Hugging Face's logo

khulnasoft
/
llama2-13b-sql-lora

PEFT
Model card Files
xet
Community
khulnasoft commited on
Commit
e79ec0b
·
verified ·
1 Parent(s): 593219b

Create trainer_state.json

Browse files
Files changed (1) hide show
  1. trainer_state.json +175 -0
trainer_state.json ADDED
@@ -0,0 +1,175 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.8475750577367207,
5
+ "global_step": 500,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.07,
12
+ "learning_rate": 0.0002,
13
+ "loss": 1.0758,
14
+ "step": 20
15
+ },
16
+ {
17
+ "epoch": 0.15,
18
+ "learning_rate": 0.0002,
19
+ "loss": 1.0262,
20
+ "step": 40
21
+ },
22
+ {
23
+ "epoch": 0.22,
24
+ "learning_rate": 0.0002,
25
+ "loss": 0.972,
26
+ "step": 60
27
+ },
28
+ {
29
+ "epoch": 0.3,
30
+ "learning_rate": 0.0002,
31
+ "loss": 0.2251,
32
+ "step": 80
33
+ },
34
+ {
35
+ "epoch": 0.37,
36
+ "learning_rate": 0.0002,
37
+ "loss": 0.144,
38
+ "step": 100
39
+ },
40
+ {
41
+ "epoch": 0.44,
42
+ "learning_rate": 0.0002,
43
+ "loss": 0.1766,
44
+ "step": 120
45
+ },
46
+ {
47
+ "epoch": 0.52,
48
+ "learning_rate": 0.0002,
49
+ "loss": 0.1494,
50
+ "step": 140
51
+ },
52
+ {
53
+ "epoch": 0.59,
54
+ "learning_rate": 0.0002,
55
+ "loss": 0.1483,
56
+ "step": 160
57
+ },
58
+ {
59
+ "epoch": 0.67,
60
+ "learning_rate": 0.0002,
61
+ "loss": 0.1188,
62
+ "step": 180
63
+ },
64
+ {
65
+ "epoch": 0.74,
66
+ "learning_rate": 0.0002,
67
+ "loss": 0.0918,
68
+ "step": 200
69
+ },
70
+ {
71
+ "epoch": 0.81,
72
+ "learning_rate": 0.0002,
73
+ "loss": 0.1356,
74
+ "step": 220
75
+ },
76
+ {
77
+ "epoch": 0.89,
78
+ "learning_rate": 0.0002,
79
+ "loss": 0.0969,
80
+ "step": 240
81
+ },
82
+ {
83
+ "epoch": 0.96,
84
+ "learning_rate": 0.0002,
85
+ "loss": 0.1145,
86
+ "step": 260
87
+ },
88
+ {
89
+ "epoch": 1.03,
90
+ "learning_rate": 0.0002,
91
+ "loss": 0.1058,
92
+ "step": 280
93
+ },
94
+ {
95
+ "epoch": 1.11,
96
+ "learning_rate": 0.0002,
97
+ "loss": 0.0827,
98
+ "step": 300
99
+ },
100
+ {
101
+ "epoch": 1.18,
102
+ "learning_rate": 0.0002,
103
+ "loss": 0.0537,
104
+ "step": 320
105
+ },
106
+ {
107
+ "epoch": 1.26,
108
+ "learning_rate": 0.0002,
109
+ "loss": 0.0969,
110
+ "step": 340
111
+ },
112
+ {
113
+ "epoch": 1.33,
114
+ "learning_rate": 0.0002,
115
+ "loss": 0.06,
116
+ "step": 360
117
+ },
118
+ {
119
+ "epoch": 1.4,
120
+ "learning_rate": 0.0002,
121
+ "loss": 0.0777,
122
+ "step": 380
123
+ },
124
+ {
125
+ "epoch": 1.48,
126
+ "learning_rate": 0.0002,
127
+ "loss": 0.071,
128
+ "step": 400
129
+ },
130
+ {
131
+ "epoch": 1.55,
132
+ "learning_rate": 0.0002,
133
+ "loss": 0.0487,
134
+ "step": 420
135
+ },
136
+ {
137
+ "epoch": 1.63,
138
+ "learning_rate": 0.0002,
139
+ "loss": 0.0871,
140
+ "step": 440
141
+ },
142
+ {
143
+ "epoch": 1.7,
144
+ "learning_rate": 0.0002,
145
+ "loss": 0.0577,
146
+ "step": 460
147
+ },
148
+ {
149
+ "epoch": 1.77,
150
+ "learning_rate": 0.0002,
151
+ "loss": 0.073,
152
+ "step": 480
153
+ },
154
+ {
155
+ "epoch": 1.85,
156
+ "learning_rate": 0.0002,
157
+ "loss": 0.0658,
158
+ "step": 500
159
+ },
160
+ {
161
+ "epoch": 1.85,
162
+ "step": 500,
163
+ "total_flos": 5.366331835972915e+17,
164
+ "train_loss": 0.2142012220621109,
165
+ "train_runtime": 37295.4093,
166
+ "train_samples_per_second": 0.429,
167
+ "train_steps_per_second": 0.013
168
+ }
169
+ ],
170
+ "max_steps": 500,
171
+ "num_train_epochs": 2,
172
+ "total_flos": 5.366331835972915e+17,
173
+ "trial_name": null,
174
+ "trial_params": null
175
+ }