ArabicNewSplits7_B_usingWellWrittenEssays_FineTuningAraBERT_run3_AugV5_k17_task1_organization

This model is a fine-tuned version of aubmindlab/bert-base-arabertv02 on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 1.4407
  • Qwk: 0.4091
  • Mse: 1.4407
  • Rmse: 1.2003

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: 2e-05
  • train_batch_size: 8
  • eval_batch_size: 8
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 100

Training results

Training Loss Epoch Step Validation Loss Qwk Mse Rmse
No log 0.025 2 7.0527 0.0056 7.0527 2.6557
No log 0.05 4 4.4386 0.0964 4.4386 2.1068
No log 0.075 6 3.0348 0.0595 3.0348 1.7421
No log 0.1 8 2.3563 0.0921 2.3563 1.5350
No log 0.125 10 2.2054 0.1259 2.2054 1.4851
No log 0.15 12 1.8667 0.2143 1.8667 1.3663
No log 0.175 14 1.6516 0.1905 1.6516 1.2851
No log 0.2 16 1.7285 0.1111 1.7285 1.3147
No log 0.225 18 2.1644 0.1129 2.1644 1.4712
No log 0.25 20 3.1631 0.0 3.1631 1.7785
No log 0.275 22 2.8313 0.0263 2.8313 1.6826
No log 0.3 24 1.9554 0.1803 1.9554 1.3983
No log 0.325 26 1.5807 0.1698 1.5807 1.2572
No log 0.35 28 1.5426 0.1714 1.5426 1.2420
No log 0.375 30 1.5261 0.1714 1.5261 1.2353
No log 0.4 32 1.6189 0.2321 1.6189 1.2724
No log 0.425 34 1.7369 0.3387 1.7369 1.3179
No log 0.45 36 1.6484 0.3566 1.6484 1.2839
No log 0.475 38 1.5572 0.3780 1.5572 1.2479
No log 0.5 40 1.3517 0.3333 1.3517 1.1626
No log 0.525 42 1.5859 0.2182 1.5859 1.2593
No log 0.55 44 1.4198 0.2222 1.4198 1.1916
No log 0.575 46 1.1857 0.5323 1.1857 1.0889
No log 0.6 48 1.4850 0.4593 1.4850 1.2186
No log 0.625 50 1.3208 0.4328 1.3208 1.1493
No log 0.65 52 1.1460 0.4786 1.1460 1.0705
No log 0.675 54 1.6800 0.2703 1.6800 1.2962
No log 0.7 56 1.8699 0.1786 1.8699 1.3674
No log 0.725 58 1.4035 0.2407 1.4035 1.1847
No log 0.75 60 1.3519 0.3214 1.3519 1.1627
No log 0.775 62 1.4073 0.3186 1.4073 1.1863
No log 0.8 64 1.3580 0.3091 1.3580 1.1653
No log 0.825 66 1.3296 0.3604 1.3296 1.1531
No log 0.85 68 1.4164 0.2909 1.4164 1.1901
No log 0.875 70 1.3641 0.3894 1.3641 1.1679
No log 0.9 72 1.2195 0.4655 1.2195 1.1043
No log 0.925 74 1.1882 0.4706 1.1882 1.0901
No log 0.95 76 1.1622 0.5397 1.1622 1.0781
No log 0.975 78 1.1662 0.5354 1.1662 1.0799
No log 1.0 80 1.2375 0.4769 1.2375 1.1124
No log 1.025 82 1.2251 0.4961 1.2251 1.1068
No log 1.05 84 1.2349 0.5714 1.2349 1.1113
No log 1.075 86 1.2815 0.4733 1.2815 1.1320
No log 1.1 88 1.4190 0.4211 1.4190 1.1912
No log 1.125 90 1.4342 0.4179 1.4342 1.1976
No log 1.15 92 1.4713 0.4186 1.4713 1.2130
No log 1.175 94 1.5939 0.35 1.5939 1.2625
No log 1.2 96 1.4695 0.4219 1.4695 1.2122
No log 1.225 98 1.3772 0.4496 1.3772 1.1735
No log 1.25 100 1.3847 0.4409 1.3847 1.1767
No log 1.275 102 1.4560 0.4355 1.4560 1.2067
No log 1.3 104 1.5996 0.3636 1.5996 1.2647
No log 1.325 106 1.5954 0.3390 1.5954 1.2631
No log 1.35 108 1.4898 0.3186 1.4898 1.2206
No log 1.375 110 1.4792 0.3243 1.4792 1.2162
No log 1.4 112 1.4851 0.2906 1.4851 1.2187
No log 1.425 114 1.4948 0.3390 1.4948 1.2226
No log 1.45 116 1.8037 0.2794 1.8037 1.3430
No log 1.475 118 1.9432 0.2302 1.9432 1.3940
No log 1.5 120 1.7818 0.2794 1.7818 1.3348
No log 1.525 122 1.4041 0.4308 1.4041 1.1849
No log 1.55 124 1.3599 0.3465 1.3599 1.1661
No log 1.575 126 1.5007 0.4511 1.5007 1.2250
No log 1.6 128 1.3563 0.4308 1.3563 1.1646
No log 1.625 130 1.2375 0.4580 1.2375 1.1124
No log 1.65 132 1.6052 0.3636 1.6052 1.2670
No log 1.675 134 1.8658 0.2899 1.8658 1.3659
No log 1.7 136 1.8836 0.2899 1.8836 1.3724
No log 1.725 138 1.6982 0.3788 1.6982 1.3032
No log 1.75 140 1.4949 0.3548 1.4949 1.2227
No log 1.775 142 1.3636 0.3540 1.3636 1.1677
No log 1.8 144 1.3699 0.3509 1.3699 1.1704
No log 1.825 146 1.5085 0.3140 1.5085 1.2282
No log 1.85 148 1.7036 0.3636 1.7036 1.3052
No log 1.875 150 1.7191 0.3636 1.7191 1.3111
No log 1.9 152 1.5250 0.4480 1.5250 1.2349
No log 1.925 154 1.3608 0.2703 1.3608 1.1665
No log 1.95 156 1.3856 0.3036 1.3856 1.1771
No log 1.975 158 1.4270 0.25 1.4270 1.1946
No log 2.0 160 1.5907 0.3281 1.5907 1.2612
No log 2.025 162 1.7408 0.3259 1.7408 1.3194
No log 2.05 164 1.8903 0.2286 1.8903 1.3749
No log 2.075 166 1.7539 0.2590 1.7539 1.3244
No log 2.1 168 1.5186 0.3636 1.5186 1.2323
No log 2.125 170 1.3346 0.4262 1.3346 1.1552
No log 2.15 172 1.3703 0.3898 1.3703 1.1706
No log 2.175 174 1.4333 0.3529 1.4333 1.1972
No log 2.2 176 1.4181 0.3667 1.4181 1.1908
No log 2.225 178 1.2797 0.4202 1.2797 1.1312
No log 2.25 180 1.2270 0.4370 1.2270 1.1077
No log 2.275 182 1.2332 0.3793 1.2332 1.1105
No log 2.3 184 1.3729 0.4262 1.3729 1.1717
No log 2.325 186 1.7020 0.2920 1.7020 1.3046
No log 2.35 188 1.7949 0.2609 1.7949 1.3397
No log 2.375 190 1.6058 0.3284 1.6058 1.2672
No log 2.4 192 1.4361 0.5075 1.4361 1.1984
No log 2.425 194 1.4646 0.4545 1.4646 1.2102
No log 2.45 196 1.5450 0.3566 1.5450 1.2430
No log 2.475 198 1.6761 0.3664 1.6761 1.2946
No log 2.5 200 1.6967 0.3622 1.6967 1.3026
No log 2.525 202 1.6108 0.2833 1.6108 1.2692
No log 2.55 204 1.5542 0.2957 1.5542 1.2467
No log 2.575 206 1.5471 0.3577 1.5471 1.2438
No log 2.6 208 1.5475 0.3566 1.5475 1.2440
No log 2.625 210 1.5404 0.3566 1.5404 1.2411
No log 2.65 212 1.6430 0.3182 1.6430 1.2818
No log 2.675 214 1.8300 0.2754 1.8300 1.3528
No log 2.7 216 1.6990 0.3182 1.6990 1.3035
No log 2.725 218 1.4968 0.4094 1.4968 1.2234
No log 2.75 220 1.5317 0.3306 1.5317 1.2376
No log 2.775 222 1.6386 0.3387 1.6386 1.2801
No log 2.8 224 1.7619 0.2946 1.7619 1.3274
No log 2.825 226 1.7979 0.2985 1.7979 1.3409
No log 2.85 228 1.7132 0.3150 1.7132 1.3089
No log 2.875 230 1.5949 0.2667 1.5949 1.2629
No log 2.9 232 1.5761 0.2735 1.5761 1.2554
No log 2.925 234 1.6066 0.2951 1.6066 1.2675
No log 2.95 236 1.7195 0.3788 1.7195 1.3113
No log 2.975 238 1.7553 0.3609 1.7553 1.3249
No log 3.0 240 1.6105 0.3566 1.6105 1.2690
No log 3.025 242 1.4804 0.3443 1.4804 1.2167
No log 3.05 244 1.4165 0.35 1.4165 1.1902
No log 3.075 246 1.4602 0.4000 1.4602 1.2084
No log 3.1 248 1.5846 0.4688 1.5846 1.2588
No log 3.125 250 1.5959 0.4688 1.5959 1.2633
No log 3.15 252 1.4126 0.4262 1.4126 1.1885
No log 3.175 254 1.3728 0.3621 1.3728 1.1717
No log 3.2 256 1.4529 0.2727 1.4529 1.2054
No log 3.225 258 1.4654 0.3063 1.4654 1.2105
No log 3.25 260 1.4853 0.3276 1.4853 1.2187
No log 3.275 262 1.7708 0.2857 1.7708 1.3307
No log 3.3 264 2.0518 0.2113 2.0518 1.4324
No log 3.325 266 1.9851 0.2345 1.9851 1.4089
No log 3.35 268 1.7035 0.2519 1.7035 1.3052
No log 3.375 270 1.5280 0.3636 1.5280 1.2361
No log 3.4 272 1.5362 0.3934 1.5362 1.2395
No log 3.425 274 1.6471 0.2586 1.6471 1.2834
No log 3.45 276 1.6775 0.2478 1.6775 1.2952
No log 3.475 278 1.7276 0.2414 1.7276 1.3144
No log 3.5 280 1.6596 0.2456 1.6596 1.2883
No log 3.525 282 1.6270 0.2679 1.6270 1.2756
No log 3.55 284 1.6515 0.35 1.6515 1.2851
No log 3.575 286 1.7334 0.3538 1.7334 1.3166
No log 3.6 288 1.6846 0.3876 1.6846 1.2979
No log 3.625 290 1.5441 0.4127 1.5441 1.2426
No log 3.65 292 1.4478 0.4355 1.4478 1.2032
No log 3.675 294 1.4220 0.4640 1.4220 1.1925
No log 3.7 296 1.3820 0.4640 1.3820 1.1756
No log 3.725 298 1.3967 0.4677 1.3967 1.1818
No log 3.75 300 1.4709 0.3934 1.4709 1.2128
No log 3.775 302 1.4218 0.3898 1.4218 1.1924
No log 3.8 304 1.3869 0.3793 1.3869 1.1776
No log 3.825 306 1.4120 0.3761 1.4120 1.1883
No log 3.85 308 1.5203 0.3667 1.5203 1.2330
No log 3.875 310 1.6442 0.3259 1.6442 1.2823
No log 3.9 312 1.6151 0.3308 1.6151 1.2709
No log 3.925 314 1.4662 0.4320 1.4662 1.2109
No log 3.95 316 1.3590 0.4407 1.3590 1.1657
No log 3.975 318 1.3689 0.4407 1.3689 1.1700
No log 4.0 320 1.3991 0.3826 1.3991 1.1828
No log 4.025 322 1.4348 0.3652 1.4348 1.1978
No log 4.05 324 1.5235 0.3937 1.5235 1.2343
No log 4.075 326 1.6019 0.3088 1.6019 1.2657
No log 4.1 328 1.5135 0.3485 1.5135 1.2302
No log 4.125 330 1.3075 0.4923 1.3075 1.1435
No log 4.15 332 1.2199 0.5312 1.2199 1.1045
No log 4.175 334 1.2287 0.5271 1.2287 1.1084
No log 4.2 336 1.2812 0.4806 1.2812 1.1319
No log 4.225 338 1.4237 0.4186 1.4237 1.1932
No log 4.25 340 1.6460 0.3259 1.6460 1.2830
No log 4.275 342 1.6649 0.3259 1.6649 1.2903
No log 4.3 344 1.5473 0.4186 1.5473 1.2439
No log 4.325 346 1.4178 0.4202 1.4178 1.1907
No log 4.35 348 1.3790 0.4035 1.3790 1.1743
No log 4.375 350 1.3830 0.3243 1.3830 1.1760
No log 4.4 352 1.3753 0.4103 1.3753 1.1727
No log 4.425 354 1.4252 0.4065 1.4252 1.1938
No log 4.45 356 1.5343 0.3876 1.5343 1.2387
No log 4.475 358 1.6967 0.3088 1.6967 1.3026
No log 4.5 360 1.7224 0.2774 1.7224 1.3124
No log 4.525 362 1.6897 0.2537 1.6897 1.2999
No log 4.55 364 1.6561 0.3125 1.6561 1.2869
No log 4.575 366 1.5397 0.3967 1.5397 1.2409
No log 4.6 368 1.4105 0.4274 1.4105 1.1876
No log 4.625 370 1.3621 0.4348 1.3621 1.1671
No log 4.65 372 1.3546 0.3894 1.3546 1.1639
No log 4.675 374 1.3585 0.4211 1.3585 1.1656
No log 4.7 376 1.3713 0.4211 1.3713 1.1710
No log 4.725 378 1.3725 0.3363 1.3725 1.1715
No log 4.75 380 1.3697 0.3509 1.3697 1.1703
No log 4.775 382 1.3802 0.3509 1.3802 1.1748
No log 4.8 384 1.4134 0.4202 1.4134 1.1889
No log 4.825 386 1.4579 0.4320 1.4579 1.2074
No log 4.85 388 1.4541 0.4186 1.4541 1.2059
No log 4.875 390 1.4881 0.3817 1.4881 1.2199
No log 4.9 392 1.4378 0.3817 1.4378 1.1991
No log 4.925 394 1.4033 0.4186 1.4033 1.1846
No log 4.95 396 1.3438 0.4186 1.3438 1.1592
No log 4.975 398 1.4050 0.4462 1.4050 1.1853
No log 5.0 400 1.4211 0.4462 1.4211 1.1921
No log 5.025 402 1.3713 0.4496 1.3713 1.1710
No log 5.05 404 1.4366 0.4186 1.4366 1.1986
No log 5.075 406 1.3974 0.4275 1.3974 1.1821
No log 5.1 408 1.2557 0.5426 1.2557 1.1206
No log 5.125 410 1.1461 0.5161 1.1461 1.0706
No log 5.15 412 1.1330 0.5 1.1330 1.0644
No log 5.175 414 1.1230 0.4959 1.1230 1.0597
No log 5.2 416 1.1287 0.5000 1.1287 1.0624
No log 5.225 418 1.1134 0.4918 1.1134 1.0552
No log 5.25 420 1.1092 0.5323 1.1092 1.0532
No log 5.275 422 1.1678 0.512 1.1678 1.0807
No log 5.3 424 1.2416 0.5156 1.2416 1.1143
No log 5.325 426 1.2319 0.5238 1.2319 1.1099
No log 5.35 428 1.2649 0.5082 1.2649 1.1247
No log 5.375 430 1.3406 0.3717 1.3406 1.1578
No log 5.4 432 1.3903 0.3717 1.3903 1.1791
No log 5.425 434 1.3807 0.3243 1.3807 1.1750
No log 5.45 436 1.3625 0.4035 1.3625 1.1673
No log 5.475 438 1.3698 0.3932 1.3698 1.1704
No log 5.5 440 1.4175 0.4480 1.4175 1.1906
No log 5.525 442 1.4346 0.4219 1.4346 1.1978
No log 5.55 444 1.3901 0.4769 1.3901 1.1790
No log 5.575 446 1.2978 0.5312 1.2978 1.1392
No log 5.6 448 1.3042 0.5231 1.3042 1.1420
No log 5.625 450 1.4179 0.4219 1.4179 1.1907
No log 5.65 452 1.5522 0.3788 1.5522 1.2459
No log 5.675 454 1.4851 0.4341 1.4851 1.2187
No log 5.7 456 1.3373 0.4516 1.3373 1.1564
No log 5.725 458 1.3268 0.4407 1.3268 1.1519
No log 5.75 460 1.3395 0.3894 1.3395 1.1574
No log 5.775 462 1.3371 0.4202 1.3371 1.1563
No log 5.8 464 1.3680 0.4194 1.3680 1.1696
No log 5.825 466 1.4116 0.4194 1.4116 1.1881
No log 5.85 468 1.4943 0.3876 1.4943 1.2224
No log 5.875 470 1.5317 0.3721 1.5317 1.2376
No log 5.9 472 1.4274 0.4603 1.4274 1.1947
No log 5.925 474 1.3522 0.4034 1.3522 1.1629
No log 5.95 476 1.3294 0.3866 1.3294 1.1530
No log 5.975 478 1.3283 0.4516 1.3283 1.1525
No log 6.0 480 1.3668 0.4444 1.3668 1.1691
No log 6.025 482 1.4007 0.4567 1.4007 1.1835
No log 6.05 484 1.3667 0.4567 1.3667 1.1691
No log 6.075 486 1.2571 0.4516 1.2571 1.1212
No log 6.1 488 1.2132 0.4839 1.2132 1.1014
No log 6.125 490 1.2259 0.4839 1.2259 1.1072
No log 6.15 492 1.3044 0.4444 1.3044 1.1421
No log 6.175 494 1.4986 0.4091 1.4986 1.2242
No log 6.2 496 1.5454 0.4091 1.5454 1.2431
No log 6.225 498 1.5150 0.4091 1.5150 1.2309
0.39 6.25 500 1.3897 0.4154 1.3897 1.1789
0.39 6.275 502 1.2783 0.4724 1.2783 1.1306
0.39 6.3 504 1.2840 0.4444 1.2840 1.1331
0.39 6.325 506 1.3509 0.4409 1.3509 1.1623
0.39 6.35 508 1.4387 0.4531 1.4387 1.1995
0.39 6.375 510 1.4183 0.4409 1.4183 1.1909
0.39 6.4 512 1.4046 0.4228 1.4046 1.1852
0.39 6.425 514 1.3617 0.4426 1.3617 1.1669
0.39 6.45 516 1.3166 0.4426 1.3166 1.1474
0.39 6.475 518 1.3370 0.4390 1.3370 1.1563
0.39 6.5 520 1.3171 0.4333 1.3171 1.1476
0.39 6.525 522 1.2985 0.4628 1.2985 1.1395
0.39 6.55 524 1.3195 0.4262 1.3195 1.1487
0.39 6.575 526 1.3712 0.4603 1.3712 1.1710
0.39 6.6 528 1.4230 0.4603 1.4230 1.1929
0.39 6.625 530 1.4765 0.4031 1.4765 1.2151
0.39 6.65 532 1.4691 0.4031 1.4691 1.2120
0.39 6.675 534 1.4679 0.4567 1.4679 1.2116
0.39 6.7 536 1.4491 0.4603 1.4491 1.2038
0.39 6.725 538 1.3711 0.4882 1.3711 1.1709
0.39 6.75 540 1.3362 0.4921 1.3362 1.1559
0.39 6.775 542 1.3601 0.4677 1.3601 1.1662
0.39 6.8 544 1.4186 0.4762 1.4186 1.1910
0.39 6.825 546 1.4606 0.4603 1.4606 1.2086
0.39 6.85 548 1.5377 0.4 1.5377 1.2400
0.39 6.875 550 1.6332 0.3636 1.6332 1.2780
0.39 6.9 552 1.5725 0.3969 1.5725 1.2540
0.39 6.925 554 1.4450 0.4252 1.4450 1.2021
0.39 6.95 556 1.3662 0.4553 1.3662 1.1689
0.39 6.975 558 1.3573 0.4407 1.3573 1.1650
0.39 7.0 560 1.3800 0.4298 1.3800 1.1747
0.39 7.025 562 1.3989 0.48 1.3989 1.1827
0.39 7.05 564 1.3745 0.4724 1.3745 1.1724
0.39 7.075 566 1.3597 0.4531 1.3597 1.1661
0.39 7.1 568 1.3563 0.5 1.3563 1.1646
0.39 7.125 570 1.3640 0.5 1.3640 1.1679
0.39 7.15 572 1.3826 0.5079 1.3826 1.1758
0.39 7.175 574 1.4013 0.48 1.4013 1.1838
0.39 7.2 576 1.4544 0.4531 1.4544 1.2060
0.39 7.225 578 1.4860 0.4651 1.4860 1.2190
0.39 7.25 580 1.4873 0.4651 1.4873 1.2196
0.39 7.275 582 1.4140 0.4724 1.4140 1.1891
0.39 7.3 584 1.3384 0.4793 1.3384 1.1569
0.39 7.325 586 1.3202 0.4793 1.3202 1.1490
0.39 7.35 588 1.3301 0.4762 1.3301 1.1533
0.39 7.375 590 1.3726 0.4724 1.3726 1.1716
0.39 7.4 592 1.3918 0.4651 1.3918 1.1798
0.39 7.425 594 1.3926 0.4615 1.3926 1.1801
0.39 7.45 596 1.3566 0.4844 1.3566 1.1647
0.39 7.475 598 1.2916 0.4960 1.2916 1.1365
0.39 7.5 600 1.2437 0.5669 1.2437 1.1152
0.39 7.525 602 1.2889 0.5156 1.2889 1.1353
0.39 7.55 604 1.3236 0.4769 1.3236 1.1505
0.39 7.575 606 1.3093 0.4885 1.3093 1.1443
0.39 7.6 608 1.2971 0.5373 1.2971 1.1389
0.39 7.625 610 1.3731 0.4733 1.3731 1.1718
0.39 7.65 612 1.3842 0.4615 1.3842 1.1765
0.39 7.675 614 1.3047 0.5038 1.3047 1.1422
0.39 7.7 616 1.2747 0.5156 1.2747 1.1290
0.39 7.725 618 1.3129 0.4921 1.3129 1.1458
0.39 7.75 620 1.3819 0.4762 1.3819 1.1755
0.39 7.775 622 1.4867 0.4603 1.4867 1.2193
0.39 7.8 624 1.5506 0.4480 1.5506 1.2452
0.39 7.825 626 1.5789 0.4098 1.5789 1.2565
0.39 7.85 628 1.5675 0.4390 1.5675 1.2520
0.39 7.875 630 1.5067 0.4390 1.5067 1.2275
0.39 7.9 632 1.4496 0.4444 1.4496 1.2040
0.39 7.925 634 1.4385 0.4186 1.4385 1.1994
0.39 7.95 636 1.3817 0.4062 1.3817 1.1754
0.39 7.975 638 1.3738 0.4062 1.3738 1.1721
0.39 8.0 640 1.3751 0.4186 1.3751 1.1727
0.39 8.025 642 1.3923 0.3906 1.3923 1.1799
0.39 8.05 644 1.3361 0.3968 1.3361 1.1559
0.39 8.075 646 1.2963 0.4 1.2963 1.1385
0.39 8.1 648 1.3419 0.4094 1.3419 1.1584
0.39 8.125 650 1.4407 0.4091 1.4407 1.2003

Framework versions

  • Transformers 4.44.2
  • Pytorch 2.4.0+cu118
  • Datasets 2.21.0
  • Tokenizers 0.19.1
Downloads last month
-
Safetensors
Model size
0.1B params
Tensor type
F32
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for MayBashendy/ArabicNewSplits7_B_usingWellWrittenEssays_FineTuningAraBERT_run3_AugV5_k17_task1_organization

Finetuned
(4019)
this model