ArabicNewSplits7_usingWellWrittenEssays_FineTuningAraBERT_run3_AugV5_k18_task3_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: 0.9889
  • Qwk: -0.0336
  • Mse: 0.9889
  • Rmse: 0.9944

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 0.0444 2 3.6132 -0.0252 3.6132 1.9008
No log 0.0889 4 2.3154 0.0431 2.3154 1.5217
No log 0.1333 6 2.3802 0.0304 2.3802 1.5428
No log 0.1778 8 1.5836 -0.0015 1.5836 1.2584
No log 0.2222 10 1.0974 0.0423 1.0974 1.0476
No log 0.2667 12 1.1507 -0.0178 1.1507 1.0727
No log 0.3111 14 1.0164 -0.0345 1.0164 1.0081
No log 0.3556 16 0.7562 -0.0188 0.7562 0.8696
No log 0.4 18 0.7388 -0.1223 0.7388 0.8596
No log 0.4444 20 0.7972 -0.0188 0.7972 0.8929
No log 0.4889 22 1.0593 0.0446 1.0593 1.0292
No log 0.5333 24 1.5707 0.0 1.5707 1.2533
No log 0.5778 26 1.7024 0.0 1.7024 1.3048
No log 0.6222 28 1.7264 0.0 1.7264 1.3139
No log 0.6667 30 1.5152 0.0 1.5153 1.2310
No log 0.7111 32 1.3409 0.0 1.3409 1.1580
No log 0.7556 34 1.3414 0.0 1.3414 1.1582
No log 0.8 36 1.3420 0.0 1.3420 1.1585
No log 0.8444 38 1.3156 0.0 1.3156 1.1470
No log 0.8889 40 1.1599 0.0 1.1599 1.0770
No log 0.9333 42 0.9175 0.0006 0.9175 0.9578
No log 0.9778 44 0.8567 -0.0861 0.8567 0.9256
No log 1.0222 46 0.8364 -0.0766 0.8364 0.9145
No log 1.0667 48 0.9196 0.0404 0.9196 0.9589
No log 1.1111 50 1.2286 -0.1023 1.2286 1.1084
No log 1.1556 52 1.4689 -0.1023 1.4689 1.2120
No log 1.2 54 1.4188 -0.1292 1.4188 1.1911
No log 1.2444 56 1.3135 -0.0372 1.3135 1.1461
No log 1.2889 58 1.3043 -0.0992 1.3043 1.1421
No log 1.3333 60 1.3114 -0.1019 1.3114 1.1452
No log 1.3778 62 1.1451 -0.0500 1.1451 1.0701
No log 1.4222 64 1.0647 0.0 1.0647 1.0318
No log 1.4667 66 0.9364 0.0156 0.9364 0.9677
No log 1.5111 68 0.8602 0.0486 0.8602 0.9274
No log 1.5556 70 0.8936 -0.0013 0.8936 0.9453
No log 1.6 72 0.9734 -0.0385 0.9734 0.9866
No log 1.6444 74 1.0561 -0.0704 1.0561 1.0277
No log 1.6889 76 1.2600 -0.0234 1.2600 1.1225
No log 1.7333 78 1.4230 -0.0234 1.4230 1.1929
No log 1.7778 80 1.3553 0.0 1.3553 1.1642
No log 1.8222 82 1.3527 0.0 1.3527 1.1631
No log 1.8667 84 1.2124 0.0 1.2124 1.1011
No log 1.9111 86 1.1366 0.0 1.1366 1.0661
No log 1.9556 88 1.1698 0.0016 1.1698 1.0816
No log 2.0 90 1.2174 0.0298 1.2174 1.1034
No log 2.0444 92 1.1943 0.0065 1.1943 1.0928
No log 2.0889 94 1.3236 0.0298 1.3236 1.1505
No log 2.1333 96 1.4890 0.0279 1.4890 1.2203
No log 2.1778 98 1.4975 0.0279 1.4975 1.2237
No log 2.2222 100 1.2778 0.0298 1.2778 1.1304
No log 2.2667 102 1.1577 0.0610 1.1577 1.0760
No log 2.3111 104 1.1609 0.0937 1.1609 1.0774
No log 2.3556 106 1.3082 0.0610 1.3082 1.1438
No log 2.4 108 1.1645 -0.0101 1.1645 1.0791
No log 2.4444 110 0.9901 -0.0200 0.9901 0.9950
No log 2.4889 112 1.0211 0.0089 1.0211 1.0105
No log 2.5333 114 1.1197 -0.0638 1.1197 1.0581
No log 2.5778 116 1.2420 -0.0067 1.2420 1.1144
No log 2.6222 118 1.3571 -0.0399 1.3571 1.1650
No log 2.6667 120 1.1483 -0.0331 1.1483 1.0716
No log 2.7111 122 0.9710 0.0377 0.9710 0.9854
No log 2.7556 124 1.0238 0.0068 1.0238 1.0118
No log 2.8 126 1.2901 -0.0610 1.2901 1.1358
No log 2.8444 128 1.4083 -0.1211 1.4083 1.1867
No log 2.8889 130 1.1137 -0.0526 1.1137 1.0553
No log 2.9333 132 0.9132 -0.1747 0.9132 0.9556
No log 2.9778 134 0.9658 -0.0766 0.9658 0.9828
No log 3.0222 136 1.3832 -0.1207 1.3832 1.1761
No log 3.0667 138 1.6500 -0.0367 1.6500 1.2845
No log 3.1111 140 1.3660 -0.1205 1.3660 1.1688
No log 3.1556 142 1.0934 -0.0799 1.0934 1.0456
No log 3.2 144 0.9983 -0.1394 0.9983 0.9991
No log 3.2444 146 0.9682 -0.1994 0.9682 0.9840
No log 3.2889 148 1.0200 0.0831 1.0200 1.0100
No log 3.3333 150 1.3874 -0.0620 1.3874 1.1779
No log 3.3778 152 1.4977 -0.0655 1.4977 1.2238
No log 3.4222 154 1.1348 -0.0855 1.1348 1.0653
No log 3.4667 156 0.8821 -0.0287 0.8821 0.9392
No log 3.5111 158 0.8365 -0.2278 0.8365 0.9146
No log 3.5556 160 0.8966 0.0129 0.8966 0.9469
No log 3.6 162 1.0100 0.0260 1.0100 1.0050
No log 3.6444 164 1.0432 -0.0138 1.0432 1.0214
No log 3.6889 166 1.0857 -0.0409 1.0857 1.0420
No log 3.7333 168 1.2380 -0.1148 1.2380 1.1127
No log 3.7778 170 1.2348 -0.1148 1.2348 1.1112
No log 3.8222 172 1.0722 -0.1605 1.0722 1.0355
No log 3.8667 174 1.0411 -0.0812 1.0411 1.0204
No log 3.9111 176 1.1826 -0.1184 1.1826 1.0875
No log 3.9556 178 1.4610 -0.0319 1.4610 1.2087
No log 4.0 180 1.2737 -0.1196 1.2737 1.1286
No log 4.0444 182 0.9823 -0.0390 0.9823 0.9911
No log 4.0889 184 0.9664 -0.0801 0.9664 0.9831
No log 4.1333 186 1.0647 -0.0459 1.0647 1.0318
No log 4.1778 188 0.9969 -0.1259 0.9969 0.9984
No log 4.2222 190 0.9392 -0.1668 0.9392 0.9691
No log 4.2667 192 0.9222 -0.1690 0.9222 0.9603
No log 4.3111 194 0.9077 -0.1168 0.9077 0.9527
No log 4.3556 196 0.9824 -0.2511 0.9824 0.9911
No log 4.4 198 1.0798 -0.0870 1.0798 1.0392
No log 4.4444 200 1.0211 -0.1688 1.0211 1.0105
No log 4.4889 202 0.9200 -0.2219 0.9200 0.9592
No log 4.5333 204 0.8945 -0.1675 0.8945 0.9458
No log 4.5778 206 0.9463 -0.1730 0.9463 0.9728
No log 4.6222 208 1.1476 0.0537 1.1476 1.0713
No log 4.6667 210 1.3094 -0.0319 1.3094 1.1443
No log 4.7111 212 1.0968 0.0152 1.0968 1.0473
No log 4.7556 214 0.8963 -0.0228 0.8963 0.9467
No log 4.8 216 0.9317 -0.1588 0.9317 0.9652
No log 4.8444 218 0.9531 -0.1163 0.9531 0.9763
No log 4.8889 220 0.9802 -0.1140 0.9802 0.9901
No log 4.9333 222 1.1647 0.0481 1.1647 1.0792
No log 4.9778 224 1.3476 -0.0647 1.3476 1.1609
No log 5.0222 226 1.3438 -0.0647 1.3438 1.1592
No log 5.0667 228 1.1363 -0.0211 1.1363 1.0660
No log 5.1111 230 0.9138 -0.0686 0.9138 0.9559
No log 5.1556 232 0.8797 -0.0091 0.8797 0.9379
No log 5.2 234 0.8528 -0.0091 0.8528 0.9235
No log 5.2444 236 0.8975 -0.1701 0.8975 0.9473
No log 5.2889 238 0.9686 -0.1261 0.9686 0.9842
No log 5.3333 240 0.9922 -0.1676 0.9922 0.9961
No log 5.3778 242 0.9976 -0.1501 0.9976 0.9988
No log 5.4222 244 1.0122 -0.1219 1.0122 1.0061
No log 5.4667 246 1.0253 -0.2346 1.0253 1.0126
No log 5.5111 248 0.9428 -0.1939 0.9428 0.9710
No log 5.5556 250 0.9121 -0.1172 0.9121 0.9550
No log 5.6 252 0.9633 -0.0790 0.9633 0.9815
No log 5.6444 254 1.0218 -0.0852 1.0218 1.0108
No log 5.6889 256 0.9994 -0.1257 0.9994 0.9997
No log 5.7333 258 1.0007 -0.1257 1.0007 1.0004
No log 5.7778 260 0.9231 -0.0753 0.9231 0.9608
No log 5.8222 262 0.9303 -0.1233 0.9303 0.9645
No log 5.8667 264 0.9906 -0.0658 0.9906 0.9953
No log 5.9111 266 1.0737 -0.1623 1.0737 1.0362
No log 5.9556 268 1.0438 -0.1708 1.0438 1.0217
No log 6.0 270 1.0702 -0.0425 1.0702 1.0345
No log 6.0444 272 0.9991 0.0017 0.9991 0.9995
No log 6.0889 274 0.9122 -0.0766 0.9122 0.9551
No log 6.1333 276 0.9079 -0.0252 0.9079 0.9528
No log 6.1778 278 1.0981 -0.0441 1.0981 1.0479
No log 6.2222 280 1.1755 -0.0496 1.1755 1.0842
No log 6.2667 282 1.1364 -0.0832 1.1364 1.0660
No log 6.3111 284 0.9594 0.0095 0.9594 0.9795
No log 6.3556 286 0.8870 -0.0252 0.8870 0.9418
No log 6.4 288 0.9110 -0.0309 0.9110 0.9545
No log 6.4444 290 1.1059 -0.0877 1.1059 1.0516
No log 6.4889 292 1.2185 -0.0586 1.2185 1.1039
No log 6.5333 294 1.1050 -0.0182 1.1050 1.0512
No log 6.5778 296 0.8960 0.0129 0.8960 0.9466
No log 6.6222 298 0.8515 -0.0766 0.8515 0.9228
No log 6.6667 300 0.9236 0.0129 0.9236 0.9611
No log 6.7111 302 1.0960 -0.0500 1.0960 1.0469
No log 6.7556 304 1.0758 -0.0471 1.0758 1.0372
No log 6.8 306 0.9712 -0.0390 0.9712 0.9855
No log 6.8444 308 0.8442 -0.0766 0.8442 0.9188
No log 6.8889 310 0.8493 -0.0766 0.8493 0.9216
No log 6.9333 312 0.9819 -0.0390 0.9819 0.9909
No log 6.9778 314 1.2440 -0.0575 1.2440 1.1153
No log 7.0222 316 1.2166 -0.0575 1.2166 1.1030
No log 7.0667 318 1.0627 -0.0456 1.0627 1.0309
No log 7.1111 320 0.9583 -0.0495 0.9583 0.9789
No log 7.1556 322 0.9730 -0.1077 0.9730 0.9864
No log 7.2 324 0.9711 -0.0744 0.9711 0.9854
No log 7.2444 326 0.9831 -0.0970 0.9831 0.9915
No log 7.2889 328 1.0695 -0.0797 1.0695 1.0342
No log 7.3333 330 0.9915 -0.0008 0.9915 0.9958
No log 7.3778 332 0.8451 0.0159 0.8451 0.9193
No log 7.4222 334 0.8133 0.0225 0.8133 0.9018
No log 7.4667 336 0.8312 -0.0331 0.8312 0.9117
No log 7.5111 338 0.7853 -0.0711 0.7853 0.8862
No log 7.5556 340 0.7749 -0.1230 0.7749 0.8803
No log 7.6 342 0.8495 -0.0331 0.8495 0.9217
No log 7.6444 344 0.9488 -0.0801 0.9488 0.9741
No log 7.6889 346 0.9641 -0.0801 0.9641 0.9819
No log 7.7333 348 0.9717 -0.0008 0.9717 0.9857
No log 7.7778 350 0.9073 -0.0331 0.9073 0.9525
No log 7.8222 352 0.8278 0.0723 0.8278 0.9098
No log 7.8667 354 0.8244 0.0723 0.8244 0.9080
No log 7.9111 356 0.8779 0.0152 0.8779 0.9369
No log 7.9556 358 0.9241 0.0956 0.9241 0.9613
No log 8.0 360 0.9433 0.0913 0.9433 0.9712
No log 8.0444 362 1.0426 -0.0504 1.0426 1.0211
No log 8.0889 364 1.0765 -0.0518 1.0765 1.0376
No log 8.1333 366 1.0406 -0.0518 1.0406 1.0201
No log 8.1778 368 0.9153 0.0099 0.9153 0.9567
No log 8.2222 370 0.8574 0.0282 0.8574 0.9260
No log 8.2667 372 0.8583 0.0338 0.8583 0.9265
No log 8.3111 374 0.8897 0.0214 0.8897 0.9432
No log 8.3556 376 0.9842 -0.1257 0.9842 0.9921
No log 8.4 378 0.9781 -0.1257 0.9781 0.9890
No log 8.4444 380 0.9226 -0.0778 0.9226 0.9605
No log 8.4889 382 0.9197 -0.0228 0.9197 0.9590
No log 8.5333 384 0.9495 -0.0766 0.9495 0.9744
No log 8.5778 386 0.9993 -0.1257 0.9993 0.9997
No log 8.6222 388 1.0017 -0.0842 1.0017 1.0008
No log 8.6667 390 1.0461 -0.1261 1.0461 1.0228
No log 8.7111 392 0.9679 -0.0842 0.9679 0.9838
No log 8.7556 394 0.9279 -0.0766 0.9279 0.9633
No log 8.8 396 0.9443 -0.0252 0.9443 0.9717
No log 8.8444 398 0.9768 -0.0316 0.9768 0.9883
No log 8.8889 400 1.0476 -0.0391 1.0476 1.0235
No log 8.9333 402 1.1371 -0.0440 1.1371 1.0663
No log 8.9778 404 1.0808 -0.0409 1.0808 1.0396
No log 9.0222 406 1.0027 -0.0755 1.0027 1.0013
No log 9.0667 408 1.0175 -0.0778 1.0175 1.0087
No log 9.1111 410 1.0237 -0.0391 1.0237 1.0118
No log 9.1556 412 0.9919 -0.0391 0.9919 0.9959
No log 9.2 414 0.9532 -0.0274 0.9532 0.9763
No log 9.2444 416 0.9055 -0.0218 0.9055 0.9516
No log 9.2889 418 0.8658 -0.0228 0.8658 0.9305
No log 9.3333 420 0.8592 -0.0766 0.8592 0.9269
No log 9.3778 422 0.8439 -0.0753 0.8439 0.9186
No log 9.4222 424 0.8592 -0.0725 0.8592 0.9270
No log 9.4667 426 0.9461 -0.1246 0.9461 0.9727
No log 9.5111 428 1.0170 -0.1131 1.0170 1.0085
No log 9.5556 430 1.0610 -0.1088 1.0610 1.0300
No log 9.6 432 1.1586 -0.1162 1.1586 1.0764
No log 9.6444 434 1.2284 -0.0513 1.2284 1.1083
No log 9.6889 436 1.2235 -0.0877 1.2235 1.1061
No log 9.7333 438 1.0638 -0.0474 1.0638 1.0314
No log 9.7778 440 0.9141 -0.2116 0.9141 0.9561
No log 9.8222 442 0.9068 -0.2463 0.9068 0.9523
No log 9.8667 444 0.9166 -0.1211 0.9166 0.9574
No log 9.9111 446 0.8920 -0.2564 0.8920 0.9445
No log 9.9556 448 0.8754 -0.2201 0.8754 0.9356
No log 10.0 450 0.9258 0.0043 0.9258 0.9622
No log 10.0444 452 1.0316 -0.0143 1.0316 1.0157
No log 10.0889 454 1.1101 -0.0532 1.1101 1.0536
No log 10.1333 456 1.1636 -0.0885 1.1636 1.0787
No log 10.1778 458 1.0551 -0.0056 1.0551 1.0272
No log 10.2222 460 0.9770 -0.1644 0.9770 0.9884
No log 10.2667 462 0.9530 -0.1121 0.9530 0.9762
No log 10.3111 464 1.0057 -0.1509 1.0057 1.0028
No log 10.3556 466 1.0619 -0.1390 1.0619 1.0305
No log 10.4 468 1.1306 -0.0378 1.1306 1.0633
No log 10.4444 470 1.1506 -0.1224 1.1506 1.0726
No log 10.4889 472 1.0578 -0.0442 1.0578 1.0285
No log 10.5333 474 0.9183 -0.1249 0.9183 0.9583
No log 10.5778 476 0.8550 -0.0240 0.8550 0.9247
No log 10.6222 478 0.8489 -0.0753 0.8489 0.9214
No log 10.6667 480 0.8665 -0.0778 0.8665 0.9309
No log 10.7111 482 0.9333 -0.0425 0.9333 0.9661
No log 10.7556 484 0.9803 -0.0056 0.9803 0.9901
No log 10.8 486 1.0848 0.0304 1.0848 1.0415
No log 10.8444 488 1.1011 0.0304 1.1011 1.0494
No log 10.8889 490 1.0290 0.0200 1.0290 1.0144
No log 10.9333 492 1.0058 -0.0491 1.0058 1.0029
No log 10.9778 494 1.0208 -0.0630 1.0208 1.0104
No log 11.0222 496 1.0882 0.0719 1.0882 1.0431
No log 11.0667 498 1.0824 -0.0101 1.0824 1.0404
0.3428 11.1111 500 1.0190 0.0316 1.0190 1.0095
0.3428 11.1556 502 0.9418 -0.1135 0.9418 0.9705
0.3428 11.2 504 0.9130 -0.1184 0.9130 0.9555
0.3428 11.2444 506 0.9036 -0.0778 0.9036 0.9506
0.3428 11.2889 508 0.9194 -0.0790 0.9194 0.9588
0.3428 11.3333 510 0.9567 0.0456 0.9567 0.9781
0.3428 11.3778 512 0.9943 0.0016 0.9943 0.9972
0.3428 11.4222 514 0.9831 -0.0336 0.9831 0.9915
0.3428 11.4667 516 0.9544 -0.0978 0.9544 0.9769
0.3428 11.5111 518 0.9438 -0.0533 0.9438 0.9715
0.3428 11.5556 520 0.9889 -0.0336 0.9889 0.9944

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_usingWellWrittenEssays_FineTuningAraBERT_run3_AugV5_k18_task3_organization

Finetuned
(4019)
this model