Hugging Face's logo

rooftopcoder
/
roberta-base-coqa

Question Answering
Transformers
PyTorch
TensorBoard
roberta
Generated from Trainer
Model card Files Metrics Community
1
rooftopcoder commited on
Commit
628f3f5
路
1 Parent(s): 0c13af3

End of training

Browse files
Files changed (3) hide show
  1. all_results.json +8 -0
  2. train_results.json +8 -0
  3. trainer_state.json +199 -0
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.97,
3
+ "train_loss": 0.0,
4
+ "train_runtime": 32.9708,
5
+ "train_samples": 156240,
6
+ "train_samples_per_second": 14216.232,
7
+ "train_steps_per_second": 111.098
8
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.97,
3
+ "train_loss": 0.0,
4
+ "train_runtime": 32.9708,
5
+ "train_samples": 156240,
6
+ "train_samples_per_second": 14216.232,
7
+ "train_steps_per_second": 111.098
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,199 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.9694859717386852,
5
+ "global_step": 14500,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.1,
12
+ "learning_rate": 0.00025904995904995904,
13
+ "loss": 5.6935,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.2,
18
+ "learning_rate": 0.00021809991809991808,
19
+ "loss": 5.9538,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 0.31,
24
+ "learning_rate": 0.00017714987714987715,
25
+ "loss": 5.9526,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 0.41,
30
+ "learning_rate": 0.0001361998361998362,
31
+ "loss": 5.9532,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 0.51,
36
+ "learning_rate": 9.524979524979524e-05,
37
+ "loss": 5.9517,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 0.61,
42
+ "learning_rate": 5.429975429975429e-05,
43
+ "loss": 5.9514,
44
+ "step": 3000
45
+ },
46
+ {
47
+ "epoch": 0.72,
48
+ "learning_rate": 1.3349713349713349e-05,
49
+ "loss": 5.9512,
50
+ "step": 3500
51
+ },
52
+ {
53
+ "epoch": 0.82,
54
+ "learning_rate": 0.0,
55
+ "loss": 5.9513,
56
+ "step": 4000
57
+ },
58
+ {
59
+ "epoch": 0.92,
60
+ "learning_rate": 0.0,
61
+ "loss": 5.9513,
62
+ "step": 4500
63
+ },
64
+ {
65
+ "epoch": 1.02,
66
+ "learning_rate": 0.0,
67
+ "loss": 5.9516,
68
+ "step": 5000
69
+ },
70
+ {
71
+ "epoch": 1.13,
72
+ "learning_rate": 0.0,
73
+ "loss": 5.9515,
74
+ "step": 5500
75
+ },
76
+ {
77
+ "epoch": 1.23,
78
+ "learning_rate": 0.0,
79
+ "loss": 5.9514,
80
+ "step": 6000
81
+ },
82
+ {
83
+ "epoch": 1.33,
84
+ "learning_rate": 0.0,
85
+ "loss": 5.9518,
86
+ "step": 6500
87
+ },
88
+ {
89
+ "epoch": 1.43,
90
+ "learning_rate": 0.0,
91
+ "loss": 5.9514,
92
+ "step": 7000
93
+ },
94
+ {
95
+ "epoch": 1.54,
96
+ "learning_rate": 0.0,
97
+ "loss": 5.9513,
98
+ "step": 7500
99
+ },
100
+ {
101
+ "epoch": 1.64,
102
+ "learning_rate": 0.0,
103
+ "loss": 5.9514,
104
+ "step": 8000
105
+ },
106
+ {
107
+ "epoch": 1.74,
108
+ "learning_rate": 0.0,
109
+ "loss": 5.9516,
110
+ "step": 8500
111
+ },
112
+ {
113
+ "epoch": 1.84,
114
+ "learning_rate": 0.0,
115
+ "loss": 5.9515,
116
+ "step": 9000
117
+ },
118
+ {
119
+ "epoch": 1.95,
120
+ "learning_rate": 0.0,
121
+ "loss": 5.9512,
122
+ "step": 9500
123
+ },
124
+ {
125
+ "epoch": 2.05,
126
+ "learning_rate": 0.0,
127
+ "loss": 5.9512,
128
+ "step": 10000
129
+ },
130
+ {
131
+ "epoch": 2.15,
132
+ "learning_rate": 0.0,
133
+ "loss": 5.9517,
134
+ "step": 10500
135
+ },
136
+ {
137
+ "epoch": 2.25,
138
+ "learning_rate": 0.0,
139
+ "loss": 5.9515,
140
+ "step": 11000
141
+ },
142
+ {
143
+ "epoch": 2.36,
144
+ "learning_rate": 0.0,
145
+ "loss": 5.9518,
146
+ "step": 11500
147
+ },
148
+ {
149
+ "epoch": 2.46,
150
+ "learning_rate": 0.0,
151
+ "loss": 5.9516,
152
+ "step": 12000
153
+ },
154
+ {
155
+ "epoch": 2.56,
156
+ "learning_rate": 0.0,
157
+ "loss": 5.9517,
158
+ "step": 12500
159
+ },
160
+ {
161
+ "epoch": 2.66,
162
+ "learning_rate": 0.0,
163
+ "loss": 5.9511,
164
+ "step": 13000
165
+ },
166
+ {
167
+ "epoch": 2.76,
168
+ "learning_rate": 0.0,
169
+ "loss": 5.9508,
170
+ "step": 13500
171
+ },
172
+ {
173
+ "epoch": 2.87,
174
+ "learning_rate": 0.0,
175
+ "loss": 5.9514,
176
+ "step": 14000
177
+ },
178
+ {
179
+ "epoch": 2.97,
180
+ "learning_rate": 0.0,
181
+ "loss": 5.9511,
182
+ "step": 14500
183
+ },
184
+ {
185
+ "epoch": 2.97,
186
+ "step": 14500,
187
+ "total_flos": 9.092500022196634e+16,
188
+ "train_loss": 0.0,
189
+ "train_runtime": 32.9708,
190
+ "train_samples_per_second": 14216.232,
191
+ "train_steps_per_second": 111.098
192
+ }
193
+ ],
194
+ "max_steps": 3663,
195
+ "num_train_epochs": 3,
196
+ "total_flos": 9.092500022196634e+16,
197
+ "trial_name": null,
198
+ "trial_params": null
199
+ }