Hugging Face's logo

prashrex
/
chatDoctor

Model card Files Community
prashrex commited on
Commit
55d9b7f
•
1 Parent(s): 6fc413e

Upload trainer_state.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. trainer_state.json +160 -0
trainer_state.json ADDED
@@ -0,0 +1,160 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.22522522522522523,
5
+ "global_step": 600,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.01,
12
+ "learning_rate": 0.0002,
13
+ "loss": 2.5366,
14
+ "step": 25
15
+ },
16
+ {
17
+ "epoch": 0.02,
18
+ "learning_rate": 0.0002,
19
+ "loss": 2.2614,
20
+ "step": 50
21
+ },
22
+ {
23
+ "epoch": 0.03,
24
+ "learning_rate": 0.0002,
25
+ "loss": 2.248,
26
+ "step": 75
27
+ },
28
+ {
29
+ "epoch": 0.04,
30
+ "learning_rate": 0.0002,
31
+ "loss": 2.2142,
32
+ "step": 100
33
+ },
34
+ {
35
+ "epoch": 0.05,
36
+ "learning_rate": 0.0002,
37
+ "loss": 2.1638,
38
+ "step": 125
39
+ },
40
+ {
41
+ "epoch": 0.06,
42
+ "learning_rate": 0.0002,
43
+ "loss": 2.1349,
44
+ "step": 150
45
+ },
46
+ {
47
+ "epoch": 0.07,
48
+ "learning_rate": 0.0002,
49
+ "loss": 2.2323,
50
+ "step": 175
51
+ },
52
+ {
53
+ "epoch": 0.08,
54
+ "learning_rate": 0.0002,
55
+ "loss": 2.1278,
56
+ "step": 200
57
+ },
58
+ {
59
+ "epoch": 0.08,
60
+ "learning_rate": 0.0002,
61
+ "loss": 2.1992,
62
+ "step": 225
63
+ },
64
+ {
65
+ "epoch": 0.09,
66
+ "learning_rate": 0.0002,
67
+ "loss": 2.0986,
68
+ "step": 250
69
+ },
70
+ {
71
+ "epoch": 0.1,
72
+ "learning_rate": 0.0002,
73
+ "loss": 2.2049,
74
+ "step": 275
75
+ },
76
+ {
77
+ "epoch": 0.11,
78
+ "learning_rate": 0.0002,
79
+ "loss": 2.1108,
80
+ "step": 300
81
+ },
82
+ {
83
+ "epoch": 0.12,
84
+ "learning_rate": 0.0002,
85
+ "loss": 2.1739,
86
+ "step": 325
87
+ },
88
+ {
89
+ "epoch": 0.13,
90
+ "learning_rate": 0.0002,
91
+ "loss": 2.0718,
92
+ "step": 350
93
+ },
94
+ {
95
+ "epoch": 0.14,
96
+ "learning_rate": 0.0002,
97
+ "loss": 2.1104,
98
+ "step": 375
99
+ },
100
+ {
101
+ "epoch": 0.15,
102
+ "learning_rate": 0.0002,
103
+ "loss": 2.1098,
104
+ "step": 400
105
+ },
106
+ {
107
+ "epoch": 0.16,
108
+ "learning_rate": 0.0002,
109
+ "loss": 2.1431,
110
+ "step": 425
111
+ },
112
+ {
113
+ "epoch": 0.17,
114
+ "learning_rate": 0.0002,
115
+ "loss": 2.0492,
116
+ "step": 450
117
+ },
118
+ {
119
+ "epoch": 0.18,
120
+ "learning_rate": 0.0002,
121
+ "loss": 2.1305,
122
+ "step": 475
123
+ },
124
+ {
125
+ "epoch": 0.19,
126
+ "learning_rate": 0.0002,
127
+ "loss": 2.0664,
128
+ "step": 500
129
+ },
130
+ {
131
+ "epoch": 0.2,
132
+ "learning_rate": 0.0002,
133
+ "loss": 2.117,
134
+ "step": 525
135
+ },
136
+ {
137
+ "epoch": 0.21,
138
+ "learning_rate": 0.0002,
139
+ "loss": 2.0769,
140
+ "step": 550
141
+ },
142
+ {
143
+ "epoch": 0.22,
144
+ "learning_rate": 0.0002,
145
+ "loss": 2.1066,
146
+ "step": 575
147
+ },
148
+ {
149
+ "epoch": 0.23,
150
+ "learning_rate": 0.0002,
151
+ "loss": 1.9691,
152
+ "step": 600
153
+ }
154
+ ],
155
+ "max_steps": 2664,
156
+ "num_train_epochs": 1,
157
+ "total_flos": 1.51942000140288e+16,
158
+ "trial_name": null,
159
+ "trial_params": null
160
+ }