Hugging Face's logo

prashrex
/
chatDoctor-750

Model card Files Community
prashrex commited on
Commit
64b3451
•
1 Parent(s): da4a66a

Upload trainer_state.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. trainer_state.json +196 -0
trainer_state.json ADDED
@@ -0,0 +1,196 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.0281542099928676,
5
+ "global_step": 750,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.0,
12
+ "learning_rate": 0.0002,
13
+ "loss": 2.5676,
14
+ "step": 25
15
+ },
16
+ {
17
+ "epoch": 0.0,
18
+ "learning_rate": 0.0002,
19
+ "loss": 2.2721,
20
+ "step": 50
21
+ },
22
+ {
23
+ "epoch": 0.0,
24
+ "learning_rate": 0.0002,
25
+ "loss": 2.181,
26
+ "step": 75
27
+ },
28
+ {
29
+ "epoch": 0.0,
30
+ "learning_rate": 0.0002,
31
+ "loss": 2.1398,
32
+ "step": 100
33
+ },
34
+ {
35
+ "epoch": 0.0,
36
+ "learning_rate": 0.0002,
37
+ "loss": 2.1887,
38
+ "step": 125
39
+ },
40
+ {
41
+ "epoch": 0.01,
42
+ "learning_rate": 0.0002,
43
+ "loss": 2.1021,
44
+ "step": 150
45
+ },
46
+ {
47
+ "epoch": 0.01,
48
+ "learning_rate": 0.0002,
49
+ "loss": 2.1441,
50
+ "step": 175
51
+ },
52
+ {
53
+ "epoch": 0.01,
54
+ "learning_rate": 0.0002,
55
+ "loss": 2.1414,
56
+ "step": 200
57
+ },
58
+ {
59
+ "epoch": 0.01,
60
+ "learning_rate": 0.0002,
61
+ "loss": 2.2161,
62
+ "step": 225
63
+ },
64
+ {
65
+ "epoch": 0.01,
66
+ "learning_rate": 0.0002,
67
+ "loss": 2.0418,
68
+ "step": 250
69
+ },
70
+ {
71
+ "epoch": 0.01,
72
+ "learning_rate": 0.0002,
73
+ "loss": 2.1488,
74
+ "step": 275
75
+ },
76
+ {
77
+ "epoch": 0.01,
78
+ "learning_rate": 0.0002,
79
+ "loss": 2.0276,
80
+ "step": 300
81
+ },
82
+ {
83
+ "epoch": 0.01,
84
+ "learning_rate": 0.0002,
85
+ "loss": 2.1425,
86
+ "step": 325
87
+ },
88
+ {
89
+ "epoch": 0.01,
90
+ "learning_rate": 0.0002,
91
+ "loss": 2.0713,
92
+ "step": 350
93
+ },
94
+ {
95
+ "epoch": 0.01,
96
+ "learning_rate": 0.0002,
97
+ "loss": 2.1438,
98
+ "step": 375
99
+ },
100
+ {
101
+ "epoch": 0.02,
102
+ "learning_rate": 0.0002,
103
+ "loss": 2.0475,
104
+ "step": 400
105
+ },
106
+ {
107
+ "epoch": 0.02,
108
+ "learning_rate": 0.0002,
109
+ "loss": 2.1166,
110
+ "step": 425
111
+ },
112
+ {
113
+ "epoch": 0.02,
114
+ "learning_rate": 0.0002,
115
+ "loss": 2.0796,
116
+ "step": 450
117
+ },
118
+ {
119
+ "epoch": 0.02,
120
+ "learning_rate": 0.0002,
121
+ "loss": 2.1399,
122
+ "step": 475
123
+ },
124
+ {
125
+ "epoch": 0.02,
126
+ "learning_rate": 0.0002,
127
+ "loss": 2.0803,
128
+ "step": 500
129
+ },
130
+ {
131
+ "epoch": 0.02,
132
+ "learning_rate": 0.0002,
133
+ "loss": 2.1041,
134
+ "step": 525
135
+ },
136
+ {
137
+ "epoch": 0.02,
138
+ "learning_rate": 0.0002,
139
+ "loss": 2.0854,
140
+ "step": 550
141
+ },
142
+ {
143
+ "epoch": 0.02,
144
+ "learning_rate": 0.0002,
145
+ "loss": 2.0958,
146
+ "step": 575
147
+ },
148
+ {
149
+ "epoch": 0.02,
150
+ "learning_rate": 0.0002,
151
+ "loss": 2.0094,
152
+ "step": 600
153
+ },
154
+ {
155
+ "epoch": 0.02,
156
+ "learning_rate": 0.0002,
157
+ "loss": 2.0519,
158
+ "step": 625
159
+ },
160
+ {
161
+ "epoch": 0.02,
162
+ "learning_rate": 0.0002,
163
+ "loss": 2.0341,
164
+ "step": 650
165
+ },
166
+ {
167
+ "epoch": 0.03,
168
+ "learning_rate": 0.0002,
169
+ "loss": 2.1016,
170
+ "step": 675
171
+ },
172
+ {
173
+ "epoch": 0.03,
174
+ "learning_rate": 0.0002,
175
+ "loss": 2.0138,
176
+ "step": 700
177
+ },
178
+ {
179
+ "epoch": 0.03,
180
+ "learning_rate": 0.0002,
181
+ "loss": 2.1485,
182
+ "step": 725
183
+ },
184
+ {
185
+ "epoch": 0.03,
186
+ "learning_rate": 0.0002,
187
+ "loss": 2.0358,
188
+ "step": 750
189
+ }
190
+ ],
191
+ "max_steps": 26639,
192
+ "num_train_epochs": 1,
193
+ "total_flos": 1.874951786299392e+16,
194
+ "trial_name": null,
195
+ "trial_params": null
196
+ }