xiaosena commited on
Commit
cda1eb1
·
verified ·
1 Parent(s): e0f81e4

Upload trainer_state.json

Browse files
Files changed (1) hide show
  1. trainer_state.json +173 -0
trainer_state.json ADDED
@@ -0,0 +1,173 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.6,
5
+ "eval_steps": 500,
6
+ "global_step": 200,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.08,
13
+ "grad_norm": 0.18740172684192657,
14
+ "learning_rate": 2.5e-05,
15
+ "loss": 1.2734,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.16,
20
+ "grad_norm": 0.251604825258255,
21
+ "learning_rate": 5e-05,
22
+ "loss": 1.4087,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.24,
27
+ "grad_norm": 0.20867587625980377,
28
+ "learning_rate": 4.962019382530521e-05,
29
+ "loss": 1.3661,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.32,
34
+ "grad_norm": 0.2381608933210373,
35
+ "learning_rate": 4.849231551964771e-05,
36
+ "loss": 1.427,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.4,
41
+ "grad_norm": 0.22688065469264984,
42
+ "learning_rate": 4.665063509461097e-05,
43
+ "loss": 1.2651,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.48,
48
+ "grad_norm": 0.31808537244796753,
49
+ "learning_rate": 4.415111107797445e-05,
50
+ "loss": 1.1864,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.56,
55
+ "grad_norm": 0.35343658924102783,
56
+ "learning_rate": 4.1069690242163484e-05,
57
+ "loss": 1.2428,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.64,
62
+ "grad_norm": 0.3015511929988861,
63
+ "learning_rate": 3.7500000000000003e-05,
64
+ "loss": 1.2391,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.72,
69
+ "grad_norm": 0.314265638589859,
70
+ "learning_rate": 3.355050358314172e-05,
71
+ "loss": 1.2293,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.8,
76
+ "grad_norm": 0.28097280859947205,
77
+ "learning_rate": 2.9341204441673266e-05,
78
+ "loss": 1.0963,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 0.88,
83
+ "grad_norm": 0.29236894845962524,
84
+ "learning_rate": 2.5e-05,
85
+ "loss": 1.1362,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 0.96,
90
+ "grad_norm": 0.27073583006858826,
91
+ "learning_rate": 2.0658795558326743e-05,
92
+ "loss": 1.0739,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 1.04,
97
+ "grad_norm": 0.27945125102996826,
98
+ "learning_rate": 1.6449496416858284e-05,
99
+ "loss": 1.1863,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 1.12,
104
+ "grad_norm": 0.3041883707046509,
105
+ "learning_rate": 1.2500000000000006e-05,
106
+ "loss": 1.0847,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 1.2,
111
+ "grad_norm": 0.3387562334537506,
112
+ "learning_rate": 8.930309757836517e-06,
113
+ "loss": 1.1705,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 1.28,
118
+ "grad_norm": 0.33508458733558655,
119
+ "learning_rate": 5.848888922025553e-06,
120
+ "loss": 1.1119,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 1.3599999999999999,
125
+ "grad_norm": 0.2545669972896576,
126
+ "learning_rate": 3.3493649053890326e-06,
127
+ "loss": 1.0686,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 1.44,
132
+ "grad_norm": 0.28630197048187256,
133
+ "learning_rate": 1.5076844803522922e-06,
134
+ "loss": 1.0835,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 1.52,
139
+ "grad_norm": 0.3333503305912018,
140
+ "learning_rate": 3.7980617469479953e-07,
141
+ "loss": 1.0836,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 1.6,
146
+ "grad_norm": 0.35926613211631775,
147
+ "learning_rate": 0.0,
148
+ "loss": 1.2031,
149
+ "step": 200
150
+ }
151
+ ],
152
+ "logging_steps": 10,
153
+ "max_steps": 200,
154
+ "num_input_tokens_seen": 0,
155
+ "num_train_epochs": 2,
156
+ "save_steps": 100,
157
+ "stateful_callbacks": {
158
+ "TrainerControl": {
159
+ "args": {
160
+ "should_epoch_stop": false,
161
+ "should_evaluate": false,
162
+ "should_log": false,
163
+ "should_save": true,
164
+ "should_training_stop": true
165
+ },
166
+ "attributes": {}
167
+ }
168
+ },
169
+ "total_flos": 3796509917184000.0,
170
+ "train_batch_size": 1,
171
+ "trial_name": null,
172
+ "trial_params": null
173
+ }