Lisibonny commited on
Commit
b7aaee1
1 Parent(s): 37ec54d

End of training

Browse files
Files changed (3) hide show
  1. README.md +12 -502
  2. model.safetensors +1 -1
  3. training_args.bin +1 -1
README.md CHANGED
@@ -14,7 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
14
 
15
  This model is a fine-tuned version of [dccuchile/bert-base-spanish-wwm-uncased](https://huggingface.co/dccuchile/bert-base-spanish-wwm-uncased) on the None dataset.
16
  It achieves the following results on the evaluation set:
17
- - Loss: 3.5601
18
 
19
  ## Model description
20
 
@@ -39,512 +39,22 @@ The following hyperparameters were used during training:
39
  - seed: 42
40
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
41
  - lr_scheduler_type: linear
42
- - num_epochs: 500
43
 
44
  ### Training results
45
 
46
  | Training Loss | Epoch | Step | Validation Loss |
47
  |:-------------:|:-----:|:----:|:---------------:|
48
- | 5.8255 | 1.0 | 4 | 5.3891 |
49
- | 5.1117 | 2.0 | 8 | 4.5893 |
50
- | 4.1827 | 3.0 | 12 | 3.7720 |
51
- | 3.3531 | 4.0 | 16 | 3.3087 |
52
- | 2.8805 | 5.0 | 20 | 3.0557 |
53
- | 2.5266 | 6.0 | 24 | 2.8821 |
54
- | 2.1218 | 7.0 | 28 | 2.8081 |
55
- | 1.7735 | 8.0 | 32 | 2.8738 |
56
- | 1.5445 | 9.0 | 36 | 2.8422 |
57
- | 1.255 | 10.0 | 40 | 2.7625 |
58
- | 1.0832 | 11.0 | 44 | 2.8552 |
59
- | 0.9661 | 12.0 | 48 | 3.0972 |
60
- | 0.8375 | 13.0 | 52 | 2.8615 |
61
- | 0.7235 | 14.0 | 56 | 2.7642 |
62
- | 0.7015 | 15.0 | 60 | 2.6978 |
63
- | 0.583 | 16.0 | 64 | 2.7134 |
64
- | 0.5179 | 17.0 | 68 | 3.0464 |
65
- | 0.568 | 18.0 | 72 | 2.9223 |
66
- | 0.4952 | 19.0 | 76 | 2.7379 |
67
- | 0.4919 | 20.0 | 80 | 2.9426 |
68
- | 0.4154 | 21.0 | 84 | 3.0189 |
69
- | 0.38 | 22.0 | 88 | 3.0521 |
70
- | 0.3726 | 23.0 | 92 | 3.2195 |
71
- | 0.3862 | 24.0 | 96 | 3.2656 |
72
- | 0.3007 | 25.0 | 100 | 3.3022 |
73
- | 0.2702 | 26.0 | 104 | 3.4350 |
74
- | 0.3367 | 27.0 | 108 | 3.1174 |
75
- | 0.2882 | 28.0 | 112 | 3.1469 |
76
- | 0.2833 | 29.0 | 116 | 3.4144 |
77
- | 0.1932 | 30.0 | 120 | 3.4515 |
78
- | 0.2376 | 31.0 | 124 | 3.3375 |
79
- | 0.1912 | 32.0 | 128 | 3.2425 |
80
- | 0.1834 | 33.0 | 132 | 3.3439 |
81
- | 0.2208 | 34.0 | 136 | 3.2172 |
82
- | 0.231 | 35.0 | 140 | 3.1026 |
83
- | 0.1795 | 36.0 | 144 | 3.2363 |
84
- | 0.1769 | 37.0 | 148 | 3.4713 |
85
- | 0.1616 | 38.0 | 152 | 3.5202 |
86
- | 0.1376 | 39.0 | 156 | 3.4871 |
87
- | 0.1514 | 40.0 | 160 | 3.4514 |
88
- | 0.1489 | 41.0 | 164 | 3.3153 |
89
- | 0.1893 | 42.0 | 168 | 3.3107 |
90
- | 0.1229 | 43.0 | 172 | 3.2508 |
91
- | 0.1387 | 44.0 | 176 | 3.2126 |
92
- | 0.1596 | 45.0 | 180 | 3.2700 |
93
- | 0.1967 | 46.0 | 184 | 3.2496 |
94
- | 0.1348 | 47.0 | 188 | 3.2059 |
95
- | 0.109 | 48.0 | 192 | 3.2958 |
96
- | 0.1258 | 49.0 | 196 | 3.3931 |
97
- | 0.2339 | 50.0 | 200 | 3.4541 |
98
- | 0.1568 | 51.0 | 204 | 3.3084 |
99
- | 0.1188 | 52.0 | 208 | 3.2903 |
100
- | 0.0895 | 53.0 | 212 | 3.2917 |
101
- | 0.1052 | 54.0 | 216 | 3.2793 |
102
- | 0.1172 | 55.0 | 220 | 3.2244 |
103
- | 0.1104 | 56.0 | 224 | 3.0923 |
104
- | 0.1057 | 57.0 | 228 | 3.1605 |
105
- | 0.1512 | 58.0 | 232 | 3.3020 |
106
- | 0.1147 | 59.0 | 236 | 3.3719 |
107
- | 0.1131 | 60.0 | 240 | 3.4687 |
108
- | 0.0929 | 61.0 | 244 | 3.5465 |
109
- | 0.1143 | 62.0 | 248 | 3.5919 |
110
- | 0.1308 | 63.0 | 252 | 3.5481 |
111
- | 0.1138 | 64.0 | 256 | 3.5466 |
112
- | 0.1108 | 65.0 | 260 | 3.6229 |
113
- | 0.1035 | 66.0 | 264 | 3.7497 |
114
- | 0.0984 | 67.0 | 268 | 3.7572 |
115
- | 0.1654 | 68.0 | 272 | 3.6967 |
116
- | 0.0954 | 69.0 | 276 | 3.5673 |
117
- | 0.1227 | 70.0 | 280 | 3.4336 |
118
- | 0.1278 | 71.0 | 284 | 3.1626 |
119
- | 0.097 | 72.0 | 288 | 3.0338 |
120
- | 0.1091 | 73.0 | 292 | 3.0301 |
121
- | 0.1071 | 74.0 | 296 | 2.9816 |
122
- | 0.1142 | 75.0 | 300 | 2.9814 |
123
- | 0.1107 | 76.0 | 304 | 3.2266 |
124
- | 0.1005 | 77.0 | 308 | 3.5266 |
125
- | 0.0834 | 78.0 | 312 | 3.6279 |
126
- | 0.1441 | 79.0 | 316 | 3.5709 |
127
- | 0.1257 | 80.0 | 320 | 3.3583 |
128
- | 0.1075 | 81.0 | 324 | 3.2398 |
129
- | 0.1004 | 82.0 | 328 | 3.1442 |
130
- | 0.1055 | 83.0 | 332 | 3.1434 |
131
- | 0.0993 | 84.0 | 336 | 3.1982 |
132
- | 0.1184 | 85.0 | 340 | 3.2464 |
133
- | 0.106 | 86.0 | 344 | 3.2476 |
134
- | 0.1069 | 87.0 | 348 | 3.2862 |
135
- | 0.1029 | 88.0 | 352 | 3.3547 |
136
- | 0.1069 | 89.0 | 356 | 3.3963 |
137
- | 0.1119 | 90.0 | 360 | 3.4494 |
138
- | 0.0824 | 91.0 | 364 | 3.5189 |
139
- | 0.1078 | 92.0 | 368 | 3.5612 |
140
- | 0.1077 | 93.0 | 372 | 3.5916 |
141
- | 0.1198 | 94.0 | 376 | 3.6031 |
142
- | 0.1155 | 95.0 | 380 | 3.6733 |
143
- | 0.0963 | 96.0 | 384 | 3.7254 |
144
- | 0.0969 | 97.0 | 388 | 3.7617 |
145
- | 0.1091 | 98.0 | 392 | 3.8113 |
146
- | 0.1013 | 99.0 | 396 | 3.8227 |
147
- | 0.0968 | 100.0 | 400 | 3.7379 |
148
- | 0.0979 | 101.0 | 404 | 3.6634 |
149
- | 0.0991 | 102.0 | 408 | 3.5453 |
150
- | 0.0926 | 103.0 | 412 | 3.5034 |
151
- | 0.0829 | 104.0 | 416 | 3.5217 |
152
- | 0.1073 | 105.0 | 420 | 3.5459 |
153
- | 0.1012 | 106.0 | 424 | 3.5478 |
154
- | 0.0912 | 107.0 | 428 | 3.5307 |
155
- | 0.0979 | 108.0 | 432 | 3.4828 |
156
- | 0.1082 | 109.0 | 436 | 3.4641 |
157
- | 0.0896 | 110.0 | 440 | 3.5300 |
158
- | 0.1008 | 111.0 | 444 | 3.4829 |
159
- | 0.0924 | 112.0 | 448 | 3.4521 |
160
- | 0.0975 | 113.0 | 452 | 3.4344 |
161
- | 0.0952 | 114.0 | 456 | 3.4458 |
162
- | 0.0974 | 115.0 | 460 | 3.4821 |
163
- | 0.1132 | 116.0 | 464 | 3.5841 |
164
- | 0.1189 | 117.0 | 468 | 3.6406 |
165
- | 0.0874 | 118.0 | 472 | 3.6157 |
166
- | 0.0908 | 119.0 | 476 | 3.6541 |
167
- | 0.1083 | 120.0 | 480 | 3.7194 |
168
- | 0.1428 | 121.0 | 484 | 3.7080 |
169
- | 0.1002 | 122.0 | 488 | 3.7075 |
170
- | 0.104 | 123.0 | 492 | 3.7148 |
171
- | 0.1077 | 124.0 | 496 | 3.7953 |
172
- | 0.1136 | 125.0 | 500 | 3.8299 |
173
- | 0.0866 | 126.0 | 504 | 3.8417 |
174
- | 0.1092 | 127.0 | 508 | 3.7402 |
175
- | 0.0874 | 128.0 | 512 | 3.6366 |
176
- | 0.0951 | 129.0 | 516 | 3.6289 |
177
- | 0.0973 | 130.0 | 520 | 3.6400 |
178
- | 0.105 | 131.0 | 524 | 3.6316 |
179
- | 0.0898 | 132.0 | 528 | 3.5793 |
180
- | 0.0964 | 133.0 | 532 | 3.5406 |
181
- | 0.1 | 134.0 | 536 | 3.5471 |
182
- | 0.0971 | 135.0 | 540 | 3.5857 |
183
- | 0.0955 | 136.0 | 544 | 3.6425 |
184
- | 0.1083 | 137.0 | 548 | 3.7226 |
185
- | 0.0903 | 138.0 | 552 | 3.7742 |
186
- | 0.0874 | 139.0 | 556 | 3.8052 |
187
- | 0.09 | 140.0 | 560 | 3.8108 |
188
- | 0.0968 | 141.0 | 564 | 3.8019 |
189
- | 0.1005 | 142.0 | 568 | 3.7772 |
190
- | 0.0838 | 143.0 | 572 | 3.8121 |
191
- | 0.0956 | 144.0 | 576 | 3.8996 |
192
- | 0.1134 | 145.0 | 580 | 3.9859 |
193
- | 0.0944 | 146.0 | 584 | 3.9801 |
194
- | 0.0925 | 147.0 | 588 | 3.7870 |
195
- | 0.0926 | 148.0 | 592 | 3.6757 |
196
- | 0.0916 | 149.0 | 596 | 3.5706 |
197
- | 0.0861 | 150.0 | 600 | 3.4892 |
198
- | 0.1119 | 151.0 | 604 | 3.3924 |
199
- | 0.0989 | 152.0 | 608 | 3.2933 |
200
- | 0.0814 | 153.0 | 612 | 3.3393 |
201
- | 0.1064 | 154.0 | 616 | 3.3962 |
202
- | 0.0958 | 155.0 | 620 | 3.4558 |
203
- | 0.0994 | 156.0 | 624 | 3.4584 |
204
- | 0.0952 | 157.0 | 628 | 3.4579 |
205
- | 0.0962 | 158.0 | 632 | 3.4528 |
206
- | 0.0926 | 159.0 | 636 | 3.4584 |
207
- | 0.0979 | 160.0 | 640 | 3.4959 |
208
- | 0.0863 | 161.0 | 644 | 3.5602 |
209
- | 0.0916 | 162.0 | 648 | 3.5990 |
210
- | 0.0908 | 163.0 | 652 | 3.4985 |
211
- | 0.0878 | 164.0 | 656 | 3.5034 |
212
- | 0.1558 | 165.0 | 660 | 3.5467 |
213
- | 0.1269 | 166.0 | 664 | 3.4501 |
214
- | 0.1235 | 167.0 | 668 | 3.3853 |
215
- | 0.0923 | 168.0 | 672 | 3.3369 |
216
- | 0.0943 | 169.0 | 676 | 3.3161 |
217
- | 0.0983 | 170.0 | 680 | 3.2985 |
218
- | 0.0949 | 171.0 | 684 | 3.2924 |
219
- | 0.0949 | 172.0 | 688 | 3.2861 |
220
- | 0.1001 | 173.0 | 692 | 3.2781 |
221
- | 0.1015 | 174.0 | 696 | 3.2720 |
222
- | 0.0826 | 175.0 | 700 | 3.2689 |
223
- | 0.0817 | 176.0 | 704 | 3.3497 |
224
- | 0.1024 | 177.0 | 708 | 3.3691 |
225
- | 0.1056 | 178.0 | 712 | 3.3532 |
226
- | 0.1043 | 179.0 | 716 | 3.3737 |
227
- | 0.0946 | 180.0 | 720 | 3.3813 |
228
- | 0.1075 | 181.0 | 724 | 3.3969 |
229
- | 0.0832 | 182.0 | 728 | 3.4573 |
230
- | 0.1137 | 183.0 | 732 | 3.4740 |
231
- | 0.0963 | 184.0 | 736 | 3.4878 |
232
- | 0.0938 | 185.0 | 740 | 3.5141 |
233
- | 0.0918 | 186.0 | 744 | 3.5336 |
234
- | 0.0835 | 187.0 | 748 | 3.5830 |
235
- | 0.0848 | 188.0 | 752 | 3.6413 |
236
- | 0.0965 | 189.0 | 756 | 3.6873 |
237
- | 0.0988 | 190.0 | 760 | 3.6537 |
238
- | 0.0922 | 191.0 | 764 | 3.5926 |
239
- | 0.1221 | 192.0 | 768 | 3.5160 |
240
- | 0.1234 | 193.0 | 772 | 3.3286 |
241
- | 0.0951 | 194.0 | 776 | 3.2649 |
242
- | 0.1063 | 195.0 | 780 | 3.1876 |
243
- | 0.0962 | 196.0 | 784 | 3.1829 |
244
- | 0.0966 | 197.0 | 788 | 3.2851 |
245
- | 0.0902 | 198.0 | 792 | 3.2709 |
246
- | 0.0947 | 199.0 | 796 | 3.2424 |
247
- | 0.0873 | 200.0 | 800 | 3.2230 |
248
- | 0.0911 | 201.0 | 804 | 3.1615 |
249
- | 0.0844 | 202.0 | 808 | 3.1014 |
250
- | 0.0913 | 203.0 | 812 | 3.1057 |
251
- | 0.101 | 204.0 | 816 | 3.1949 |
252
- | 0.0962 | 205.0 | 820 | 3.2591 |
253
- | 0.0892 | 206.0 | 824 | 3.3306 |
254
- | 0.1034 | 207.0 | 828 | 3.3670 |
255
- | 0.1023 | 208.0 | 832 | 3.3720 |
256
- | 0.1029 | 209.0 | 836 | 3.4103 |
257
- | 0.0979 | 210.0 | 840 | 3.4560 |
258
- | 0.0878 | 211.0 | 844 | 3.4824 |
259
- | 0.0869 | 212.0 | 848 | 3.4960 |
260
- | 0.0848 | 213.0 | 852 | 3.5188 |
261
- | 0.0926 | 214.0 | 856 | 3.5291 |
262
- | 0.0892 | 215.0 | 860 | 3.5051 |
263
- | 0.0951 | 216.0 | 864 | 3.4328 |
264
- | 0.087 | 217.0 | 868 | 3.4252 |
265
- | 0.086 | 218.0 | 872 | 3.4237 |
266
- | 0.0946 | 219.0 | 876 | 3.4475 |
267
- | 0.0884 | 220.0 | 880 | 3.5321 |
268
- | 0.0826 | 221.0 | 884 | 3.6659 |
269
- | 0.1062 | 222.0 | 888 | 3.7643 |
270
- | 0.0876 | 223.0 | 892 | 3.7874 |
271
- | 0.1 | 224.0 | 896 | 3.7657 |
272
- | 0.081 | 225.0 | 900 | 3.7110 |
273
- | 0.0879 | 226.0 | 904 | 3.7582 |
274
- | 0.0978 | 227.0 | 908 | 3.8041 |
275
- | 0.0959 | 228.0 | 912 | 3.8070 |
276
- | 0.0954 | 229.0 | 916 | 3.8455 |
277
- | 0.1085 | 230.0 | 920 | 3.8336 |
278
- | 0.09 | 231.0 | 924 | 3.7963 |
279
- | 0.0907 | 232.0 | 928 | 3.8347 |
280
- | 0.0894 | 233.0 | 932 | 3.8755 |
281
- | 0.0862 | 234.0 | 936 | 3.9903 |
282
- | 0.0966 | 235.0 | 940 | 4.0796 |
283
- | 0.0838 | 236.0 | 944 | 4.1039 |
284
- | 0.0847 | 237.0 | 948 | 4.1028 |
285
- | 0.0899 | 238.0 | 952 | 4.1061 |
286
- | 0.0921 | 239.0 | 956 | 4.0822 |
287
- | 0.0932 | 240.0 | 960 | 4.0745 |
288
- | 0.0942 | 241.0 | 964 | 4.0804 |
289
- | 0.0938 | 242.0 | 968 | 4.1175 |
290
- | 0.0959 | 243.0 | 972 | 4.1314 |
291
- | 0.095 | 244.0 | 976 | 4.1374 |
292
- | 0.0926 | 245.0 | 980 | 4.1482 |
293
- | 0.0892 | 246.0 | 984 | 4.1512 |
294
- | 0.0816 | 247.0 | 988 | 4.1510 |
295
- | 0.0928 | 248.0 | 992 | 4.1619 |
296
- | 0.0864 | 249.0 | 996 | 4.1735 |
297
- | 0.0845 | 250.0 | 1000 | 4.1694 |
298
- | 0.0915 | 251.0 | 1004 | 4.1395 |
299
- | 0.0819 | 252.0 | 1008 | 4.1065 |
300
- | 0.0929 | 253.0 | 1012 | 4.1102 |
301
- | 0.0918 | 254.0 | 1016 | 4.1331 |
302
- | 0.0916 | 255.0 | 1020 | 4.1412 |
303
- | 0.0938 | 256.0 | 1024 | 4.1258 |
304
- | 0.0867 | 257.0 | 1028 | 4.0901 |
305
- | 0.0895 | 258.0 | 1032 | 4.0611 |
306
- | 0.0801 | 259.0 | 1036 | 4.0435 |
307
- | 0.0929 | 260.0 | 1040 | 4.0051 |
308
- | 0.0983 | 261.0 | 1044 | 3.9689 |
309
- | 0.0911 | 262.0 | 1048 | 3.9449 |
310
- | 0.0892 | 263.0 | 1052 | 3.9534 |
311
- | 0.0991 | 264.0 | 1056 | 3.9735 |
312
- | 0.0828 | 265.0 | 1060 | 3.9995 |
313
- | 0.0866 | 266.0 | 1064 | 4.0005 |
314
- | 0.0794 | 267.0 | 1068 | 3.9316 |
315
- | 0.0921 | 268.0 | 1072 | 3.7251 |
316
- | 0.0898 | 269.0 | 1076 | 3.6213 |
317
- | 0.1025 | 270.0 | 1080 | 3.6076 |
318
- | 0.1008 | 271.0 | 1084 | 3.6108 |
319
- | 0.0905 | 272.0 | 1088 | 3.5909 |
320
- | 0.1052 | 273.0 | 1092 | 3.5671 |
321
- | 0.0862 | 274.0 | 1096 | 3.5699 |
322
- | 0.0851 | 275.0 | 1100 | 3.5922 |
323
- | 0.0847 | 276.0 | 1104 | 3.6125 |
324
- | 0.0863 | 277.0 | 1108 | 3.6739 |
325
- | 0.0946 | 278.0 | 1112 | 3.7260 |
326
- | 0.0875 | 279.0 | 1116 | 3.7954 |
327
- | 0.0804 | 280.0 | 1120 | 3.8552 |
328
- | 0.0806 | 281.0 | 1124 | 3.8995 |
329
- | 0.0853 | 282.0 | 1128 | 3.9081 |
330
- | 0.0891 | 283.0 | 1132 | 3.9181 |
331
- | 0.0954 | 284.0 | 1136 | 3.7867 |
332
- | 0.0946 | 285.0 | 1140 | 3.5997 |
333
- | 0.1063 | 286.0 | 1144 | 3.4835 |
334
- | 0.0951 | 287.0 | 1148 | 3.4053 |
335
- | 0.0936 | 288.0 | 1152 | 3.3867 |
336
- | 0.0917 | 289.0 | 1156 | 3.3936 |
337
- | 0.1082 | 290.0 | 1160 | 3.4833 |
338
- | 0.0932 | 291.0 | 1164 | 3.5953 |
339
- | 0.0811 | 292.0 | 1168 | 3.6905 |
340
- | 0.0907 | 293.0 | 1172 | 3.7877 |
341
- | 0.0901 | 294.0 | 1176 | 3.8603 |
342
- | 0.1039 | 295.0 | 1180 | 3.9000 |
343
- | 0.0913 | 296.0 | 1184 | 3.8906 |
344
- | 0.0892 | 297.0 | 1188 | 3.8456 |
345
- | 0.09 | 298.0 | 1192 | 3.7831 |
346
- | 0.0831 | 299.0 | 1196 | 3.7753 |
347
- | 0.0991 | 300.0 | 1200 | 3.7674 |
348
- | 0.0853 | 301.0 | 1204 | 3.7839 |
349
- | 0.0946 | 302.0 | 1208 | 3.8273 |
350
- | 0.0916 | 303.0 | 1212 | 3.8447 |
351
- | 0.0856 | 304.0 | 1216 | 3.8587 |
352
- | 0.0914 | 305.0 | 1220 | 3.8825 |
353
- | 0.0897 | 306.0 | 1224 | 3.8877 |
354
- | 0.09 | 307.0 | 1228 | 3.8699 |
355
- | 0.085 | 308.0 | 1232 | 3.8003 |
356
- | 0.0939 | 309.0 | 1236 | 3.7440 |
357
- | 0.0835 | 310.0 | 1240 | 3.6700 |
358
- | 0.0975 | 311.0 | 1244 | 3.6276 |
359
- | 0.0826 | 312.0 | 1248 | 3.6249 |
360
- | 0.0851 | 313.0 | 1252 | 3.6494 |
361
- | 0.0931 | 314.0 | 1256 | 3.6850 |
362
- | 0.0964 | 315.0 | 1260 | 3.7294 |
363
- | 0.0946 | 316.0 | 1264 | 3.7988 |
364
- | 0.0901 | 317.0 | 1268 | 3.8034 |
365
- | 0.0927 | 318.0 | 1272 | 3.8010 |
366
- | 0.0881 | 319.0 | 1276 | 3.8071 |
367
- | 0.0825 | 320.0 | 1280 | 3.8155 |
368
- | 0.0883 | 321.0 | 1284 | 3.8148 |
369
- | 0.0892 | 322.0 | 1288 | 3.8015 |
370
- | 0.0941 | 323.0 | 1292 | 3.7773 |
371
- | 0.0855 | 324.0 | 1296 | 3.7556 |
372
- | 0.0937 | 325.0 | 1300 | 3.7623 |
373
- | 0.0869 | 326.0 | 1304 | 3.7801 |
374
- | 0.0882 | 327.0 | 1308 | 3.7967 |
375
- | 0.0974 | 328.0 | 1312 | 3.7955 |
376
- | 0.0922 | 329.0 | 1316 | 3.7720 |
377
- | 0.0942 | 330.0 | 1320 | 3.7536 |
378
- | 0.0889 | 331.0 | 1324 | 3.7578 |
379
- | 0.0985 | 332.0 | 1328 | 3.7704 |
380
- | 0.096 | 333.0 | 1332 | 3.7745 |
381
- | 0.0888 | 334.0 | 1336 | 3.7735 |
382
- | 0.0998 | 335.0 | 1340 | 3.7788 |
383
- | 0.0958 | 336.0 | 1344 | 3.7809 |
384
- | 0.0871 | 337.0 | 1348 | 3.7908 |
385
- | 0.0905 | 338.0 | 1352 | 3.7993 |
386
- | 0.0884 | 339.0 | 1356 | 3.8020 |
387
- | 0.0994 | 340.0 | 1360 | 3.7687 |
388
- | 0.0949 | 341.0 | 1364 | 3.6491 |
389
- | 0.1015 | 342.0 | 1368 | 3.5751 |
390
- | 0.0904 | 343.0 | 1372 | 3.5586 |
391
- | 0.096 | 344.0 | 1376 | 3.5412 |
392
- | 0.0845 | 345.0 | 1380 | 3.5382 |
393
- | 0.0853 | 346.0 | 1384 | 3.5359 |
394
- | 0.086 | 347.0 | 1388 | 3.5468 |
395
- | 0.0907 | 348.0 | 1392 | 3.5806 |
396
- | 0.088 | 349.0 | 1396 | 3.6311 |
397
- | 0.0955 | 350.0 | 1400 | 3.6754 |
398
- | 0.0853 | 351.0 | 1404 | 3.7017 |
399
- | 0.0854 | 352.0 | 1408 | 3.7180 |
400
- | 0.0908 | 353.0 | 1412 | 3.7386 |
401
- | 0.0897 | 354.0 | 1416 | 3.7726 |
402
- | 0.097 | 355.0 | 1420 | 3.7952 |
403
- | 0.0931 | 356.0 | 1424 | 3.8112 |
404
- | 0.0862 | 357.0 | 1428 | 3.8326 |
405
- | 0.0892 | 358.0 | 1432 | 3.8527 |
406
- | 0.097 | 359.0 | 1436 | 3.8629 |
407
- | 0.0805 | 360.0 | 1440 | 3.8076 |
408
- | 0.0949 | 361.0 | 1444 | 3.7724 |
409
- | 0.0914 | 362.0 | 1448 | 3.7761 |
410
- | 0.0892 | 363.0 | 1452 | 3.7955 |
411
- | 0.0842 | 364.0 | 1456 | 3.7648 |
412
- | 0.0978 | 365.0 | 1460 | 3.7531 |
413
- | 0.0961 | 366.0 | 1464 | 3.7609 |
414
- | 0.0799 | 367.0 | 1468 | 3.7799 |
415
- | 0.0921 | 368.0 | 1472 | 3.7923 |
416
- | 0.0898 | 369.0 | 1476 | 3.8243 |
417
- | 0.0882 | 370.0 | 1480 | 3.8440 |
418
- | 0.0879 | 371.0 | 1484 | 3.8466 |
419
- | 0.091 | 372.0 | 1488 | 3.8287 |
420
- | 0.0883 | 373.0 | 1492 | 3.8056 |
421
- | 0.0895 | 374.0 | 1496 | 3.7981 |
422
- | 0.0849 | 375.0 | 1500 | 3.8065 |
423
- | 0.1001 | 376.0 | 1504 | 3.8139 |
424
- | 0.1021 | 377.0 | 1508 | 3.8406 |
425
- | 0.0954 | 378.0 | 1512 | 3.8464 |
426
- | 0.0837 | 379.0 | 1516 | 3.8391 |
427
- | 0.0858 | 380.0 | 1520 | 3.8267 |
428
- | 0.0915 | 381.0 | 1524 | 3.8125 |
429
- | 0.088 | 382.0 | 1528 | 3.7995 |
430
- | 0.0872 | 383.0 | 1532 | 3.7862 |
431
- | 0.0829 | 384.0 | 1536 | 3.7618 |
432
- | 0.0923 | 385.0 | 1540 | 3.7419 |
433
- | 0.1123 | 386.0 | 1544 | 3.7257 |
434
- | 0.0875 | 387.0 | 1548 | 3.7200 |
435
- | 0.0935 | 388.0 | 1552 | 3.7273 |
436
- | 0.0902 | 389.0 | 1556 | 3.7084 |
437
- | 0.0878 | 390.0 | 1560 | 3.6877 |
438
- | 0.088 | 391.0 | 1564 | 3.6732 |
439
- | 0.0895 | 392.0 | 1568 | 3.6701 |
440
- | 0.0812 | 393.0 | 1572 | 3.6898 |
441
- | 0.0855 | 394.0 | 1576 | 3.7130 |
442
- | 0.0925 | 395.0 | 1580 | 3.7392 |
443
- | 0.0885 | 396.0 | 1584 | 3.7490 |
444
- | 0.0874 | 397.0 | 1588 | 3.7572 |
445
- | 0.0826 | 398.0 | 1592 | 3.7622 |
446
- | 0.0892 | 399.0 | 1596 | 3.7660 |
447
- | 0.0908 | 400.0 | 1600 | 3.7733 |
448
- | 0.0973 | 401.0 | 1604 | 3.7822 |
449
- | 0.0932 | 402.0 | 1608 | 3.7805 |
450
- | 0.0836 | 403.0 | 1612 | 3.7732 |
451
- | 0.096 | 404.0 | 1616 | 3.7702 |
452
- | 0.0953 | 405.0 | 1620 | 3.7685 |
453
- | 0.0826 | 406.0 | 1624 | 3.7535 |
454
- | 0.1012 | 407.0 | 1628 | 3.7427 |
455
- | 0.0925 | 408.0 | 1632 | 3.7470 |
456
- | 0.0844 | 409.0 | 1636 | 3.7452 |
457
- | 0.089 | 410.0 | 1640 | 3.7418 |
458
- | 0.0906 | 411.0 | 1644 | 3.7358 |
459
- | 0.0904 | 412.0 | 1648 | 3.7197 |
460
- | 0.0923 | 413.0 | 1652 | 3.6977 |
461
- | 0.0958 | 414.0 | 1656 | 3.6810 |
462
- | 0.0882 | 415.0 | 1660 | 3.6696 |
463
- | 0.0843 | 416.0 | 1664 | 3.6555 |
464
- | 0.089 | 417.0 | 1668 | 3.6434 |
465
- | 0.0832 | 418.0 | 1672 | 3.6356 |
466
- | 0.0856 | 419.0 | 1676 | 3.6237 |
467
- | 0.0849 | 420.0 | 1680 | 3.6123 |
468
- | 0.0891 | 421.0 | 1684 | 3.5956 |
469
- | 0.09 | 422.0 | 1688 | 3.5906 |
470
- | 0.0994 | 423.0 | 1692 | 3.5979 |
471
- | 0.0927 | 424.0 | 1696 | 3.6102 |
472
- | 0.1069 | 425.0 | 1700 | 3.6162 |
473
- | 0.0968 | 426.0 | 1704 | 3.6362 |
474
- | 0.0887 | 427.0 | 1708 | 3.6637 |
475
- | 0.0869 | 428.0 | 1712 | 3.6765 |
476
- | 0.1048 | 429.0 | 1716 | 3.6808 |
477
- | 0.0915 | 430.0 | 1720 | 3.6798 |
478
- | 0.0943 | 431.0 | 1724 | 3.6750 |
479
- | 0.0859 | 432.0 | 1728 | 3.6659 |
480
- | 0.0841 | 433.0 | 1732 | 3.6556 |
481
- | 0.0873 | 434.0 | 1736 | 3.6422 |
482
- | 0.0848 | 435.0 | 1740 | 3.6365 |
483
- | 0.0964 | 436.0 | 1744 | 3.6359 |
484
- | 0.0939 | 437.0 | 1748 | 3.6288 |
485
- | 0.0926 | 438.0 | 1752 | 3.6157 |
486
- | 0.0861 | 439.0 | 1756 | 3.6108 |
487
- | 0.0897 | 440.0 | 1760 | 3.6138 |
488
- | 0.0935 | 441.0 | 1764 | 3.6172 |
489
- | 0.0858 | 442.0 | 1768 | 3.6025 |
490
- | 0.0935 | 443.0 | 1772 | 3.5891 |
491
- | 0.1 | 444.0 | 1776 | 3.5821 |
492
- | 0.0924 | 445.0 | 1780 | 3.5866 |
493
- | 0.0935 | 446.0 | 1784 | 3.5922 |
494
- | 0.0968 | 447.0 | 1788 | 3.6109 |
495
- | 0.1057 | 448.0 | 1792 | 3.6257 |
496
- | 0.086 | 449.0 | 1796 | 3.6347 |
497
- | 0.0887 | 450.0 | 1800 | 3.6403 |
498
- | 0.0929 | 451.0 | 1804 | 3.6412 |
499
- | 0.095 | 452.0 | 1808 | 3.6418 |
500
- | 0.0928 | 453.0 | 1812 | 3.6280 |
501
- | 0.1041 | 454.0 | 1816 | 3.6107 |
502
- | 0.1036 | 455.0 | 1820 | 3.6037 |
503
- | 0.0948 | 456.0 | 1824 | 3.5972 |
504
- | 0.0845 | 457.0 | 1828 | 3.5890 |
505
- | 0.0813 | 458.0 | 1832 | 3.5868 |
506
- | 0.0898 | 459.0 | 1836 | 3.5852 |
507
- | 0.0914 | 460.0 | 1840 | 3.5886 |
508
- | 0.0817 | 461.0 | 1844 | 3.5919 |
509
- | 0.0887 | 462.0 | 1848 | 3.5812 |
510
- | 0.0837 | 463.0 | 1852 | 3.5701 |
511
- | 0.0883 | 464.0 | 1856 | 3.5654 |
512
- | 0.0879 | 465.0 | 1860 | 3.5652 |
513
- | 0.0895 | 466.0 | 1864 | 3.5654 |
514
- | 0.0936 | 467.0 | 1868 | 3.5642 |
515
- | 0.087 | 468.0 | 1872 | 3.5632 |
516
- | 0.0964 | 469.0 | 1876 | 3.5639 |
517
- | 0.0898 | 470.0 | 1880 | 3.5624 |
518
- | 0.0871 | 471.0 | 1884 | 3.5636 |
519
- | 0.1032 | 472.0 | 1888 | 3.5650 |
520
- | 0.0901 | 473.0 | 1892 | 3.5648 |
521
- | 0.0865 | 474.0 | 1896 | 3.5623 |
522
- | 0.0786 | 475.0 | 1900 | 3.5600 |
523
- | 0.0934 | 476.0 | 1904 | 3.5611 |
524
- | 0.0906 | 477.0 | 1908 | 3.5627 |
525
- | 0.0813 | 478.0 | 1912 | 3.5652 |
526
- | 0.0879 | 479.0 | 1916 | 3.5682 |
527
- | 0.0889 | 480.0 | 1920 | 3.5708 |
528
- | 0.0858 | 481.0 | 1924 | 3.5718 |
529
- | 0.0984 | 482.0 | 1928 | 3.5731 |
530
- | 0.0904 | 483.0 | 1932 | 3.5735 |
531
- | 0.0875 | 484.0 | 1936 | 3.5741 |
532
- | 0.0922 | 485.0 | 1940 | 3.5746 |
533
- | 0.094 | 486.0 | 1944 | 3.5745 |
534
- | 0.0879 | 487.0 | 1948 | 3.5721 |
535
- | 0.0866 | 488.0 | 1952 | 3.5682 |
536
- | 0.0807 | 489.0 | 1956 | 3.5646 |
537
- | 0.0893 | 490.0 | 1960 | 3.5623 |
538
- | 0.0867 | 491.0 | 1964 | 3.5612 |
539
- | 0.0872 | 492.0 | 1968 | 3.5615 |
540
- | 0.0881 | 493.0 | 1972 | 3.5611 |
541
- | 0.093 | 494.0 | 1976 | 3.5605 |
542
- | 0.097 | 495.0 | 1980 | 3.5603 |
543
- | 0.0852 | 496.0 | 1984 | 3.5596 |
544
- | 0.0849 | 497.0 | 1988 | 3.5597 |
545
- | 0.0919 | 498.0 | 1992 | 3.5599 |
546
- | 0.0871 | 499.0 | 1996 | 3.5600 |
547
- | 0.0844 | 500.0 | 2000 | 3.5601 |
548
 
549
 
550
  ### Framework versions
 
14
 
15
  This model is a fine-tuned version of [dccuchile/bert-base-spanish-wwm-uncased](https://huggingface.co/dccuchile/bert-base-spanish-wwm-uncased) on the None dataset.
16
  It achieves the following results on the evaluation set:
17
+ - Loss: 3.1317
18
 
19
  ## Model description
20
 
 
39
  - seed: 42
40
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
41
  - lr_scheduler_type: linear
42
+ - num_epochs: 10
43
 
44
  ### Training results
45
 
46
  | Training Loss | Epoch | Step | Validation Loss |
47
  |:-------------:|:-----:|:----:|:---------------:|
48
+ | 5.8229 | 1.0 | 4 | 5.4307 |
49
+ | 5.135 | 2.0 | 8 | 4.7853 |
50
+ | 4.3794 | 3.0 | 12 | 4.0528 |
51
+ | 3.6234 | 4.0 | 16 | 3.5797 |
52
+ | 3.209 | 5.0 | 20 | 3.3848 |
53
+ | 2.9192 | 6.0 | 24 | 3.2615 |
54
+ | 2.7301 | 7.0 | 28 | 3.1942 |
55
+ | 2.5314 | 8.0 | 32 | 3.1553 |
56
+ | 2.4218 | 9.0 | 36 | 3.1365 |
57
+ | 2.3592 | 10.0 | 40 | 3.1317 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
58
 
59
 
60
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2cba075c4b33394b3e23cdc0bbc5be8f25dd8940be122f2bc4cc4cd378b46966
3
  size 437070648
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f83d826b7d005cecf00b05a1c2a6bdaa553c3785bf1eb00aa2b2378ac4afaebd
3
  size 437070648
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5eb04fb5ca78031a4053b78b74ee37088a1b0dc309e042ba8ba1e6505e3ff467
3
  size 4536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a14be870f9fa0a3678b6c8dc953d5d54fdd4b2254951df13b846b16c32c7126
3
  size 4536