bert-base-greek-uncased-v3-finetuned-polylex

This model is a fine-tuned version of nlpaueb/bert-base-greek-uncased-v1 on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 1.2388

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:

  • learning_rate: 5e-06
  • train_batch_size: 512
  • eval_batch_size: 512
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 500

Training results

Training Loss Epoch Step Validation Loss
2.7244 1.0 13 2.6291
2.694 2.0 26 2.6311
2.7107 3.0 39 2.4722
2.6558 4.0 52 2.5651
2.6605 5.0 65 2.5038
2.6573 6.0 78 2.4791
2.6467 7.0 91 2.4887
2.5708 8.0 104 2.4863
2.5622 9.0 117 2.3389
2.5644 10.0 130 2.4384
2.5504 11.0 143 2.4352
2.5182 12.0 156 2.4158
2.5046 13.0 169 2.4234
2.4485 14.0 182 2.4289
2.473 15.0 195 2.3559
2.4475 16.0 208 2.3746
2.4487 17.0 221 2.3665
2.428 18.0 234 2.2715
2.4131 19.0 247 2.3679
2.3936 20.0 260 2.2356
2.3946 21.0 273 2.3008
2.3449 22.0 286 2.3134
2.3708 23.0 299 2.3177
2.3152 24.0 312 2.2009
2.3192 25.0 325 2.2506
2.3304 26.0 338 2.2458
2.2691 27.0 351 2.2125
2.2592 28.0 364 2.1254
2.2714 29.0 377 2.1649
2.3054 30.0 390 2.1633
2.2601 31.0 403 2.1433
2.2445 32.0 416 2.1790
2.2251 33.0 429 2.1874
2.2402 34.0 442 2.0976
2.2485 35.0 455 2.2506
2.2158 36.0 468 2.1411
2.1912 37.0 481 2.1640
2.1883 38.0 494 2.1221
2.1869 39.0 507 2.1404
2.1613 40.0 520 2.1048
2.1562 41.0 533 2.1490
2.1135 42.0 546 2.1360
2.1588 43.0 559 2.1085
2.1245 44.0 572 2.0455
2.1256 45.0 585 2.0955
2.1175 46.0 598 2.0554
2.0986 47.0 611 2.1592
2.0672 48.0 624 2.0547
2.0834 49.0 637 2.1018
2.0637 50.0 650 1.9672
2.0934 51.0 663 2.0244
2.0624 52.0 676 2.0206
2.0654 53.0 689 2.0019
2.0375 54.0 702 1.9709
2.0247 55.0 715 2.0573
2.0051 56.0 728 2.0118
2.0272 57.0 741 1.9811
1.9794 58.0 754 2.0686
2.0075 59.0 767 1.9908
1.9903 60.0 780 1.9719
1.9861 61.0 793 1.8938
1.9723 62.0 806 1.9435
1.9757 63.0 819 1.9853
1.9652 64.0 832 1.9546
1.9082 65.0 845 1.9496
1.9565 66.0 858 2.0053
1.9461 67.0 871 1.9123
1.9348 68.0 884 1.9159
1.9582 69.0 897 1.9521
1.9226 70.0 910 1.8827
1.8822 71.0 923 1.8913
1.9009 72.0 936 1.9483
1.8754 73.0 949 1.8115
1.8989 74.0 962 1.8791
1.9258 75.0 975 1.8749
1.8691 76.0 988 1.7972
1.8842 77.0 1001 1.8793
1.8788 78.0 1014 1.8586
1.8319 79.0 1027 1.8892
1.8608 80.0 1040 1.9646
1.8318 81.0 1053 1.9309
1.8437 82.0 1066 1.8566
1.8203 83.0 1079 1.8284
1.824 84.0 1092 1.7816
1.8182 85.0 1105 1.9069
1.8179 86.0 1118 1.9081
1.7929 87.0 1131 1.8425
1.8193 88.0 1144 1.8563
1.7839 89.0 1157 1.8833
1.7921 90.0 1170 1.9352
1.815 91.0 1183 1.7930
1.7462 92.0 1196 1.8891
1.7404 93.0 1209 1.7958
1.7678 94.0 1222 1.8088
1.7639 95.0 1235 1.8375
1.7631 96.0 1248 1.7708
1.766 97.0 1261 1.7981
1.7695 98.0 1274 1.7941
1.7176 99.0 1287 1.8595
1.7293 100.0 1300 1.7562
1.7483 101.0 1313 1.7352
1.7082 102.0 1326 1.8223
1.7325 103.0 1339 1.6402
1.7099 104.0 1352 1.7554
1.721 105.0 1365 1.7200
1.7241 106.0 1378 1.6550
1.6731 107.0 1391 1.7392
1.6811 108.0 1404 1.8979
1.7082 109.0 1417 1.7811
1.6629 110.0 1430 1.6550
1.6965 111.0 1443 1.7140
1.7202 112.0 1456 1.6252
1.6947 113.0 1469 1.6977
1.6858 114.0 1482 1.7298
1.6741 115.0 1495 1.7912
1.6703 116.0 1508 1.7231
1.6155 117.0 1521 1.7453
1.6872 118.0 1534 1.7383
1.6271 119.0 1547 1.7250
1.6729 120.0 1560 1.6696
1.6422 121.0 1573 1.6866
1.6668 122.0 1586 1.7051
1.5937 123.0 1599 1.7192
1.651 124.0 1612 1.7196
1.6286 125.0 1625 1.7460
1.6103 126.0 1638 1.6972
1.6341 127.0 1651 1.6315
1.6032 128.0 1664 1.7183
1.6089 129.0 1677 1.6223
1.6019 130.0 1690 1.6137
1.5891 131.0 1703 1.7023
1.597 132.0 1716 1.6243
1.5559 133.0 1729 1.6536
1.5882 134.0 1742 1.6405
1.5728 135.0 1755 1.6444
1.6019 136.0 1768 1.6513
1.571 137.0 1781 1.6124
1.5488 138.0 1794 1.6870
1.5376 139.0 1807 1.6583
1.5641 140.0 1820 1.6581
1.5722 141.0 1833 1.6245
1.5446 142.0 1846 1.5859
1.5441 143.0 1859 1.6329
1.56 144.0 1872 1.6646
1.5571 145.0 1885 1.6170
1.5331 146.0 1898 1.6471
1.5476 147.0 1911 1.6206
1.5573 148.0 1924 1.6275
1.5182 149.0 1937 1.6181
1.4818 150.0 1950 1.6150
1.5521 151.0 1963 1.5718
1.5039 152.0 1976 1.6621
1.5349 153.0 1989 1.5775
1.4856 154.0 2002 1.5395
1.5132 155.0 2015 1.6016
1.4865 156.0 2028 1.6300
1.4883 157.0 2041 1.6204
1.4763 158.0 2054 1.6024
1.497 159.0 2067 1.5947
1.4897 160.0 2080 1.5532
1.4797 161.0 2093 1.5129
1.4714 162.0 2106 1.5091
1.5007 163.0 2119 1.4499
1.5007 164.0 2132 1.5607
1.4778 165.0 2145 1.5594
1.4871 166.0 2158 1.5438
1.4718 167.0 2171 1.6030
1.487 168.0 2184 1.5506
1.464 169.0 2197 1.5435
1.4691 170.0 2210 1.5132
1.4438 171.0 2223 1.5154
1.461 172.0 2236 1.5698
1.4319 173.0 2249 1.6740
1.4798 174.0 2262 1.5586
1.4681 175.0 2275 1.5489
1.4587 176.0 2288 1.5589
1.4543 177.0 2301 1.5321
1.4611 178.0 2314 1.5495
1.4155 179.0 2327 1.5491
1.4228 180.0 2340 1.4871
1.4345 181.0 2353 1.5680
1.4325 182.0 2366 1.5306
1.404 183.0 2379 1.5051
1.4216 184.0 2392 1.5427
1.4229 185.0 2405 1.4961
1.4293 186.0 2418 1.4781
1.4318 187.0 2431 1.4869
1.4135 188.0 2444 1.5986
1.3873 189.0 2457 1.5333
1.394 190.0 2470 1.4695
1.4098 191.0 2483 1.5061
1.4605 192.0 2496 1.5591
1.3858 193.0 2509 1.4991
1.4076 194.0 2522 1.4924
1.3853 195.0 2535 1.4368
1.3562 196.0 2548 1.4973
1.3752 197.0 2561 1.4802
1.396 198.0 2574 1.5606
1.3836 199.0 2587 1.4912
1.3682 200.0 2600 1.5184
1.3821 201.0 2613 1.4448
1.3792 202.0 2626 1.4727
1.3755 203.0 2639 1.4996
1.3664 204.0 2652 1.4469
1.3574 205.0 2665 1.4670
1.3948 206.0 2678 1.5356
1.3378 207.0 2691 1.4756
1.3546 208.0 2704 1.4507
1.3547 209.0 2717 1.4986
1.3551 210.0 2730 1.4478
1.3262 211.0 2743 1.4450
1.3577 212.0 2756 1.4713
1.3698 213.0 2769 1.4404
1.3604 214.0 2782 1.3906
1.3733 215.0 2795 1.4844
1.3574 216.0 2808 1.4104
1.3227 217.0 2821 1.4512
1.3409 218.0 2834 1.4661
1.3411 219.0 2847 1.4515
1.3258 220.0 2860 1.5193
1.3194 221.0 2873 1.3303
1.332 222.0 2886 1.5037
1.3477 223.0 2899 1.4095
1.3182 224.0 2912 1.5021
1.3456 225.0 2925 1.4410
1.3082 226.0 2938 1.5183
1.3253 227.0 2951 1.3419
1.3171 228.0 2964 1.4621
1.2994 229.0 2977 1.4418
1.3039 230.0 2990 1.4845
1.3418 231.0 3003 1.5488
1.2917 232.0 3016 1.4748
1.3174 233.0 3029 1.4301
1.2929 234.0 3042 1.3867
1.3301 235.0 3055 1.5229
1.3154 236.0 3068 1.5099
1.316 237.0 3081 1.3725
1.3278 238.0 3094 1.4296
1.311 239.0 3107 1.3594
1.3149 240.0 3120 1.4675
1.3151 241.0 3133 1.3854
1.2792 242.0 3146 1.3681
1.2755 243.0 3159 1.3866
1.2748 244.0 3172 1.3623
1.2969 245.0 3185 1.3822
1.2839 246.0 3198 1.4040
1.2728 247.0 3211 1.4649
1.2853 248.0 3224 1.3486
1.3091 249.0 3237 1.3852
1.2677 250.0 3250 1.4326
1.2627 251.0 3263 1.3952
1.2794 252.0 3276 1.3576
1.2893 253.0 3289 1.3751
1.2483 254.0 3302 1.3861
1.2799 255.0 3315 1.3946
1.2774 256.0 3328 1.5043
1.2501 257.0 3341 1.3320
1.2491 258.0 3354 1.2201
1.2587 259.0 3367 1.3994
1.2771 260.0 3380 1.4088
1.2635 261.0 3393 1.3706
1.2805 262.0 3406 1.3330
1.2196 263.0 3419 1.3849
1.2485 264.0 3432 1.3607
1.2259 265.0 3445 1.3942
1.2653 266.0 3458 1.4019
1.2355 267.0 3471 1.2494
1.2687 268.0 3484 1.4765
1.2547 269.0 3497 1.3954
1.2613 270.0 3510 1.4220
1.2216 271.0 3523 1.4526
1.2494 272.0 3536 1.3749
1.2324 273.0 3549 1.4229
1.2415 274.0 3562 1.3641
1.244 275.0 3575 1.2835
1.2287 276.0 3588 1.3544
1.2151 277.0 3601 1.3578
1.2219 278.0 3614 1.3710
1.2077 279.0 3627 1.3806
1.2186 280.0 3640 1.3459
1.2053 281.0 3653 1.3691
1.2268 282.0 3666 1.2611
1.2174 283.0 3679 1.3259
1.2263 284.0 3692 1.3702
1.214 285.0 3705 1.2818
1.226 286.0 3718 1.2994
1.2331 287.0 3731 1.3583
1.2301 288.0 3744 1.3379
1.212 289.0 3757 1.3326
1.1784 290.0 3770 1.3129
1.2246 291.0 3783 1.3665
1.2156 292.0 3796 1.3132
1.2281 293.0 3809 1.3519
1.1816 294.0 3822 1.2700
1.2088 295.0 3835 1.3741
1.2216 296.0 3848 1.3393
1.2214 297.0 3861 1.3340
1.1606 298.0 3874 1.4059
1.1932 299.0 3887 1.4301
1.1879 300.0 3900 1.4612
1.2086 301.0 3913 1.2934
1.2026 302.0 3926 1.3369
1.171 303.0 3939 1.4190
1.1941 304.0 3952 1.3881
1.1981 305.0 3965 1.3244
1.1938 306.0 3978 1.3505
1.2111 307.0 3991 1.3938
1.2041 308.0 4004 1.2997
1.2012 309.0 4017 1.3563
1.1794 310.0 4030 1.3185
1.2042 311.0 4043 1.3803
1.171 312.0 4056 1.2954
1.1567 313.0 4069 1.3422
1.1743 314.0 4082 1.2974
1.205 315.0 4095 1.3749
1.1745 316.0 4108 1.4046
1.1917 317.0 4121 1.3082
1.1749 318.0 4134 1.3277
1.1897 319.0 4147 1.2651
1.1862 320.0 4160 1.3003
1.158 321.0 4173 1.3515
1.1488 322.0 4186 1.3738
1.1961 323.0 4199 1.2749
1.1884 324.0 4212 1.2602
1.1475 325.0 4225 1.2695
1.1769 326.0 4238 1.2700
1.1798 327.0 4251 1.3313
1.1643 328.0 4264 1.3272
1.1788 329.0 4277 1.2919
1.1696 330.0 4290 1.3841
1.1562 331.0 4303 1.2884
1.1734 332.0 4316 1.2844
1.1519 333.0 4329 1.3076
1.1685 334.0 4342 1.3387
1.1687 335.0 4355 1.2754
1.1349 336.0 4368 1.2932
1.1367 337.0 4381 1.2461
1.1429 338.0 4394 1.3838
1.1656 339.0 4407 1.3135
1.149 340.0 4420 1.2941
1.1412 341.0 4433 1.3608
1.1375 342.0 4446 1.2460
1.1527 343.0 4459 1.2603
1.17 344.0 4472 1.2844
1.1512 345.0 4485 1.2820
1.1404 346.0 4498 1.1912
1.167 347.0 4511 1.3074
1.1748 348.0 4524 1.3113
1.149 349.0 4537 1.2842
1.1907 350.0 4550 1.2868
1.1344 351.0 4563 1.3040
1.1368 352.0 4576 1.3053
1.1519 353.0 4589 1.2947
1.1439 354.0 4602 1.2751
1.1459 355.0 4615 1.2740
1.1673 356.0 4628 1.1941
1.1415 357.0 4641 1.2766
1.1384 358.0 4654 1.2161
1.1411 359.0 4667 1.3156
1.1362 360.0 4680 1.3086
1.1317 361.0 4693 1.3608
1.1168 362.0 4706 1.2478
1.1347 363.0 4719 1.2681
1.1553 364.0 4732 1.2650
1.1487 365.0 4745 1.3514
1.1135 366.0 4758 1.3292
1.1388 367.0 4771 1.3192
1.1818 368.0 4784 1.2937
1.1256 369.0 4797 1.3446
1.1284 370.0 4810 1.2609
1.1352 371.0 4823 1.2070
1.1151 372.0 4836 1.2035
1.1148 373.0 4849 1.3513
1.124 374.0 4862 1.2842
1.1213 375.0 4875 1.2513
1.1305 376.0 4888 1.2974
1.1271 377.0 4901 1.2245
1.1085 378.0 4914 1.2812
1.1383 379.0 4927 1.2253
1.1319 380.0 4940 1.3116
1.1268 381.0 4953 1.3139
1.1302 382.0 4966 1.2785
1.1197 383.0 4979 1.1841
1.1167 384.0 4992 1.2763
1.1279 385.0 5005 1.2248
1.1426 386.0 5018 1.1960
1.0997 387.0 5031 1.2735
1.1212 388.0 5044 1.3007
1.108 389.0 5057 1.2739
1.1189 390.0 5070 1.2446
1.1156 391.0 5083 1.2815
1.1342 392.0 5096 1.2405
1.1082 393.0 5109 1.2778
1.1091 394.0 5122 1.2683
1.1516 395.0 5135 1.1883
1.1136 396.0 5148 1.3215
1.1115 397.0 5161 1.2671
1.1356 398.0 5174 1.1809
1.1281 399.0 5187 1.2935
1.1241 400.0 5200 1.2595
1.0893 401.0 5213 1.2746
1.1045 402.0 5226 1.2215
1.1184 403.0 5239 1.1524
1.1088 404.0 5252 1.3651
1.1331 405.0 5265 1.1774
1.1151 406.0 5278 1.3032
1.1061 407.0 5291 1.3317
1.1103 408.0 5304 1.3300
1.1343 409.0 5317 1.2831
1.1056 410.0 5330 1.2202
1.1037 411.0 5343 1.3218
1.1131 412.0 5356 1.2714
1.1237 413.0 5369 1.2526
1.1241 414.0 5382 1.2328
1.1332 415.0 5395 1.2634
1.128 416.0 5408 1.3259
1.0864 417.0 5421 1.3554
1.1214 418.0 5434 1.2347
1.1177 419.0 5447 1.3417
1.0893 420.0 5460 1.2682
1.0809 421.0 5473 1.2308
1.1074 422.0 5486 1.3069
1.1101 423.0 5499 1.2414
1.1052 424.0 5512 1.2131
1.1036 425.0 5525 1.2598
1.1041 426.0 5538 1.2435
1.0916 427.0 5551 1.3050
1.1182 428.0 5564 1.2315
1.1401 429.0 5577 1.2985
1.0783 430.0 5590 1.2561
1.1023 431.0 5603 1.2018
1.0812 432.0 5616 1.2776
1.0972 433.0 5629 1.3098
1.0974 434.0 5642 1.2912
1.1034 435.0 5655 1.2527
1.1113 436.0 5668 1.3305
1.1026 437.0 5681 1.2507
1.1173 438.0 5694 1.1933
1.1059 439.0 5707 1.2326
1.1059 440.0 5720 1.3398
1.0857 441.0 5733 1.2865
1.1101 442.0 5746 1.2175
1.0909 443.0 5759 1.2195
1.0842 444.0 5772 1.1917
1.1266 445.0 5785 1.3260
1.1003 446.0 5798 1.1981
1.1132 447.0 5811 1.3115
1.1144 448.0 5824 1.2113
1.0909 449.0 5837 1.2275
1.0901 450.0 5850 1.3206
1.0966 451.0 5863 1.2821
1.1113 452.0 5876 1.2246
1.1166 453.0 5889 1.2174
1.1008 454.0 5902 1.2261
1.0867 455.0 5915 1.2382
1.0946 456.0 5928 1.2275
1.0806 457.0 5941 1.2702
1.092 458.0 5954 1.2788
1.0781 459.0 5967 1.1919
1.0708 460.0 5980 1.2266
1.0716 461.0 5993 1.2876
1.087 462.0 6006 1.2632
1.0925 463.0 6019 1.1550
1.0998 464.0 6032 1.2398
1.0816 465.0 6045 1.2901
1.0661 466.0 6058 1.2204
1.0896 467.0 6071 1.2587
1.1085 468.0 6084 1.2251
1.0629 469.0 6097 1.2259
1.0755 470.0 6110 1.1535
1.1145 471.0 6123 1.2034
1.0803 472.0 6136 1.2616
1.0787 473.0 6149 1.2261
1.1043 474.0 6162 1.2071
1.091 475.0 6175 1.2788
1.0938 476.0 6188 1.3360
1.0846 477.0 6201 1.1932
1.1042 478.0 6214 1.2023
1.0737 479.0 6227 1.2668
1.0857 480.0 6240 1.2893
1.0677 481.0 6253 1.1550
1.0779 482.0 6266 1.2404
1.0847 483.0 6279 1.2260
1.064 484.0 6292 1.2843
1.1016 485.0 6305 1.2789
1.088 486.0 6318 1.2207
1.0721 487.0 6331 1.2481
1.0622 488.0 6344 1.2128
1.0849 489.0 6357 1.2319
1.0665 490.0 6370 1.2880
1.0823 491.0 6383 1.2155
1.0956 492.0 6396 1.2121
1.0685 493.0 6409 1.1844
1.0871 494.0 6422 1.3001
1.0755 495.0 6435 1.2396
1.064 496.0 6448 1.1924
1.0898 497.0 6461 1.2475
1.0737 498.0 6474 1.2293
1.0828 499.0 6487 1.2668
1.0921 500.0 6500 1.2141

Framework versions

  • Transformers 4.30.2
  • Pytorch 2.0.1+cu118
  • Datasets 2.13.1
  • Tokenizers 0.13.3
Downloads last month
18
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.