hung200504
commited on
Commit
•
ebc4e3f
1
Parent(s):
18c7a0c
bert-cased
Browse files- README.md +45 -438
- pytorch_model.bin +1 -1
- 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:
|
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:
|
44 |
|
45 |
### Training results
|
46 |
|
47 |
| Training Loss | Epoch | Step | Validation Loss |
|
48 |
|:-------------:|:-----:|:----:|:---------------:|
|
49 |
-
| 10.
|
50 |
-
| 10.
|
51 |
-
| 11.
|
52 |
-
| 9.
|
53 |
-
| 9.
|
54 |
-
| 8.
|
55 |
-
|
|
56 |
-
| 8.
|
57 |
-
|
|
58 |
-
|
|
59 |
-
| 6.
|
60 |
-
|
|
61 |
-
| 6.
|
62 |
-
|
|
63 |
-
| 6.
|
64 |
-
| 6.
|
65 |
-
| 6.
|
66 |
-
| 6.
|
67 |
-
|
|
68 |
-
|
|
69 |
-
|
|
70 |
-
| 5.
|
71 |
-
|
|
72 |
-
|
|
73 |
-
| 5.
|
74 |
-
| 5.
|
75 |
-
| 5.
|
76 |
-
| 5.
|
77 |
-
| 5.
|
78 |
-
| 5.
|
79 |
-
| 5.
|
80 |
-
| 5.
|
81 |
-
| 5.
|
82 |
-
| 5.
|
83 |
-
| 5.
|
84 |
-
| 5.
|
85 |
-
| 5.
|
86 |
-
| 5.
|
87 |
-
| 5.
|
88 |
-
| 5.
|
89 |
-
| 5.
|
90 |
-
| 5.
|
91 |
-
| 5.
|
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:
|
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:
|
3 |
size 4027
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d491a81cf9d9d1a4314df04908a115efce975e4b2296f725f72aad5eff84c15d
|
3 |
size 4027
|