Hugging Face's logo

anas-awadalla
/
bert-medium-pretrained-finetuned-squad

Question Answering
Transformers
PyTorch
bert
Generated from Trainer
Inference Endpoints
Model card Files Community
2
anas-awadalla commited on
Commit
06b5088
路
1 Parent(s): 2d288fc

Upload trainer_state.json

Browse files
Files changed (1) hide show
  1. trainer_state.json +223 -0
trainer_state.json ADDED
@@ -0,0 +1,223 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.0,
5
+ "global_step": 16599,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.09,
12
+ "learning_rate": 4.849388517380565e-05,
13
+ "loss": 2.4052,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.18,
18
+ "learning_rate": 4.6987770347611306e-05,
19
+ "loss": 1.6715,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 0.27,
24
+ "learning_rate": 4.5481655521416954e-05,
25
+ "loss": 1.5473,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 0.36,
30
+ "learning_rate": 4.397554069522261e-05,
31
+ "loss": 1.4151,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 0.45,
36
+ "learning_rate": 4.246942586902826e-05,
37
+ "loss": 1.3605,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 0.54,
42
+ "learning_rate": 4.0963311042833905e-05,
43
+ "loss": 1.3104,
44
+ "step": 3000
45
+ },
46
+ {
47
+ "epoch": 0.63,
48
+ "learning_rate": 3.945719621663956e-05,
49
+ "loss": 1.2118,
50
+ "step": 3500
51
+ },
52
+ {
53
+ "epoch": 0.72,
54
+ "learning_rate": 3.795108139044521e-05,
55
+ "loss": 1.2702,
56
+ "step": 4000
57
+ },
58
+ {
59
+ "epoch": 0.81,
60
+ "learning_rate": 3.644496656425086e-05,
61
+ "loss": 1.2225,
62
+ "step": 4500
63
+ },
64
+ {
65
+ "epoch": 0.9,
66
+ "learning_rate": 3.493885173805651e-05,
67
+ "loss": 1.1811,
68
+ "step": 5000
69
+ },
70
+ {
71
+ "epoch": 0.99,
72
+ "learning_rate": 3.343273691186216e-05,
73
+ "loss": 1.1898,
74
+ "step": 5500
75
+ },
76
+ {
77
+ "epoch": 1.08,
78
+ "learning_rate": 3.1926622085667815e-05,
79
+ "loss": 0.929,
80
+ "step": 6000
81
+ },
82
+ {
83
+ "epoch": 1.17,
84
+ "learning_rate": 3.0420507259473463e-05,
85
+ "loss": 0.8824,
86
+ "step": 6500
87
+ },
88
+ {
89
+ "epoch": 1.27,
90
+ "learning_rate": 2.8914392433279115e-05,
91
+ "loss": 0.8851,
92
+ "step": 7000
93
+ },
94
+ {
95
+ "epoch": 1.36,
96
+ "learning_rate": 2.7408277607084763e-05,
97
+ "loss": 0.9067,
98
+ "step": 7500
99
+ },
100
+ {
101
+ "epoch": 1.45,
102
+ "learning_rate": 2.5902162780890415e-05,
103
+ "loss": 0.9111,
104
+ "step": 8000
105
+ },
106
+ {
107
+ "epoch": 1.54,
108
+ "learning_rate": 2.4396047954696066e-05,
109
+ "loss": 0.8716,
110
+ "step": 8500
111
+ },
112
+ {
113
+ "epoch": 1.63,
114
+ "learning_rate": 2.2889933128501718e-05,
115
+ "loss": 0.8914,
116
+ "step": 9000
117
+ },
118
+ {
119
+ "epoch": 1.72,
120
+ "learning_rate": 2.138381830230737e-05,
121
+ "loss": 0.8454,
122
+ "step": 9500
123
+ },
124
+ {
125
+ "epoch": 1.81,
126
+ "learning_rate": 1.9877703476113018e-05,
127
+ "loss": 0.8956,
128
+ "step": 10000
129
+ },
130
+ {
131
+ "epoch": 1.9,
132
+ "learning_rate": 1.837158864991867e-05,
133
+ "loss": 0.8595,
134
+ "step": 10500
135
+ },
136
+ {
137
+ "epoch": 1.99,
138
+ "learning_rate": 1.686547382372432e-05,
139
+ "loss": 0.8699,
140
+ "step": 11000
141
+ },
142
+ {
143
+ "epoch": 2.08,
144
+ "learning_rate": 1.5359358997529973e-05,
145
+ "loss": 0.6436,
146
+ "step": 11500
147
+ },
148
+ {
149
+ "epoch": 2.17,
150
+ "learning_rate": 1.3853244171335622e-05,
151
+ "loss": 0.6209,
152
+ "step": 12000
153
+ },
154
+ {
155
+ "epoch": 2.26,
156
+ "learning_rate": 1.2347129345141274e-05,
157
+ "loss": 0.6164,
158
+ "step": 12500
159
+ },
160
+ {
161
+ "epoch": 2.35,
162
+ "learning_rate": 1.0841014518946926e-05,
163
+ "loss": 0.6244,
164
+ "step": 13000
165
+ },
166
+ {
167
+ "epoch": 2.44,
168
+ "learning_rate": 9.334899692752576e-06,
169
+ "loss": 0.6159,
170
+ "step": 13500
171
+ },
172
+ {
173
+ "epoch": 2.53,
174
+ "learning_rate": 7.828784866558227e-06,
175
+ "loss": 0.6309,
176
+ "step": 14000
177
+ },
178
+ {
179
+ "epoch": 2.62,
180
+ "learning_rate": 6.322670040363877e-06,
181
+ "loss": 0.617,
182
+ "step": 14500
183
+ },
184
+ {
185
+ "epoch": 2.71,
186
+ "learning_rate": 4.816555214169529e-06,
187
+ "loss": 0.615,
188
+ "step": 15000
189
+ },
190
+ {
191
+ "epoch": 2.8,
192
+ "learning_rate": 3.310440387975179e-06,
193
+ "loss": 0.5898,
194
+ "step": 15500
195
+ },
196
+ {
197
+ "epoch": 2.89,
198
+ "learning_rate": 1.8043255617808302e-06,
199
+ "loss": 0.6219,
200
+ "step": 16000
201
+ },
202
+ {
203
+ "epoch": 2.98,
204
+ "learning_rate": 2.982107355864811e-07,
205
+ "loss": 0.6043,
206
+ "step": 16500
207
+ },
208
+ {
209
+ "epoch": 3.0,
210
+ "step": 16599,
211
+ "total_flos": 1.5432246862350336e+16,
212
+ "train_loss": 0.9777237792009043,
213
+ "train_runtime": 2351.827,
214
+ "train_samples_per_second": 112.922,
215
+ "train_steps_per_second": 7.058
216
+ }
217
+ ],
218
+ "max_steps": 16599,
219
+ "num_train_epochs": 3,
220
+ "total_flos": 1.5432246862350336e+16,
221
+ "trial_name": null,
222
+ "trial_params": null
223
+ }