ArabicNewSplits7_usingWellWrittenEssays_FineTuningAraBERT_run1_AugV5_k11_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: 2.0081
  • Qwk: 0.2590
  • Mse: 2.0081
  • Rmse: 1.4171

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 0.0417 2 6.8782 0.0111 6.8782 2.6226
No log 0.0833 4 4.2683 0.0779 4.2683 2.0660
No log 0.125 6 3.1666 -0.0111 3.1666 1.7795
No log 0.1667 8 2.5527 0.1304 2.5527 1.5977
No log 0.2083 10 1.8714 0.1695 1.8714 1.3680
No log 0.25 12 1.8445 0.2037 1.8445 1.3581
No log 0.2917 14 1.9861 0.2521 1.9861 1.4093
No log 0.3333 16 2.2188 0.1286 2.2188 1.4895
No log 0.375 18 1.9550 0.2833 1.9550 1.3982
No log 0.4167 20 1.8027 0.1296 1.8027 1.3426
No log 0.4583 22 1.7955 0.1905 1.7955 1.3400
No log 0.5 24 1.7049 0.1905 1.7049 1.3057
No log 0.5417 26 1.7401 0.1308 1.7401 1.3191
No log 0.5833 28 1.9391 0.1217 1.9391 1.3925
No log 0.625 30 1.9515 0.1695 1.9515 1.3970
No log 0.6667 32 2.0803 0.1774 2.0803 1.4423
No log 0.7083 34 1.8150 0.25 1.8150 1.3472
No log 0.75 36 1.8070 0.2459 1.8070 1.3442
No log 0.7917 38 1.5943 0.2712 1.5943 1.2627
No log 0.8333 40 1.5487 0.2712 1.5487 1.2445
No log 0.875 42 1.6893 0.3415 1.6893 1.2997
No log 0.9167 44 1.4699 0.3390 1.4699 1.2124
No log 0.9583 46 1.3397 0.2982 1.3397 1.1574
No log 1.0 48 1.2942 0.3158 1.2942 1.1376
No log 1.0417 50 1.3401 0.3761 1.3401 1.1576
No log 1.0833 52 1.4260 0.3529 1.4260 1.1941
No log 1.125 54 1.3928 0.3667 1.3928 1.1802
No log 1.1667 56 1.2095 0.4068 1.2095 1.0998
No log 1.2083 58 1.1794 0.5528 1.1794 1.0860
No log 1.25 60 1.4204 0.4762 1.4204 1.1918
No log 1.2917 62 1.3777 0.5 1.3777 1.1737
No log 1.3333 64 1.2612 0.5455 1.2612 1.1230
No log 1.375 66 1.4437 0.4060 1.4437 1.2016
No log 1.4167 68 1.4453 0.4328 1.4453 1.2022
No log 1.4583 70 1.2427 0.5692 1.2427 1.1148
No log 1.5 72 1.2194 0.4921 1.2194 1.1043
No log 1.5417 74 1.2507 0.4516 1.2507 1.1184
No log 1.5833 76 1.5001 0.4031 1.5001 1.2248
No log 1.625 78 1.6823 0.3607 1.6823 1.2970
No log 1.6667 80 1.6261 0.3577 1.6261 1.2752
No log 1.7083 82 1.3836 0.4496 1.3836 1.1763
No log 1.75 84 1.1525 0.5397 1.1525 1.0735
No log 1.7917 86 1.1504 0.5354 1.1504 1.0726
No log 1.8333 88 1.3371 0.4615 1.3371 1.1563
No log 1.875 90 1.5797 0.3704 1.5797 1.2569
No log 1.9167 92 2.0375 0.2411 2.0375 1.4274
No log 1.9583 94 1.8068 0.3333 1.8068 1.3442
No log 2.0 96 1.4492 0.4627 1.4492 1.2038
No log 2.0417 98 1.3550 0.5333 1.3550 1.1640
No log 2.0833 100 1.5285 0.4030 1.5285 1.2363
No log 2.125 102 2.2039 0.0758 2.2039 1.4846
No log 2.1667 104 2.2578 0.0458 2.2578 1.5026
No log 2.2083 106 1.7935 0.2222 1.7935 1.3392
No log 2.25 108 1.4010 0.4923 1.4010 1.1836
No log 2.2917 110 1.2913 0.4567 1.2913 1.1364
No log 2.3333 112 1.3219 0.4286 1.3219 1.1497
No log 2.375 114 1.5644 0.4308 1.5644 1.2508
No log 2.4167 116 2.0632 0.1286 2.0632 1.4364
No log 2.4583 118 2.0462 0.1594 2.0462 1.4304
No log 2.5 120 1.7074 0.3281 1.7074 1.3067
No log 2.5417 122 1.3788 0.4098 1.3788 1.1742
No log 2.5833 124 1.3360 0.4390 1.3360 1.1559
No log 2.625 126 1.4122 0.4516 1.4122 1.1883
No log 2.6667 128 1.7159 0.3411 1.7159 1.3099
No log 2.7083 130 2.2597 0.0296 2.2597 1.5032
No log 2.75 132 2.5980 0.0 2.5980 1.6118
No log 2.7917 134 2.5776 0.0423 2.5776 1.6055
No log 2.8333 136 2.2484 0.1781 2.2484 1.4995
No log 2.875 138 2.0508 0.2041 2.0508 1.4321
No log 2.9167 140 1.7930 0.2797 1.7930 1.3390
No log 2.9583 142 1.8884 0.3056 1.8884 1.3742
No log 3.0 144 1.8913 0.2603 1.8913 1.3753
No log 3.0417 146 1.8622 0.2345 1.8622 1.3646
No log 3.0833 148 2.1176 0.1389 2.1176 1.4552
No log 3.125 150 2.2401 0.1389 2.2401 1.4967
No log 3.1667 152 2.2036 0.1389 2.2036 1.4845
No log 3.2083 154 1.9841 0.2754 1.9841 1.4086
No log 3.25 156 1.9078 0.2754 1.9078 1.3812
No log 3.2917 158 1.5898 0.3824 1.5898 1.2609
No log 3.3333 160 1.3972 0.5039 1.3972 1.1820
No log 3.375 162 1.3665 0.4921 1.3665 1.1690
No log 3.4167 164 1.5211 0.4478 1.5211 1.2333
No log 3.4583 166 1.7786 0.3623 1.7786 1.3337
No log 3.5 168 2.1032 0.2254 2.1032 1.4502
No log 3.5417 170 1.9656 0.2254 1.9656 1.4020
No log 3.5833 172 1.9148 0.2857 1.9148 1.3838
No log 3.625 174 1.7690 0.3188 1.7690 1.3300
No log 3.6667 176 1.5341 0.3824 1.5341 1.2386
No log 3.7083 178 1.4392 0.4148 1.4392 1.1997
No log 3.75 180 1.7060 0.3333 1.7060 1.3061
No log 3.7917 182 2.1066 0.2446 2.1066 1.4514
No log 3.8333 184 2.2605 0.1528 2.2605 1.5035
No log 3.875 186 2.0537 0.2920 2.0537 1.4331
No log 3.9167 188 1.6346 0.3259 1.6346 1.2785
No log 3.9583 190 1.5558 0.3433 1.5558 1.2473
No log 4.0 192 1.7002 0.3504 1.7002 1.3039
No log 4.0417 194 2.0149 0.2754 2.0149 1.4195
No log 4.0833 196 2.0663 0.2286 2.0663 1.4375
No log 4.125 198 2.0003 0.2446 2.0003 1.4143
No log 4.1667 200 1.7255 0.3235 1.7255 1.3136
No log 4.2083 202 1.6371 0.3308 1.6371 1.2795
No log 4.25 204 1.6631 0.3704 1.6631 1.2896
No log 4.2917 206 1.7419 0.3676 1.7419 1.3198
No log 4.3333 208 2.0288 0.2254 2.0288 1.4244
No log 4.375 210 2.3029 0.1389 2.3029 1.5175
No log 4.4167 212 2.3431 0.0714 2.3431 1.5307
No log 4.4583 214 2.2253 0.1714 2.2253 1.4918
No log 4.5 216 2.0191 0.2517 2.0191 1.4209
No log 4.5417 218 1.9956 0.2394 1.9956 1.4127
No log 4.5833 220 2.1416 0.2128 2.1416 1.4634
No log 4.625 222 2.0910 0.1857 2.0910 1.4460
No log 4.6667 224 1.8591 0.25 1.8591 1.3635
No log 4.7083 226 1.6871 0.3088 1.6871 1.2989
No log 4.75 228 1.7013 0.2794 1.7013 1.3044
No log 4.7917 230 1.9177 0.2429 1.9177 1.3848
No log 4.8333 232 1.9616 0.2429 1.9616 1.4006
No log 4.875 234 1.8570 0.2446 1.8570 1.3627
No log 4.9167 236 1.7455 0.2754 1.7455 1.3212
No log 4.9583 238 1.6539 0.3358 1.6539 1.2860
No log 5.0 240 1.8352 0.2553 1.8352 1.3547
No log 5.0417 242 2.3263 0.1389 2.3263 1.5252
No log 5.0833 244 2.4905 0.1241 2.4905 1.5781
No log 5.125 246 2.3739 0.1119 2.3739 1.5407
No log 5.1667 248 2.0125 0.2411 2.0125 1.4186
No log 5.2083 250 1.6631 0.3788 1.6631 1.2896
No log 5.25 252 1.6270 0.3788 1.6270 1.2755
No log 5.2917 254 1.7977 0.3582 1.7977 1.3408
No log 5.3333 256 1.9595 0.2647 1.9595 1.3998
No log 5.375 258 1.8997 0.2815 1.8997 1.3783
No log 5.4167 260 1.7375 0.3796 1.7375 1.3181
No log 5.4583 262 1.6171 0.4179 1.6171 1.2717
No log 5.5 264 1.5984 0.4179 1.5984 1.2643
No log 5.5417 266 1.7553 0.3676 1.7553 1.3249
No log 5.5833 268 1.8419 0.2446 1.8419 1.3572
No log 5.625 270 1.8366 0.2464 1.8366 1.3552
No log 5.6667 272 1.6818 0.3852 1.6818 1.2969
No log 5.7083 274 1.6596 0.3852 1.6596 1.2883
No log 5.75 276 1.8432 0.2302 1.8432 1.3577
No log 5.7917 278 2.1208 0.1690 2.1208 1.4563
No log 5.8333 280 2.0931 0.1986 2.0931 1.4468
No log 5.875 282 1.7984 0.2628 1.7984 1.3411
No log 5.9167 284 1.6772 0.3609 1.6772 1.2951
No log 5.9583 286 1.7118 0.3284 1.7118 1.3083
No log 6.0 288 1.7653 0.2920 1.7653 1.3287
No log 6.0417 290 1.8702 0.2676 1.8702 1.3675
No log 6.0833 292 1.8110 0.2676 1.8110 1.3457
No log 6.125 294 1.6856 0.3407 1.6856 1.2983
No log 6.1667 296 1.6965 0.3407 1.6965 1.3025
No log 6.2083 298 1.8711 0.2553 1.8711 1.3679
No log 6.25 300 2.0730 0.2553 2.0730 1.4398
No log 6.2917 302 2.1792 0.2553 2.1792 1.4762
No log 6.3333 304 2.1241 0.2553 2.1241 1.4574
No log 6.375 306 1.8648 0.2676 1.8648 1.3656
No log 6.4167 308 1.6589 0.3043 1.6589 1.2880
No log 6.4583 310 1.6378 0.3066 1.6378 1.2798
No log 6.5 312 1.8470 0.2553 1.8470 1.3590
No log 6.5417 314 1.8116 0.2714 1.8116 1.3459
No log 6.5833 316 1.6563 0.2963 1.6563 1.2870
No log 6.625 318 1.4953 0.4427 1.4953 1.2228
No log 6.6667 320 1.5305 0.4511 1.5305 1.2371
No log 6.7083 322 1.5497 0.4 1.5497 1.2449
No log 6.75 324 1.7525 0.3022 1.7525 1.3238
No log 6.7917 326 1.9813 0.2553 1.9813 1.4076
No log 6.8333 328 1.9181 0.2553 1.9181 1.3850
No log 6.875 330 1.6309 0.3768 1.6309 1.2771
No log 6.9167 332 1.5872 0.4 1.5872 1.2599
No log 6.9583 334 1.6205 0.3704 1.6205 1.2730
No log 7.0 336 1.8020 0.3504 1.8020 1.3424
No log 7.0417 338 2.0009 0.2286 2.0009 1.4145
No log 7.0833 340 2.2687 0.1268 2.2687 1.5062
No log 7.125 342 2.3143 0.0704 2.3143 1.5213
No log 7.1667 344 2.1864 0.1986 2.1864 1.4786
No log 7.2083 346 1.9356 0.2676 1.9356 1.3912
No log 7.25 348 1.7056 0.3333 1.7056 1.3060
No log 7.2917 350 1.5756 0.3913 1.5756 1.2552
No log 7.3333 352 1.6071 0.3571 1.6071 1.2677
No log 7.375 354 1.8198 0.3121 1.8198 1.3490
No log 7.4167 356 2.1589 0.1986 2.1589 1.4693
No log 7.4583 358 2.4779 0.1528 2.4779 1.5741
No log 7.5 360 2.5344 0.1528 2.5344 1.5920
No log 7.5417 362 2.3021 0.1986 2.3021 1.5173
No log 7.5833 364 1.8516 0.2734 1.8516 1.3607
No log 7.625 366 1.5204 0.3910 1.5204 1.2330
No log 7.6667 368 1.4220 0.3939 1.4220 1.1925
No log 7.7083 370 1.4939 0.3881 1.4939 1.2222
No log 7.75 372 1.7198 0.3333 1.7198 1.3114
No log 7.7917 374 2.0420 0.2857 2.0420 1.4290
No log 7.8333 376 2.2099 0.1986 2.2099 1.4866
No log 7.875 378 2.1114 0.2286 2.1114 1.4531
No log 7.9167 380 1.8587 0.3235 1.8587 1.3633
No log 7.9583 382 1.5607 0.3609 1.5607 1.2493
No log 8.0 384 1.5160 0.3664 1.5160 1.2313
No log 8.0417 386 1.6044 0.3485 1.6044 1.2667
No log 8.0833 388 1.7547 0.3066 1.7547 1.3247
No log 8.125 390 1.9537 0.2286 1.9537 1.3978
No log 8.1667 392 1.9817 0.2286 1.9817 1.4077
No log 8.2083 394 1.9253 0.2158 1.9253 1.3875
No log 8.25 396 1.8662 0.2286 1.8662 1.3661
No log 8.2917 398 1.7160 0.3358 1.7160 1.3100
No log 8.3333 400 1.6668 0.3650 1.6668 1.2911
No log 8.375 402 1.7074 0.3571 1.7074 1.3067
No log 8.4167 404 1.8220 0.3143 1.8220 1.3498
No log 8.4583 406 1.9903 0.2286 1.9903 1.4108
No log 8.5 408 1.9674 0.2286 1.9674 1.4026
No log 8.5417 410 1.8185 0.2319 1.8185 1.3485
No log 8.5833 412 1.6627 0.3259 1.6627 1.2895
No log 8.625 414 1.6336 0.3529 1.6336 1.2781
No log 8.6667 416 1.7730 0.3022 1.7730 1.3315
No log 8.7083 418 1.8421 0.2857 1.8421 1.3572
No log 8.75 420 1.9121 0.2286 1.9121 1.3828
No log 8.7917 422 1.8428 0.2286 1.8428 1.3575
No log 8.8333 424 1.6690 0.3134 1.6690 1.2919
No log 8.875 426 1.6062 0.3582 1.6062 1.2674
No log 8.9167 428 1.6154 0.3556 1.6154 1.2710
No log 8.9583 430 1.5578 0.3556 1.5578 1.2481
No log 9.0 432 1.6153 0.3529 1.6153 1.2710
No log 9.0417 434 1.7101 0.3333 1.7101 1.3077
No log 9.0833 436 1.9060 0.2837 1.9060 1.3806
No log 9.125 438 1.9583 0.2837 1.9583 1.3994
No log 9.1667 440 1.9172 0.2837 1.9172 1.3846
No log 9.2083 442 1.8445 0.2837 1.8445 1.3581
No log 9.25 444 1.7346 0.3529 1.7346 1.3170
No log 9.2917 446 1.5688 0.3817 1.5688 1.2525
No log 9.3333 448 1.5301 0.3817 1.5301 1.2370
No log 9.375 450 1.6345 0.3881 1.6345 1.2785
No log 9.4167 452 1.8171 0.3165 1.8171 1.3480
No log 9.4583 454 1.8873 0.3000 1.8873 1.3738
No log 9.5 456 1.9228 0.2695 1.9228 1.3867
No log 9.5417 458 1.8426 0.3478 1.8426 1.3574
No log 9.5833 460 1.7265 0.3796 1.7265 1.3140
No log 9.625 462 1.7076 0.3796 1.7076 1.3068
No log 9.6667 464 1.6803 0.3852 1.6803 1.2963
No log 9.7083 466 1.6995 0.3582 1.6995 1.3036
No log 9.75 468 1.6593 0.3731 1.6593 1.2881
No log 9.7917 470 1.6469 0.3971 1.6469 1.2833
No log 9.8333 472 1.6478 0.3971 1.6478 1.2837
No log 9.875 474 1.8020 0.3504 1.8020 1.3424
No log 9.9167 476 1.9683 0.3022 1.9683 1.4030
No log 9.9583 478 2.0652 0.2553 2.0652 1.4371
No log 10.0 480 1.9597 0.2754 1.9597 1.3999
No log 10.0417 482 1.7339 0.3358 1.7339 1.3168
No log 10.0833 484 1.5442 0.4328 1.5442 1.2426
No log 10.125 486 1.5042 0.4697 1.5042 1.2264
No log 10.1667 488 1.5468 0.4328 1.5468 1.2437
No log 10.2083 490 1.6718 0.3453 1.6718 1.2930
No log 10.25 492 1.8001 0.3143 1.8001 1.3417
No log 10.2917 494 1.8559 0.3143 1.8559 1.3623
No log 10.3333 496 1.8125 0.3143 1.8125 1.3463
No log 10.375 498 1.6890 0.3478 1.6890 1.2996
0.4146 10.4167 500 1.4528 0.3846 1.4528 1.2053
0.4146 10.4583 502 1.3753 0.4961 1.3753 1.1727
0.4146 10.5 504 1.4398 0.4296 1.4398 1.1999
0.4146 10.5417 506 1.6778 0.3741 1.6778 1.2953
0.4146 10.5833 508 1.7527 0.3358 1.7527 1.3239
0.4146 10.625 510 1.6043 0.3478 1.6043 1.2666
0.4146 10.6667 512 1.3951 0.4060 1.3951 1.1811
0.4146 10.7083 514 1.2983 0.4640 1.2983 1.1394
0.4146 10.75 516 1.3396 0.4444 1.3396 1.1574
0.4146 10.7917 518 1.3504 0.4688 1.3504 1.1621
0.4146 10.8333 520 1.4217 0.4060 1.4217 1.1924
0.4146 10.875 522 1.6307 0.3358 1.6307 1.2770
0.4146 10.9167 524 1.8116 0.3188 1.8116 1.3460
0.4146 10.9583 526 1.9095 0.3188 1.9095 1.3818
0.4146 11.0 528 1.9715 0.2754 1.9715 1.4041
0.4146 11.0417 530 2.0081 0.2590 2.0081 1.4171

Framework versions

  • Transformers 4.44.2
  • Pytorch 2.4.0+cu118
  • Datasets 2.21.0
  • Tokenizers 0.19.1
Downloads last month
3
Safetensors
Model size
135M params
Tensor type
F32
·
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.

Model tree for MayBashendy/ArabicNewSplits7_usingWellWrittenEssays_FineTuningAraBERT_run1_AugV5_k11_task1_organization

Finetuned
(4222)
this model