ArabicNewSplits6_FineTuningAraBERT_run3_AugV5_k12_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: 0.6070
  • Qwk: 0.7335
  • Mse: 0.6070
  • Rmse: 0.7791

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: 10

Training results

Training Loss Epoch Step Validation Loss Qwk Mse Rmse
No log 0.0328 2 5.2134 -0.0306 5.2134 2.2833
No log 0.0656 4 3.1498 0.0940 3.1498 1.7748
No log 0.0984 6 1.9114 0.1210 1.9114 1.3825
No log 0.1311 8 1.6665 0.0605 1.6665 1.2909
No log 0.1639 10 1.4419 0.1104 1.4419 1.2008
No log 0.1967 12 1.2237 0.2487 1.2237 1.1062
No log 0.2295 14 1.3435 0.0945 1.3435 1.1591
No log 0.2623 16 1.6774 0.0523 1.6774 1.2952
No log 0.2951 18 1.9159 0.1250 1.9159 1.3842
No log 0.3279 20 1.9283 0.1250 1.9283 1.3886
No log 0.3607 22 1.5927 0.1379 1.5927 1.2620
No log 0.3934 24 1.1752 0.3134 1.1752 1.0841
No log 0.4262 26 1.1396 0.3321 1.1396 1.0675
No log 0.4590 28 1.2030 0.2367 1.2030 1.0968
No log 0.4918 30 0.9481 0.4387 0.9481 0.9737
No log 0.5246 32 1.0975 0.4235 1.0975 1.0476
No log 0.5574 34 1.7617 0.2812 1.7617 1.3273
No log 0.5902 36 2.6550 0.1329 2.6550 1.6294
No log 0.6230 38 2.9405 0.1059 2.9405 1.7148
No log 0.6557 40 2.4160 0.2270 2.4160 1.5543
No log 0.6885 42 1.5617 0.3299 1.5617 1.2497
No log 0.7213 44 1.0758 0.3827 1.0758 1.0372
No log 0.7541 46 0.8890 0.4572 0.8890 0.9429
No log 0.7869 48 0.8598 0.4621 0.8598 0.9273
No log 0.8197 50 1.1350 0.3080 1.1350 1.0654
No log 0.8525 52 1.3630 0.1067 1.3630 1.1675
No log 0.8852 54 1.4218 0.1522 1.4218 1.1924
No log 0.9180 56 1.4854 0.2259 1.4854 1.2188
No log 0.9508 58 1.4824 0.2434 1.4824 1.2175
No log 0.9836 60 1.3938 0.2350 1.3938 1.1806
No log 1.0164 62 1.3805 0.2856 1.3805 1.1750
No log 1.0492 64 1.3348 0.3022 1.3348 1.1554
No log 1.0820 66 1.3288 0.2839 1.3288 1.1527
No log 1.1148 68 1.4295 0.2622 1.4295 1.1956
No log 1.1475 70 1.3477 0.3098 1.3477 1.1609
No log 1.1803 72 1.4586 0.3153 1.4586 1.2077
No log 1.2131 74 1.6516 0.2876 1.6516 1.2851
No log 1.2459 76 1.6305 0.3186 1.6305 1.2769
No log 1.2787 78 1.6497 0.3057 1.6497 1.2844
No log 1.3115 80 1.4542 0.3135 1.4542 1.2059
No log 1.3443 82 0.9978 0.5655 0.9978 0.9989
No log 1.3770 84 0.7524 0.5965 0.7524 0.8674
No log 1.4098 86 0.8143 0.6101 0.8143 0.9024
No log 1.4426 88 0.9788 0.5234 0.9788 0.9893
No log 1.4754 90 1.0976 0.4660 1.0976 1.0476
No log 1.5082 92 1.2115 0.4397 1.2115 1.1007
No log 1.5410 94 1.0488 0.4723 1.0488 1.0241
No log 1.5738 96 0.7399 0.6085 0.7399 0.8602
No log 1.6066 98 0.6393 0.6706 0.6393 0.7996
No log 1.6393 100 0.6657 0.6781 0.6657 0.8159
No log 1.6721 102 0.6586 0.6993 0.6586 0.8116
No log 1.7049 104 0.6410 0.6825 0.6410 0.8006
No log 1.7377 106 0.7584 0.6282 0.7584 0.8709
No log 1.7705 108 1.0918 0.4984 1.0918 1.0449
No log 1.8033 110 1.2319 0.4833 1.2319 1.1099
No log 1.8361 112 1.1119 0.5351 1.1119 1.0544
No log 1.8689 114 0.9832 0.5543 0.9832 0.9915
No log 1.9016 116 0.8389 0.6021 0.8389 0.9159
No log 1.9344 118 0.7358 0.6487 0.7358 0.8578
No log 1.9672 120 0.6681 0.6670 0.6681 0.8174
No log 2.0 122 0.6370 0.7185 0.6370 0.7981
No log 2.0328 124 0.6713 0.6830 0.6713 0.8193
No log 2.0656 126 0.6180 0.7159 0.6180 0.7861
No log 2.0984 128 0.5795 0.6916 0.5795 0.7613
No log 2.1311 130 0.7213 0.6663 0.7213 0.8493
No log 2.1639 132 0.8104 0.5903 0.8104 0.9002
No log 2.1967 134 0.7839 0.6546 0.7839 0.8854
No log 2.2295 136 0.6531 0.7221 0.6531 0.8082
No log 2.2623 138 0.5922 0.7055 0.5922 0.7696
No log 2.2951 140 0.6756 0.6659 0.6756 0.8219
No log 2.3279 142 0.7831 0.6252 0.7831 0.8849
No log 2.3607 144 0.8516 0.5740 0.8516 0.9228
No log 2.3934 146 0.8060 0.6400 0.8060 0.8978
No log 2.4262 148 0.7539 0.6510 0.7539 0.8683
No log 2.4590 150 0.7938 0.6452 0.7938 0.8909
No log 2.4918 152 0.8378 0.6245 0.8378 0.9153
No log 2.5246 154 0.9770 0.5594 0.9770 0.9884
No log 2.5574 156 1.1699 0.4996 1.1699 1.0816
No log 2.5902 158 1.3245 0.4640 1.3245 1.1509
No log 2.6230 160 1.4237 0.4674 1.4237 1.1932
No log 2.6557 162 1.1821 0.5088 1.1821 1.0873
No log 2.6885 164 0.8428 0.6221 0.8428 0.9181
No log 2.7213 166 0.6899 0.7004 0.6899 0.8306
No log 2.7541 168 0.7075 0.6841 0.7075 0.8411
No log 2.7869 170 0.7012 0.6804 0.7012 0.8373
No log 2.8197 172 0.6557 0.7195 0.6557 0.8098
No log 2.8525 174 0.6463 0.7138 0.6463 0.8039
No log 2.8852 176 0.6794 0.6812 0.6794 0.8243
No log 2.9180 178 0.6906 0.6730 0.6906 0.8310
No log 2.9508 180 0.6544 0.6966 0.6544 0.8090
No log 2.9836 182 0.6316 0.7107 0.6316 0.7947
No log 3.0164 184 0.6356 0.7147 0.6356 0.7973
No log 3.0492 186 0.6408 0.7276 0.6408 0.8005
No log 3.0820 188 0.6502 0.7231 0.6502 0.8064
No log 3.1148 190 0.6891 0.6966 0.6891 0.8301
No log 3.1475 192 0.7062 0.6863 0.7062 0.8404
No log 3.1803 194 0.6907 0.7084 0.6907 0.8311
No log 3.2131 196 0.6973 0.7215 0.6973 0.8351
No log 3.2459 198 0.6936 0.7215 0.6936 0.8328
No log 3.2787 200 0.6846 0.7136 0.6846 0.8274
No log 3.3115 202 0.6946 0.7005 0.6946 0.8334
No log 3.3443 204 0.7248 0.6693 0.7248 0.8514
No log 3.3770 206 0.7635 0.6590 0.7635 0.8738
No log 3.4098 208 0.7346 0.6323 0.7346 0.8571
No log 3.4426 210 0.6734 0.6894 0.6734 0.8206
No log 3.4754 212 0.6995 0.6434 0.6995 0.8364
No log 3.5082 214 0.7833 0.6325 0.7833 0.8850
No log 3.5410 216 0.7672 0.6161 0.7672 0.8759
No log 3.5738 218 0.6942 0.6382 0.6942 0.8332
No log 3.6066 220 0.6684 0.7197 0.6684 0.8176
No log 3.6393 222 0.7602 0.6446 0.7602 0.8719
No log 3.6721 224 0.8394 0.5941 0.8394 0.9162
No log 3.7049 226 0.8822 0.5998 0.8822 0.9393
No log 3.7377 228 0.8064 0.6406 0.8064 0.8980
No log 3.7705 230 0.7191 0.6864 0.7191 0.8480
No log 3.8033 232 0.6590 0.7138 0.6590 0.8118
No log 3.8361 234 0.6302 0.7181 0.6302 0.7939
No log 3.8689 236 0.6156 0.7092 0.6156 0.7846
No log 3.9016 238 0.5988 0.7211 0.5988 0.7738
No log 3.9344 240 0.5941 0.7125 0.5941 0.7708
No log 3.9672 242 0.6120 0.7165 0.6120 0.7823
No log 4.0 244 0.5952 0.7277 0.5952 0.7715
No log 4.0328 246 0.5695 0.7422 0.5695 0.7546
No log 4.0656 248 0.6042 0.7040 0.6042 0.7773
No log 4.0984 250 0.7180 0.6636 0.7180 0.8473
No log 4.1311 252 0.7182 0.6704 0.7182 0.8475
No log 4.1639 254 0.6336 0.7178 0.6336 0.7960
No log 4.1967 256 0.5975 0.7562 0.5975 0.7730
No log 4.2295 258 0.6585 0.7056 0.6585 0.8115
No log 4.2623 260 0.7407 0.7033 0.7407 0.8606
No log 4.2951 262 0.8702 0.6264 0.8702 0.9329
No log 4.3279 264 0.8833 0.6123 0.8833 0.9398
No log 4.3607 266 0.8313 0.6149 0.8313 0.9117
No log 4.3934 268 0.7279 0.7181 0.7279 0.8532
No log 4.4262 270 0.6492 0.7548 0.6492 0.8057
No log 4.4590 272 0.6204 0.7325 0.6204 0.7876
No log 4.4918 274 0.6140 0.7336 0.6140 0.7836
No log 4.5246 276 0.6230 0.7477 0.6230 0.7893
No log 4.5574 278 0.6467 0.7262 0.6467 0.8042
No log 4.5902 280 0.6216 0.7443 0.6216 0.7884
No log 4.6230 282 0.5835 0.7482 0.5835 0.7639
No log 4.6557 284 0.5829 0.7340 0.5829 0.7635
No log 4.6885 286 0.5832 0.7363 0.5832 0.7637
No log 4.7213 288 0.5771 0.7412 0.5771 0.7597
No log 4.7541 290 0.5730 0.7318 0.5730 0.7570
No log 4.7869 292 0.5863 0.7153 0.5863 0.7657
No log 4.8197 294 0.6147 0.6832 0.6147 0.7840
No log 4.8525 296 0.6336 0.6730 0.6336 0.7960
No log 4.8852 298 0.6014 0.6558 0.6014 0.7755
No log 4.9180 300 0.5783 0.6820 0.5783 0.7605
No log 4.9508 302 0.5770 0.6820 0.5770 0.7596
No log 4.9836 304 0.5744 0.6873 0.5744 0.7579
No log 5.0164 306 0.5659 0.6897 0.5659 0.7523
No log 5.0492 308 0.5585 0.6861 0.5585 0.7474
No log 5.0820 310 0.5477 0.7069 0.5477 0.7401
No log 5.1148 312 0.5451 0.7439 0.5451 0.7383
No log 5.1475 314 0.5570 0.7474 0.5570 0.7463
No log 5.1803 316 0.5608 0.7443 0.5608 0.7489
No log 5.2131 318 0.5709 0.7301 0.5709 0.7556
No log 5.2459 320 0.5872 0.7366 0.5872 0.7663
No log 5.2787 322 0.6010 0.7404 0.6010 0.7752
No log 5.3115 324 0.5944 0.7491 0.5944 0.7710
No log 5.3443 326 0.5896 0.7176 0.5896 0.7679
No log 5.3770 328 0.5844 0.7403 0.5844 0.7645
No log 5.4098 330 0.5831 0.7365 0.5831 0.7636
No log 5.4426 332 0.5802 0.7363 0.5802 0.7617
No log 5.4754 334 0.6075 0.7256 0.6075 0.7794
No log 5.5082 336 0.6189 0.7273 0.6189 0.7867
No log 5.5410 338 0.5985 0.7319 0.5985 0.7736
No log 5.5738 340 0.5729 0.7125 0.5729 0.7569
No log 5.6066 342 0.6038 0.6948 0.6038 0.7770
No log 5.6393 344 0.6344 0.6633 0.6344 0.7965
No log 5.6721 346 0.6126 0.7040 0.6126 0.7827
No log 5.7049 348 0.5862 0.7256 0.5862 0.7656
No log 5.7377 350 0.6210 0.7384 0.6210 0.7881
No log 5.7705 352 0.6667 0.7199 0.6667 0.8165
No log 5.8033 354 0.6473 0.7373 0.6473 0.8046
No log 5.8361 356 0.6035 0.7346 0.6035 0.7769
No log 5.8689 358 0.5813 0.7039 0.5813 0.7624
No log 5.9016 360 0.5782 0.6717 0.5782 0.7604
No log 5.9344 362 0.5777 0.6994 0.5777 0.7600
No log 5.9672 364 0.5805 0.7148 0.5805 0.7619
No log 6.0 366 0.5916 0.7336 0.5916 0.7692
No log 6.0328 368 0.5823 0.7365 0.5823 0.7631
No log 6.0656 370 0.5670 0.7174 0.5670 0.7530
No log 6.0984 372 0.5646 0.7318 0.5646 0.7514
No log 6.1311 374 0.5643 0.7014 0.5643 0.7512
No log 6.1639 376 0.5621 0.7167 0.5621 0.7497
No log 6.1967 378 0.5562 0.7012 0.5562 0.7458
No log 6.2295 380 0.5592 0.7115 0.5592 0.7478
No log 6.2623 382 0.5758 0.7533 0.5758 0.7588
No log 6.2951 384 0.5853 0.7492 0.5853 0.7650
No log 6.3279 386 0.5738 0.7400 0.5738 0.7575
No log 6.3607 388 0.5676 0.7526 0.5676 0.7534
No log 6.3934 390 0.5666 0.7526 0.5666 0.7527
No log 6.4262 392 0.5667 0.7526 0.5667 0.7528
No log 6.4590 394 0.5702 0.7439 0.5702 0.7551
No log 6.4918 396 0.5683 0.7506 0.5683 0.7539
No log 6.5246 398 0.5677 0.7529 0.5677 0.7535
No log 6.5574 400 0.5574 0.7161 0.5574 0.7466
No log 6.5902 402 0.5536 0.7381 0.5536 0.7440
No log 6.6230 404 0.5548 0.7399 0.5548 0.7448
No log 6.6557 406 0.5563 0.7188 0.5563 0.7458
No log 6.6885 408 0.5608 0.7327 0.5608 0.7488
No log 6.7213 410 0.5758 0.7557 0.5758 0.7588
No log 6.7541 412 0.5921 0.7450 0.5921 0.7695
No log 6.7869 414 0.6021 0.7403 0.6021 0.7759
No log 6.8197 416 0.6030 0.7711 0.6030 0.7765
No log 6.8525 418 0.5982 0.7560 0.5982 0.7734
No log 6.8852 420 0.6153 0.7553 0.6153 0.7844
No log 6.9180 422 0.6318 0.7526 0.6318 0.7949
No log 6.9508 424 0.6393 0.7538 0.6393 0.7996
No log 6.9836 426 0.6185 0.7532 0.6185 0.7864
No log 7.0164 428 0.5967 0.7462 0.5967 0.7725
No log 7.0492 430 0.5694 0.7139 0.5694 0.7546
No log 7.0820 432 0.5606 0.7172 0.5606 0.7487
No log 7.1148 434 0.5641 0.7305 0.5641 0.7511
No log 7.1475 436 0.5689 0.7239 0.5689 0.7543
No log 7.1803 438 0.5748 0.7011 0.5748 0.7581
No log 7.2131 440 0.5739 0.6947 0.5739 0.7576
No log 7.2459 442 0.5713 0.7176 0.5713 0.7559
No log 7.2787 444 0.5725 0.7127 0.5725 0.7566
No log 7.3115 446 0.5786 0.7183 0.5786 0.7607
No log 7.3443 448 0.5843 0.7131 0.5843 0.7644
No log 7.3770 450 0.5910 0.7255 0.5910 0.7688
No log 7.4098 452 0.5913 0.7306 0.5913 0.7689
No log 7.4426 454 0.5900 0.7318 0.5900 0.7681
No log 7.4754 456 0.5890 0.7443 0.5890 0.7675
No log 7.5082 458 0.5846 0.7501 0.5846 0.7646
No log 7.5410 460 0.5785 0.7473 0.5785 0.7606
No log 7.5738 462 0.5784 0.7456 0.5784 0.7606
No log 7.6066 464 0.5855 0.7480 0.5855 0.7652
No log 7.6393 466 0.5804 0.7503 0.5804 0.7618
No log 7.6721 468 0.5687 0.7409 0.5687 0.7541
No log 7.7049 470 0.5571 0.7333 0.5571 0.7464
No log 7.7377 472 0.5521 0.7392 0.5521 0.7430
No log 7.7705 474 0.5541 0.7095 0.5541 0.7444
No log 7.8033 476 0.5581 0.6974 0.5581 0.7471
No log 7.8361 478 0.5570 0.6974 0.5570 0.7463
No log 7.8689 480 0.5523 0.7318 0.5523 0.7432
No log 7.9016 482 0.5548 0.7363 0.5548 0.7448
No log 7.9344 484 0.5756 0.7625 0.5756 0.7587
No log 7.9672 486 0.6226 0.7373 0.6226 0.7891
No log 8.0 488 0.6734 0.7192 0.6734 0.8206
No log 8.0328 490 0.7118 0.6975 0.7118 0.8437
No log 8.0656 492 0.7287 0.6921 0.7287 0.8536
No log 8.0984 494 0.7150 0.6993 0.7150 0.8456
No log 8.1311 496 0.6904 0.7058 0.6904 0.8309
No log 8.1639 498 0.6554 0.7340 0.6554 0.8096
0.4705 8.1967 500 0.6304 0.7612 0.6304 0.7940
0.4705 8.2295 502 0.6210 0.7612 0.6210 0.7880
0.4705 8.2623 504 0.6140 0.7635 0.6140 0.7836
0.4705 8.2951 506 0.6138 0.7593 0.6138 0.7834
0.4705 8.3279 508 0.6223 0.7525 0.6223 0.7889
0.4705 8.3607 510 0.6349 0.7493 0.6349 0.7968
0.4705 8.3934 512 0.6330 0.7535 0.6330 0.7956
0.4705 8.4262 514 0.6235 0.7535 0.6235 0.7896
0.4705 8.4590 516 0.6103 0.7520 0.6103 0.7812
0.4705 8.4918 518 0.6001 0.7424 0.6001 0.7746
0.4705 8.5246 520 0.5857 0.7474 0.5857 0.7653
0.4705 8.5574 522 0.5725 0.7694 0.5725 0.7566
0.4705 8.5902 524 0.5661 0.7617 0.5661 0.7524
0.4705 8.6230 526 0.5657 0.7617 0.5657 0.7521
0.4705 8.6557 528 0.5664 0.7617 0.5664 0.7526
0.4705 8.6885 530 0.5661 0.7598 0.5661 0.7524
0.4705 8.7213 532 0.5683 0.7617 0.5683 0.7538
0.4705 8.7541 534 0.5698 0.7617 0.5698 0.7548
0.4705 8.7869 536 0.5706 0.7680 0.5706 0.7554
0.4705 8.8197 538 0.5728 0.7617 0.5728 0.7568
0.4705 8.8525 540 0.5752 0.7573 0.5752 0.7584
0.4705 8.8852 542 0.5833 0.7402 0.5833 0.7637
0.4705 8.9180 544 0.5868 0.7477 0.5868 0.7661
0.4705 8.9508 546 0.5923 0.7507 0.5923 0.7696
0.4705 8.9836 548 0.5988 0.7463 0.5988 0.7739
0.4705 9.0164 550 0.6014 0.7463 0.6014 0.7755
0.4705 9.0492 552 0.6040 0.7463 0.6040 0.7772
0.4705 9.0820 554 0.6040 0.7463 0.6040 0.7771
0.4705 9.1148 556 0.5989 0.7463 0.5989 0.7739
0.4705 9.1475 558 0.5944 0.7507 0.5944 0.7709
0.4705 9.1803 560 0.5928 0.7507 0.5928 0.7699
0.4705 9.2131 562 0.5964 0.7463 0.5964 0.7722
0.4705 9.2459 564 0.6044 0.7463 0.6044 0.7774
0.4705 9.2787 566 0.6151 0.7335 0.6151 0.7843
0.4705 9.3115 568 0.6279 0.7351 0.6279 0.7924
0.4705 9.3443 570 0.6363 0.7262 0.6363 0.7977
0.4705 9.3770 572 0.6379 0.7262 0.6379 0.7987
0.4705 9.4098 574 0.6328 0.7262 0.6328 0.7955
0.4705 9.4426 576 0.6297 0.7284 0.6297 0.7935
0.4705 9.4754 578 0.6259 0.7268 0.6259 0.7912
0.4705 9.5082 580 0.6260 0.7335 0.6260 0.7912
0.4705 9.5410 582 0.6240 0.7335 0.6240 0.7900
0.4705 9.5738 584 0.6192 0.7335 0.6192 0.7869
0.4705 9.6066 586 0.6163 0.7335 0.6163 0.7850
0.4705 9.6393 588 0.6148 0.7335 0.6148 0.7841
0.4705 9.6721 590 0.6128 0.7335 0.6128 0.7828
0.4705 9.7049 592 0.6102 0.7335 0.6102 0.7812
0.4705 9.7377 594 0.6065 0.7335 0.6065 0.7788
0.4705 9.7705 596 0.6052 0.7335 0.6052 0.7780
0.4705 9.8033 598 0.6058 0.7335 0.6058 0.7783
0.4705 9.8361 600 0.6063 0.7335 0.6063 0.7787
0.4705 9.8689 602 0.6069 0.7335 0.6069 0.7791
0.4705 9.9016 604 0.6072 0.7335 0.6072 0.7792
0.4705 9.9344 606 0.6073 0.7335 0.6073 0.7793
0.4705 9.9672 608 0.6072 0.7335 0.6072 0.7792
0.4705 10.0 610 0.6070 0.7335 0.6070 0.7791

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/ArabicNewSplits6_FineTuningAraBERT_run3_AugV5_k12_task1_organization

Finetuned
(4023)
this model