hung200504 commited on
Commit
ebc4e3f
1 Parent(s): 18c7a0c

bert-cased

Browse files
Files changed (3) hide show
  1. README.md +45 -438
  2. pytorch_model.bin +1 -1
  3. training_args.bin +1 -1
README.md CHANGED
@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  This model is a fine-tuned version of [deepset/bert-base-cased-squad2](https://huggingface.co/deepset/bert-base-cased-squad2) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
- - Loss: 5.4502
19
 
20
  ## Model description
21
 
@@ -40,448 +40,55 @@ The following hyperparameters were used during training:
40
  - seed: 42
41
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
  - lr_scheduler_type: linear
43
- - num_epochs: 10
44
 
45
  ### Training results
46
 
47
  | Training Loss | Epoch | Step | Validation Loss |
48
  |:-------------:|:-----:|:----:|:---------------:|
49
- | 10.223 | 0.02 | 5 | 11.9913 |
50
- | 10.8523 | 0.05 | 10 | 11.5145 |
51
- | 11.086 | 0.07 | 15 | 11.0371 |
52
- | 9.6289 | 0.09 | 20 | 10.5684 |
53
- | 9.72 | 0.11 | 25 | 10.1112 |
54
- | 8.4493 | 0.14 | 30 | 9.6688 |
55
- | 8.8585 | 0.16 | 35 | 9.2391 |
56
- | 8.4229 | 0.18 | 40 | 8.8177 |
57
- | 7.8945 | 0.21 | 45 | 8.4118 |
58
- | 7.8876 | 0.23 | 50 | 8.0288 |
59
- | 6.4909 | 0.25 | 55 | 7.6809 |
60
- | 6.746 | 0.28 | 60 | 7.3743 |
61
- | 6.5319 | 0.3 | 65 | 7.0997 |
62
- | 6.634 | 0.32 | 70 | 6.8609 |
63
- | 6.2445 | 0.34 | 75 | 6.6653 |
64
- | 6.0545 | 0.37 | 80 | 6.5160 |
65
- | 6.3467 | 0.39 | 85 | 6.4028 |
66
- | 6.0512 | 0.41 | 90 | 6.3212 |
67
- | 5.7648 | 0.44 | 95 | 6.2668 |
68
- | 5.8706 | 0.46 | 100 | 6.2278 |
69
- | 5.9064 | 0.48 | 105 | 6.1932 |
70
- | 5.6687 | 0.5 | 110 | 6.1695 |
71
- | 5.7971 | 0.53 | 115 | 6.1496 |
72
- | 5.8467 | 0.55 | 120 | 6.1282 |
73
- | 5.5549 | 0.57 | 125 | 6.1093 |
74
- | 5.6604 | 0.6 | 130 | 6.0900 |
75
- | 5.7023 | 0.62 | 135 | 6.0691 |
76
- | 5.4075 | 0.64 | 140 | 6.0513 |
77
- | 5.3794 | 0.67 | 145 | 6.0366 |
78
- | 5.4388 | 0.69 | 150 | 6.0273 |
79
- | 5.5245 | 0.71 | 155 | 6.0153 |
80
- | 5.4477 | 0.73 | 160 | 6.0009 |
81
- | 5.5064 | 0.76 | 165 | 5.9854 |
82
- | 5.449 | 0.78 | 170 | 5.9681 |
83
- | 5.5521 | 0.8 | 175 | 5.9505 |
84
- | 5.4184 | 0.83 | 180 | 5.9342 |
85
- | 5.5076 | 0.85 | 185 | 5.9168 |
86
- | 5.3001 | 0.87 | 190 | 5.8997 |
87
- | 5.4266 | 0.89 | 195 | 5.8855 |
88
- | 5.303 | 0.92 | 200 | 5.8703 |
89
- | 5.1433 | 0.94 | 205 | 5.8559 |
90
- | 5.4247 | 0.96 | 210 | 5.8443 |
91
- | 5.2913 | 0.99 | 215 | 5.8347 |
92
- | 5.2319 | 1.01 | 220 | 5.8229 |
93
- | 4.9284 | 1.03 | 225 | 5.8150 |
94
- | 5.0118 | 1.06 | 230 | 5.8098 |
95
- | 5.1533 | 1.08 | 235 | 5.8078 |
96
- | 5.201 | 1.1 | 240 | 5.8056 |
97
- | 5.478 | 1.12 | 245 | 5.8026 |
98
- | 5.1066 | 1.15 | 250 | 5.7979 |
99
- | 5.4474 | 1.17 | 255 | 5.7918 |
100
- | 5.1567 | 1.19 | 260 | 5.7841 |
101
- | 5.0761 | 1.22 | 265 | 5.7812 |
102
- | 4.5299 | 1.24 | 270 | 5.7782 |
103
- | 5.1725 | 1.26 | 275 | 5.7735 |
104
- | 5.2841 | 1.28 | 280 | 5.7678 |
105
- | 5.1418 | 1.31 | 285 | 5.7614 |
106
- | 4.8134 | 1.33 | 290 | 5.7517 |
107
- | 5.0168 | 1.35 | 295 | 5.7470 |
108
- | 5.1415 | 1.38 | 300 | 5.7425 |
109
- | 4.8406 | 1.4 | 305 | 5.7409 |
110
- | 5.1648 | 1.42 | 310 | 5.7393 |
111
- | 4.6012 | 1.44 | 315 | 5.7391 |
112
- | 5.1008 | 1.47 | 320 | 5.7400 |
113
- | 4.9874 | 1.49 | 325 | 5.7420 |
114
- | 4.7481 | 1.51 | 330 | 5.7397 |
115
- | 5.0807 | 1.54 | 335 | 5.7349 |
116
- | 4.8219 | 1.56 | 340 | 5.7280 |
117
- | 5.2918 | 1.58 | 345 | 5.7196 |
118
- | 4.7966 | 1.61 | 350 | 5.7132 |
119
- | 5.1547 | 1.63 | 355 | 5.7059 |
120
- | 4.6691 | 1.65 | 360 | 5.7027 |
121
- | 4.7643 | 1.67 | 365 | 5.7022 |
122
- | 4.7299 | 1.7 | 370 | 5.7011 |
123
- | 4.8645 | 1.72 | 375 | 5.6987 |
124
- | 4.9112 | 1.74 | 380 | 5.6921 |
125
- | 4.6916 | 1.77 | 385 | 5.6878 |
126
- | 4.5665 | 1.79 | 390 | 5.6872 |
127
- | 5.0208 | 1.81 | 395 | 5.6878 |
128
- | 4.9818 | 1.83 | 400 | 5.6881 |
129
- | 4.4626 | 1.86 | 405 | 5.6891 |
130
- | 4.2459 | 1.88 | 410 | 5.6876 |
131
- | 4.389 | 1.9 | 415 | 5.6903 |
132
- | 4.4375 | 1.93 | 420 | 5.6925 |
133
- | 4.8058 | 1.95 | 425 | 5.6920 |
134
- | 4.6665 | 1.97 | 430 | 5.6879 |
135
- | 5.0375 | 2.0 | 435 | 5.6815 |
136
- | 4.7157 | 2.02 | 440 | 5.6734 |
137
- | 4.5099 | 2.04 | 445 | 5.6680 |
138
- | 4.7305 | 2.06 | 450 | 5.6628 |
139
- | 5.0492 | 2.09 | 455 | 5.6574 |
140
- | 4.2156 | 2.11 | 460 | 5.6531 |
141
- | 4.8362 | 2.13 | 465 | 5.6484 |
142
- | 4.4528 | 2.16 | 470 | 5.6506 |
143
- | 4.4387 | 2.18 | 475 | 5.6565 |
144
- | 4.7415 | 2.2 | 480 | 5.6584 |
145
- | 4.3772 | 2.22 | 485 | 5.6556 |
146
- | 4.558 | 2.25 | 490 | 5.6521 |
147
- | 4.5496 | 2.27 | 495 | 5.6495 |
148
- | 4.6056 | 2.29 | 500 | 5.6466 |
149
- | 4.9125 | 2.32 | 505 | 5.6432 |
150
- | 4.7728 | 2.34 | 510 | 5.6411 |
151
- | 4.5707 | 2.36 | 515 | 5.6424 |
152
- | 4.3599 | 2.39 | 520 | 5.6422 |
153
- | 4.2373 | 2.41 | 525 | 5.6450 |
154
- | 3.7878 | 2.43 | 530 | 5.6470 |
155
- | 4.3124 | 2.45 | 535 | 5.6491 |
156
- | 4.4129 | 2.48 | 540 | 5.6536 |
157
- | 4.1161 | 2.5 | 545 | 5.6581 |
158
- | 4.5554 | 2.52 | 550 | 5.6545 |
159
- | 4.4718 | 2.55 | 555 | 5.6501 |
160
- | 4.5906 | 2.57 | 560 | 5.6491 |
161
- | 4.3833 | 2.59 | 565 | 5.6512 |
162
- | 4.2949 | 2.61 | 570 | 5.6532 |
163
- | 4.3212 | 2.64 | 575 | 5.6584 |
164
- | 5.0496 | 2.66 | 580 | 5.6585 |
165
- | 4.5141 | 2.68 | 585 | 5.6602 |
166
- | 4.4106 | 2.71 | 590 | 5.6634 |
167
- | 4.397 | 2.73 | 595 | 5.6696 |
168
- | 4.8454 | 2.75 | 600 | 5.6738 |
169
- | 4.4965 | 2.78 | 605 | 5.6724 |
170
- | 4.129 | 2.8 | 610 | 5.6707 |
171
- | 4.433 | 2.82 | 615 | 5.6646 |
172
- | 4.5548 | 2.84 | 620 | 5.6561 |
173
- | 4.411 | 2.87 | 625 | 5.6492 |
174
- | 4.2796 | 2.89 | 630 | 5.6445 |
175
- | 4.7535 | 2.91 | 635 | 5.6377 |
176
- | 4.4193 | 2.94 | 640 | 5.6301 |
177
- | 5.0327 | 2.96 | 645 | 5.6227 |
178
- | 4.6815 | 2.98 | 650 | 5.6193 |
179
- | 4.5112 | 3.0 | 655 | 5.6178 |
180
- | 4.6954 | 3.03 | 660 | 5.6143 |
181
- | 4.691 | 3.05 | 665 | 5.6119 |
182
- | 4.6675 | 3.07 | 670 | 5.6063 |
183
- | 4.7901 | 3.1 | 675 | 5.5997 |
184
- | 4.6184 | 3.12 | 680 | 5.5925 |
185
- | 4.2704 | 3.14 | 685 | 5.5915 |
186
- | 4.3209 | 3.17 | 690 | 5.5895 |
187
- | 4.5131 | 3.19 | 695 | 5.5892 |
188
- | 4.4782 | 3.21 | 700 | 5.5895 |
189
- | 4.6145 | 3.23 | 705 | 5.5899 |
190
- | 4.3155 | 3.26 | 710 | 5.5908 |
191
- | 4.2195 | 3.28 | 715 | 5.5968 |
192
- | 4.7464 | 3.3 | 720 | 5.5977 |
193
- | 4.4204 | 3.33 | 725 | 5.6000 |
194
- | 4.3541 | 3.35 | 730 | 5.6034 |
195
- | 4.0531 | 3.37 | 735 | 5.6073 |
196
- | 4.1244 | 3.39 | 740 | 5.6110 |
197
- | 4.4016 | 3.42 | 745 | 5.6131 |
198
- | 4.1842 | 3.44 | 750 | 5.6155 |
199
- | 4.4012 | 3.46 | 755 | 5.6199 |
200
- | 4.3157 | 3.49 | 760 | 5.6278 |
201
- | 4.5788 | 3.51 | 765 | 5.6357 |
202
- | 4.0343 | 3.53 | 770 | 5.6433 |
203
- | 4.2088 | 3.56 | 775 | 5.6463 |
204
- | 4.4668 | 3.58 | 780 | 5.6464 |
205
- | 4.1564 | 3.6 | 785 | 5.6514 |
206
- | 4.6138 | 3.62 | 790 | 5.6527 |
207
- | 4.0778 | 3.65 | 795 | 5.6516 |
208
- | 4.9551 | 3.67 | 800 | 5.6485 |
209
- | 4.7297 | 3.69 | 805 | 5.6459 |
210
- | 4.2442 | 3.72 | 810 | 5.6444 |
211
- | 4.42 | 3.74 | 815 | 5.6414 |
212
- | 3.8831 | 3.76 | 820 | 5.6408 |
213
- | 4.4075 | 3.78 | 825 | 5.6400 |
214
- | 4.5851 | 3.81 | 830 | 5.6300 |
215
- | 4.2949 | 3.83 | 835 | 5.6189 |
216
- | 3.8835 | 3.85 | 840 | 5.6134 |
217
- | 4.1109 | 3.88 | 845 | 5.6094 |
218
- | 4.845 | 3.9 | 850 | 5.6011 |
219
- | 4.4053 | 3.92 | 855 | 5.5883 |
220
- | 4.1683 | 3.94 | 860 | 5.5803 |
221
- | 3.9257 | 3.97 | 865 | 5.5762 |
222
- | 4.0174 | 3.99 | 870 | 5.5797 |
223
- | 3.8825 | 4.01 | 875 | 5.5854 |
224
- | 4.3911 | 4.04 | 880 | 5.5896 |
225
- | 4.5066 | 4.06 | 885 | 5.5873 |
226
- | 4.3192 | 4.08 | 890 | 5.5818 |
227
- | 4.8764 | 4.11 | 895 | 5.5771 |
228
- | 4.3541 | 4.13 | 900 | 5.5724 |
229
- | 4.7328 | 4.15 | 905 | 5.5685 |
230
- | 3.9713 | 4.17 | 910 | 5.5657 |
231
- | 4.3436 | 4.2 | 915 | 5.5640 |
232
- | 4.6016 | 4.22 | 920 | 5.5671 |
233
- | 4.7167 | 4.24 | 925 | 5.5666 |
234
- | 4.6485 | 4.27 | 930 | 5.5664 |
235
- | 4.3609 | 4.29 | 935 | 5.5629 |
236
- | 4.5688 | 4.31 | 940 | 5.5582 |
237
- | 3.6015 | 4.33 | 945 | 5.5605 |
238
- | 3.8749 | 4.36 | 950 | 5.5666 |
239
- | 3.9043 | 4.38 | 955 | 5.5697 |
240
- | 4.7317 | 4.4 | 960 | 5.5697 |
241
- | 4.4383 | 4.43 | 965 | 5.5649 |
242
- | 4.5584 | 4.45 | 970 | 5.5560 |
243
- | 4.3123 | 4.47 | 975 | 5.5467 |
244
- | 3.9965 | 4.5 | 980 | 5.5418 |
245
- | 4.3387 | 4.52 | 985 | 5.5382 |
246
- | 3.26 | 4.54 | 990 | 5.5385 |
247
- | 4.4314 | 4.56 | 995 | 5.5390 |
248
- | 4.2901 | 4.59 | 1000 | 5.5375 |
249
- | 4.0901 | 4.61 | 1005 | 5.5355 |
250
- | 4.3606 | 4.63 | 1010 | 5.5362 |
251
- | 3.9168 | 4.66 | 1015 | 5.5373 |
252
- | 4.539 | 4.68 | 1020 | 5.5382 |
253
- | 4.3531 | 4.7 | 1025 | 5.5422 |
254
- | 4.1748 | 4.72 | 1030 | 5.5461 |
255
- | 4.1432 | 4.75 | 1035 | 5.5484 |
256
- | 3.9481 | 4.77 | 1040 | 5.5502 |
257
- | 4.7143 | 4.79 | 1045 | 5.5492 |
258
- | 4.4564 | 4.82 | 1050 | 5.5454 |
259
- | 4.4885 | 4.84 | 1055 | 5.5389 |
260
- | 4.1448 | 4.86 | 1060 | 5.5344 |
261
- | 4.0414 | 4.89 | 1065 | 5.5308 |
262
- | 4.174 | 4.91 | 1070 | 5.5267 |
263
- | 3.8038 | 4.93 | 1075 | 5.5267 |
264
- | 4.6791 | 4.95 | 1080 | 5.5281 |
265
- | 4.1429 | 4.98 | 1085 | 5.5289 |
266
- | 3.8355 | 5.0 | 1090 | 5.5321 |
267
- | 3.9843 | 5.02 | 1095 | 5.5337 |
268
- | 3.9889 | 5.05 | 1100 | 5.5375 |
269
- | 4.0622 | 5.07 | 1105 | 5.5403 |
270
- | 4.8474 | 5.09 | 1110 | 5.5395 |
271
- | 4.0241 | 5.11 | 1115 | 5.5403 |
272
- | 4.0762 | 5.14 | 1120 | 5.5439 |
273
- | 4.4967 | 5.16 | 1125 | 5.5442 |
274
- | 3.774 | 5.18 | 1130 | 5.5420 |
275
- | 4.3855 | 5.21 | 1135 | 5.5394 |
276
- | 3.8964 | 5.23 | 1140 | 5.5364 |
277
- | 4.2257 | 5.25 | 1145 | 5.5337 |
278
- | 4.1188 | 5.28 | 1150 | 5.5301 |
279
- | 4.7414 | 5.3 | 1155 | 5.5251 |
280
- | 4.0087 | 5.32 | 1160 | 5.5238 |
281
- | 3.9588 | 5.34 | 1165 | 5.5226 |
282
- | 4.3741 | 5.37 | 1170 | 5.5220 |
283
- | 4.3756 | 5.39 | 1175 | 5.5218 |
284
- | 4.3859 | 5.41 | 1180 | 5.5222 |
285
- | 4.2934 | 5.44 | 1185 | 5.5208 |
286
- | 4.2357 | 5.46 | 1190 | 5.5197 |
287
- | 4.1551 | 5.48 | 1195 | 5.5202 |
288
- | 4.1445 | 5.5 | 1200 | 5.5217 |
289
- | 4.2856 | 5.53 | 1205 | 5.5227 |
290
- | 4.1534 | 5.55 | 1210 | 5.5238 |
291
- | 4.3472 | 5.57 | 1215 | 5.5209 |
292
- | 4.2422 | 5.6 | 1220 | 5.5182 |
293
- | 4.578 | 5.62 | 1225 | 5.5173 |
294
- | 4.6536 | 5.64 | 1230 | 5.5153 |
295
- | 3.997 | 5.67 | 1235 | 5.5114 |
296
- | 4.0307 | 5.69 | 1240 | 5.5090 |
297
- | 3.9198 | 5.71 | 1245 | 5.5113 |
298
- | 4.3694 | 5.73 | 1250 | 5.5141 |
299
- | 4.2031 | 5.76 | 1255 | 5.5158 |
300
- | 4.0642 | 5.78 | 1260 | 5.5172 |
301
- | 3.8952 | 5.8 | 1265 | 5.5184 |
302
- | 3.8807 | 5.83 | 1270 | 5.5204 |
303
- | 4.209 | 5.85 | 1275 | 5.5186 |
304
- | 4.0276 | 5.87 | 1280 | 5.5134 |
305
- | 4.5011 | 5.89 | 1285 | 5.5076 |
306
- | 4.5032 | 5.92 | 1290 | 5.5014 |
307
- | 4.0724 | 5.94 | 1295 | 5.4960 |
308
- | 4.3952 | 5.96 | 1300 | 5.4922 |
309
- | 3.9391 | 5.99 | 1305 | 5.4887 |
310
- | 4.5013 | 6.01 | 1310 | 5.4882 |
311
- | 3.7748 | 6.03 | 1315 | 5.4890 |
312
- | 4.1817 | 6.06 | 1320 | 5.4898 |
313
- | 4.4581 | 6.08 | 1325 | 5.4897 |
314
- | 3.7311 | 6.1 | 1330 | 5.4902 |
315
- | 4.0439 | 6.12 | 1335 | 5.4910 |
316
- | 3.8044 | 6.15 | 1340 | 5.4924 |
317
- | 3.8836 | 6.17 | 1345 | 5.4932 |
318
- | 4.0835 | 6.19 | 1350 | 5.4952 |
319
- | 3.8672 | 6.22 | 1355 | 5.4979 |
320
- | 3.8561 | 6.24 | 1360 | 5.5016 |
321
- | 3.9088 | 6.26 | 1365 | 5.5073 |
322
- | 4.5821 | 6.28 | 1370 | 5.5111 |
323
- | 4.5992 | 6.31 | 1375 | 5.5128 |
324
- | 4.1571 | 6.33 | 1380 | 5.5115 |
325
- | 4.4918 | 6.35 | 1385 | 5.5088 |
326
- | 4.8008 | 6.38 | 1390 | 5.5020 |
327
- | 4.3536 | 6.4 | 1395 | 5.4963 |
328
- | 3.5612 | 6.42 | 1400 | 5.4946 |
329
- | 4.2318 | 6.44 | 1405 | 5.4949 |
330
- | 4.1321 | 6.47 | 1410 | 5.4931 |
331
- | 4.0747 | 6.49 | 1415 | 5.4935 |
332
- | 3.5846 | 6.51 | 1420 | 5.4974 |
333
- | 4.5849 | 6.54 | 1425 | 5.4998 |
334
- | 4.7748 | 6.56 | 1430 | 5.4980 |
335
- | 4.3293 | 6.58 | 1435 | 5.4938 |
336
- | 3.862 | 6.61 | 1440 | 5.4925 |
337
- | 4.561 | 6.63 | 1445 | 5.4904 |
338
- | 4.3999 | 6.65 | 1450 | 5.4883 |
339
- | 4.0645 | 6.67 | 1455 | 5.4869 |
340
- | 4.4209 | 6.7 | 1460 | 5.4863 |
341
- | 4.0743 | 6.72 | 1465 | 5.4824 |
342
- | 4.0407 | 6.74 | 1470 | 5.4784 |
343
- | 4.2352 | 6.77 | 1475 | 5.4743 |
344
- | 4.3184 | 6.79 | 1480 | 5.4711 |
345
- | 3.9865 | 6.81 | 1485 | 5.4694 |
346
- | 4.1335 | 6.83 | 1490 | 5.4677 |
347
- | 4.2359 | 6.86 | 1495 | 5.4679 |
348
- | 4.2628 | 6.88 | 1500 | 5.4668 |
349
- | 3.7522 | 6.9 | 1505 | 5.4659 |
350
- | 4.0455 | 6.93 | 1510 | 5.4659 |
351
- | 3.6454 | 6.95 | 1515 | 5.4707 |
352
- | 4.2362 | 6.97 | 1520 | 5.4718 |
353
- | 4.3081 | 7.0 | 1525 | 5.4722 |
354
- | 4.5218 | 7.02 | 1530 | 5.4725 |
355
- | 3.8774 | 7.04 | 1535 | 5.4713 |
356
- | 4.3145 | 7.06 | 1540 | 5.4717 |
357
- | 3.6431 | 7.09 | 1545 | 5.4723 |
358
- | 4.627 | 7.11 | 1550 | 5.4718 |
359
- | 4.3412 | 7.13 | 1555 | 5.4698 |
360
- | 4.4363 | 7.16 | 1560 | 5.4662 |
361
- | 4.347 | 7.18 | 1565 | 5.4611 |
362
- | 3.9902 | 7.2 | 1570 | 5.4596 |
363
- | 4.8042 | 7.22 | 1575 | 5.4581 |
364
- | 4.1393 | 7.25 | 1580 | 5.4559 |
365
- | 3.5405 | 7.27 | 1585 | 5.4558 |
366
- | 4.4046 | 7.29 | 1590 | 5.4544 |
367
- | 3.8726 | 7.32 | 1595 | 5.4540 |
368
- | 4.3668 | 7.34 | 1600 | 5.4541 |
369
- | 4.0284 | 7.36 | 1605 | 5.4551 |
370
- | 4.0001 | 7.39 | 1610 | 5.4560 |
371
- | 3.9638 | 7.41 | 1615 | 5.4580 |
372
- | 3.9117 | 7.43 | 1620 | 5.4590 |
373
- | 4.1366 | 7.45 | 1625 | 5.4593 |
374
- | 3.6279 | 7.48 | 1630 | 5.4607 |
375
- | 3.9993 | 7.5 | 1635 | 5.4615 |
376
- | 3.8984 | 7.52 | 1640 | 5.4611 |
377
- | 4.3549 | 7.55 | 1645 | 5.4605 |
378
- | 4.5955 | 7.57 | 1650 | 5.4590 |
379
- | 4.5273 | 7.59 | 1655 | 5.4573 |
380
- | 4.7872 | 7.61 | 1660 | 5.4554 |
381
- | 3.8104 | 7.64 | 1665 | 5.4535 |
382
- | 3.9645 | 7.66 | 1670 | 5.4526 |
383
- | 4.1494 | 7.68 | 1675 | 5.4521 |
384
- | 4.3821 | 7.71 | 1680 | 5.4506 |
385
- | 4.241 | 7.73 | 1685 | 5.4506 |
386
- | 3.4331 | 7.75 | 1690 | 5.4518 |
387
- | 4.4166 | 7.78 | 1695 | 5.4508 |
388
- | 4.0632 | 7.8 | 1700 | 5.4498 |
389
- | 4.1161 | 7.82 | 1705 | 5.4491 |
390
- | 4.0772 | 7.84 | 1710 | 5.4492 |
391
- | 3.7952 | 7.87 | 1715 | 5.4504 |
392
- | 4.2083 | 7.89 | 1720 | 5.4519 |
393
- | 3.7412 | 7.91 | 1725 | 5.4537 |
394
- | 3.8471 | 7.94 | 1730 | 5.4548 |
395
- | 3.8493 | 7.96 | 1735 | 5.4568 |
396
- | 3.8865 | 7.98 | 1740 | 5.4592 |
397
- | 4.2943 | 8.0 | 1745 | 5.4605 |
398
- | 3.9963 | 8.03 | 1750 | 5.4604 |
399
- | 4.8524 | 8.05 | 1755 | 5.4599 |
400
- | 4.4317 | 8.07 | 1760 | 5.4596 |
401
- | 4.3839 | 8.1 | 1765 | 5.4576 |
402
- | 4.6761 | 8.12 | 1770 | 5.4555 |
403
- | 4.2357 | 8.14 | 1775 | 5.4553 |
404
- | 4.3056 | 8.17 | 1780 | 5.4550 |
405
- | 4.364 | 8.19 | 1785 | 5.4554 |
406
- | 3.9463 | 8.21 | 1790 | 5.4553 |
407
- | 3.7338 | 8.23 | 1795 | 5.4556 |
408
- | 4.1336 | 8.26 | 1800 | 5.4545 |
409
- | 3.7407 | 8.28 | 1805 | 5.4544 |
410
- | 4.144 | 8.3 | 1810 | 5.4535 |
411
- | 3.4893 | 8.33 | 1815 | 5.4546 |
412
- | 4.8741 | 8.35 | 1820 | 5.4552 |
413
- | 4.0134 | 8.37 | 1825 | 5.4550 |
414
- | 3.8344 | 8.39 | 1830 | 5.4562 |
415
- | 4.0182 | 8.42 | 1835 | 5.4579 |
416
- | 4.1428 | 8.44 | 1840 | 5.4584 |
417
- | 3.7402 | 8.46 | 1845 | 5.4578 |
418
- | 4.1636 | 8.49 | 1850 | 5.4582 |
419
- | 4.0718 | 8.51 | 1855 | 5.4590 |
420
- | 4.0971 | 8.53 | 1860 | 5.4594 |
421
- | 3.4578 | 8.56 | 1865 | 5.4605 |
422
- | 3.8789 | 8.58 | 1870 | 5.4618 |
423
- | 3.9694 | 8.6 | 1875 | 5.4619 |
424
- | 3.9383 | 8.62 | 1880 | 5.4621 |
425
- | 4.2296 | 8.65 | 1885 | 5.4620 |
426
- | 4.2349 | 8.67 | 1890 | 5.4617 |
427
- | 4.3128 | 8.69 | 1895 | 5.4610 |
428
- | 4.3512 | 8.72 | 1900 | 5.4600 |
429
- | 4.0034 | 8.74 | 1905 | 5.4596 |
430
- | 3.4403 | 8.76 | 1910 | 5.4598 |
431
- | 4.1383 | 8.78 | 1915 | 5.4602 |
432
- | 3.737 | 8.81 | 1920 | 5.4609 |
433
- | 4.4348 | 8.83 | 1925 | 5.4616 |
434
- | 3.7228 | 8.85 | 1930 | 5.4618 |
435
- | 4.1752 | 8.88 | 1935 | 5.4618 |
436
- | 3.9442 | 8.9 | 1940 | 5.4608 |
437
- | 4.094 | 8.92 | 1945 | 5.4595 |
438
- | 4.4811 | 8.94 | 1950 | 5.4585 |
439
- | 3.9241 | 8.97 | 1955 | 5.4569 |
440
- | 3.7469 | 8.99 | 1960 | 5.4551 |
441
- | 3.6785 | 9.01 | 1965 | 5.4554 |
442
- | 3.8777 | 9.04 | 1970 | 5.4551 |
443
- | 4.0055 | 9.06 | 1975 | 5.4549 |
444
- | 3.8735 | 9.08 | 1980 | 5.4551 |
445
- | 3.9355 | 9.11 | 1985 | 5.4561 |
446
- | 4.6091 | 9.13 | 1990 | 5.4569 |
447
- | 4.2451 | 9.15 | 1995 | 5.4570 |
448
- | 4.5107 | 9.17 | 2000 | 5.4568 |
449
- | 3.9787 | 9.2 | 2005 | 5.4568 |
450
- | 4.3155 | 9.22 | 2010 | 5.4565 |
451
- | 3.5519 | 9.24 | 2015 | 5.4571 |
452
- | 4.3125 | 9.27 | 2020 | 5.4564 |
453
- | 4.2182 | 9.29 | 2025 | 5.4562 |
454
- | 3.7688 | 9.31 | 2030 | 5.4569 |
455
- | 4.522 | 9.33 | 2035 | 5.4571 |
456
- | 4.2626 | 9.36 | 2040 | 5.4570 |
457
- | 4.2814 | 9.38 | 2045 | 5.4562 |
458
- | 4.3051 | 9.4 | 2050 | 5.4556 |
459
- | 4.0578 | 9.43 | 2055 | 5.4550 |
460
- | 4.4805 | 9.45 | 2060 | 5.4547 |
461
- | 4.3125 | 9.47 | 2065 | 5.4539 |
462
- | 4.087 | 9.5 | 2070 | 5.4528 |
463
- | 4.1643 | 9.52 | 2075 | 5.4523 |
464
- | 3.812 | 9.54 | 2080 | 5.4519 |
465
- | 4.2929 | 9.56 | 2085 | 5.4515 |
466
- | 4.1114 | 9.59 | 2090 | 5.4514 |
467
- | 3.6871 | 9.61 | 2095 | 5.4510 |
468
- | 4.0303 | 9.63 | 2100 | 5.4506 |
469
- | 4.5228 | 9.66 | 2105 | 5.4501 |
470
- | 3.9624 | 9.68 | 2110 | 5.4496 |
471
- | 3.4067 | 9.7 | 2115 | 5.4497 |
472
- | 3.8828 | 9.72 | 2120 | 5.4498 |
473
- | 4.8057 | 9.75 | 2125 | 5.4494 |
474
- | 3.7825 | 9.77 | 2130 | 5.4493 |
475
- | 3.3242 | 9.79 | 2135 | 5.4495 |
476
- | 4.1648 | 9.82 | 2140 | 5.4498 |
477
- | 3.6472 | 9.84 | 2145 | 5.4499 |
478
- | 3.9233 | 9.86 | 2150 | 5.4501 |
479
- | 4.6137 | 9.89 | 2155 | 5.4502 |
480
- | 4.257 | 9.91 | 2160 | 5.4501 |
481
- | 3.6456 | 9.93 | 2165 | 5.4501 |
482
- | 4.1111 | 9.95 | 2170 | 5.4501 |
483
- | 4.4644 | 9.98 | 2175 | 5.4502 |
484
- | 4.029 | 10.0 | 2180 | 5.4502 |
485
 
486
 
487
  ### Framework versions
 
15
 
16
  This model is a fine-tuned version of [deepset/bert-base-cased-squad2](https://huggingface.co/deepset/bert-base-cased-squad2) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 6.1568
19
 
20
  ## Model description
21
 
 
40
  - seed: 42
41
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
  - lr_scheduler_type: linear
43
+ - num_epochs: 1
44
 
45
  ### Training results
46
 
47
  | Training Loss | Epoch | Step | Validation Loss |
48
  |:-------------:|:-----:|:----:|:---------------:|
49
+ | 10.2234 | 0.02 | 5 | 11.9934 |
50
+ | 10.8592 | 0.05 | 10 | 11.5287 |
51
+ | 11.1095 | 0.07 | 15 | 11.0729 |
52
+ | 9.6708 | 0.09 | 20 | 10.6345 |
53
+ | 9.8014 | 0.11 | 25 | 10.2156 |
54
+ | 8.5541 | 0.14 | 30 | 9.8183 |
55
+ | 9.0229 | 0.16 | 35 | 9.4399 |
56
+ | 8.6368 | 0.18 | 40 | 9.0751 |
57
+ | 8.1449 | 0.21 | 45 | 8.7287 |
58
+ | 8.2085 | 0.23 | 50 | 8.4043 |
59
+ | 6.7635 | 0.25 | 55 | 8.1085 |
60
+ | 7.109 | 0.28 | 60 | 7.8431 |
61
+ | 6.8781 | 0.3 | 65 | 7.5985 |
62
+ | 7.0699 | 0.32 | 70 | 7.3754 |
63
+ | 6.7036 | 0.34 | 75 | 7.1764 |
64
+ | 6.4062 | 0.37 | 80 | 7.0033 |
65
+ | 6.8335 | 0.39 | 85 | 6.8531 |
66
+ | 6.2913 | 0.41 | 90 | 6.7252 |
67
+ | 6.0877 | 0.44 | 95 | 6.6208 |
68
+ | 6.1684 | 0.46 | 100 | 6.5346 |
69
+ | 6.1907 | 0.48 | 105 | 6.4630 |
70
+ | 5.9105 | 0.5 | 110 | 6.4073 |
71
+ | 6.0136 | 0.53 | 115 | 6.3652 |
72
+ | 6.0264 | 0.55 | 120 | 6.3287 |
73
+ | 5.782 | 0.57 | 125 | 6.3013 |
74
+ | 5.843 | 0.6 | 130 | 6.2805 |
75
+ | 5.9236 | 0.62 | 135 | 6.2619 |
76
+ | 5.7016 | 0.64 | 140 | 6.2473 |
77
+ | 5.704 | 0.67 | 145 | 6.2352 |
78
+ | 5.7283 | 0.69 | 150 | 6.2272 |
79
+ | 5.8303 | 0.71 | 155 | 6.2179 |
80
+ | 5.7584 | 0.73 | 160 | 6.2092 |
81
+ | 5.8322 | 0.76 | 165 | 6.2009 |
82
+ | 5.8232 | 0.78 | 170 | 6.1927 |
83
+ | 5.871 | 0.8 | 175 | 6.1852 |
84
+ | 5.7416 | 0.83 | 180 | 6.1791 |
85
+ | 5.936 | 0.85 | 185 | 6.1735 |
86
+ | 5.7006 | 0.87 | 190 | 6.1685 |
87
+ | 5.7799 | 0.89 | 195 | 6.1649 |
88
+ | 5.8199 | 0.92 | 200 | 6.1616 |
89
+ | 5.6763 | 0.94 | 205 | 6.1592 |
90
+ | 5.7938 | 0.96 | 210 | 6.1576 |
91
+ | 5.6812 | 0.99 | 215 | 6.1568 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
92
 
93
 
94
  ### Framework versions
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e39e90954c5c8d68c1a24d6ed3baa914b9c907fdcfad808738d0a63aafa40704
3
  size 430952617
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b7260dfdcc745b4637b978b8d3bf9cc48e195fe0933df0ca26e005e3dac5f05
3
  size 430952617
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bb5e0f117eb598e69f42fed1c83dd3c670c197df60bd9eca285ee698de1a71a0
3
  size 4027
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d491a81cf9d9d1a4314df04908a115efce975e4b2296f725f72aad5eff84c15d
3
  size 4027