ArabicNewSplits7_FineTuningAraBERT_run3_AugV5_k14_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: 1.0779
  • Qwk: 0.5909
  • Mse: 1.0779
  • Rmse: 1.0382

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 0.0312 2 7.1012 0.0057 7.1012 2.6648
No log 0.0625 4 5.2373 0.0426 5.2373 2.2885
No log 0.0938 6 3.4284 0.0460 3.4284 1.8516
No log 0.125 8 3.4955 -0.0447 3.4955 1.8696
No log 0.1562 10 3.3805 -0.0769 3.3805 1.8386
No log 0.1875 12 2.4206 -0.0992 2.4206 1.5558
No log 0.2188 14 2.6876 -0.1203 2.6876 1.6394
No log 0.25 16 2.2839 0.0775 2.2839 1.5112
No log 0.2812 18 2.0472 0.1905 2.0472 1.4308
No log 0.3125 20 1.7548 0.2018 1.7548 1.3247
No log 0.3438 22 1.7160 0.2385 1.7160 1.3100
No log 0.375 24 1.6364 0.2545 1.6364 1.2792
No log 0.4062 26 1.5951 0.3770 1.5951 1.2630
No log 0.4375 28 1.6806 0.3714 1.6806 1.2964
No log 0.4688 30 1.5220 0.3768 1.5220 1.2337
No log 0.5 32 1.3747 0.2569 1.3747 1.1725
No log 0.5312 34 1.6903 0.1538 1.6903 1.3001
No log 0.5625 36 2.0840 0.0962 2.0840 1.4436
No log 0.5938 38 2.4951 -0.1913 2.4951 1.5796
No log 0.625 40 2.5809 -0.2167 2.5809 1.6065
No log 0.6562 42 2.2211 -0.0708 2.2211 1.4903
No log 0.6875 44 1.9618 0.1165 1.9618 1.4006
No log 0.7188 46 1.7343 0.1887 1.7343 1.3169
No log 0.75 48 1.4424 0.2545 1.4424 1.2010
No log 0.7812 50 1.3462 0.3478 1.3462 1.1603
No log 0.8125 52 1.6078 0.4062 1.6078 1.2680
No log 0.8438 54 1.6075 0.4062 1.6075 1.2679
No log 0.875 56 1.6494 0.4179 1.6494 1.2843
No log 0.9062 58 1.3222 0.4733 1.3222 1.1499
No log 0.9375 60 1.0582 0.4677 1.0582 1.0287
No log 0.9688 62 1.0464 0.6406 1.0464 1.0229
No log 1.0 64 1.0368 0.528 1.0368 1.0182
No log 1.0312 66 1.0389 0.5538 1.0389 1.0193
No log 1.0625 68 1.0924 0.5373 1.0924 1.0452
No log 1.0938 70 1.1581 0.4553 1.1581 1.0761
No log 1.125 72 1.1541 0.5079 1.1541 1.0743
No log 1.1562 74 1.0185 0.6154 1.0185 1.0092
No log 1.1875 76 0.9342 0.6765 0.9342 0.9666
No log 1.2188 78 0.9667 0.6957 0.9667 0.9832
No log 1.25 80 1.0157 0.6857 1.0157 1.0078
No log 1.2812 82 1.1754 0.5547 1.1754 1.0841
No log 1.3125 84 1.3910 0.4789 1.3910 1.1794
No log 1.3438 86 1.4399 0.5103 1.4399 1.2000
No log 1.375 88 1.2445 0.5652 1.2445 1.1156
No log 1.4062 90 0.9757 0.6222 0.9757 0.9878
No log 1.4375 92 0.8231 0.7673 0.8231 0.9073
No log 1.4688 94 0.9599 0.6538 0.9599 0.9797
No log 1.5 96 1.1211 0.6405 1.1211 1.0588
No log 1.5312 98 1.1607 0.6536 1.1607 1.0774
No log 1.5625 100 0.9907 0.6087 0.9907 0.9954
No log 1.5938 102 1.2892 0.5429 1.2892 1.1354
No log 1.625 104 1.6617 0.3188 1.6617 1.2891
No log 1.6562 106 1.8334 0.2016 1.8334 1.3540
No log 1.6875 108 1.7922 0.2114 1.7922 1.3387
No log 1.7188 110 1.6184 0.4211 1.6184 1.2722
No log 1.75 112 1.4398 0.4580 1.4398 1.1999
No log 1.7812 114 1.2982 0.5496 1.2982 1.1394
No log 1.8125 116 1.1796 0.5736 1.1796 1.0861
No log 1.8438 118 1.1290 0.5397 1.1290 1.0625
No log 1.875 120 1.1608 0.5039 1.1608 1.0774
No log 1.9062 122 1.2006 0.4839 1.2006 1.0957
No log 1.9375 124 1.3012 0.4921 1.3012 1.1407
No log 1.9688 126 1.4305 0.4511 1.4305 1.1961
No log 2.0 128 1.5199 0.3824 1.5199 1.2328
No log 2.0312 130 1.4768 0.4412 1.4768 1.2152
No log 2.0625 132 1.3208 0.5303 1.3208 1.1493
No log 2.0938 134 1.2632 0.5778 1.2632 1.1239
No log 2.125 136 1.3309 0.5180 1.3309 1.1536
No log 2.1562 138 1.2868 0.5180 1.2868 1.1344
No log 2.1875 140 1.2450 0.5547 1.2450 1.1158
No log 2.2188 142 1.3841 0.4714 1.3841 1.1765
No log 2.25 144 1.5272 0.3688 1.5272 1.2358
No log 2.2812 146 1.9534 0.1727 1.9534 1.3976
No log 2.3125 148 2.1867 0.1000 2.1867 1.4787
No log 2.3438 150 1.5315 0.4429 1.5315 1.2375
No log 2.375 152 1.5783 0.375 1.5783 1.2563
No log 2.4062 154 1.6571 0.3586 1.6571 1.2873
No log 2.4375 156 1.5383 0.3636 1.5383 1.2403
No log 2.4688 158 1.2464 0.5324 1.2464 1.1164
No log 2.5 160 1.0228 0.6131 1.0228 1.0113
No log 2.5312 162 1.0140 0.6222 1.0140 1.0070
No log 2.5625 164 1.1296 0.5821 1.1296 1.0628
No log 2.5938 166 1.1095 0.5970 1.1095 1.0533
No log 2.625 168 1.0724 0.5970 1.0724 1.0356
No log 2.6562 170 0.9511 0.6364 0.9511 0.9753
No log 2.6875 172 0.7804 0.6667 0.7804 0.8834
No log 2.7188 174 0.7304 0.6806 0.7304 0.8546
No log 2.75 176 0.7039 0.7347 0.7039 0.8390
No log 2.7812 178 0.7695 0.6667 0.7695 0.8772
No log 2.8125 180 0.8095 0.6620 0.8095 0.8997
No log 2.8438 182 0.8374 0.6525 0.8374 0.9151
No log 2.875 184 1.0852 0.5926 1.0852 1.0417
No log 2.9062 186 1.3427 0.5 1.3427 1.1587
No log 2.9375 188 1.4407 0.5036 1.4407 1.2003
No log 2.9688 190 1.2621 0.5630 1.2621 1.1234
No log 3.0 192 0.9527 0.6370 0.9527 0.9761
No log 3.0312 194 0.7328 0.7075 0.7328 0.8560
No log 3.0625 196 0.6900 0.7484 0.6900 0.8307
No log 3.0938 198 0.6940 0.7564 0.6940 0.8331
No log 3.125 200 0.8422 0.6621 0.8422 0.9177
No log 3.1562 202 1.0582 0.6131 1.0582 1.0287
No log 3.1875 204 1.1586 0.5778 1.1586 1.0764
No log 3.2188 206 1.1945 0.5865 1.1945 1.0929
No log 3.25 208 1.1383 0.5778 1.1383 1.0669
No log 3.2812 210 1.0358 0.5970 1.0358 1.0177
No log 3.3125 212 0.7767 0.6620 0.7767 0.8813
No log 3.3438 214 0.7263 0.6849 0.7263 0.8523
No log 3.375 216 0.7556 0.6620 0.7556 0.8693
No log 3.4062 218 0.8500 0.6567 0.8500 0.9220
No log 3.4375 220 0.9367 0.5970 0.9367 0.9678
No log 3.4688 222 1.0085 0.5758 1.0085 1.0043
No log 3.5 224 0.9664 0.6212 0.9664 0.9830
No log 3.5312 226 0.9524 0.6212 0.9524 0.9759
No log 3.5625 228 0.8899 0.6412 0.8899 0.9433
No log 3.5938 230 0.8077 0.6866 0.8077 0.8987
No log 3.625 232 0.7815 0.7050 0.7815 0.8840
No log 3.6562 234 0.7032 0.7651 0.7032 0.8386
No log 3.6875 236 0.6804 0.72 0.6804 0.8249
No log 3.7188 238 0.7557 0.6761 0.7557 0.8693
No log 3.75 240 0.7971 0.6370 0.7971 0.8928
No log 3.7812 242 0.8383 0.6767 0.8383 0.9156
No log 3.8125 244 0.9009 0.6767 0.9009 0.9492
No log 3.8438 246 1.0174 0.6269 1.0174 1.0087
No log 3.875 248 1.1305 0.5693 1.1305 1.0633
No log 3.9062 250 1.1623 0.5693 1.1623 1.0781
No log 3.9375 252 1.0830 0.6269 1.0830 1.0407
No log 3.9688 254 1.0571 0.6370 1.0571 1.0282
No log 4.0 256 1.1076 0.5693 1.1076 1.0524
No log 4.0312 258 1.1485 0.5693 1.1485 1.0717
No log 4.0625 260 1.3132 0.5 1.3132 1.1460
No log 4.0938 262 1.6033 0.3099 1.6033 1.2662
No log 4.125 264 1.6575 0.3425 1.6575 1.2874
No log 4.1562 266 1.5094 0.3889 1.5094 1.2286
No log 4.1875 268 1.2675 0.5075 1.2675 1.1258
No log 4.2188 270 1.0990 0.6015 1.0990 1.0484
No log 4.25 272 1.0462 0.6512 1.0462 1.0229
No log 4.2812 274 1.0173 0.6412 1.0173 1.0086
No log 4.3125 276 0.9769 0.6061 0.9769 0.9884
No log 4.3438 278 0.9797 0.6269 0.9797 0.9898
No log 4.375 280 0.9047 0.6269 0.9047 0.9512
No log 4.4062 282 0.8375 0.6370 0.8375 0.9151
No log 4.4375 284 0.7728 0.6269 0.7728 0.8791
No log 4.4688 286 0.7319 0.6667 0.7319 0.8555
No log 4.5 288 0.7162 0.6667 0.7162 0.8463
No log 4.5312 290 0.7123 0.6767 0.7123 0.8440
No log 4.5625 292 0.7203 0.6466 0.7203 0.8487
No log 4.5938 294 0.7296 0.6618 0.7296 0.8542
No log 4.625 296 0.7622 0.6519 0.7622 0.8731
No log 4.6562 298 0.8081 0.6324 0.8081 0.8989
No log 4.6875 300 0.8030 0.6423 0.8030 0.8961
No log 4.7188 302 0.7474 0.6667 0.7474 0.8645
No log 4.75 304 0.6863 0.6857 0.6863 0.8284
No log 4.7812 306 0.6737 0.7183 0.6737 0.8208
No log 4.8125 308 0.7467 0.6619 0.7467 0.8641
No log 4.8438 310 0.8392 0.6475 0.8392 0.9161
No log 4.875 312 0.9952 0.6087 0.9952 0.9976
No log 4.9062 314 0.9552 0.5865 0.9552 0.9773
No log 4.9375 316 0.8934 0.6515 0.8934 0.9452
No log 4.9688 318 0.9016 0.6364 0.9016 0.9495
No log 5.0 320 0.9719 0.5865 0.9719 0.9858
No log 5.0312 322 0.9993 0.5865 0.9993 0.9996
No log 5.0625 324 1.0908 0.5441 1.0908 1.0444
No log 5.0938 326 1.0867 0.5821 1.0867 1.0424
No log 5.125 328 1.0126 0.5865 1.0126 1.0063
No log 5.1562 330 0.9060 0.6131 0.9060 0.9519
No log 5.1875 332 0.8624 0.6143 0.8624 0.9287
No log 5.2188 334 0.7868 0.6761 0.7868 0.8870
No log 5.25 336 0.7071 0.7671 0.7071 0.8409
No log 5.2812 338 0.7078 0.7703 0.7078 0.8413
No log 5.3125 340 0.6875 0.7534 0.6875 0.8292
No log 5.3438 342 0.7740 0.6620 0.7740 0.8798
No log 5.375 344 0.8896 0.6029 0.8896 0.9432
No log 5.4062 346 1.0075 0.5865 1.0075 1.0038
No log 5.4375 348 1.0221 0.5865 1.0221 1.0110
No log 5.4688 350 1.0178 0.5882 1.0178 1.0089
No log 5.5 352 1.1418 0.5797 1.1418 1.0686
No log 5.5312 354 1.0945 0.5839 1.0945 1.0462
No log 5.5625 356 0.9993 0.6241 0.9993 0.9996
No log 5.5938 358 0.9606 0.6370 0.9606 0.9801
No log 5.625 360 1.0102 0.6316 1.0102 1.0051
No log 5.6562 362 1.0598 0.6061 1.0598 1.0295
No log 5.6875 364 1.0644 0.6107 1.0644 1.0317
No log 5.7188 366 1.0466 0.6 1.0466 1.0231
No log 5.75 368 1.0559 0.6107 1.0559 1.0275
No log 5.7812 370 1.0934 0.5865 1.0934 1.0456
No log 5.8125 372 1.0350 0.6056 1.0350 1.0174
No log 5.8438 374 0.8581 0.6667 0.8581 0.9263
No log 5.875 376 0.7510 0.6933 0.7510 0.8666
No log 5.9062 378 0.7472 0.7162 0.7472 0.8644
No log 5.9375 380 0.8287 0.6853 0.8287 0.9103
No log 5.9688 382 0.8903 0.6619 0.8903 0.9436
No log 6.0 384 0.9207 0.6619 0.9207 0.9595
No log 6.0312 386 0.8874 0.6619 0.8874 0.9420
No log 6.0625 388 0.8803 0.6812 0.8803 0.9382
No log 6.0938 390 0.9217 0.6471 0.9217 0.9601
No log 6.125 392 0.9042 0.6667 0.9042 0.9509
No log 6.1562 394 0.9084 0.6667 0.9084 0.9531
No log 6.1875 396 0.9172 0.6667 0.9172 0.9577
No log 6.2188 398 0.9150 0.6567 0.9150 0.9566
No log 6.25 400 0.8903 0.6569 0.8903 0.9436
No log 6.2812 402 0.8331 0.6714 0.8331 0.9128
No log 6.3125 404 0.6926 0.7286 0.6926 0.8322
No log 6.3438 406 0.6434 0.7586 0.6434 0.8021
No log 6.375 408 0.6318 0.7619 0.6318 0.7949
No log 6.4062 410 0.6462 0.7639 0.6462 0.8038
No log 6.4375 412 0.7321 0.6950 0.7321 0.8556
No log 6.4688 414 0.9216 0.6107 0.9216 0.9600
No log 6.5 416 1.0244 0.5909 1.0244 1.0121
No log 6.5312 418 1.0931 0.5672 1.0931 1.0455
No log 6.5625 420 1.0642 0.5865 1.0642 1.0316
No log 6.5938 422 1.0171 0.5846 1.0171 1.0085
No log 6.625 424 0.9419 0.6119 0.9419 0.9705
No log 6.6562 426 0.9180 0.6522 0.9180 0.9581
No log 6.6875 428 0.9740 0.6525 0.9740 0.9869
No log 6.7188 430 1.1197 0.5839 1.1197 1.0582
No log 6.75 432 1.1063 0.6 1.1063 1.0518
No log 6.7812 434 1.0350 0.6187 1.0350 1.0173
No log 6.8125 436 0.9544 0.6131 0.9544 0.9769
No log 6.8438 438 0.9719 0.5970 0.9719 0.9858
No log 6.875 440 1.0174 0.5865 1.0174 1.0087
No log 6.9062 442 1.0198 0.5865 1.0198 1.0098
No log 6.9375 444 0.9203 0.6074 0.9203 0.9593
No log 6.9688 446 0.8664 0.6713 0.8664 0.9308
No log 7.0 448 0.8399 0.6986 0.8399 0.9164
No log 7.0312 450 0.8479 0.6849 0.8479 0.9208
No log 7.0625 452 0.8761 0.6803 0.8761 0.9360
No log 7.0938 454 1.0222 0.6301 1.0222 1.0111
No log 7.125 456 1.2369 0.5405 1.2369 1.1122
No log 7.1562 458 1.3486 0.5034 1.3486 1.1613
No log 7.1875 460 1.2975 0.5103 1.2975 1.1391
No log 7.2188 462 1.1042 0.6164 1.1042 1.0508
No log 7.25 464 0.8711 0.6528 0.8711 0.9333
No log 7.2812 466 0.7644 0.7333 0.7644 0.8743
No log 7.3125 468 0.7087 0.7297 0.7087 0.8418
No log 7.3438 470 0.6928 0.7297 0.6928 0.8323
No log 7.375 472 0.7026 0.7123 0.7026 0.8382
No log 7.4062 474 0.7538 0.6901 0.7538 0.8682
No log 7.4375 476 0.7722 0.6853 0.7722 0.8787
No log 7.4688 478 0.7262 0.6901 0.7262 0.8522
No log 7.5 480 0.6965 0.6906 0.6965 0.8345
No log 7.5312 482 0.7426 0.6763 0.7426 0.8617
No log 7.5625 484 0.8129 0.6423 0.8129 0.9016
No log 7.5938 486 0.9187 0.6370 0.9187 0.9585
No log 7.625 488 1.0142 0.6176 1.0142 1.0071
No log 7.6562 490 1.0708 0.5547 1.0708 1.0348
No log 7.6875 492 1.0747 0.5882 1.0747 1.0367
No log 7.7188 494 1.0542 0.5882 1.0542 1.0267
No log 7.75 496 0.9569 0.6370 0.9569 0.9782
No log 7.7812 498 0.9665 0.6370 0.9665 0.9831
0.5198 7.8125 500 0.9882 0.6176 0.9882 0.9941
0.5198 7.8438 502 0.9931 0.6043 0.9931 0.9966
0.5198 7.875 504 0.8979 0.6571 0.8979 0.9476
0.5198 7.9062 506 0.8122 0.6809 0.8122 0.9012
0.5198 7.9375 508 0.7072 0.7042 0.7072 0.8409
0.5198 7.9688 510 0.7059 0.7092 0.7059 0.8402
0.5198 8.0 512 0.7239 0.6906 0.7239 0.8509
0.5198 8.0312 514 0.7760 0.6809 0.7760 0.8809
0.5198 8.0625 516 0.8281 0.6761 0.8281 0.9100
0.5198 8.0938 518 0.7838 0.6761 0.7838 0.8853
0.5198 8.125 520 0.7242 0.6809 0.7242 0.8510
0.5198 8.1562 522 0.7120 0.6957 0.7120 0.8438
0.5198 8.1875 524 0.7531 0.6618 0.7531 0.8678
0.5198 8.2188 526 0.8033 0.6761 0.8033 0.8963
0.5198 8.25 528 0.7667 0.6761 0.7667 0.8756
0.5198 8.2812 530 0.7120 0.6993 0.7120 0.8438
0.5198 8.3125 532 0.6615 0.7183 0.6615 0.8133
0.5198 8.3438 534 0.6872 0.6950 0.6872 0.8290
0.5198 8.375 536 0.8395 0.6232 0.8395 0.9163
0.5198 8.4062 538 1.0209 0.5630 1.0209 1.0104
0.5198 8.4375 540 1.2168 0.5362 1.2168 1.1031
0.5198 8.4688 542 1.1983 0.5693 1.1983 1.0947
0.5198 8.5 544 1.1182 0.5714 1.1182 1.0574
0.5198 8.5312 546 1.0779 0.5909 1.0779 1.0382

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
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_FineTuningAraBERT_run3_AugV5_k14_task1_organization

Finetuned
(4040)
this model