step": 55
340
+ },
341
+ {
342
+ "epoch": 0.57,
343
+ "learning_rate": 1.870967741935484e-05,
344
+ "loss": 1.6055,
345
+ "step": 56
346
+ },
347
+ {
348
+ "epoch": 0.58,
349
+ "learning_rate": 1.866666666666667e-05,
350
+ "loss": 1.3791,
351
+ "step": 57
352
+ },
353
+ {
354
+ "epoch": 0.59,
355
+ "learning_rate": 1.8623655913978497e-05,
356
+ "loss": 1.4353,
357
+ "step": 58
358
+ },
359
+ {
360
+ "epoch": 0.6,
361
+ "learning_rate": 1.8580645161290326e-05,
362
+ "loss": 1.4798,
363
+ "step": 59
364
+ },
365
+ {
366
+ "epoch": 0.61,
367
+ "learning_rate": 1.853763440860215e-05,
368
+ "loss": 1.4247,
369
+ "step": 60
370
+ },
371
+ {
372
+ "epoch": 0.62,
373
+ "learning_rate": 1.849462365591398e-05,
374
+ "loss": 1.5351,
375
+ "step": 61
376
+ },
377
+ {
378
+ "epoch": 0.63,
379
+ "learning_rate": 1.845161290322581e-05,
380
+ "loss": 1.5758,
381
+ "step": 62
382
+ },
383
+ {
384
+ "epoch": 0.64,
385
+ "learning_rate": 1.8408602150537637e-05,
386
+ "loss": 1.6437,
387
+ "step": 63
388
+ },
389
+ {
390
+ "epoch": 0.65,
391
+ "learning_rate": 1.8365591397849466e-05,
392
+ "loss": 1.6213,
393
+ "step": 64
394
+ },
395
+ {
396
+ "epoch": 0.66,
397
+ "learning_rate": 1.832258064516129e-05,
398
+ "loss": 1.6822,
399
+ "step": 65
400
+ },
401
+ {
402
+ "epoch": 0.67,
403
+ "learning_rate": 1.827956989247312e-05,
404
+ "loss": 1.7296,
405
+ "step": 66
406
+ },
407
+ {
408
+ "epoch": 0.68,
409
+ "learning_rate": 1.8236559139784948e-05,
410
+ "loss": 1.7892,
411
+ "step": 67
412
+ },
413
+ {
414
+ "epoch": 0.69,
415
+ "learning_rate": 1.8193548387096777e-05,
416
+ "loss": 1.6259,
417
+ "step": 68
418
+ },
419
+ {
420
+ "epoch": 0.7,
421
+ "learning_rate": 1.8150537634408602e-05,
422
+ "loss": 1.4952,
423
+ "step": 69
424
+ },
425
+ {
426
+ "epoch": 0.71,
427
+ "learning_rate": 1.810752688172043e-05,
428
+ "loss": 1.6235,
429
+ "step": 70
430
+ },
431
+ {
432
+ "epoch": 0.72,
433
+ "learning_rate": 1.806451612903226e-05,
434
+ "loss": 1.6421,
435
+ "step": 71
436
+ },
437
+ {
438
+ "epoch": 0.73,
439
+ "learning_rate": 1.8021505376344088e-05,
440
+ "loss": 1.6154,
441
+ "step": 72
442
+ },
443
+ {
444
+ "epoch": 0.74,
445
+ "learning_rate": 1.7978494623655916e-05,
446
+ "loss": 1.47,
447
+ "step": 73
448
+ },
449
+ {
450
+ "epoch": 0.75,
451
+ "learning_rate": 1.7935483870967742e-05,
452
+ "loss": 1.4677,
453
+ "step": 74
454
+ },
455
+ {
456
+ "epoch": 0.76,
457
+ "learning_rate": 1.789247311827957e-05,
458
+ "loss": 1.4999,
459
+ "step": 75
460
+ },
461
+ {
462
+ "epoch": 0.77,
463
+ "learning_rate": 1.78494623655914e-05,
464
+ "loss": 1.6743,
465
+ "step": 76
466
+ },
467
+ {
468
+ "epoch": 0.78,
469
+ "learning_rate": 1.7806451612903228e-05,
470
+ "loss": 1.4953,
471
+ "step": 77
472
+ },
473
+ {
474
+ "epoch": 0.79,
475
+ "learning_rate": 1.7763440860215056e-05,
476
+ "loss": 1.6313,
477
+ "step": 78
478
+ },
479
+ {
480
+ "epoch": 0.8,
481
+ "learning_rate": 1.772043010752688e-05,
482
+ "loss": 1.5617,
483
+ "step": 79
484
+ },
485
+ {
486
+ "epoch": 0.81,
487
+ "learning_rate": 1.7677419354838713e-05,
488
+ "loss": 1.5945,
489
+ "step": 80
490
+ },
491
+ {
492
+ "epoch": 0.82,
493
+ "learning_rate": 1.763440860215054e-05,
494
+ "loss": 1.5671,
495
+ "step": 81
496
+ },
497
+ {
498
+ "epoch": 0.83,
499
+ "learning_rate": 1.7591397849462367e-05,
500
+ "loss": 1.4768,
501
+ "step": 82
502
+ },
503
+ {
504
+ "epoch": 0.84,
505
+ "learning_rate": 1.7548387096774196e-05,
506
+ "loss": 1.5294,
507
+ "step": 83
508
+ },
509
+ {
510
+ "epoch": 0.85,
511
+ "learning_rate": 1.750537634408602e-05,
512
+ "loss": 1.499,
513
+ "step": 84
514
+ },
515
+ {
516
+ "epoch": 0.86,
517
+ "learning_rate": 1.7462365591397853e-05,
518
+ "loss": 1.5867,
519
+ "step": 85
520
+ },
521
+ {
522
+ "epoch": 0.87,
523
+ "learning_rate": 1.741935483870968e-05,
524
+ "loss": 1.4942,
525
+ "step": 86
526
+ },
527
+ {
528
+ "epoch": 0.88,
529
+ "learning_rate": 1.7376344086021507e-05,
530
+ "loss": 1.5331,
531
+ "step": 87
532
+ },
533
+ {
534
+ "epoch": 0.89,
535
+ "learning_rate": 1.7333333333333336e-05,
536
+ "loss": 1.7325,
537
+ "step": 88
538
+ },
539
+ {
540
+ "epoch": 0.9,
541
+ "learning_rate": 1.729032258064516e-05,
542
+ "loss": 1.6354,
543
+ "step": 89
544
+ },
545
+ {
546
+ "epoch": 0.91,
547
+ "learning_rate": 1.724731182795699e-05,
548
+ "loss": 1.6768,
549
+ "step": 90
550
+ },
551
+ {
552
+ "epoch": 0.92,
553
+ "learning_rate": 1.7204301075268818e-05,
554
+ "loss": 1.4602,
555
+ "step": 91
556
+ },
557
+ {
558
+ "epoch": 0.93,
559
+ "learning_rate": 1.7161290322580647e-05,
560
+ "loss": 1.4933,
561
+ "step": 92
562
+ },
563
+ {
564
+ "epoch": 0.94,
565
+ "learning_rate": 1.7118279569892475e-05,
566
+ "loss": 1.4517,
567
+ "step": 93
568
+ },
569
+ {
570
+ "epoch": 0.95,
571
+ "learning_rate": 1.7075268817204304e-05,
572
+ "loss": 1.7103,
573
+ "step": 94
574
+ },
575
+ {
576
+ "epoch": 0.96,
577
+ "learning_rate": 1.703225806451613e-05,
578
+ "loss": 1.5579,
579
+ "step": 95
580
+ },
581
+ {
582
+ "epoch": 0.97,
583
+ "learning_rate": 1.6989247311827958e-05,
584
+ "loss": 1.4942,
585
+ "step": 96
586
+ },
587
+ {
588
+ "epoch": 0.98,
589
+ "learning_rate": 1.6946236559139786e-05,
590
+ "loss": 1.5904,
591
+ "step": 97
592
+ },
593
+ {
594
+ "epoch": 0.99,
595
+ "learning_rate": 1.6903225806451615e-05,
596
+ "loss": 1.5026,
597
+ "step": 98
598
+ },
599
+ {
600
+ "epoch": 1.0,
601
+ "learning_rate": 1.6860215053763444e-05,
602
+ "loss": 1.3493,
603
+ "step": 99
604
+ },
605
+ {
606
+ "epoch": 1.01,
607
+ "learning_rate": 1.681720430107527e-05,
608
+ "loss": 0.9543,
609
+ "step": 100
610
+ },
611
+ {
612
+ "epoch": 1.02,
613
+ "learning_rate": 1.6774193548387098e-05,
614
+ "loss": 0.9765,
615
+ "step": 101
616
+ },
617
+ {
618
+ "epoch": 1.03,
619
+ "learning_rate": 1.6731182795698926e-05,
620
+ "loss": 0.9687,
621
+ "step": 102
622
+ },
623
+ {
624
+ "epoch": 1.04,
625
+ "learning_rate": 1.668817204301075e-05,
626
+ "loss": 1.0385,
627
+ "step": 103
628
+ },
629
+ {
630
+ "epoch": 1.05,
631
+ "learning_rate": 1.6645161290322583e-05,
632
+ "loss": 1.0394,
633
+ "step": 104
634
+ },
635
+ {
636
+ "epoch": 1.06,
637
+ "learning_rate": 1.660215053763441e-05,
638
+ "loss": 0.9033,
639
+ "step": 105
640
+ },
641
+ {
642
+ "epoch": 1.07,
643
+ "learning_rate": 1.6559139784946237e-05,
644
+ "loss": 0.8905,
645
+ "step": 106
646
+ },
647
+ {
648
+ "epoch": 1.08,
649
+ "learning_rate": 1.6516129032258066e-05,
650
+ "loss": 1.4783,
651
+ "step": 107
652
+ },
653
+ {
654
+ "epoch": 1.09,
655
+ "learning_rate": 1.6473118279569895e-05,
656
+ "loss": 1.1471,
657
+ "step": 108
658
+ },
659
+ {
660
+ "epoch": 1.1,
661
+ "learning_rate": 1.6430107526881723e-05,
662
+ "loss": 1.061,
663
+ "step": 109
664
+ },
665
+ {
666
+ "epoch": 1.11,
667
+ "learning_rate": 1.638709677419355e-05,
668
+ "loss": 1.0713,
669
+ "step": 110
670
+ },
671
+ {
672
+ "epoch": 1.12,
673
+ "learning_rate": 1.6344086021505377e-05,
674
+ "loss": 0.918,
675
+ "step": 111
676
+ },
677
+ {
678
+ "epoch": 1.13,
679
+ "learning_rate": 1.6301075268817206e-05,
680
+ "loss": 1.0217,
681
+ "step": 112
682
+ },
683
+ {
684
+ "epoch": 1.14,
685
+ "learning_rate": 1.6258064516129034e-05,
686
+ "loss": 0.9848,
687
+ "step": 113
688
+ },
689
+ {
690
+ "epoch": 1.15,
691
+ "learning_rate": 1.6215053763440863e-05,
692
+ "loss": 1.0507,
693
+ "step": 114
694
+ },
695
+ {
696
+ "epoch": 1.16,
697
+ "learning_rate": 1.6172043010752688e-05,
698
+ "loss": 1.2116,
699
+ "step": 115
700
+ },
701
+ {
702
+ "epoch": 1.17,
703
+ "learning_rate": 1.6129032258064517e-05,
704
+ "loss": 1.1489,
705
+ "step": 116
706
+ },
707
+ {
708
+ "epoch": 1.18,
709
+ "learning_rate": 1.6086021505376345e-05,
710
+ "loss": 0.9653,
711
+ "step": 117
712
+ },
713
+ {
714
+ "epoch": 1.19,
715
+ "learning_rate": 1.6043010752688174e-05,
716
+ "loss": 0.912,
717
+ "step": 118
718
+ },
719
+ {
720
+ "epoch": 1.21,
721
+ "learning_rate": 1.6000000000000003e-05,
722
+ "loss": 1.1097,
723
+ "step": 119
724
+ },
725
+ {
726
+ "epoch": 1.22,
727
+ "learning_rate": 1.5956989247311828e-05,
728
+ "loss": 1.0009,
729
+ "step": 120
730
+ },
731
+ {
732
+ "epoch": 1.23,
733
+ "learning_rate": 1.5913978494623657e-05,
734
+ "loss": 1.1487,
735
+ "step": 121
736
+ },
737
+ {
738
+ "epoch": 1.24,
739
+ "learning_rate": 1.5870967741935485e-05,
740
+ "loss": 0.9222,
741
+ "step": 122
742
+ },
743
+ {
744
+ "epoch": 1.25,
745
+ "learning_rate": 1.5827956989247314e-05,
746
+ "loss": 0.9213,
747
+ "step": 123
748
+ },
749
+ {
750
+ "epoch": 1.26,
751
+ "learning_rate": 1.5784946236559142e-05,
752
+ "loss": 1.0347,
753
+ "step": 124
754
+ },
755
+ {
756
+ "epoch": 1.27,
757
+ "learning_rate": 1.5741935483870968e-05,
758
+ "loss": 1.014,
759
+ "step": 125
760
+ },
761
+ {
762
+ "epoch": 1.28,
763
+ "learning_rate": 1.5698924731182796e-05,
764
+ "loss": 0.9657,
765
+ "step": 126
766
+ },
767
+ {
768
+ "epoch": 1.29,
769
+ "learning_rate": 1.5655913978494625e-05,
770
+ "loss": 1.0616,
771
+ "step": 127
772
+ },
773
+ {
774
+ "epoch": 1.3,
775
+ "learning_rate": 1.5612903225806454e-05,
776
+ "loss": 0.8538,
777
+ "step": 128
778
+ },
779
+ {
780
+ "epoch": 1.31,
781
+ "learning_rate": 1.556989247311828e-05,
782
+ "loss": 0.8506,
783
+ "step": 129
784
+ },
785
+ {
786
+ "epoch": 1.32,
787
+ "learning_rate": 1.552688172043011e-05,
788
+ "loss": 1.0627,
789
+ "step": 130
790
+ },
791
+ {
792
+ "epoch": 1.33,
793
+ "learning_rate": 1.5483870967741936e-05,
794
+ "loss": 0.8975,
795
+ "step": 131
796
+ },
797
+ {
798
+ "epoch": 1.34,
799
+ "learning_rate": 1.5440860215053765e-05,
800
+ "loss": 0.8824,
801
+ "step": 132
802
+ },
803
+ {
804
+ "epoch": 1.35,
805
+ "learning_rate": 1.5397849462365593e-05,
806
+ "loss": 1.0609,
807
+ "step": 133
808
+ },
809
+ {
810
+ "epoch": 1.36,
811
+ "learning_rate": 1.535483870967742e-05,
812
+ "loss": 0.8495,
813
+ "step": 134
814
+ },
815
+ {
816
+ "epoch": 1.37,
817
+ "learning_rate": 1.531182795698925e-05,
818
+ "loss": 0.9624,
819
+ "step": 135
820
+ },
821
+ {
822
+ "epoch": 1.38,
823
+ "learning_rate": 1.5268817204301076e-05,
824
+ "loss": 0.9412,
825
+ "step": 136
826
+ },
827
+ {
828
+ "epoch": 1.39,
829
+ "learning_rate": 1.5225806451612903e-05,
830
+ "loss": 0.8386,
831
+ "step": 137
832
+ },
833
+ {
834
+ "epoch": 1.4,
835
+ "learning_rate": 1.5182795698924733e-05,
836
+ "loss": 0.912,
837
+ "step": 138
838
+ },
839
+ {
840
+ "epoch": 1.41,
841
+ "learning_rate": 1.513978494623656e-05,
842
+ "loss": 0.8699,
843
+ "step": 139
844
+ },
845
+ {
846
+ "epoch": 1.42,
847
+ "learning_rate": 1.5096774193548389e-05,
848
+ "loss": 0.9416,
849
+ "step": 140
850
+ },
851
+ {
852
+ "epoch": 1.43,
853
+ "learning_rate": 1.5053763440860215e-05,
854
+ "loss": 1.0873,
855
+ "step": 141
856
+ },
857
+ {
858
+ "epoch": 1.44,
859
+ "learning_rate": 1.5010752688172044e-05,
860
+ "loss": 0.9139,
861
+ "step": 142
862
+ },
863
+ {
864
+ "epoch": 1.45,
865
+ "learning_rate": 1.4967741935483873e-05,
866
+ "loss": 0.9538,
867
+ "step": 143
868
+ },
869
+ {
870
+ "epoch": 1.46,
871
+ "learning_rate": 1.49247311827957e-05,
872
+ "loss": 0.9326,
873
+ "step": 144
874
+ },
875
+ {
876
+ "epoch": 1.47,
877
+ "learning_rate": 1.4881720430107528e-05,
878
+ "loss": 1.0359,
879
+ "step": 145
880
+ },
881
+ {
882
+ "epoch": 1.48,
883
+ "learning_rate": 1.4838709677419357e-05,
884
+ "loss": 1.0978,
885
+ "step": 146
886
+ },
887
+ {
888
+ "epoch": 1.49,
889
+ "learning_rate": 1.4795698924731184e-05,
890
+ "loss": 0.922,
891
+ "step": 147
892
+ },
893
+ {
894
+ "epoch": 1.5,
895
+ "learning_rate": 1.4752688172043012e-05,
896
+ "loss": 0.9583,
897
+ "step": 148
898
+ },
899
+ {
900
+ "epoch": 1.51,
901
+ "learning_rate": 1.470967741935484e-05,
902
+ "loss": 0.9822,
903
+ "step": 149
904
+ },
905
+ {
906
+ "epoch": 1.52,
907
+ "learning_rate": 1.4666666666666666e-05,
908
+ "loss": 0.8844,
909
+ "step": 150
910
+ },
911
+ {
912
+ "epoch": 1.53,
913
+ "learning_rate": 1.4623655913978497e-05,
914
+ "loss": 0.9124,
915
+ "step": 151
916
+ },
917
+ {
918
+ "epoch": 1.54,
919
+ "learning_rate": 1.4580645161290324e-05,
920
+ "loss": 0.915,
921
+ "step": 152
922
+ },
923
+ {
924
+ "epoch": 1.55,
925
+ "learning_rate": 1.4537634408602152e-05,
926
+ "loss": 1.0011,
927
+ "step": 153
928
+ },
929
+ {
930
+ "epoch": 1.56,
931
+ "learning_rate": 1.4494623655913979e-05,
932
+ "loss": 0.9509,
933
+ "step": 154
934
+ },
935
+ {
936
+ "epoch": 1.57,
937
+ "learning_rate": 1.4451612903225806e-05,
938
+ "loss": 0.875,
939
+ "step": 155
940
+ },
941
+ {
942
+ "epoch": 1.58,
943
+ "learning_rate": 1.4408602150537636e-05,
944
+ "loss": 0.9167,
945
+ "step": 156
946
+ },
947
+ {
948
+ "epoch": 1.59,
949
+ "learning_rate": 1.4365591397849463e-05,
950
+ "loss": 1.0028,
951
+ "step": 157
952
+ },
953
+ {
954
+ "epoch": 1.6,
955
+ "learning_rate": 1.4322580645161292e-05,
956
+ "loss": 1.0519,
957
+ "step": 158
958
+ },
959
+ {
960
+ "epoch": 1.61,
961
+ "learning_rate": 1.4279569892473119e-05,
962
+ "loss": 0.9254,
963
+ "step": 159
964
+ },
965
+ {
966
+ "epoch": 1.62,
967
+ "learning_rate": 1.4236559139784947e-05,
968
+ "loss": 0.9952,
969
+ "step": 160
970
+ },
971
+ {
972
+ "epoch": 1.63,
973
+ "learning_rate": 1.4193548387096776e-05,
974
+ "loss": 0.8365,
975
+ "step": 161
976
+ },
977
+ {
978
+ "epoch": 1.64,
979
+ "learning_rate": 1.4150537634408603e-05,
980
+ "loss": 0.8959,
981
+ "step": 162
982
+ },
983
+ {
984
+ "epoch": 1.65,
985
+ "learning_rate": 1.410752688172043e-05,
986
+ "loss": 0.906,
987
+ "step": 163
988
+ },
989
+ {
990
+ "epoch": 1.66,
991
+ "learning_rate": 1.406451612903226e-05,
992
+ "loss": 0.9985,
993
+ "step": 164
994
+ },
995
+ {
996
+ "epoch": 1.67,
997
+ "learning_rate": 1.4021505376344087e-05,
998
+ "loss": 1.0443,
999
+ "step": 165
1000
+ },
1001
+ {
1002
+ "epoch": 1.68,
1003
+ "learning_rate": 1.3978494623655916e-05,
1004
+ "loss": 0.8452,
1005
+ "step": 166
1006
+ },
1007
+ {
1008
+ "epoch": 1.69,
1009
+ "learning_rate": 1.3935483870967743e-05,
1010
+ "loss": 0.9754,
1011
+ "step": 167
1012
+ },
1013
+ {
1014
+ "epoch": 1.7,
1015
+ "learning_rate": 1.389247311827957e-05,
1016
+ "loss": 1.029,
1017
+ "step": 168
1018
+ },
1019
+ {
1020
+ "epoch": 1.71,
1021
+ "learning_rate": 1.38494623655914e-05,
1022
+ "loss": 0.9344,
1023
+ "step": 169
1024
+ },
1025
+ {
1026
+ "epoch": 1.72,
1027
+ "learning_rate": 1.3806451612903227e-05,
1028
+ "loss": 0.8564,
1029
+ "step": 170
1030
+ },
1031
+ {
1032
+ "epoch": 1.73,
1033
+ "learning_rate": 1.3763440860215056e-05,
1034
+ "loss": 0.8746,
1035
+ "step": 171
1036
+ },
1037
+ {
1038
+ "epoch": 1.74,
1039
+ "learning_rate": 1.3720430107526882e-05,
1040
+ "loss": 0.9671,
1041
+ "step": 172
1042
+ },
1043
+ {
1044
+ "epoch": 1.75,
1045
+ "learning_rate": 1.367741935483871e-05,
1046
+ "loss": 0.9063,
1047
+ "step": 173
1048
+ },
1049
+ {
1050
+ "epoch": 1.76,
1051
+ "learning_rate": 1.363440860215054e-05,
1052
+ "loss": 0.8366,
1053
+ "step": 174
1054
+ },
1055
+ {
1056
+ "epoch": 1.77,
1057
+ "learning_rate": 1.3591397849462367e-05,
1058
+ "loss": 0.9146,
1059
+ "step": 175
1060
+ },
1061
+ {
1062
+ "epoch": 1.78,
1063
+ "learning_rate": 1.3548387096774194e-05,
1064
+ "loss": 0.9435,
1065
+ "step": 176
1066
+ },
1067
+ {
1068
+ "epoch": 1.79,
1069
+ "learning_rate": 1.3505376344086024e-05,
1070
+ "loss": 1.0586,
1071
+ "step": 177
1072
+ },
1073
+ {
1074
+ "epoch": 1.8,
1075
+ "learning_rate": 1.346236559139785e-05,
1076
+ "loss": 0.9272,
1077
+ "step": 178
1078
+ },
1079
+ {
1080
+ "epoch": 1.81,
1081
+ "learning_rate": 1.341935483870968e-05,
1082
+ "loss": 0.9492,
1083
+ "step": 179
1084
+ },
1085
+ {
1086
+ "epoch": 1.82,
1087
+ "learning_rate": 1.3376344086021506e-05,
1088
+ "loss": 0.939,
1089
+ "step": 180
1090
+ },
1091
+ {
1092
+ "epoch": 1.83,
1093
+ "learning_rate": 1.3333333333333333e-05,
1094
+ "loss": 0.9346,
1095
+ "step": 181
1096
+ },
1097
+ {
1098
+ "epoch": 1.84,
1099
+ "learning_rate": 1.3290322580645164e-05,
1100
+ "loss": 0.9455,
1101
+ "step": 182
1102
+ },
1103
+ {
1104
+ "epoch": 1.85,
1105
+ "learning_rate": 1.324731182795699e-05,
1106
+ "loss": 0.8325,
1107
+ "step": 183
1108
+ },
1109
+ {
1110
+ "epoch": 1.86,
1111
+ "learning_rate": 1.3204301075268817e-05,
1112
+ "loss": 1.074,
1113
+ "step": 184
1114
+ },
1115
+ {
1116
+ "epoch": 1.87,
1117
+ "learning_rate": 1.3161290322580646e-05,
1118
+ "loss": 1.1218,
1119
+ "step": 185
1120
+ },
1121
+ {
1122
+ "epoch": 1.88,
1123
+ "learning_rate": 1.3118279569892473e-05,
1124
+ "loss": 0.9108,
1125
+ "step": 186
1126
+ },
1127
+ {
1128
+ "epoch": 1.89,
1129
+ "learning_rate": 1.3075268817204303e-05,
1130
+ "loss": 0.9461,
1131
+ "step": 187
1132
+ },
1133
+ {
1134
+ "epoch": 1.9,
1135
+ "learning_rate": 1.303225806451613e-05,
1136
+ "loss": 0.9079,
1137
+ "step": 188
1138
+ },
1139
+ {
1140
+ "epoch": 1.91,
1141
+ "learning_rate": 1.2989247311827957e-05,
1142
+ "loss": 0.8472,
1143
+ "step": 189
1144
+ },
1145
+ {
1146
+ "epoch": 1.92,
1147
+ "learning_rate": 1.2946236559139786e-05,
1148
+ "loss": 0.8697,
1149
+ "step": 190
1150
+ },
1151
+ {
1152
+ "epoch": 1.93,
1153
+ "learning_rate": 1.2903225806451613e-05,
1154
+ "loss": 0.9297,
1155
+ "step": 191
1156
+ },
1157
+ {
1158
+ "epoch": 1.94,
1159
+ "learning_rate": 1.2860215053763443e-05,
1160
+ "loss": 0.8979,
1161
+ "step": 192
1162
+ },
1163
+ {
1164
+ "epoch": 1.95,
1165
+ "learning_rate": 1.281720430107527e-05,
1166
+ "loss": 0.7667,
1167
+ "step": 193
1168
+ },
1169
+ {
1170
+ "epoch": 1.96,
1171
+ "learning_rate": 1.2774193548387097e-05,
1172
+ "loss": 0.9026,
1173
+ "step": 194
1174
+ },
1175
+ {
1176
+ "epoch": 1.97,
1177
+ "learning_rate": 1.2731182795698927e-05,
1178
+ "loss": 0.9931,
1179
+ "step": 195
1180
+ },
1181
+ {
1182
+ "epoch": 1.98,
1183
+ "learning_rate": 1.2688172043010754e-05,
1184
+ "loss": 1.0038,
1185
+ "step": 196
1186
+ },
1187
+ {
1188
+ "epoch": 1.99,
1189
+ "learning_rate": 1.2645161290322581e-05,
1190
+ "loss": 0.9209,
1191
+ "step": 197
1192
+ },
1193
+ {
1194
+ "epoch": 2.01,
1195
+ "learning_rate": 1.260215053763441e-05,
1196
+ "loss": 0.7258,
1197
+ "step": 198
1198
+ },
1199
+ {
1200
+ "epoch": 2.02,
1201
+ "learning_rate": 1.2559139784946237e-05,
1202
+ "loss": 0.491,
1203
+ "step": 199
1204
+ },
1205
+ {
1206
+ "epoch": 2.03,
1207
+ "learning_rate": 1.2516129032258067e-05,
1208
+ "loss": 0.6607,
1209
+ "step": 200
1210
+ },
1211
+ {
1212
+ "epoch": 2.04,
1213
+ "learning_rate": 1.2473118279569894e-05,
1214
+ "loss": 0.5564,
1215
+ "step": 201
1216
+ },
1217
+ {
1218
+ "epoch": 2.05,
1219
+ "learning_rate": 1.243010752688172e-05,
1220
+ "loss": 0.5636,
1221
+ "step": 202
1222
+ },
1223
+ {
1224
+ "epoch": 2.06,
1225
+ "learning_rate": 1.238709677419355e-05,
1226
+ "loss": 0.5425,
1227
+ "step": 203
1228
+ },
1229
+ {
1230
+ "epoch": 2.07,
1231
+ "learning_rate": 1.2344086021505376e-05,
1232
+ "loss": 0.5245,
1233
+ "step": 204
1234
+ },
1235
+ {
1236
+ "epoch": 2.08,
1237
+ "learning_rate": 1.2301075268817207e-05,
1238
+ "loss": 0.4281,
1239
+ "step": 205
1240
+ },
1241
+ {
1242
+ "epoch": 2.09,
1243
+ "learning_rate": 1.2258064516129034e-05,
1244
+ "loss": 0.5537,
1245
+ "step": 206
1246
+ },
1247
+ {
1248
+ "epoch": 2.1,
1249
+ "learning_rate": 1.221505376344086e-05,
1250
+ "loss": 0.5108,
1251
+ "step": 207
1252
+ },
1253
+ {
1254
+ "epoch": 2.11,
1255
+ "learning_rate": 1.217204301075269e-05,
1256
+ "loss": 0.5137,
1257
+ "step": 208
1258
+ },
1259
+ {
1260
+ "epoch": 2.12,
1261
+ "learning_rate": 1.2129032258064518e-05,
1262
+ "loss": 0.5287,
1263
+ "step": 209
1264
+ },
1265
+ {
1266
+ "epoch": 2.13,
1267
+ "learning_rate": 1.2086021505376345e-05,
1268
+ "loss": 0.5948,
1269
+ "step": 210
1270
+ },
1271
+ {
1272
+ "epoch": 2.14,
1273
+ "learning_rate": 1.2043010752688173e-05,
1274
+ "loss": 0.5296,
1275
+ "step": 211
1276
+ },
1277
+ {
1278
+ "epoch": 2.15,
1279
+ "learning_rate": 1.2e-05,
1280
+ "loss": 0.5619,
1281
+ "step": 212
1282
+ },
1283
+ {
1284
+ "epoch": 2.16,
1285
+ "learning_rate": 1.195698924731183e-05,
1286
+ "loss": 0.5297,
1287
+ "step": 213
1288
+ },
1289
+ {
1290
+ "epoch": 2.17,
1291
+ "learning_rate": 1.1913978494623658e-05,
1292
+ "loss": 0.5508,
1293
+ "step": 214
1294
+ },
1295
+ {
1296
+ "epoch": 2.18,
1297
+ "learning_rate": 1.1870967741935484e-05,
1298
+ "loss": 0.5285,
1299
+ "step": 215
1300
+ },
1301
+ {
1302
+ "epoch": 2.19,
1303
+ "learning_rate": 1.1827956989247313e-05,
1304
+ "loss": 0.5449,
1305
+ "step": 216
1306
+ },
1307
+ {
1308
+ "epoch": 2.2,
1309
+ "learning_rate": 1.178494623655914e-05,
1310
+ "loss": 0.5877,
1311
+ "step": 217
1312
+ },
1313
+ {
1314
+ "epoch": 2.21,
1315
+ "learning_rate": 1.1741935483870967e-05,
1316
+ "loss": 0.6124,
1317
+ "step": 218
1318
+ },
1319
+ {
1320
+ "epoch": 2.22,
1321
+ "learning_rate": 1.1698924731182797e-05,
1322
+ "loss": 0.4578,
1323
+ "step": 219
1324
+ },
1325
+ {
1326
+ "epoch": 2.23,
1327
+ "learning_rate": 1.1655913978494624e-05,
1328
+ "loss": 0.5648,
1329
+ "step": 220
1330
+ },
1331
+ {
1332
+ "epoch": 2.24,
1333
+ "learning_rate": 1.1612903225806453e-05,
1334
+ "loss": 0.5497,
1335
+ "step": 221
1336
+ },
1337
+ {
1338
+ "epoch": 2.25,
1339
+ "learning_rate": 1.156989247311828e-05,
1340
+ "loss": 0.4563,
1341
+ "step": 222
1342
+ },
1343
+ {
1344
+ "epoch": 2.26,
1345
+ "learning_rate": 1.1526881720430108e-05,
1346
+ "loss": 0.5004,
1347
+ "step": 223
1348
+ },
1349
+ {
1350
+ "epoch": 2.27,
1351
+ "learning_rate": 1.1483870967741937e-05,
1352
+ "loss": 0.5579,
1353
+ "step": 224
1354
+ },
1355
+ {
1356
+ "epoch": 2.28,
1357
+ "learning_rate": 1.1440860215053764e-05,
1358
+ "loss": 0.5161,
1359
+ "step": 225
1360
+ },
1361
+ {
1362
+ "epoch": 2.29,
1363
+ "learning_rate": 1.1397849462365593e-05,
1364
+ "loss": 0.4854,
1365
+ "step": 226
1366
+ },
1367
+ {
1368
+ "epoch": 2.3,
1369
+ "learning_rate": 1.1354838709677421e-05,
1370
+ "loss": 0.5003,
1371
+ "step": 227
1372
+ },
1373
+ {
1374
+ "epoch": 2.31,
1375
+ "learning_rate": 1.1311827956989248e-05,
1376
+ "loss": 0.5601,
1377
+ "step": 228
1378
+ },
1379
+ {
1380
+ "epoch": 2.32,
1381
+ "learning_rate": 1.1268817204301077e-05,
1382
+ "loss": 0.4731,
1383
+ "step": 229
1384
+ },
1385
+ {
1386
+ "epoch": 2.33,
1387
+ "learning_rate": 1.1225806451612904e-05,
1388
+ "loss": 0.5628,
1389
+ "step": 230
1390
+ },
1391
+ {
1392
+ "epoch": 2.34,
1393
+ "learning_rate": 1.118279569892473e-05,
1394
+ "loss": 0.502,
1395
+ "step": 231
1396
+ },
1397
+ {
1398
+ "epoch": 2.35,
1399
+ "learning_rate": 1.1139784946236561e-05,
1400
+ "loss": 0.4052,
1401
+ "step": 232
1402
+ },
1403
+ {
1404
+ "epoch": 2.36,
1405
+ "learning_rate": 1.1096774193548388e-05,
1406
+ "loss": 0.5881,
1407
+ "step": 233
1408
+ },
1409
+ {
1410
+ "epoch": 2.37,
1411
+ "learning_rate": 1.1053763440860216e-05,
1412
+ "loss": 0.5344,
1413
+ "step": 234
1414
+ },
1415
+ {
1416
+ "epoch": 2.38,
1417
+ "learning_rate": 1.1010752688172043e-05,
1418
+ "loss": 0.5503,
1419
+ "step": 235
1420
+ },
1421
+ {
1422
+ "epoch": 2.39,
1423
+ "learning_rate": 1.096774193548387e-05,
1424
+ "loss": 0.4168,
1425
+ "step": 236
1426
+ },
1427
+ {
1428
+ "epoch": 2.4,
1429
+ "learning_rate": 1.09247311827957e-05,
1430
+ "loss": 0.4879,
1431
+ "step": 237
1432
+ },
1433
+ {
1434
+ "epoch": 2.41,
1435
+ "learning_rate": 1.0881720430107528e-05,
1436
+ "loss": 0.4623,
1437
+ "step": 238
1438
+ },
1439
+ {
1440
+ "epoch": 2.42,
1441
+ "learning_rate": 1.0838709677419356e-05,
1442
+ "loss": 0.4799,
1443
+ "step": 239
1444
+ },
1445
+ {
1446
+ "epoch": 2.43,
1447
+ "learning_rate": 1.0795698924731183e-05,
1448
+ "loss": 0.5277,
1449
+ "step": 240
1450
+ },
1451
+ {
1452
+ "epoch": 2.44,
1453
+ "learning_rate": 1.0752688172043012e-05,
1454
+ "loss": 0.6051,
1455
+ "step": 241
1456
+ },
1457
+ {
1458
+ "epoch": 2.45,
1459
+ "learning_rate": 1.070967741935484e-05,
1460
+ "loss": 0.5192,
1461
+ "step": 242
1462
+ },
1463
+ {
1464
+ "epoch": 2.46,
1465
+ "learning_rate": 1.0666666666666667e-05,
1466
+ "loss": 0.4111,
1467
+ "step": 243
1468
+ },
1469
+ {
1470
+ "epoch": 2.47,
1471
+ "learning_rate": 1.0623655913978494e-05,
1472
+ "loss": 0.5806,
1473
+ "step": 244
1474
+ },
1475
+ {
1476
+ "epoch": 2.48,
1477
+ "learning_rate": 1.0580645161290325e-05,
1478
+ "loss": 0.5616,
1479
+ "step": 245
1480
+ },
1481
+ {
1482
+ "epoch": 2.49,
1483
+ "learning_rate": 1.0537634408602151e-05,
1484
+ "loss": 0.5773,
1485
+ "step": 246
1486
+ },
1487
+ {
1488
+ "epoch": 2.5,
1489
+ "learning_rate": 1.049462365591398e-05,
1490
+ "loss": 0.4419,
1491
+ "step": 247
1492
+ },
1493
+ {
1494
+ "epoch": 2.51,
1495
+ "learning_rate": 1.0451612903225807e-05,
1496
+ "loss": 0.6086,
1497
+ "step": 248
1498
+ },
1499
+ {
1500
+ "epoch": 2.52,
1501
+ "learning_rate": 1.0408602150537634e-05,
1502
+ "loss": 0.5957,
1503
+ "step": 249
1504
+ },
1505
+ {
1506
+ "epoch": 2.53,
1507
+ "learning_rate": 1.0365591397849464e-05,
1508
+ "loss": 0.4609,
1509
+ "step": 250
1510
+ },
1511
+ {
1512
+ "epoch": 2.54,
1513
+ "learning_rate": 1.0322580645161291e-05,
1514
+ "loss": 0.4956,
1515
+ "step": 251
1516
+ },
1517
+ {
1518
+ "epoch": 2.55,
1519
+ "learning_rate": 1.027956989247312e-05,
1520
+ "loss": 0.5612,
1521
+ "step": 252
1522
+ },
1523
+ {
1524
+ "epoch": 2.56,
1525
+ "learning_rate": 1.0236559139784947e-05,
1526
+ "loss": 0.5157,
1527
+ "step": 253
1528
+ },
1529
+ {
1530
+ "epoch": 2.57,
1531
+ "learning_rate": 1.0193548387096774e-05,
1532
+ "loss": 0.4884,
1533
+ "step": 254
1534
+ },
1535
+ {
1536
+ "epoch": 2.58,
1537
+ "learning_rate": 1.0150537634408604e-05,
1538
+ "loss": 0.4576,
1539
+ "step": 255
1540
+ },
1541
+ {
1542
+ "epoch": 2.59,
1543
+ "learning_rate": 1.0107526881720431e-05,
1544
+ "loss": 0.4093,
1545
+ "step": 256
1546
+ },
1547
+ {
1548
+ "epoch": 2.6,
1549
+ "learning_rate": 1.0064516129032258e-05,
1550
+ "loss": 0.5521,
1551
+ "step": 257
1552
+ },
1553
+ {
1554
+ "epoch": 2.61,
1555
+ "learning_rate": 1.0021505376344087e-05,
1556
+ "loss": 0.6088,
1557
+ "step": 258
1558
+ },
1559
+ {
1560
+ "epoch": 2.62,
1561
+ "learning_rate": 9.978494623655915e-06,
1562
+ "loss": 0.4471,
1563
+ "step": 259
1564
+ },
1565
+ {
1566
+ "epoch": 2.63,
1567
+ "learning_rate": 9.935483870967742e-06,
1568
+ "loss": 0.488,
1569
+ "step": 260
1570
+ },
1571
+ {
1572
+ "epoch": 2.64,
1573
+ "learning_rate": 9.89247311827957e-06,
1574
+ "loss": 0.552,
1575
+ "step": 261
1576
+ },
1577
+ {
1578
+ "epoch": 2.65,
1579
+ "learning_rate": 9.8494623655914e-06,
1580
+ "loss": 0.4774,
1581
+ "step": 262
1582
+ },
1583
+ {
1584
+ "epoch": 2.66,
1585
+ "learning_rate": 9.806451612903226e-06,
1586
+ "loss": 0.5985,
1587
+ "step": 263
1588
+ },
1589
+ {
1590
+ "epoch": 2.67,
1591
+ "learning_rate": 9.763440860215055e-06,
1592
+ "loss": 0.4899,
1593
+ "step": 264
1594
+ },
1595
+ {
1596
+ "epoch": 2.68,
1597
+ "learning_rate": 9.720430107526882e-06,
1598
+ "loss": 0.5514,
1599
+ "step": 265
1600
+ },
1601
+ {
1602
+ "epoch": 2.69,
1603
+ "learning_rate": 9.67741935483871e-06,
1604
+ "loss": 0.5196,
1605
+ "step": 266
1606
+ },
1607
+ {
1608
+ "epoch": 2.7,
1609
+ "learning_rate": 9.634408602150539e-06,
1610
+ "loss": 0.4633,
1611
+ "step": 267
1612
+ },
1613
+ {
1614
+ "epoch": 2.71,
1615
+ "learning_rate": 9.591397849462366e-06,
1616
+ "loss": 0.4797,
1617
+ "step": 268
1618
+ },
1619
+ {
1620
+ "epoch": 2.72,
1621
+ "learning_rate": 9.548387096774195e-06,
1622
+ "loss": 0.6344,
1623
+ "step": 269
1624
+ },
1625
+ {
1626
+ "epoch": 2.73,
1627
+ "learning_rate": 9.505376344086023e-06,
1628
+ "loss": 0.4854,
1629
+ "step": 270
1630
+ },
1631
+ {
1632
+ "epoch": 2.74,
1633
+ "learning_rate": 9.46236559139785e-06,
1634
+ "loss": 0.4978,
1635
+ "step": 271
1636
+ },
1637
+ {
1638
+ "epoch": 2.75,
1639
+ "learning_rate": 9.419354838709677e-06,
1640
+ "loss": 0.4673,
1641
+ "step": 272
1642
+ },
1643
+ {
1644
+ "epoch": 2.76,
1645
+ "learning_rate": 9.376344086021506e-06,
1646
+ "loss": 0.5449,
1647
+ "step": 273
1648
+ },
1649
+ {
1650
+ "epoch": 2.77,
1651
+ "learning_rate": 9.333333333333334e-06,
1652
+ "loss": 0.4383,
1653
+ "step": 274
1654
+ },
1655
+ {
1656
+ "epoch": 2.78,
1657
+ "learning_rate": 9.290322580645163e-06,
1658
+ "loss": 0.4366,
1659
+ "step": 275
1660
+ },
1661
+ {
1662
+ "epoch": 2.79,
1663
+ "learning_rate": 9.24731182795699e-06,
1664
+ "loss": 0.496,
1665
+ "step": 276
1666
+ },
1667
+ {
1668
+ "epoch": 2.81,
1669
+ "learning_rate": 9.204301075268819e-06,
1670
+ "loss": 0.4166,
1671
+ "step": 277
1672
+ },
1673
+ {
1674
+ "epoch": 2.82,
1675
+ "learning_rate": 9.161290322580645e-06,
1676
+ "loss": 0.5266,
1677
+ "step": 278
1678
+ },
1679
+ {
1680
+ "epoch": 2.83,
1681
+ "learning_rate": 9.118279569892474e-06,
1682
+ "loss": 0.6554,
1683
+ "step": 279
1684
+ },
1685
+ {
1686
+ "epoch": 2.84,
1687
+ "learning_rate": 9.075268817204301e-06,
1688
+ "loss": 0.5783,
1689
+ "step": 280
1690
+ },
1691
+ {
1692
+ "epoch": 2.85,
1693
+ "learning_rate": 9.03225806451613e-06,
1694
+ "loss": 0.4905,
1695
+ "step": 281
1696
+ },
1697
+ {
1698
+ "epoch": 2.86,
1699
+ "learning_rate": 8.989247311827958e-06,
1700
+ "loss": 0.4702,
1701
+ "step": 282
1702
+ },
1703
+ {
1704
+ "epoch": 2.87,
1705
+ "learning_rate": 8.946236559139785e-06,
1706
+ "loss": 0.4972,
1707
+ "step": 283
1708
+ },
1709
+ {
1710
+ "epoch": 2.88,
1711
+ "learning_rate": 8.903225806451614e-06,
1712
+ "loss": 0.4287,
1713
+ "step": 284
1714
+ },
1715
+ {
1716
+ "epoch": 2.89,
1717
+ "learning_rate": 8.86021505376344e-06,
1718
+ "loss": 0.6365,
1719
+ "step": 285
1720
+ },
1721
+ {
1722
+ "epoch": 2.9,
1723
+ "learning_rate": 8.81720430107527e-06,
1724
+ "loss": 0.5102,
1725
+ "step": 286
1726
+ },
1727
+ {
1728
+ "epoch": 2.91,
1729
+ "learning_rate": 8.774193548387098e-06,
1730
+ "loss": 0.4436,
1731
+ "step": 287
1732
+ },
1733
+ {
1734
+ "epoch": 2.92,
1735
+ "learning_rate": 8.731182795698927e-06,
1736
+ "loss": 0.4853,
1737
+ "step": 288
1738
+ },
1739
+ {
1740
+ "epoch": 2.93,
1741
+ "learning_rate": 8.688172043010754e-06,
1742
+ "loss": 0.612,
1743
+ "step": 289
1744
+ },
1745
+ {
1746
+ "epoch": 2.94,
1747
+ "learning_rate": 8.64516129032258e-06,
1748
+ "loss": 0.51,
1749
+ "step": 290
1750
+ },
1751
+ {
1752
+ "epoch": 2.95,
1753
+ "learning_rate": 8.602150537634409e-06,
1754
+ "loss": 0.552,
1755
+ "step": 291
1756
+ },
1757
+ {
1758
+ "epoch": 2.96,
1759
+ "learning_rate": 8.559139784946238e-06,
1760
+ "loss": 0.5142,
1761
+ "step": 292
1762
+ },
1763
+ {
1764
+ "epoch": 2.97,
1765
+ "learning_rate": 8.516129032258065e-06,
1766
+ "loss": 0.5301,
1767
+ "step": 293
1768
+ },
1769
+ {
1770
+ "epoch": 2.98,
1771
+ "learning_rate": 8.473118279569893e-06,
1772
+ "loss": 0.5718,
1773
+ "step": 294
1774
+ },
1775
+ {
1776
+ "epoch": 2.99,
1777
+ "learning_rate": 8.430107526881722e-06,
1778
+ "loss": 0.5609,
1779
+ "step": 295
1780
+ },
1781
+ {
1782
+ "epoch": 3.0,
1783
+ "learning_rate": 8.387096774193549e-06,
1784
+ "loss": 0.6477,
1785
+ "step": 296
1786
+ },
1787
+ {
1788
+ "epoch": 3.01,
1789
+ "learning_rate": 8.344086021505376e-06,
1790
+ "loss": 0.2912,
1791
+ "step": 297
1792
+ },
1793
+ {
1794
+ "epoch": 3.02,
1795
+ "learning_rate": 8.301075268817204e-06,
1796
+ "loss": 0.2973,
1797
+ "step": 298
1798
+ },
1799
+ {
1800
+ "epoch": 3.03,
1801
+ "learning_rate": 8.258064516129033e-06,
1802
+ "loss": 0.2227,
1803
+ "step": 299
1804
+ },
1805
+ {
1806
+ "epoch": 3.04,
1807
+ "learning_rate": 8.215053763440862e-06,
1808
+ "loss": 0.2563,
1809
+ "step": 300
1810
+ },
1811
+ {
1812
+ "epoch": 3.05,
1813
+ "learning_rate": 8.172043010752689e-06,
1814
+ "loss": 0.2987,
1815
+ "step": 301
1816
+ },
1817
+ {
1818
+ "epoch": 3.06,
1819
+ "learning_rate": 8.129032258064517e-06,
1820
+ "loss": 0.2424,
1821
+ "step": 302
1822
+ },
1823
+ {
1824
+ "epoch": 3.07,
1825
+ "learning_rate": 8.086021505376344e-06,
1826
+ "loss": 0.284,
1827
+ "step": 303
1828
+ },
1829
+ {
1830
+ "epoch": 3.08,
1831
+ "learning_rate": 8.043010752688173e-06,
1832
+ "loss": 0.2172,
1833
+ "step": 304
1834
+ },
1835
+ {
1836
+ "epoch": 3.09,
1837
+ "learning_rate": 8.000000000000001e-06,
1838
+ "loss": 0.2786,
1839
+ "step": 305
1840
+ },
1841
+ {
1842
+ "epoch": 3.1,
1843
+ "learning_rate": 7.956989247311828e-06,
1844
+ "loss": 0.245,
1845
+ "step": 306
1846
+ },
1847
+ {
1848
+ "epoch": 3.11,
1849
+ "learning_rate": 7.913978494623657e-06,
1850
+ "loss": 0.241,
1851
+ "step": 307
1852
+ },
1853
+ {
1854
+ "epoch": 3.12,
1855
+ "learning_rate": 7.870967741935484e-06,
1856
+ "loss": 0.2075,
1857
+ "step": 308
1858
+ },
1859
+ {
1860
+ "epoch": 3.13,
1861
+ "learning_rate": 7.827956989247312e-06,
1862
+ "loss": 0.243,
1863
+ "step": 309
1864
+ },
1865
+ {
1866
+ "epoch": 3.14,
1867
+ "learning_rate": 7.78494623655914e-06,
1868
+ "loss": 0.2792,
1869
+ "step": 310
1870
+ },
1871
+ {
1872
+ "epoch": 3.15,
1873
+ "learning_rate": 7.741935483870968e-06,
1874
+ "loss": 0.2247,
1875
+ "step": 311
1876
+ },
1877
+ {
1878
+ "epoch": 3.16,
1879
+ "learning_rate": 7.698924731182797e-06,
1880
+ "loss": 0.2449,
1881
+ "step": 312
1882
+ },
1883
+ {
1884
+ "epoch": 3.17,
1885
+ "learning_rate": 7.655913978494625e-06,
1886
+ "loss": 0.2253,
1887
+ "step": 313
1888
+ },
1889
+ {
1890
+ "epoch": 3.18,
1891
+ "learning_rate": 7.612903225806451e-06,
1892
+ "loss": 0.3203,
1893
+ "step": 314
1894
+ },
1895
+ {
1896
+ "epoch": 3.19,
1897
+ "learning_rate": 7.56989247311828e-06,
1898
+ "loss": 0.1737,
1899
+ "step": 315
1900
+ },
1901
+ {
1902
+ "epoch": 3.2,
1903
+ "learning_rate": 7.526881720430108e-06,
1904
+ "loss": 0.2394,
1905
+ "step": 316
1906
+ },
1907
+ {
1908
+ "epoch": 3.21,
1909
+ "learning_rate": 7.483870967741936e-06,
1910
+ "loss": 0.3014,
1911
+ "step": 317
1912
+ },
1913
+ {
1914
+ "epoch": 3.22,
1915
+ "learning_rate": 7.440860215053764e-06,
1916
+ "loss": 0.2347,
1917
+ "step": 318
1918
+ },
1919
+ {
1920
+ "epoch": 3.23,
1921
+ "learning_rate": 7.397849462365592e-06,
1922
+ "loss": 0.2315,
1923
+ "step": 319
1924
+ },
1925
+ {
1926
+ "epoch": 3.24,
1927
+ "learning_rate": 7.35483870967742e-06,
1928
+ "loss": 0.2328,
1929
+ "step": 320
1930
+ },
1931
+ {
1932
+ "epoch": 3.25,
1933
+ "learning_rate": 7.311827956989248e-06,
1934
+ "loss": 0.2297,
1935
+ "step": 321
1936
+ },
1937
+ {
1938
+ "epoch": 3.26,
1939
+ "learning_rate": 7.268817204301076e-06,
1940
+ "loss": 0.3137,
1941
+ "step": 322
1942
+ },
1943
+ {
1944
+ "epoch": 3.27,
1945
+ "learning_rate": 7.225806451612903e-06,
1946
+ "loss": 0.2103,
1947
+ "step": 323
1948
+ },
1949
+ {
1950
+ "epoch": 3.28,
1951
+ "learning_rate": 7.182795698924732e-06,
1952
+ "loss": 0.1881,
1953
+ "step": 324
1954
+ },
1955
+ {
1956
+ "epoch": 3.29,
1957
+ "learning_rate": 7.139784946236559e-06,
1958
+ "loss": 0.2187,
1959
+ "step": 325
1960
+ },
1961
+ {
1962
+ "epoch": 3.3,
1963
+ "learning_rate": 7.096774193548388e-06,
1964
+ "loss": 0.2592,
1965
+ "step": 326
1966
+ },
1967
+ {
1968
+ "epoch": 3.31,
1969
+ "learning_rate": 7.053763440860215e-06,
1970
+ "loss": 0.1173,
1971
+ "step": 327
1972
+ },
1973
+ {
1974
+ "epoch": 3.32,
1975
+ "learning_rate": 7.010752688172044e-06,
1976
+ "loss": 0.1956,
1977
+ "step": 328
1978
+ },
1979
+ {
1980
+ "epoch": 3.33,
1981
+ "learning_rate": 6.967741935483871e-06,
1982
+ "loss": 0.214,
1983
+ "step": 329
1984
+ },
1985
+ {
1986
+ "epoch": 3.34,
1987
+ "learning_rate": 6.9247311827957e-06,
1988
+ "loss": 0.211,
1989
+ "step": 330
1990
+ },
1991
+ {
1992
+ "epoch": 3.35,
1993
+ "learning_rate": 6.881720430107528e-06,
1994
+ "loss": 0.2597,
1995
+ "step": 331
1996
+ },
1997
+ {
1998
+ "epoch": 3.36,
1999
+ "learning_rate": 6.838709677419355e-06,
2000
+ "loss": 0.1829,
2001
+ "step": 332
2002
+ },
2003
+ {
2004
+ "epoch": 3.37,
2005
+ "learning_rate": 6.795698924731183e-06,
2006
+ "loss": 0.2693,
2007
+ "step": 333
2008
+ },
2009
+ {
2010
+ "epoch": 3.38,
2011
+ "learning_rate": 6.752688172043012e-06,
2012
+ "loss": 0.2176,
2013
+ "step": 334
2014
+ },
2015
+ {
2016
+ "epoch": 3.39,
2017
+ "learning_rate": 6.70967741935484e-06,
2018
+ "loss": 0.1621,
2019
+ "step": 335
2020
+ },
2021
+ {
2022
+ "epoch": 3.4,
2023
+ "learning_rate": 6.666666666666667e-06,
2024
+ "loss": 0.2793,
2025
+ "step": 336
2026
+ },
2027
+ {
2028
+ "epoch": 3.41,
2029
+ "learning_rate": 6.623655913978495e-06,
2030
+ "loss": 0.22,
2031
+ "step": 337
2032
+ },
2033
+ {
2034
+ "epoch": 3.42,
2035
+ "learning_rate": 6.580645161290323e-06,
2036
+ "loss": 0.2257,
2037
+ "step": 338
2038
+ },
2039
+ {
2040
+ "epoch": 3.43,
2041
+ "learning_rate": 6.537634408602152e-06,
2042
+ "loss": 0.2905,
2043
+ "step": 339
2044
+ },
2045
+ {
2046
+ "epoch": 3.44,
2047
+ "learning_rate": 6.494623655913979e-06,
2048
+ "loss": 0.2309,
2049
+ "step": 340
2050
+ },
2051
+ {
2052
+ "epoch": 3.45,
2053
+ "learning_rate": 6.451612903225806e-06,
2054
+ "loss": 0.2152,
2055
+ "step": 341
2056
+ },
2057
+ {
2058
+ "epoch": 3.46,
2059
+ "learning_rate": 6.408602150537635e-06,
2060
+ "loss": 0.3047,
2061
+ "step": 342
2062
+ },
2063
+ {
2064
+ "epoch": 3.47,
2065
+ "learning_rate": 6.365591397849464e-06,
2066
+ "loss": 0.2,
2067
+ "step": 343
2068
+ },
2069
+ {
2070
+ "epoch": 3.48,
2071
+ "learning_rate": 6.3225806451612906e-06,
2072
+ "loss": 0.1949,
2073
+ "step": 344
2074
+ },
2075
+ {
2076
+ "epoch": 3.49,
2077
+ "learning_rate": 6.279569892473118e-06,
2078
+ "loss": 0.2897,
2079
+ "step": 345
2080
+ },
2081
+ {
2082
+ "epoch": 3.5,
2083
+ "learning_rate": 6.236559139784947e-06,
2084
+ "loss": 0.2341,
2085
+ "step": 346
2086
+ },
2087
+ {
2088
+ "epoch": 3.51,
2089
+ "learning_rate": 6.193548387096775e-06,
2090
+ "loss": 0.286,
2091
+ "step": 347
2092
+ },
2093
+ {
2094
+ "epoch": 3.52,
2095
+ "learning_rate": 6.150537634408603e-06,
2096
+ "loss": 0.291,
2097
+ "step": 348
2098
+ },
2099
+ {
2100
+ "epoch": 3.53,
2101
+ "learning_rate": 6.10752688172043e-06,
2102
+ "loss": 0.2408,
2103
+ "step": 349
2104
+ },
2105
+ {
2106
+ "epoch": 3.54,
2107
+ "learning_rate": 6.064516129032259e-06,
2108
+ "loss": 0.2166,
2109
+ "step": 350
2110
+ },
2111
+ {
2112
+ "epoch": 3.55,
2113
+ "learning_rate": 6.021505376344087e-06,
2114
+ "loss": 0.213,
2115
+ "step": 351
2116
+ },
2117
+ {
2118
+ "epoch": 3.56,
2119
+ "learning_rate": 5.978494623655915e-06,
2120
+ "loss": 0.2057,
2121
+ "step": 352
2122
+ },
2123
+ {
2124
+ "epoch": 3.57,
2125
+ "learning_rate": 5.935483870967742e-06,
2126
+ "loss": 0.2169,
2127
+ "step": 353
2128
+ },
2129
+ {
2130
+ "epoch": 3.58,
2131
+ "learning_rate": 5.89247311827957e-06,
2132
+ "loss": 0.19,
2133
+ "step": 354
2134
+ },
2135
+ {
2136
+ "epoch": 3.59,
2137
+ "learning_rate": 5.849462365591399e-06,
2138
+ "loss": 0.2565,
2139
+ "step": 355
2140
+ },
2141
+ {
2142
+ "epoch": 3.61,
2143
+ "learning_rate": 5.806451612903226e-06,
2144
+ "loss": 0.2503,
2145
+ "step": 356
2146
+ },
2147
+ {
2148
+ "epoch": 3.62,
2149
+ "learning_rate": 5.763440860215054e-06,
2150
+ "loss": 0.207,
2151
+ "step": 357
2152
+ },
2153
+ {
2154
+ "epoch": 3.63,
2155
+ "learning_rate": 5.720430107526882e-06,
2156
+ "loss": 0.1996,
2157
+ "step": 358
2158
+ },
2159
+ {
2160
+ "epoch": 3.64,
2161
+ "learning_rate": 5.677419354838711e-06,
2162
+ "loss": 0.2092,
2163
+ "step": 359
2164
+ },
2165
+ {
2166
+ "epoch": 3.65,
2167
+ "learning_rate": 5.634408602150538e-06,
2168
+ "loss": 0.1877,
2169
+ "step": 360
2170
+ },
2171
+ {
2172
+ "epoch": 3.66,
2173
+ "learning_rate": 5.591397849462365e-06,
2174
+ "loss": 0.2511,
2175
+ "step": 361
2176
+ },
2177
+ {
2178
+ "epoch": 3.67,
2179
+ "learning_rate": 5.548387096774194e-06,
2180
+ "loss": 0.2252,
2181
+ "step": 362
2182
+ },
2183
+ {
2184
+ "epoch": 3.68,
2185
+ "learning_rate": 5.505376344086022e-06,
2186
+ "loss": 0.212,
2187
+ "step": 363
2188
+ },
2189
+ {
2190
+ "epoch": 3.69,
2191
+ "learning_rate": 5.46236559139785e-06,
2192
+ "loss": 0.2778,
2193
+ "step": 364
2194
+ },
2195
+ {
2196
+ "epoch": 3.7,
2197
+ "learning_rate": 5.419354838709678e-06,
2198
+ "loss": 0.2931,
2199
+ "step": 365
2200
+ },
2201
+ {
2202
+ "epoch": 3.71,
2203
+ "learning_rate": 5.376344086021506e-06,
2204
+ "loss": 0.2711,
2205
+ "step": 366
2206
+ },
2207
+ {
2208
+ "epoch": 3.72,
2209
+ "learning_rate": 5.333333333333334e-06,
2210
+ "loss": 0.2175,
2211
+ "step": 367
2212
+ },
2213
+ {
2214
+ "epoch": 3.73,
2215
+ "learning_rate": 5.290322580645162e-06,
2216
+ "loss": 0.1713,
2217
+ "step": 368
2218
+ },
2219
+ {
2220
+ "epoch": 3.74,
2221
+ "learning_rate": 5.24731182795699e-06,
2222
+ "loss": 0.2586,
2223
+ "step": 369
2224
+ },
2225
+ {
2226
+ "epoch": 3.75,
2227
+ "learning_rate": 5.204301075268817e-06,
2228
+ "loss": 0.249,
2229
+ "step": 370
2230
+ },
2231
+ {
2232
+ "epoch": 3.76,
2233
+ "learning_rate": 5.161290322580646e-06,
2234
+ "loss": 0.1845,
2235
+ "step": 371
2236
+ },
2237
+ {
2238
+ "epoch": 3.77,
2239
+ "learning_rate": 5.118279569892473e-06,
2240
+ "loss": 0.2393,
2241
+ "step": 372
2242
+ },
2243
+ {
2244
+ "epoch": 3.78,
2245
+ "learning_rate": 5.075268817204302e-06,
2246
+ "loss": 0.2239,
2247
+ "step": 373
2248
+ },
2249
+ {
2250
+ "epoch": 3.79,
2251
+ "learning_rate": 5.032258064516129e-06,
2252
+ "loss": 0.247,
2253
+ "step": 374
2254
+ },
2255
+ {
2256
+ "epoch": 3.8,
2257
+ "learning_rate": 4.9892473118279576e-06,
2258
+ "loss": 0.2714,
2259
+ "step": 375
2260
+ },
2261
+ {
2262
+ "epoch": 3.81,
2263
+ "learning_rate": 4.946236559139785e-06,
2264
+ "loss": 0.256,
2265
+ "step": 376
2266
+ },
2267
+ {
2268
+ "epoch": 3.82,
2269
+ "learning_rate": 4.903225806451613e-06,
2270
+ "loss": 0.253,
2271
+ "step": 377
2272
+ },
2273
+ {
2274
+ "epoch": 3.83,
2275
+ "learning_rate": 4.860215053763441e-06,
2276
+ "loss": 0.2299,
2277
+ "step": 378
2278
+ },
2279
+ {
2280
+ "epoch": 3.84,
2281
+ "learning_rate": 4.8172043010752695e-06,
2282
+ "loss": 0.2029,
2283
+ "step": 379
2284
+ },
2285
+ {
2286
+ "epoch": 3.85,
2287
+ "learning_rate": 4.774193548387097e-06,
2288
+ "loss": 0.2053,
2289
+ "step": 380
2290
+ },
2291
+ {
2292
+ "epoch": 3.86,
2293
+ "learning_rate": 4.731182795698925e-06,
2294
+ "loss": 0.1907,
2295
+ "step": 381
2296
+ },
2297
+ {
2298
+ "epoch": 3.87,
2299
+ "learning_rate": 4.688172043010753e-06,
2300
+ "loss": 0.271,
2301
+ "step": 382
2302
+ },
2303
+ {
2304
+ "epoch": 3.88,
2305
+ "learning_rate": 4.6451612903225815e-06,
2306
+ "loss": 0.2088,
2307
+ "step": 383
2308
+ },
2309
+ {
2310
+ "epoch": 3.89,
2311
+ "learning_rate": 4.602150537634409e-06,
2312
+ "loss": 0.251,
2313
+ "step": 384
2314
+ },
2315
+ {
2316
+ "epoch": 3.9,
2317
+ "learning_rate": 4.559139784946237e-06,
2318
+ "loss": 0.2438,
2319
+ "step": 385
2320
+ },
2321
+ {
2322
+ "epoch": 3.91,
2323
+ "learning_rate": 4.516129032258065e-06,
2324
+ "loss": 0.272,
2325
+ "step": 386
2326
+ },
2327
+ {
2328
+ "epoch": 3.92,
2329
+ "learning_rate": 4.473118279569893e-06,
2330
+ "loss": 0.1858,
2331
+ "step": 387
2332
+ },
2333
+ {
2334
+ "epoch": 3.93,
2335
+ "learning_rate": 4.43010752688172e-06,
2336
+ "loss": 0.2267,
2337
+ "step": 388
2338
+ },
2339
+ {
2340
+ "epoch": 3.94,
2341
+ "learning_rate": 4.387096774193549e-06,
2342
+ "loss": 0.2414,
2343
+ "step": 389
2344
+ },
2345
+ {
2346
+ "epoch": 3.95,
2347
+ "learning_rate": 4.344086021505377e-06,
2348
+ "loss": 0.2263,
2349
+ "step": 390
2350
+ },
2351
+ {
2352
+ "epoch": 3.96,
2353
+ "learning_rate": 4.3010752688172045e-06,
2354
+ "loss": 0.2687,
2355
+ "step": 391
2356
+ },
2357
+ {
2358
+ "epoch": 3.97,
2359
+ "learning_rate": 4.258064516129032e-06,
2360
+ "loss": 0.1808,
2361
+ "step": 392
2362
+ },
2363
+ {
2364
+ "epoch": 3.98,
2365
+ "learning_rate": 4.215053763440861e-06,
2366
+ "loss": 0.2385,
2367
+ "step": 393
2368
+ },
2369
+ {
2370
+ "epoch": 3.99,
2371
+ "learning_rate": 4.172043010752688e-06,
2372
+ "loss": 0.1518,
2373
+ "step": 394
2374
+ },
2375
+ {
2376
+ "epoch": 4.0,
2377
+ "learning_rate": 4.1290322580645165e-06,
2378
+ "loss": 0.212,
2379
+ "step": 395
2380
+ },
2381
+ {
2382
+ "epoch": 4.01,
2383
+ "learning_rate": 4.086021505376344e-06,
2384
+ "loss": 0.1282,
2385
+ "step": 396
2386
+ },
2387
+ {
2388
+ "epoch": 4.02,
2389
+ "learning_rate": 4.043010752688172e-06,
2390
+ "loss": 0.1112,
2391
+ "step": 397
2392
+ },
2393
+ {
2394
+ "epoch": 4.03,
2395
+ "learning_rate": 4.000000000000001e-06,
2396
+ "loss": 0.0839,
2397
+ "step": 398
2398
+ },
2399
+ {
2400
+ "epoch": 4.04,
2401
+ "learning_rate": 3.9569892473118284e-06,
2402
+ "loss": 0.1306,
2403
+ "step": 399
2404
+ },
2405
+ {
2406
+ "epoch": 4.05,
2407
+ "learning_rate": 3.913978494623656e-06,
2408
+ "loss": 0.0748,
2409
+ "step": 400
2410
+ },
2411
+ {
2412
+ "epoch": 4.06,
2413
+ "learning_rate": 3.870967741935484e-06,
2414
+ "loss": 0.119,
2415
+ "step": 401
2416
+ },
2417
+ {
2418
+ "epoch": 4.07,
2419
+ "learning_rate": 3.827956989247313e-06,
2420
+ "loss": 0.0837,
2421
+ "step": 402
2422
+ },
2423
+ {
2424
+ "epoch": 4.08,
2425
+ "learning_rate": 3.78494623655914e-06,
2426
+ "loss": 0.1067,
2427
+ "step": 403
2428
+ },
2429
+ {
2430
+ "epoch": 4.09,
2431
+ "learning_rate": 3.741935483870968e-06,
2432
+ "loss": 0.1242,
2433
+ "step": 404
2434
+ },
2435
+ {
2436
+ "epoch": 4.1,
2437
+ "learning_rate": 3.698924731182796e-06,
2438
+ "loss": 0.0896,
2439
+ "step": 405
2440
+ },
2441
+ {
2442
+ "epoch": 4.11,
2443
+ "learning_rate": 3.655913978494624e-06,
2444
+ "loss": 0.0752,
2445
+ "step": 406
2446
+ },
2447
+ {
2448
+ "epoch": 4.12,
2449
+ "learning_rate": 3.6129032258064515e-06,
2450
+ "loss": 0.0812,
2451
+ "step": 407
2452
+ },
2453
+ {
2454
+ "epoch": 4.13,
2455
+ "learning_rate": 3.5698924731182797e-06,
2456
+ "loss": 0.0839,
2457
+ "step": 408
2458
+ },
2459
+ {
2460
+ "epoch": 4.14,
2461
+ "learning_rate": 3.5268817204301075e-06,
2462
+ "loss": 0.1174,
2463
+ "step": 409
2464
+ },
2465
+ {
2466
+ "epoch": 4.15,
2467
+ "learning_rate": 3.4838709677419357e-06,
2468
+ "loss": 0.1314,
2469
+ "step": 410
2470
+ },
2471
+ {
2472
+ "epoch": 4.16,
2473
+ "learning_rate": 3.440860215053764e-06,
2474
+ "loss": 0.1054,
2475
+ "step": 411
2476
+ },
2477
+ {
2478
+ "epoch": 4.17,
2479
+ "learning_rate": 3.3978494623655917e-06,
2480
+ "loss": 0.0968,
2481
+ "step": 412
2482
+ },
2483
+ {
2484
+ "epoch": 4.18,
2485
+ "learning_rate": 3.35483870967742e-06,
2486
+ "loss": 0.1095,
2487
+ "step": 413
2488
+ },
2489
+ {
2490
+ "epoch": 4.19,
2491
+ "learning_rate": 3.3118279569892476e-06,
2492
+ "loss": 0.1358,
2493
+ "step": 414
2494
+ },
2495
+ {
2496
+ "epoch": 4.2,
2497
+ "learning_rate": 3.268817204301076e-06,
2498
+ "loss": 0.0977,
2499
+ "step": 415
2500
+ },
2501
+ {
2502
+ "epoch": 4.21,
2503
+ "learning_rate": 3.225806451612903e-06,
2504
+ "loss": 0.1667,
2505
+ "step": 416
2506
+ },
2507
+ {
2508
+ "epoch": 4.22,
2509
+ "learning_rate": 3.182795698924732e-06,
2510
+ "loss": 0.0975,
2511
+ "step": 417
2512
+ },
2513
+ {
2514
+ "epoch": 4.23,
2515
+ "learning_rate": 3.139784946236559e-06,
2516
+ "loss": 0.0999,
2517
+ "step": 418
2518
+ },
2519
+ {
2520
+ "epoch": 4.24,
2521
+ "learning_rate": 3.0967741935483874e-06,
2522
+ "loss": 0.0908,
2523
+ "step": 419
2524
+ },
2525
+ {
2526
+ "epoch": 4.25,
2527
+ "learning_rate": 3.053763440860215e-06,
2528
+ "loss": 0.1005,
2529
+ "step": 420
2530
+ },
2531
+ {
2532
+ "epoch": 4.26,
2533
+ "learning_rate": 3.0107526881720433e-06,
2534
+ "loss": 0.0656,
2535
+ "step": 421
2536
+ },
2537
+ {
2538
+ "epoch": 4.27,
2539
+ "learning_rate": 2.967741935483871e-06,
2540
+ "loss": 0.1301,
2541
+ "step": 422
2542
+ },
2543
+ {
2544
+ "epoch": 4.28,
2545
+ "learning_rate": 2.9247311827956993e-06,
2546
+ "loss": 0.0677,
2547
+ "step": 423
2548
+ },
2549
+ {
2550
+ "epoch": 4.29,
2551
+ "learning_rate": 2.881720430107527e-06,
2552
+ "loss": 0.0866,
2553
+ "step": 424
2554
+ },
2555
+ {
2556
+ "epoch": 4.3,
2557
+ "learning_rate": 2.8387096774193553e-06,
2558
+ "loss": 0.0847,
2559
+ "step": 425
2560
+ },
2561
+ {
2562
+ "epoch": 4.31,
2563
+ "learning_rate": 2.7956989247311827e-06,
2564
+ "loss": 0.1039,
2565
+ "step": 426
2566
+ },
2567
+ {
2568
+ "epoch": 4.32,
2569
+ "learning_rate": 2.752688172043011e-06,
2570
+ "loss": 0.0864,
2571
+ "step": 427
2572
+ },
2573
+ {
2574
+ "epoch": 4.33,
2575
+ "learning_rate": 2.709677419354839e-06,
2576
+ "loss": 0.1166,
2577
+ "step": 428
2578
+ },
2579
+ {
2580
+ "epoch": 4.34,
2581
+ "learning_rate": 2.666666666666667e-06,
2582
+ "loss": 0.0743,
2583
+ "step": 429
2584
+ },
2585
+ {
2586
+ "epoch": 4.35,
2587
+ "learning_rate": 2.623655913978495e-06,
2588
+ "loss": 0.1162,
2589
+ "step": 430
2590
+ },
2591
+ {
2592
+ "epoch": 4.36,
2593
+ "learning_rate": 2.580645161290323e-06,
2594
+ "loss": 0.1068,
2595
+ "step": 431
2596
+ },
2597
+ {
2598
+ "epoch": 4.37,
2599
+ "learning_rate": 2.537634408602151e-06,
2600
+ "loss": 0.12,
2601
+ "step": 432
2602
+ },
2603
+ {
2604
+ "epoch": 4.38,
2605
+ "learning_rate": 2.4946236559139788e-06,
2606
+ "loss": 0.0886,
2607
+ "step": 433
2608
+ },
2609
+ {
2610
+ "epoch": 4.39,
2611
+ "learning_rate": 2.4516129032258066e-06,
2612
+ "loss": 0.0796,
2613
+ "step": 434
2614
+ },
2615
+ {
2616
+ "epoch": 4.41,
2617
+ "learning_rate": 2.4086021505376348e-06,
2618
+ "loss": 0.0748,
2619
+ "step": 435
2620
+ },
2621
+ {
2622
+ "epoch": 4.42,
2623
+ "learning_rate": 2.3655913978494625e-06,
2624
+ "loss": 0.1078,
2625
+ "step": 436
2626
+ },
2627
+ {
2628
+ "epoch": 4.43,
2629
+ "learning_rate": 2.3225806451612907e-06,
2630
+ "loss": 0.1135,
2631
+ "step": 437
2632
+ },
2633
+ {
2634
+ "epoch": 4.44,
2635
+ "learning_rate": 2.2795698924731185e-06,
2636
+ "loss": 0.1138,
2637
+ "step": 438
2638
+ },
2639
+ {
2640
+ "epoch": 4.45,
2641
+ "learning_rate": 2.2365591397849463e-06,
2642
+ "loss": 0.0867,
2643
+ "step": 439
2644
+ },
2645
+ {
2646
+ "epoch": 4.46,
2647
+ "learning_rate": 2.1935483870967745e-06,
2648
+ "loss": 0.0923,
2649
+ "step": 440
2650
+ },
2651
+ {
2652
+ "epoch": 4.47,
2653
+ "learning_rate": 2.1505376344086023e-06,
2654
+ "loss": 0.0791,
2655
+ "step": 441
2656
+ },
2657
+ {
2658
+ "epoch": 4.48,
2659
+ "learning_rate": 2.1075268817204305e-06,
2660
+ "loss": 0.0905,
2661
+ "step": 442
2662
+ },
2663
+ {
2664
+ "epoch": 4.49,
2665
+ "learning_rate": 2.0645161290322582e-06,
2666
+ "loss": 0.0952,
2667
+ "step": 443
2668
+ },
2669
+ {
2670
+ "epoch": 4.5,
2671
+ "learning_rate": 2.021505376344086e-06,
2672
+ "loss": 0.1213,
2673
+ "step": 444
2674
+ },
2675
+ {
2676
+ "epoch": 4.51,
2677
+ "learning_rate": 1.9784946236559142e-06,
2678
+ "loss": 0.0832,
2679
+ "step": 445
2680
+ },
2681
+ {
2682
+ "epoch": 4.52,
2683
+ "learning_rate": 1.935483870967742e-06,
2684
+ "loss": 0.1241,
2685
+ "step": 446
2686
+ },
2687
+ {
2688
+ "epoch": 4.53,
2689
+ "learning_rate": 1.89247311827957e-06,
2690
+ "loss": 0.0873,
2691
+ "step": 447
2692
+ },
2693
+ {
2694
+ "epoch": 4.54,
2695
+ "learning_rate": 1.849462365591398e-06,
2696
+ "loss": 0.0956,
2697
+ "step": 448
2698
+ },
2699
+ {
2700
+ "epoch": 4.55,
2701
+ "learning_rate": 1.8064516129032258e-06,
2702
+ "loss": 0.0793,
2703
+ "step": 449
2704
+ },
2705
+ {
2706
+ "epoch": 4.56,
2707
+ "learning_rate": 1.7634408602150537e-06,
2708
+ "loss": 0.1163,
2709
+ "step": 450
2710
+ },
2711
+ {
2712
+ "epoch": 4.57,
2713
+ "learning_rate": 1.720430107526882e-06,
2714
+ "loss": 0.1128,
2715
+ "step": 451
2716
+ },
2717
+ {
2718
+ "epoch": 4.58,
2719
+ "learning_rate": 1.67741935483871e-06,
2720
+ "loss": 0.1018,
2721
+ "step": 452
2722
+ },
2723
+ {
2724
+ "epoch": 4.59,
2725
+ "learning_rate": 1.634408602150538e-06,
2726
+ "loss": 0.0715,
2727
+ "step": 453
2728
+ },
2729
+ {
2730
+ "epoch": 4.6,
2731
+ "learning_rate": 1.591397849462366e-06,
2732
+ "loss": 0.1088,
2733
+ "step": 454
2734
+ },
2735
+ {
2736
+ "epoch": 4.61,
2737
+ "learning_rate": 1.5483870967741937e-06,
2738
+ "loss": 0.1119,
2739
+ "step": 455
2740
+ },
2741
+ {
2742
+ "epoch": 4.62,
2743
+ "learning_rate": 1.5053763440860217e-06,
2744
+ "loss": 0.1086,
2745
+ "step": 456
2746
+ },
2747
+ {
2748
+ "epoch": 4.63,
2749
+ "learning_rate": 1.4623655913978497e-06,
2750
+ "loss": 0.049,
2751
+ "step": 457
2752
+ },
2753
+ {
2754
+ "epoch": 4.64,
2755
+ "learning_rate": 1.4193548387096776e-06,
2756
+ "loss": 0.1056,
2757
+ "step": 458
2758
+ },
2759
+ {
2760
+ "epoch": 4.65,
2761
+ "learning_rate": 1.3763440860215054e-06,
2762
+ "loss": 0.1173,
2763
+ "step": 459
2764
+ },
2765
+ {
2766
+ "epoch": 4.66,
2767
+ "learning_rate": 1.3333333333333334e-06,
2768
+ "loss": 0.0988,
2769
+ "step": 460
2770
+ },
2771
+ {
2772
+ "epoch": 4.67,
2773
+ "learning_rate": 1.2903225806451614e-06,
2774
+ "loss": 0.1257,
2775
+ "step": 461
2776
+ },
2777
+ {
2778
+ "epoch": 4.68,
2779
+ "learning_rate": 1.2473118279569894e-06,
2780
+ "loss": 0.0812,
2781
+ "step": 462
2782
+ },
2783
+ {
2784
+ "epoch": 4.69,
2785
+ "learning_rate": 1.2043010752688174e-06,
2786
+ "loss": 0.0941,
2787
+ "step": 463
2788
+ },
2789
+ {
2790
+ "epoch": 4.7,
2791
+ "learning_rate": 1.1612903225806454e-06,
2792
+ "loss": 0.0967,
2793
+ "step": 464
2794
+ },
2795
+ {
2796
+ "epoch": 4.71,
2797
+ "learning_rate": 1.1182795698924731e-06,
2798
+ "loss": 0.0848,
2799
+ "step": 465
2800
+ },
2801
+ {
2802
+ "epoch": 4.72,
2803
+ "learning_rate": 1.0752688172043011e-06,
2804
+ "loss": 0.1152,
2805
+ "step": 466
2806
+ },
2807
+ {
2808
+ "epoch": 4.73,
2809
+ "learning_rate": 1.0322580645161291e-06,
2810
+ "loss": 0.1088,
2811
+ "step": 467
2812
+ },
2813
+ {
2814
+ "epoch": 4.74,
2815
+ "learning_rate": 9.892473118279571e-07,
2816
+ "loss": 0.134,
2817
+ "step": 468
2818
+ },
2819
+ {
2820
+ "epoch": 4.75,
2821
+ "learning_rate": 9.46236559139785e-07,
2822
+ "loss": 0.0838,
2823
+ "step": 469
2824
+ },
2825
+ {
2826
+ "epoch": 4.76,
2827
+ "learning_rate": 9.032258064516129e-07,
2828
+ "loss": 0.0887,
2829
+ "step": 470
2830
+ },
2831
+ {
2832
+ "epoch": 4.77,
2833
+ "learning_rate": 8.60215053763441e-07,
2834
+ "loss": 0.1532,
2835
+ "step": 471
2836
+ },
2837
+ {
2838
+ "epoch": 4.78,
2839
+ "learning_rate": 8.17204301075269e-07,
2840
+ "loss": 0.0614,
2841
+ "step": 472
2842
+ },
2843
+ {
2844
+ "epoch": 4.79,
2845
+ "learning_rate": 7.741935483870968e-07,
2846
+ "loss": 0.0752,
2847
+ "step": 473
2848
+ },
2849
+ {
2850
+ "epoch": 4.8,
2851
+ "learning_rate": 7.311827956989248e-07,
2852
+ "loss": 0.0647,
2853
+ "step": 474
2854
+ },
2855
+ {
2856
+ "epoch": 4.81,
2857
+ "learning_rate": 6.881720430107527e-07,
2858
+ "loss": 0.0669,
2859
+ "step": 475
2860
+ },
2861
+ {
2862
+ "epoch": 4.82,
2863
+ "learning_rate": 6.451612903225807e-07,
2864
+ "loss": 0.141,
2865
+ "step": 476
2866
+ },
2867
+ {
2868
+ "epoch": 4.83,
2869
+ "learning_rate": 6.021505376344087e-07,
2870
+ "loss": 0.1032,
2871
+ "step": 477
2872
+ },
2873
+ {
2874
+ "epoch": 4.84,
2875
+ "learning_rate": 5.591397849462366e-07,
2876
+ "loss": 0.1112,
2877
+ "step": 478
2878
+ },
2879
+ {
2880
+ "epoch": 4.85,
2881
+ "learning_rate": 5.161290322580646e-07,
2882
+ "loss": 0.0817,
2883
+ "step": 479
2884
+ },
2885
+ {
2886
+ "epoch": 4.86,
2887
+ "learning_rate": 4.731182795698925e-07,
2888
+ "loss": 0.0868,
2889
+ "step": 480
2890
+ },
2891
+ {
2892
+ "epoch": 4.87,
2893
+ "learning_rate": 4.301075268817205e-07,
2894
+ "loss": 0.1169,
2895
+ "step": 481
2896
+ },
2897
+ {
2898
+ "epoch": 4.88,
2899
+ "learning_rate": 3.870967741935484e-07,
2900
+ "loss": 0.1297,
2901
+ "step": 482
2902
+ },
2903
+ {
2904
+ "epoch": 4.89,
2905
+ "learning_rate": 3.4408602150537636e-07,
2906
+ "loss": 0.0974,
2907
+ "step": 483
2908
+ },
2909
+ {
2910
+ "epoch": 4.9,
2911
+ "learning_rate": 3.0107526881720434e-07,
2912
+ "loss": 0.0888,
2913
+ "step": 484
2914
+ },
2915
+ {
2916
+ "epoch": 4.91,
2917
+ "learning_rate": 2.580645161290323e-07,
2918
+ "loss": 0.1391,
2919
+ "step": 485
2920
+ },
2921
+ {
2922
+ "epoch": 4.92,
2923
+ "learning_rate": 2.1505376344086024e-07,
2924
+ "loss": 0.0777,
2925
+ "step": 486
2926
+ },
2927
+ {
2928
+ "epoch": 4.93,
2929
+ "learning_rate": 1.7204301075268818e-07,
2930
+ "loss": 0.0964,
2931
+ "step": 487
2932
+ },
2933
+ {
2934
+ "epoch": 4.94,
2935
+ "learning_rate": 1.2903225806451614e-07,
2936
+ "loss": 0.0738,
2937
+ "step": 488
2938
+ },
2939
+ {
2940
+ "epoch": 4.95,
2941
+ "learning_rate": 8.602150537634409e-08,
2942
+ "loss": 0.1061,
2943
+ "step": 489
2944
+ },
2945
+ {
2946
+ "epoch": 4.96,
2947
+ "learning_rate": 4.3010752688172045e-08,
2948
+ "loss": 0.098,
2949
+ "step": 490
2950
+ },
2951
+ {
2952
+ "epoch": 4.96,
2953
+ "step": 490,
2954
+ "total_flos": 146652980723712.0,
2955
+ "train_loss": 0.6916719505221259,
2956
+ "train_runtime": 14223.7593,
2957
+ "train_samples_per_second": 4.44,
2958
+ "train_steps_per_second": 0.034
2959
+ }
2960
+ ],
2961
+ "logging_steps": 1.0,
2962
+ "max_steps": 490,
2963
+ "num_input_tokens_seen": 0,
2964
+ "num_train_epochs": 5,
2965
+ "save_steps": 500,
2966
+ "total_flos": 146652980723712.0,
2967
+ "train_batch_size": 1,
2968
+ "trial_name": null,
2969
+ "trial_params": null
2970
+ }