generated_from_trainer

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

bert-small-nan-labels-500

This model is a fine-tuned version of google/bert_uncased_L-4_H-512_A-8 on the None dataset. It achieves the following results on the evaluation set:

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

Training results

Training Loss Epoch Step Validation Loss
4.9422 1.0 14 5.5730
4.4976 2.0 28 5.4533
4.2684 3.0 42 5.4158
4.2673 4.0 56 5.4162
4.0978 5.0 70 5.4121
3.8972 6.0 84 5.4649
3.7728 7.0 98 5.4233
3.7557 8.0 112 5.4381
3.693 9.0 126 5.4673
3.5627 10.0 140 5.5277
3.6456 11.0 154 5.4351
3.5487 12.0 168 5.4846
3.4018 13.0 182 5.5763
3.3807 14.0 196 5.5674
3.4219 15.0 210 5.6129
3.3481 16.0 224 5.5470
3.2522 17.0 238 5.6078
3.3047 18.0 252 5.6274
3.1542 19.0 266 5.6517
3.0939 20.0 280 5.6088
3.0951 21.0 294 5.6768
3.0876 22.0 308 5.6796
3.0098 23.0 322 5.6938
3.061 24.0 336 5.7355
2.8711 25.0 350 5.6882
2.7414 26.0 364 5.7694
2.8273 27.0 378 5.7295
2.8497 28.0 392 5.7976
2.8469 29.0 406 5.7935
2.8367 30.0 420 5.8076
2.6975 31.0 434 5.7854
2.7496 32.0 448 5.8664
2.638 33.0 462 5.8900
2.6511 34.0 476 5.8628
2.6228 35.0 490 5.8544
2.617 36.0 504 5.8830
2.498 37.0 518 5.9080
2.4956 38.0 532 6.0102
2.445 39.0 546 5.9869
2.4493 40.0 560 6.0824
2.3935 41.0 574 5.9724
2.3559 42.0 588 5.9515
2.3444 43.0 602 5.9968
2.2707 44.0 616 6.0433
2.1095 45.0 630 6.0700
2.1573 46.0 644 6.1757
2.2504 47.0 658 6.0801
2.25 48.0 672 6.1659
2.1047 49.0 686 6.1564
2.1563 50.0 700 6.2225
2.0882 51.0 714 6.2024
2.1818 52.0 728 6.1418
2.1141 53.0 742 6.2118
2.0647 54.0 756 6.2645
1.9779 55.0 770 6.3598
2.053 56.0 784 6.2241
1.9884 57.0 798 6.2838
1.8604 58.0 812 6.3798
1.882 59.0 826 6.3210
1.9414 60.0 840 6.3404
1.7435 61.0 854 6.3332
1.8813 62.0 868 6.3616
1.7517 63.0 882 6.4093
1.8046 64.0 896 6.4665
1.7258 65.0 910 6.4227
1.7862 66.0 924 6.3705
1.5828 67.0 938 6.5138
1.7249 68.0 952 6.4484
1.692 69.0 966 6.4739
1.575 70.0 980 6.4886
1.6542 71.0 994 6.4457
1.515 72.0 1008 6.5828
1.6127 73.0 1022 6.5665
1.6343 74.0 1036 6.5662
1.4653 75.0 1050 6.5909
1.5358 76.0 1064 6.5909
1.6009 77.0 1078 6.5865
1.5644 78.0 1092 6.5422
1.4766 79.0 1106 6.6528
1.4215 80.0 1120 6.6389
1.4787 81.0 1134 6.6737
1.4586 82.0 1148 6.6836
1.4559 83.0 1162 6.6922
1.4451 84.0 1176 6.6856
1.3502 85.0 1190 6.6594
1.3425 86.0 1204 6.6404
1.3091 87.0 1218 6.7316
1.3213 88.0 1232 6.7641
1.2274 89.0 1246 6.7828
1.247 90.0 1260 6.8646
1.3159 91.0 1274 6.7969
1.2061 92.0 1288 6.7785
1.214 93.0 1302 6.7910
1.2165 94.0 1316 6.9408
1.1849 95.0 1330 6.7925
1.1905 96.0 1344 6.8021
1.1714 97.0 1358 6.8445
1.1092 98.0 1372 6.8426
1.1682 99.0 1386 6.8331
1.1552 100.0 1400 6.8933
1.1374 101.0 1414 6.8102
1.1124 102.0 1428 6.8749
1.1017 103.0 1442 6.8993
1.0072 104.0 1456 6.8475
1.1771 105.0 1470 6.8908
1.0643 106.0 1484 6.8985
1.0038 107.0 1498 6.8714
0.9974 108.0 1512 6.9881
1.1195 109.0 1526 6.8764
0.9957 110.0 1540 6.9969
0.9766 111.0 1554 7.0525
0.9621 112.0 1568 6.9676
0.9562 113.0 1582 7.0268
0.9473 114.0 1596 6.9466
1.0357 115.0 1610 7.0968
0.9385 116.0 1624 7.0544
0.9579 117.0 1638 7.0054
0.9223 118.0 1652 7.0393
0.8862 119.0 1666 6.9770
0.9275 120.0 1680 7.0608
0.8642 121.0 1694 7.0661
0.8752 122.0 1708 7.0933
0.8687 123.0 1722 7.1004
0.8962 124.0 1736 7.0945
0.8157 125.0 1750 7.0379
0.903 126.0 1764 7.1082
0.9249 127.0 1778 7.0555
0.8624 128.0 1792 7.1230
0.7936 129.0 1806 7.1269
0.8292 130.0 1820 7.1401
0.7382 131.0 1834 7.1299
0.8284 132.0 1848 7.1820
0.7993 133.0 1862 7.2175
0.8493 134.0 1876 7.2064
0.8126 135.0 1890 7.1438
0.7831 136.0 1904 7.2746
0.8011 137.0 1918 7.2374
0.7512 138.0 1932 7.2725
0.7695 139.0 1946 7.2721
0.7216 140.0 1960 7.2482
0.744 141.0 1974 7.2467
0.7366 142.0 1988 7.2893
0.7214 143.0 2002 7.3204
0.7456 144.0 2016 7.2928
0.6891 145.0 2030 7.3215
0.6306 146.0 2044 7.2637
0.6763 147.0 2058 7.2491
0.6558 148.0 2072 7.3143
0.7562 149.0 2086 7.2424
0.7019 150.0 2100 7.2770
0.6251 151.0 2114 7.2743
0.6857 152.0 2128 7.3607
0.7037 153.0 2142 7.3243
0.6398 154.0 2156 7.3276
0.6231 155.0 2170 7.3595
0.6368 156.0 2184 7.4406
0.6653 157.0 2198 7.3381
0.6189 158.0 2212 7.3217
0.616 159.0 2226 7.3374
0.6029 160.0 2240 7.3500
0.6516 161.0 2254 7.3383
0.5725 162.0 2268 7.3815
0.6032 163.0 2282 7.3521
0.6228 164.0 2296 7.3883
0.5797 165.0 2310 7.4235
0.61 166.0 2324 7.4864
0.581 167.0 2338 7.4154
0.6213 168.0 2352 7.4857
0.5709 169.0 2366 7.4169
0.5898 170.0 2380 7.4947
0.5106 171.0 2394 7.4307
0.605 172.0 2408 7.4011
0.5613 173.0 2422 7.5032
0.5767 174.0 2436 7.4852
0.5344 175.0 2450 7.5135
0.5091 176.0 2464 7.4926
0.6127 177.0 2478 7.4273
0.5862 178.0 2492 7.4611
0.5571 179.0 2506 7.4977
0.496 180.0 2520 7.4286
0.5544 181.0 2534 7.4946
0.5686 182.0 2548 7.5279
0.5292 183.0 2562 7.5432
0.5372 184.0 2576 7.5062
0.5333 185.0 2590 7.6077
0.5574 186.0 2604 7.6172
0.5172 187.0 2618 7.5257
0.5379 188.0 2632 7.5016
0.513 189.0 2646 7.5428
0.5631 190.0 2660 7.5116
0.483 191.0 2674 7.5440
0.5084 192.0 2688 7.4654
0.4796 193.0 2702 7.4820
0.5265 194.0 2716 7.6189
0.4927 195.0 2730 7.6519
0.4656 196.0 2744 7.5037
0.5565 197.0 2758 7.5008
0.4415 198.0 2772 7.6129
0.4394 199.0 2786 7.6478
0.4704 200.0 2800 7.5704
0.4789 201.0 2814 7.5958
0.5131 202.0 2828 7.6163
0.4741 203.0 2842 7.6735
0.4602 204.0 2856 7.6717
0.4706 205.0 2870 7.6067
0.4978 206.0 2884 7.6456
0.5176 207.0 2898 7.6414
0.5036 208.0 2912 7.5815
0.4437 209.0 2926 7.6549
0.4844 210.0 2940 7.7083
0.4472 211.0 2954 7.6823
0.4604 212.0 2968 7.6570
0.4622 213.0 2982 7.7083
0.4588 214.0 2996 7.6794
0.4742 215.0 3010 7.6624
0.4447 216.0 3024 7.6996
0.4245 217.0 3038 7.6295
0.5189 218.0 3052 7.6853
0.4182 219.0 3066 7.6120
0.4294 220.0 3080 7.7448
0.4644 221.0 3094 7.6821
0.3955 222.0 3108 7.6801
0.4769 223.0 3122 7.7343
0.4138 224.0 3136 7.7135
0.3893 225.0 3150 7.7137
0.4479 226.0 3164 7.6837
0.4367 227.0 3178 7.6080
0.3846 228.0 3192 7.6737
0.4124 229.0 3206 7.7446
0.3533 230.0 3220 7.7186
0.4635 231.0 3234 7.6979
0.4096 232.0 3248 7.6931
0.4301 233.0 3262 7.6302
0.3656 234.0 3276 7.7928
0.4512 235.0 3290 7.8027
0.3671 236.0 3304 7.8594
0.3967 237.0 3318 7.7333
0.3829 238.0 3332 7.7669
0.3985 239.0 3346 7.7922
0.375 240.0 3360 7.8020
0.3425 241.0 3374 7.8508
0.4128 242.0 3388 7.7871
0.4449 243.0 3402 7.8075
0.4176 244.0 3416 7.7721
0.4145 245.0 3430 7.7644
0.4142 246.0 3444 7.8276
0.3336 247.0 3458 7.8112
0.3668 248.0 3472 7.8272
0.384 249.0 3486 7.7916
0.3873 250.0 3500 7.7770
0.4032 251.0 3514 7.7633
0.3166 252.0 3528 7.7615
0.3897 253.0 3542 7.7801
0.3916 254.0 3556 7.7710
0.3462 255.0 3570 7.8086
0.3705 256.0 3584 7.8322
0.3781 257.0 3598 7.7828
0.3466 258.0 3612 7.7830
0.3986 259.0 3626 7.8720
0.3335 260.0 3640 7.8438
0.3698 261.0 3654 7.8200
0.3715 262.0 3668 7.8205
0.3553 263.0 3682 7.8782
0.3664 264.0 3696 7.8409
0.3548 265.0 3710 7.8220
0.3671 266.0 3724 7.8378
0.3809 267.0 3738 7.8346
0.3595 268.0 3752 7.8602
0.317 269.0 3766 7.7957
0.3329 270.0 3780 7.8356
0.3097 271.0 3794 7.8749
0.3263 272.0 3808 7.8206
0.3278 273.0 3822 7.8923
0.3064 274.0 3836 7.8501
0.3066 275.0 3850 7.8099
0.3108 276.0 3864 7.9305
0.36 277.0 3878 7.8377
0.3743 278.0 3892 7.8080
0.3864 279.0 3906 7.8541
0.292 280.0 3920 7.9087
0.3183 281.0 3934 7.9080
0.343 282.0 3948 7.8776
0.35 283.0 3962 7.8961
0.3355 284.0 3976 7.8549
0.3684 285.0 3990 7.8964
0.3454 286.0 4004 7.9754
0.3496 287.0 4018 7.8902
0.3247 288.0 4032 7.9092
0.2945 289.0 4046 7.9472
0.3456 290.0 4060 8.0057
0.4058 291.0 4074 7.9345
0.3198 292.0 4088 7.9976
0.3459 293.0 4102 7.9268
0.3084 294.0 4116 7.8680
0.2868 295.0 4130 7.8889
0.2909 296.0 4144 7.9068
0.3799 297.0 4158 7.9200
0.3316 298.0 4172 7.9104
0.3012 299.0 4186 7.8893
0.309 300.0 4200 7.9324
0.2663 301.0 4214 7.8847
0.2809 302.0 4228 7.9753
0.2871 303.0 4242 7.9208
0.2717 304.0 4256 7.8918
0.2871 305.0 4270 7.9883
0.2763 306.0 4284 7.9588
0.3047 307.0 4298 7.9780
0.3463 308.0 4312 7.9802
0.3279 309.0 4326 7.9799
0.3224 310.0 4340 7.9768
0.2568 311.0 4354 7.9846
0.3027 312.0 4368 7.9537
0.2415 313.0 4382 7.9870
0.3115 314.0 4396 7.9839
0.3022 315.0 4410 7.9722
0.2975 316.0 4424 7.9705
0.2944 317.0 4438 8.0632
0.3164 318.0 4452 8.0619
0.2764 319.0 4466 7.9667
0.2558 320.0 4480 8.0001
0.274 321.0 4494 7.9672
0.3069 322.0 4508 8.0369
0.2984 323.0 4522 8.0224
0.2944 324.0 4536 8.0200
0.2889 325.0 4550 8.0656
0.2596 326.0 4564 7.9612
0.2624 327.0 4578 7.9776
0.2851 328.0 4592 8.0496
0.2821 329.0 4606 8.0301
0.3091 330.0 4620 8.0032
0.2426 331.0 4634 7.9657
0.2867 332.0 4648 7.9114
0.2757 333.0 4662 8.0189
0.2671 334.0 4676 8.0285
0.2651 335.0 4690 8.0251
0.2544 336.0 4704 8.0092
0.2842 337.0 4718 8.0765
0.2548 338.0 4732 8.0409
0.2953 339.0 4746 8.0289
0.2814 340.0 4760 8.0667
0.2605 341.0 4774 8.0425
0.2701 342.0 4788 8.0451
0.2279 343.0 4802 8.0257
0.2348 344.0 4816 8.0239
0.264 345.0 4830 8.0553
0.2533 346.0 4844 8.0384
0.25 347.0 4858 8.0648
0.2515 348.0 4872 8.0934
0.2235 349.0 4886 8.0480
0.2289 350.0 4900 8.0747
0.3048 351.0 4914 8.0854
0.2463 352.0 4928 8.0728
0.2984 353.0 4942 8.0424
0.2718 354.0 4956 8.0761
0.2761 355.0 4970 8.0684
0.2347 356.0 4984 8.0769
0.2683 357.0 4998 8.0191
0.2837 358.0 5012 8.0605
0.2623 359.0 5026 8.0554
0.2581 360.0 5040 8.0864
0.3162 361.0 5054 8.1435
0.2388 362.0 5068 8.0557
0.236 363.0 5082 8.1043
0.2668 364.0 5096 8.1299
0.2559 365.0 5110 8.1116
0.2523 366.0 5124 8.0916
0.2719 367.0 5138 8.0192
0.289 368.0 5152 8.1314
0.237 369.0 5166 8.0493
0.2401 370.0 5180 8.1385
0.2905 371.0 5194 8.2075
0.2806 372.0 5208 8.1328
0.2986 373.0 5222 8.1489
0.27 374.0 5236 8.0748
0.2365 375.0 5250 8.1267
0.2532 376.0 5264 8.1494
0.2142 377.0 5278 8.1415
0.2288 378.0 5292 8.1203
0.2425 379.0 5306 8.1433
0.2443 380.0 5320 8.1238
0.2516 381.0 5334 8.1401
0.2083 382.0 5348 8.1223
0.2525 383.0 5362 8.1361
0.2558 384.0 5376 8.0958
0.2491 385.0 5390 8.0831
0.2898 386.0 5404 8.0593
0.2361 387.0 5418 8.1167
0.2466 388.0 5432 8.1083
0.2386 389.0 5446 8.0997
0.2985 390.0 5460 8.1217
0.2219 391.0 5474 8.1535
0.2509 392.0 5488 8.1498
0.24 393.0 5502 8.1509
0.2282 394.0 5516 8.2027
0.2141 395.0 5530 8.1303
0.2306 396.0 5544 8.1602
0.2406 397.0 5558 8.1269
0.2253 398.0 5572 8.0594
0.2648 399.0 5586 8.1279
0.2293 400.0 5600 8.0930
0.2429 401.0 5614 8.1050
0.2143 402.0 5628 8.1141
0.2052 403.0 5642 8.1325
0.222 404.0 5656 8.1627
0.2076 405.0 5670 8.1566
0.244 406.0 5684 8.0679
0.2245 407.0 5698 8.0288
0.1934 408.0 5712 8.0412
0.2669 409.0 5726 8.0897
0.2427 410.0 5740 8.1550
0.2496 411.0 5754 8.1105
0.1992 412.0 5768 8.1120
0.2154 413.0 5782 8.1502
0.2344 414.0 5796 8.1257
0.2151 415.0 5810 8.1625
0.212 416.0 5824 8.1495
0.2031 417.0 5838 8.1356
0.2599 418.0 5852 8.2282
0.1984 419.0 5866 8.1940
0.2838 420.0 5880 8.1552
0.2143 421.0 5894 8.1256
0.2308 422.0 5908 8.1128
0.2479 423.0 5922 8.1015
0.2517 424.0 5936 8.1913
0.1897 425.0 5950 8.1807
0.2432 426.0 5964 8.1400
0.2508 427.0 5978 8.1429
0.2411 428.0 5992 8.1560
0.2125 429.0 6006 8.1515
0.2201 430.0 6020 8.1448
0.2017 431.0 6034 8.1316
0.2191 432.0 6048 8.1408
0.2201 433.0 6062 8.1918
0.243 434.0 6076 8.2030
0.2523 435.0 6090 8.1573
0.1696 436.0 6104 8.1757
0.1939 437.0 6118 8.1383
0.2103 438.0 6132 8.1768
0.1882 439.0 6146 8.1340
0.2183 440.0 6160 8.1488
0.2005 441.0 6174 8.2002
0.229 442.0 6188 8.1437
0.1998 443.0 6202 8.1717
0.2387 444.0 6216 8.1613
0.1886 445.0 6230 8.2194
0.2324 446.0 6244 8.1381
0.1908 447.0 6258 8.1834
0.1912 448.0 6272 8.1746
0.2274 449.0 6286 8.1759
0.2375 450.0 6300 8.1489
0.2202 451.0 6314 8.1356
0.241 452.0 6328 8.1379
0.2078 453.0 6342 8.1447
0.2368 454.0 6356 8.1741
0.1857 455.0 6370 8.1927
0.1854 456.0 6384 8.1514
0.1726 457.0 6398 8.0745
0.181 458.0 6412 8.1332
0.2198 459.0 6426 8.1616
0.2014 460.0 6440 8.1878
0.2341 461.0 6454 8.2081
0.1932 462.0 6468 8.1799
0.1867 463.0 6482 8.1591
0.2366 464.0 6496 8.1363
0.2169 465.0 6510 8.2088
0.2248 466.0 6524 8.1332
0.1948 467.0 6538 8.1625
0.1834 468.0 6552 8.1572
0.254 469.0 6566 8.1402
0.2015 470.0 6580 8.0961
0.2295 471.0 6594 8.1255
0.1892 472.0 6608 8.1812
0.1939 473.0 6622 8.1552
0.2081 474.0 6636 8.1145
0.2032 475.0 6650 8.1686
0.1844 476.0 6664 8.1529
0.2436 477.0 6678 8.1436
0.2618 478.0 6692 8.1719
0.1845 479.0 6706 8.0935
0.1955 480.0 6720 8.1796
0.2116 481.0 6734 8.1296
0.2261 482.0 6748 8.1882
0.2057 483.0 6762 8.1474
0.2117 484.0 6776 8.1679
0.1901 485.0 6790 8.1736
0.2001 486.0 6804 8.1548
0.2016 487.0 6818 8.1237
0.1444 488.0 6832 8.1330
0.1707 489.0 6846 8.1509
0.1731 490.0 6860 8.1368
0.2358 491.0 6874 8.1815
0.2013 492.0 6888 8.1404
0.2101 493.0 6902 8.1702
0.1833 494.0 6916 8.1405
0.2173 495.0 6930 8.1338
0.2011 496.0 6944 8.1291
0.1824 497.0 6958 8.1452
0.2303 498.0 6972 8.1726
0.2131 499.0 6986 8.1510
0.2012 500.0 7000 8.1664

Framework versions