ArabicNewSplits7_B_usingWellWrittenEssays_FineTuningAraBERT_run3_AugV5_k16_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: 1.4934
  • Qwk: 0.3824
  • Mse: 1.4934
  • Rmse: 1.2220

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 0.0263 2 6.7031 0.0308 6.7031 2.5890
No log 0.0526 4 4.5049 0.0700 4.5049 2.1225
No log 0.0789 6 3.9672 -0.0483 3.9672 1.9918
No log 0.1053 8 3.2373 0.0115 3.2373 1.7993
No log 0.1316 10 2.0511 0.1719 2.0511 1.4322
No log 0.1579 12 1.8204 0.2759 1.8204 1.3492
No log 0.1842 14 2.1504 0.0 2.1504 1.4664
No log 0.2105 16 2.7128 0.0 2.7128 1.6471
No log 0.2368 18 2.7979 0.0 2.7979 1.6727
No log 0.2632 20 2.5277 0.0134 2.5277 1.5899
No log 0.2895 22 2.3336 0.0979 2.3336 1.5276
No log 0.3158 24 2.2170 0.1727 2.2170 1.4889
No log 0.3421 26 2.2630 0.125 2.2630 1.5043
No log 0.3684 28 2.2207 0.1399 2.2207 1.4902
No log 0.3947 30 1.9477 0.3158 1.9477 1.3956
No log 0.4211 32 1.8433 0.3939 1.8433 1.3577
No log 0.4474 34 1.9969 0.3259 1.9969 1.4131
No log 0.4737 36 1.8878 0.3333 1.8878 1.3740
No log 0.5 38 1.5181 0.3077 1.5181 1.2321
No log 0.5263 40 1.4888 0.1714 1.4888 1.2202
No log 0.5526 42 1.5930 0.1538 1.5930 1.2622
No log 0.5789 44 1.4698 0.1905 1.4698 1.2124
No log 0.6053 46 1.3509 0.2301 1.3509 1.1623
No log 0.6316 48 1.4398 0.3810 1.4398 1.1999
No log 0.6579 50 1.3972 0.3810 1.3972 1.1820
No log 0.6842 52 1.2879 0.4262 1.2879 1.1349
No log 0.7105 54 1.6361 0.1682 1.6361 1.2791
No log 0.7368 56 2.1591 0.0 2.1591 1.4694
No log 0.7632 58 2.0231 0.0561 2.0231 1.4224
No log 0.7895 60 1.5471 0.1887 1.5471 1.2438
No log 0.8158 62 1.2211 0.5039 1.2211 1.1050
No log 0.8421 64 1.1885 0.4688 1.1885 1.0902
No log 0.8684 66 1.1219 0.5625 1.1219 1.0592
No log 0.8947 68 1.0990 0.6047 1.0990 1.0483
No log 0.9211 70 1.4013 0.4154 1.4013 1.1838
No log 0.9474 72 1.5052 0.3817 1.5052 1.2269
No log 0.9737 74 1.3287 0.4640 1.3287 1.1527
No log 1.0 76 1.1905 0.4793 1.1905 1.0911
No log 1.0263 78 1.1368 0.4959 1.1368 1.0662
No log 1.0526 80 1.1198 0.528 1.1198 1.0582
No log 1.0789 82 1.1615 0.5938 1.1615 1.0777
No log 1.1053 84 1.2188 0.5954 1.2188 1.1040
No log 1.1316 86 1.3394 0.4296 1.3394 1.1573
No log 1.1579 88 1.4525 0.3623 1.4525 1.2052
No log 1.1842 90 1.3260 0.4296 1.3260 1.1515
No log 1.2105 92 1.1710 0.5649 1.1710 1.0821
No log 1.2368 94 1.1972 0.5692 1.1972 1.0942
No log 1.2632 96 1.2324 0.5581 1.2324 1.1101
No log 1.2895 98 1.1816 0.6047 1.1816 1.0870
No log 1.3158 100 1.3015 0.5039 1.3015 1.1408
No log 1.3421 102 1.2557 0.5512 1.2557 1.1206
No log 1.3684 104 1.1229 0.5 1.1229 1.0597
No log 1.3947 106 1.0447 0.6165 1.0447 1.0221
No log 1.4211 108 1.2676 0.4604 1.2676 1.1259
No log 1.4474 110 1.4840 0.3597 1.4840 1.2182
No log 1.4737 112 1.7800 0.2464 1.7800 1.3342
No log 1.5 114 1.6955 0.2774 1.6955 1.3021
No log 1.5263 116 1.3759 0.4783 1.3759 1.1730
No log 1.5526 118 1.1893 0.5891 1.1893 1.0906
No log 1.5789 120 1.2284 0.5938 1.2284 1.1083
No log 1.6053 122 1.4611 0.4194 1.4611 1.2087
No log 1.6316 124 1.6946 0.2481 1.6946 1.3018
No log 1.6579 126 1.6681 0.2901 1.6681 1.2915
No log 1.6842 128 1.4676 0.3871 1.4676 1.2114
No log 1.7105 130 1.2639 0.4839 1.2639 1.1243
No log 1.7368 132 1.2305 0.512 1.2305 1.1093
No log 1.7632 134 1.4007 0.4741 1.4007 1.1835
No log 1.7895 136 1.7510 0.2754 1.7510 1.3233
No log 1.8158 138 1.8520 0.2411 1.8520 1.3609
No log 1.8421 140 1.6989 0.2754 1.6989 1.3034
No log 1.8684 142 1.3716 0.4580 1.3716 1.1712
No log 1.8947 144 1.2631 0.4833 1.2631 1.1239
No log 1.9211 146 1.2947 0.5161 1.2947 1.1378
No log 1.9474 148 1.3821 0.4806 1.3821 1.1756
No log 1.9737 150 1.4874 0.3881 1.4874 1.2196
No log 2.0 152 1.5196 0.3971 1.5196 1.2327
No log 2.0263 154 1.3883 0.4062 1.3883 1.1783
No log 2.0526 156 1.3507 0.5161 1.3507 1.1622
No log 2.0789 158 1.4316 0.4 1.4316 1.1965
No log 2.1053 160 1.5346 0.3676 1.5346 1.2388
No log 2.1316 162 1.6995 0.3333 1.6995 1.3037
No log 2.1579 164 1.6237 0.3333 1.6237 1.2742
No log 2.1842 166 1.5468 0.3942 1.5468 1.2437
No log 2.2105 168 1.4277 0.4638 1.4277 1.1949
No log 2.2368 170 1.4483 0.4380 1.4483 1.2034
No log 2.2632 172 1.5259 0.4203 1.5259 1.2353
No log 2.2895 174 1.4396 0.4460 1.4396 1.1998
No log 2.3158 176 1.3911 0.4823 1.3911 1.1794
No log 2.3421 178 1.2057 0.5109 1.2057 1.0980
No log 2.3684 180 1.1539 0.5037 1.1539 1.0742
No log 2.3947 182 1.2313 0.4925 1.2313 1.1096
No log 2.4211 184 1.4212 0.4526 1.4212 1.1921
No log 2.4474 186 1.5246 0.3824 1.5246 1.2347
No log 2.4737 188 1.4795 0.3759 1.4795 1.2164
No log 2.5 190 1.3772 0.5354 1.3772 1.1735
No log 2.5263 192 1.2986 0.5625 1.2986 1.1395
No log 2.5526 194 1.2400 0.6 1.2400 1.1135
No log 2.5789 196 1.2161 0.5758 1.2161 1.1028
No log 2.6053 198 1.2976 0.4604 1.2976 1.1391
No log 2.6316 200 1.4552 0.4088 1.4552 1.2063
No log 2.6579 202 1.5147 0.4088 1.5147 1.2307
No log 2.6842 204 1.4800 0.4088 1.4800 1.2166
No log 2.7105 206 1.4525 0.4088 1.4525 1.2052
No log 2.7368 208 1.4696 0.4348 1.4696 1.2123
No log 2.7632 210 1.3445 0.4741 1.3445 1.1595
No log 2.7895 212 1.2224 0.5625 1.2224 1.1056
No log 2.8158 214 1.2600 0.5758 1.2600 1.1225
No log 2.8421 216 1.2590 0.5185 1.2590 1.1221
No log 2.8684 218 1.2289 0.5373 1.2289 1.1085
No log 2.8947 220 1.2566 0.4962 1.2566 1.1210
No log 2.9211 222 1.4015 0.4526 1.4015 1.1839
No log 2.9474 224 1.4614 0.4265 1.4614 1.2089
No log 2.9737 226 1.4587 0.4265 1.4587 1.2078
No log 3.0 228 1.4159 0.4733 1.4159 1.1899
No log 3.0263 230 1.3433 0.5 1.3433 1.1590
No log 3.0526 232 1.2769 0.5246 1.2769 1.1300
No log 3.0789 234 1.3170 0.4733 1.3170 1.1476
No log 3.1053 236 1.3388 0.4741 1.3388 1.1571
No log 3.1316 238 1.2332 0.5 1.2332 1.1105
No log 3.1579 240 1.2271 0.5180 1.2271 1.1077
No log 3.1842 242 1.3217 0.4741 1.3217 1.1497
No log 3.2105 244 1.3985 0.4380 1.3985 1.1826
No log 3.2368 246 1.4567 0.4296 1.4567 1.2069
No log 3.2632 248 1.4614 0.4687 1.4614 1.2089
No log 3.2895 250 1.3793 0.4500 1.3793 1.1744
No log 3.3158 252 1.3093 0.4237 1.3093 1.1442
No log 3.3421 254 1.2345 0.5397 1.2345 1.1111
No log 3.3684 256 1.3679 0.4559 1.3679 1.1696
No log 3.3947 258 1.4592 0.4380 1.4592 1.2080
No log 3.4211 260 1.2917 0.4741 1.2917 1.1365
No log 3.4474 262 1.2486 0.5 1.2486 1.1174
No log 3.4737 264 1.4653 0.4348 1.4653 1.2105
No log 3.5 266 1.7798 0.3262 1.7798 1.3341
No log 3.5263 268 1.6753 0.4029 1.6753 1.2944
No log 3.5526 270 1.3209 0.4559 1.3209 1.1493
No log 3.5789 272 1.1232 0.5625 1.1232 1.0598
No log 3.6053 274 1.1422 0.5625 1.1422 1.0687
No log 3.6316 276 1.2336 0.5152 1.2336 1.1107
No log 3.6579 278 1.4437 0.4526 1.4437 1.2015
No log 3.6842 280 1.6042 0.4348 1.6042 1.2666
No log 3.7105 282 1.5615 0.3824 1.5615 1.2496
No log 3.7368 284 1.3525 0.5 1.3525 1.1630
No log 3.7632 286 1.2070 0.5484 1.2070 1.0986
No log 3.7895 288 1.1595 0.5806 1.1595 1.0768
No log 3.8158 290 1.1648 0.6154 1.1648 1.0793
No log 3.8421 292 1.1069 0.6154 1.1069 1.0521
No log 3.8684 294 1.1527 0.5714 1.1527 1.0737
No log 3.8947 296 1.3234 0.4559 1.3234 1.1504
No log 3.9211 298 1.4351 0.4348 1.4351 1.1979
No log 3.9474 300 1.4134 0.4088 1.4134 1.1889
No log 3.9737 302 1.3651 0.4444 1.3651 1.1684
No log 4.0 304 1.3320 0.4444 1.3320 1.1541
No log 4.0263 306 1.2858 0.5 1.2858 1.1339
No log 4.0526 308 1.4363 0.4265 1.4363 1.1984
No log 4.0789 310 1.7351 0.3597 1.7351 1.3172
No log 4.1053 312 1.7419 0.3597 1.7419 1.3198
No log 4.1316 314 1.4375 0.4088 1.4375 1.1990
No log 4.1579 316 1.2180 0.5147 1.2180 1.1036
No log 4.1842 318 1.0845 0.6107 1.0845 1.0414
No log 4.2105 320 1.1208 0.5920 1.1208 1.0587
No log 4.2368 322 1.2266 0.5891 1.2266 1.1075
No log 4.2632 324 1.3962 0.4380 1.3962 1.1816
No log 4.2895 326 1.4597 0.4348 1.4597 1.2082
No log 4.3158 328 1.3804 0.4741 1.3804 1.1749
No log 4.3421 330 1.3548 0.4925 1.3548 1.1639
No log 4.3684 332 1.3194 0.5625 1.3194 1.1486
No log 4.3947 334 1.2905 0.5246 1.2905 1.1360
No log 4.4211 336 1.2102 0.3243 1.2102 1.1001
No log 4.4474 338 1.0746 0.4706 1.0746 1.0366
No log 4.4737 340 0.9914 0.6667 0.9914 0.9957
No log 4.5 342 1.0580 0.6061 1.0580 1.0286
No log 4.5263 344 1.3868 0.4348 1.3868 1.1776
No log 4.5526 346 1.6934 0.3597 1.6934 1.3013
No log 4.5789 348 1.6912 0.3597 1.6912 1.3005
No log 4.6053 350 1.5427 0.4173 1.5427 1.2420
No log 4.6316 352 1.5010 0.4173 1.5010 1.2252
No log 4.6579 354 1.5243 0.4088 1.5243 1.2346
No log 4.6842 356 1.4222 0.4444 1.4222 1.1926
No log 4.7105 358 1.3931 0.5077 1.3931 1.1803
No log 4.7368 360 1.4079 0.5116 1.4079 1.1865
No log 4.7632 362 1.4553 0.4961 1.4553 1.2064
No log 4.7895 364 1.5116 0.4697 1.5116 1.2295
No log 4.8158 366 1.4875 0.4627 1.4875 1.2196
No log 4.8421 368 1.4057 0.4627 1.4057 1.1856
No log 4.8684 370 1.4342 0.4 1.4342 1.1976
No log 4.8947 372 1.5668 0.3768 1.5668 1.2517
No log 4.9211 374 1.6647 0.3571 1.6647 1.2903
No log 4.9474 376 1.6979 0.3571 1.6979 1.3030
No log 4.9737 378 1.6277 0.3571 1.6277 1.2758
No log 5.0 380 1.4556 0.4118 1.4556 1.2065
No log 5.0263 382 1.3031 0.5312 1.3031 1.1416
No log 5.0526 384 1.3038 0.5197 1.3038 1.1418
No log 5.0789 386 1.3848 0.4627 1.3848 1.1768
No log 5.1053 388 1.6305 0.3571 1.6305 1.2769
No log 5.1316 390 1.7746 0.3571 1.7746 1.3321
No log 5.1579 392 1.6650 0.3571 1.6650 1.2904
No log 5.1842 394 1.3503 0.4444 1.3503 1.1620
No log 5.2105 396 1.2057 0.5414 1.2057 1.0981
No log 5.2368 398 1.1992 0.5672 1.1992 1.0951
No log 5.2632 400 1.1467 0.5581 1.1467 1.0708
No log 5.2895 402 1.2826 0.4580 1.2826 1.1325
No log 5.3158 404 1.6825 0.3650 1.6825 1.2971
No log 5.3421 406 2.0679 0.2676 2.0679 1.4380
No log 5.3684 408 2.1952 0.2222 2.1952 1.4816
No log 5.3947 410 2.0213 0.2676 2.0213 1.4217
No log 5.4211 412 1.6329 0.3382 1.6329 1.2779
No log 5.4474 414 1.3907 0.4328 1.3907 1.1793
No log 5.4737 416 1.3787 0.4328 1.3787 1.1742
No log 5.5 418 1.4165 0.4118 1.4165 1.1902
No log 5.5263 420 1.5568 0.3741 1.5568 1.2477
No log 5.5526 422 1.7645 0.3571 1.7645 1.3283
No log 5.5789 424 1.8361 0.3143 1.8361 1.3550
No log 5.6053 426 1.8080 0.3309 1.8080 1.3446
No log 5.6316 428 1.7665 0.3043 1.7665 1.3291
No log 5.6579 430 1.6713 0.3235 1.6713 1.2928
No log 5.6842 432 1.5411 0.4275 1.5411 1.2414
No log 5.7105 434 1.3841 0.5197 1.3841 1.1765
No log 5.7368 436 1.3091 0.5197 1.3091 1.1442
No log 5.7632 438 1.3415 0.5 1.3415 1.1582
No log 5.7895 440 1.4630 0.4627 1.4630 1.2095
No log 5.8158 442 1.6273 0.3235 1.6273 1.2757
No log 5.8421 444 1.6702 0.3066 1.6702 1.2924
No log 5.8684 446 1.5507 0.3768 1.5507 1.2453
No log 5.8947 448 1.5276 0.3768 1.5276 1.2360
No log 5.9211 450 1.6042 0.3768 1.6042 1.2666
No log 5.9474 452 1.7213 0.3504 1.7213 1.3120
No log 5.9737 454 1.6312 0.3768 1.6312 1.2772
No log 6.0 456 1.5483 0.3768 1.5483 1.2443
No log 6.0263 458 1.5614 0.3768 1.5614 1.2496
No log 6.0526 460 1.7034 0.3333 1.7034 1.3051
No log 6.0789 462 1.8598 0.2695 1.8598 1.3637
No log 6.1053 464 1.7948 0.3429 1.7948 1.3397
No log 6.1316 466 1.7436 0.3429 1.7436 1.3205
No log 6.1579 468 1.6360 0.3597 1.6360 1.2791
No log 6.1842 470 1.5087 0.4148 1.5087 1.2283
No log 6.2105 472 1.4672 0.4511 1.4672 1.2113
No log 6.2368 474 1.3944 0.4545 1.3944 1.1808
No log 6.2632 476 1.4034 0.4545 1.4034 1.1846
No log 6.2895 478 1.5141 0.3971 1.5141 1.2305
No log 6.3158 480 1.5331 0.3650 1.5331 1.2382
No log 6.3421 482 1.5468 0.3768 1.5468 1.2437
No log 6.3684 484 1.5057 0.4029 1.5057 1.2271
No log 6.3947 486 1.4093 0.4088 1.4093 1.1872
No log 6.4211 488 1.3246 0.4593 1.3246 1.1509
No log 6.4474 490 1.3228 0.4511 1.3228 1.1501
No log 6.4737 492 1.3285 0.4545 1.3285 1.1526
No log 6.5 494 1.3631 0.4769 1.3631 1.1675
No log 6.5263 496 1.4647 0.3969 1.4647 1.2103
No log 6.5526 498 1.5397 0.3788 1.5397 1.2408
0.4001 6.5789 500 1.5285 0.4060 1.5285 1.2363
0.4001 6.6053 502 1.4412 0.4511 1.4412 1.2005
0.4001 6.6316 504 1.4275 0.4776 1.4275 1.1948
0.4001 6.6579 506 1.4386 0.4776 1.4386 1.1994
0.4001 6.6842 508 1.5037 0.4265 1.5037 1.2262
0.4001 6.7105 510 1.5034 0.3881 1.5034 1.2261
0.4001 6.7368 512 1.4650 0.4242 1.4650 1.2104
0.4001 6.7632 514 1.4081 0.4462 1.4081 1.1866
0.4001 6.7895 516 1.3237 0.4878 1.3237 1.1505
0.4001 6.8158 518 1.2991 0.5161 1.2991 1.1398
0.4001 6.8421 520 1.3248 0.512 1.3248 1.1510
0.4001 6.8684 522 1.4079 0.4531 1.4079 1.1866
0.4001 6.8947 524 1.4812 0.4242 1.4812 1.2171
0.4001 6.9211 526 1.4088 0.4496 1.4088 1.1869
0.4001 6.9474 528 1.3349 0.5039 1.3349 1.1554
0.4001 6.9737 530 1.2424 0.544 1.2424 1.1146
0.4001 7.0 532 1.2052 0.5323 1.2052 1.0978
0.4001 7.0263 534 1.1980 0.544 1.1980 1.0945
0.4001 7.0526 536 1.2211 0.5397 1.2211 1.1050
0.4001 7.0789 538 1.2479 0.5077 1.2479 1.1171
0.4001 7.1053 540 1.3564 0.4925 1.3564 1.1646
0.4001 7.1316 542 1.5925 0.4348 1.5925 1.2620
0.4001 7.1579 544 1.7211 0.3286 1.7211 1.3119
0.4001 7.1842 546 1.6665 0.3768 1.6665 1.2909
0.4001 7.2105 548 1.4407 0.4348 1.4407 1.2003
0.4001 7.2368 550 1.2060 0.5714 1.2060 1.0982
0.4001 7.2632 552 1.0999 0.5645 1.0999 1.0488
0.4001 7.2895 554 1.1005 0.5691 1.1005 1.0491
0.4001 7.3158 556 1.1052 0.5246 1.1052 1.0513
0.4001 7.3421 558 1.1732 0.56 1.1732 1.0831
0.4001 7.3684 560 1.3083 0.5156 1.3083 1.1438
0.4001 7.3947 562 1.4974 0.4091 1.4974 1.2237
0.4001 7.4211 564 1.4923 0.4122 1.4923 1.2216
0.4001 7.4474 566 1.3762 0.4580 1.3762 1.1731
0.4001 7.4737 568 1.2671 0.544 1.2671 1.1257
0.4001 7.5 570 1.1719 0.5714 1.1719 1.0825
0.4001 7.5263 572 1.1661 0.5714 1.1661 1.0799
0.4001 7.5526 574 1.1661 0.5714 1.1661 1.0798
0.4001 7.5789 576 1.2223 0.544 1.2223 1.1056
0.4001 7.6053 578 1.2369 0.5512 1.2369 1.1122
0.4001 7.6316 580 1.2652 0.5312 1.2652 1.1248
0.4001 7.6579 582 1.2484 0.5426 1.2484 1.1173
0.4001 7.6842 584 1.2528 0.5426 1.2528 1.1193
0.4001 7.7105 586 1.3607 0.4697 1.3607 1.1665
0.4001 7.7368 588 1.4221 0.4091 1.4221 1.1925
0.4001 7.7632 590 1.3618 0.4427 1.3618 1.1670
0.4001 7.7895 592 1.2582 0.5625 1.2582 1.1217
0.4001 7.8158 594 1.1380 0.5556 1.1380 1.0668
0.4001 7.8421 596 1.0697 0.5528 1.0697 1.0343
0.4001 7.8684 598 1.0860 0.5512 1.0860 1.0421
0.4001 7.8947 600 1.2441 0.5038 1.2441 1.1154
0.4001 7.9211 602 1.5596 0.3824 1.5596 1.2488
0.4001 7.9474 604 1.8675 0.3043 1.8675 1.3666
0.4001 7.9737 606 1.9668 0.3022 1.9668 1.4024
0.4001 8.0 608 1.8111 0.3043 1.8111 1.3458
0.4001 8.0263 610 1.4934 0.3824 1.4934 1.2220

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_k16_task1_organization

Finetuned
(4019)
this model