ArabicNewSplits7_FineTuningAraBERT_run1_AugV5_k6_task7_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: 0.8725
  • Qwk: 0.3867
  • Mse: 0.8725
  • Rmse: 0.9341

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 0.1176 2 2.7268 -0.0262 2.7268 1.6513
No log 0.2353 4 1.4160 0.0771 1.4160 1.1900
No log 0.3529 6 1.0447 -0.1304 1.0447 1.0221
No log 0.4706 8 1.2835 -0.2437 1.2835 1.1329
No log 0.5882 10 1.5149 -0.2448 1.5149 1.2308
No log 0.7059 12 1.6208 -0.1307 1.6208 1.2731
No log 0.8235 14 1.3323 -0.1803 1.3323 1.1542
No log 0.9412 16 1.0674 0.0327 1.0674 1.0331
No log 1.0588 18 0.9372 0.2227 0.9372 0.9681
No log 1.1765 20 0.9146 0.2504 0.9146 0.9564
No log 1.2941 22 0.8599 0.3425 0.8599 0.9273
No log 1.4118 24 0.8638 0.1407 0.8638 0.9294
No log 1.5294 26 0.9672 0.0 0.9672 0.9834
No log 1.6471 28 1.0828 -0.0660 1.0828 1.0406
No log 1.7647 30 1.0018 -0.0426 1.0018 1.0009
No log 1.8824 32 0.8917 0.0 0.8917 0.9443
No log 2.0 34 0.8040 0.0327 0.8040 0.8967
No log 2.1176 36 0.8083 0.2407 0.8083 0.8990
No log 2.2353 38 0.8258 0.2463 0.8258 0.9087
No log 2.3529 40 0.8547 0.3294 0.8547 0.9245
No log 2.4706 42 0.8759 0.3099 0.8759 0.9359
No log 2.5882 44 0.8845 0.0840 0.8845 0.9405
No log 2.7059 46 0.8996 0.1327 0.8996 0.9485
No log 2.8235 48 0.8627 0.1754 0.8627 0.9288
No log 2.9412 50 0.8310 0.1372 0.8310 0.9116
No log 3.0588 52 0.7444 0.0428 0.7444 0.8628
No log 3.1765 54 0.7285 0.1508 0.7285 0.8535
No log 3.2941 56 0.7495 0.1863 0.7495 0.8657
No log 3.4118 58 0.7724 0.1407 0.7724 0.8788
No log 3.5294 60 0.8269 -0.0511 0.8269 0.9093
No log 3.6471 62 0.9254 -0.0392 0.9254 0.9620
No log 3.7647 64 1.1030 -0.0264 1.1030 1.0502
No log 3.8824 66 1.2248 0.0081 1.2248 1.1067
No log 4.0 68 1.0681 -0.0112 1.0681 1.0335
No log 4.1176 70 1.0519 0.2173 1.0519 1.0256
No log 4.2353 72 1.0235 0.2076 1.0235 1.0117
No log 4.3529 74 1.0578 0.0120 1.0578 1.0285
No log 4.4706 76 1.0491 -0.0497 1.0491 1.0243
No log 4.5882 78 1.0570 0.1101 1.0570 1.0281
No log 4.7059 80 1.0229 0.1289 1.0229 1.0114
No log 4.8235 82 1.0278 0.1827 1.0278 1.0138
No log 4.9412 84 1.0840 0.1709 1.0840 1.0411
No log 5.0588 86 1.0419 0.2537 1.0419 1.0207
No log 5.1765 88 1.0101 0.0244 1.0101 1.0050
No log 5.2941 90 0.9973 -0.0108 0.9973 0.9987
No log 5.4118 92 1.0215 0.2124 1.0215 1.0107
No log 5.5294 94 1.2082 0.0948 1.2082 1.0992
No log 5.6471 96 1.2811 0.0852 1.2811 1.1319
No log 5.7647 98 1.1839 0.0881 1.1839 1.0881
No log 5.8824 100 1.0396 0.2728 1.0396 1.0196
No log 6.0 102 0.8852 0.2149 0.8852 0.9408
No log 6.1176 104 0.8421 0.1353 0.8421 0.9177
No log 6.2353 106 0.8525 0.2270 0.8525 0.9233
No log 6.3529 108 0.8804 0.3817 0.8804 0.9383
No log 6.4706 110 0.9760 0.3398 0.9760 0.9879
No log 6.5882 112 1.0358 0.2708 1.0358 1.0177
No log 6.7059 114 0.9867 0.28 0.9867 0.9933
No log 6.8235 116 0.9717 0.1843 0.9717 0.9857
No log 6.9412 118 1.0157 0.3043 1.0157 1.0078
No log 7.0588 120 1.2547 0.1409 1.2547 1.1201
No log 7.1765 122 1.3189 0.1357 1.3189 1.1484
No log 7.2941 124 1.1721 0.2231 1.1721 1.0826
No log 7.4118 126 0.9737 0.2076 0.9737 0.9868
No log 7.5294 128 0.9136 0.1373 0.9136 0.9558
No log 7.6471 130 0.9125 0.1867 0.9125 0.9553
No log 7.7647 132 0.9566 0.3110 0.9566 0.9780
No log 7.8824 134 0.8952 0.3069 0.8952 0.9462
No log 8.0 136 0.8672 0.2547 0.8672 0.9312
No log 8.1176 138 0.8373 0.2661 0.8373 0.9151
No log 8.2353 140 0.8693 0.2670 0.8693 0.9324
No log 8.3529 142 0.9026 0.4085 0.9026 0.9500
No log 8.4706 144 0.8102 0.4464 0.8102 0.9001
No log 8.5882 146 0.8687 0.3760 0.8687 0.9320
No log 8.7059 148 1.0536 0.2613 1.0536 1.0264
No log 8.8235 150 1.2256 0.2299 1.2256 1.1070
No log 8.9412 152 1.0067 0.3431 1.0067 1.0034
No log 9.0588 154 0.8420 0.3011 0.8420 0.9176
No log 9.1765 156 0.9171 0.4321 0.9171 0.9577
No log 9.2941 158 1.2507 0.1841 1.2507 1.1184
No log 9.4118 160 1.5506 0.1759 1.5506 1.2452
No log 9.5294 162 1.4346 0.1965 1.4346 1.1977
No log 9.6471 164 1.2422 0.1776 1.2422 1.1146
No log 9.7647 166 0.9861 0.3128 0.9861 0.9930
No log 9.8824 168 0.8802 0.3255 0.8802 0.9382
No log 10.0 170 0.8676 0.2402 0.8676 0.9315
No log 10.1176 172 0.8841 0.2993 0.8841 0.9403
No log 10.2353 174 0.9120 0.2937 0.9120 0.9550
No log 10.3529 176 0.9544 0.3667 0.9544 0.9769
No log 10.4706 178 0.9906 0.3582 0.9906 0.9953
No log 10.5882 180 0.9758 0.3425 0.9758 0.9878
No log 10.7059 182 0.9097 0.3125 0.9097 0.9538
No log 10.8235 184 0.8349 0.3609 0.8349 0.9137
No log 10.9412 186 0.8148 0.2172 0.8148 0.9027
No log 11.0588 188 0.8589 0.2988 0.8589 0.9268
No log 11.1765 190 0.9714 0.3483 0.9714 0.9856
No log 11.2941 192 1.0116 0.2905 1.0116 1.0058
No log 11.4118 194 0.9017 0.3645 0.9017 0.9496
No log 11.5294 196 0.8513 0.3520 0.8513 0.9227
No log 11.6471 198 0.8394 0.3520 0.8394 0.9162
No log 11.7647 200 0.8733 0.3520 0.8733 0.9345
No log 11.8824 202 0.8863 0.3520 0.8863 0.9414
No log 12.0 204 0.9484 0.3456 0.9484 0.9738
No log 12.1176 206 0.9953 0.3333 0.9953 0.9976
No log 12.2353 208 1.1126 0.2754 1.1126 1.0548
No log 12.3529 210 1.0385 0.2577 1.0385 1.0191
No log 12.4706 212 0.9103 0.3100 0.9103 0.9541
No log 12.5882 214 0.8826 0.3100 0.8826 0.9395
No log 12.7059 216 0.9827 0.2602 0.9827 0.9913
No log 12.8235 218 1.1467 0.2622 1.1467 1.0709
No log 12.9412 220 1.0604 0.2524 1.0604 1.0298
No log 13.0588 222 0.8075 0.3976 0.8075 0.8986
No log 13.1765 224 0.7876 0.3316 0.7876 0.8875
No log 13.2941 226 0.8008 0.3239 0.8008 0.8949
No log 13.4118 228 0.7293 0.3079 0.7293 0.8540
No log 13.5294 230 0.8008 0.3760 0.8008 0.8949
No log 13.6471 232 0.9776 0.2547 0.9776 0.9887
No log 13.7647 234 0.9390 0.2894 0.9390 0.9690
No log 13.8824 236 0.8179 0.3565 0.8179 0.9044
No log 14.0 238 0.8232 0.2479 0.8232 0.9073
No log 14.1176 240 0.8592 0.2747 0.8592 0.9269
No log 14.2353 242 0.9239 0.2873 0.9239 0.9612
No log 14.3529 244 1.0360 0.2636 1.0360 1.0178
No log 14.4706 246 1.1456 0.2312 1.1456 1.0703
No log 14.5882 248 1.0731 0.2312 1.0731 1.0359
No log 14.7059 250 0.9686 0.2677 0.9686 0.9842
No log 14.8235 252 0.9177 0.1884 0.9177 0.9580
No log 14.9412 254 0.8797 0.2616 0.8797 0.9379
No log 15.0588 256 0.8861 0.2887 0.8861 0.9413
No log 15.1765 258 0.9328 0.2564 0.9328 0.9658
No log 15.2941 260 0.9601 0.2777 0.9601 0.9798
No log 15.4118 262 1.0995 0.2354 1.0995 1.0486
No log 15.5294 264 0.9717 0.3022 0.9717 0.9857
No log 15.6471 266 0.8374 0.2975 0.8374 0.9151
No log 15.7647 268 0.8447 0.2832 0.8447 0.9191
No log 15.8824 270 0.9461 0.3022 0.9461 0.9727
No log 16.0 272 1.0755 0.2271 1.0755 1.0370
No log 16.1176 274 1.1718 0.2687 1.1718 1.0825
No log 16.2353 276 1.0668 0.2777 1.0668 1.0328
No log 16.3529 278 0.8756 0.2853 0.8756 0.9357
No log 16.4706 280 0.7682 0.4134 0.7682 0.8765
No log 16.5882 282 0.7629 0.3867 0.7629 0.8735
No log 16.7059 284 0.8001 0.3194 0.8001 0.8945
No log 16.8235 286 0.9030 0.2964 0.9030 0.9502
No log 16.9412 288 0.9448 0.2964 0.9448 0.9720
No log 17.0588 290 0.8439 0.3371 0.8439 0.9186
No log 17.1765 292 0.7099 0.3433 0.7099 0.8426
No log 17.2941 294 0.6892 0.3253 0.6892 0.8302
No log 17.4118 296 0.6987 0.3525 0.6987 0.8359
No log 17.5294 298 0.7808 0.4295 0.7808 0.8837
No log 17.6471 300 1.0687 0.3080 1.0687 1.0338
No log 17.7647 302 1.3421 0.2633 1.3421 1.1585
No log 17.8824 304 1.2996 0.3435 1.2996 1.1400
No log 18.0 306 1.0384 0.3131 1.0384 1.0190
No log 18.1176 308 0.8093 0.3255 0.8093 0.8996
No log 18.2353 310 0.7627 0.2508 0.7627 0.8733
No log 18.3529 312 0.7271 0.2838 0.7271 0.8527
No log 18.4706 314 0.7212 0.3677 0.7212 0.8492
No log 18.5882 316 0.7803 0.4038 0.7803 0.8833
No log 18.7059 318 0.8165 0.3803 0.8165 0.9036
No log 18.8235 320 0.7928 0.3803 0.7928 0.8904
No log 18.9412 322 0.7570 0.3868 0.7570 0.8701
No log 19.0588 324 0.7420 0.4104 0.7420 0.8614
No log 19.1765 326 0.7206 0.3567 0.7206 0.8489
No log 19.2941 328 0.7507 0.3732 0.7507 0.8664
No log 19.4118 330 0.8377 0.3699 0.8377 0.9153
No log 19.5294 332 0.9011 0.2830 0.9011 0.9493
No log 19.6471 334 0.8605 0.3217 0.8605 0.9276
No log 19.7647 336 0.8494 0.2702 0.8494 0.9216
No log 19.8824 338 0.8319 0.2958 0.8319 0.9121
No log 20.0 340 0.8117 0.2958 0.8117 0.9009
No log 20.1176 342 0.8372 0.2958 0.8372 0.9150
No log 20.2353 344 0.8763 0.2627 0.8763 0.9361
No log 20.3529 346 0.8889 0.2578 0.8889 0.9428
No log 20.4706 348 0.8182 0.3356 0.8182 0.9045
No log 20.5882 350 0.7596 0.3567 0.7596 0.8715
No log 20.7059 352 0.7057 0.3914 0.7057 0.8401
No log 20.8235 354 0.7064 0.4044 0.7064 0.8405
No log 20.9412 356 0.7592 0.4104 0.7592 0.8713
No log 21.0588 358 0.7634 0.4334 0.7634 0.8737
No log 21.1765 360 0.7164 0.4404 0.7164 0.8464
No log 21.2941 362 0.6770 0.4408 0.6770 0.8228
No log 21.4118 364 0.6566 0.4260 0.6566 0.8103
No log 21.5294 366 0.6542 0.4448 0.6542 0.8088
No log 21.6471 368 0.6998 0.4085 0.6998 0.8366
No log 21.7647 370 0.7260 0.4017 0.7260 0.8521
No log 21.8824 372 0.8142 0.4012 0.8142 0.9023
No log 22.0 374 0.9140 0.3941 0.9140 0.9560
No log 22.1176 376 0.8714 0.3803 0.8714 0.9335
No log 22.2353 378 0.7615 0.3776 0.7615 0.8726
No log 22.3529 380 0.6998 0.3051 0.6998 0.8365
No log 22.4706 382 0.6589 0.3171 0.6589 0.8117
No log 22.5882 384 0.6579 0.3417 0.6579 0.8111
No log 22.7059 386 0.6688 0.3931 0.6688 0.8178
No log 22.8235 388 0.7676 0.4759 0.7676 0.8761
No log 22.9412 390 0.9496 0.4186 0.9496 0.9745
No log 23.0588 392 0.9566 0.4003 0.9566 0.9781
No log 23.1765 394 0.8132 0.3766 0.8132 0.9018
No log 23.2941 396 0.7108 0.4759 0.7108 0.8431
No log 23.4118 398 0.6689 0.3887 0.6689 0.8179
No log 23.5294 400 0.6973 0.3149 0.6973 0.8350
No log 23.6471 402 0.7150 0.2279 0.7150 0.8456
No log 23.7647 404 0.7614 0.3567 0.7614 0.8726
No log 23.8824 406 0.9621 0.2905 0.9621 0.9809
No log 24.0 408 1.2825 0.2671 1.2825 1.1325
No log 24.1176 410 1.5997 0.2721 1.5997 1.2648
No log 24.2353 412 1.5959 0.2185 1.5959 1.2633
No log 24.3529 414 1.3474 0.2101 1.3474 1.1608
No log 24.4706 416 1.0286 0.2323 1.0286 1.0142
No log 24.5882 418 0.8202 0.2697 0.8202 0.9056
No log 24.7059 420 0.7379 0.2419 0.7379 0.8590
No log 24.8235 422 0.7354 0.2690 0.7354 0.8576
No log 24.9412 424 0.7780 0.4023 0.7780 0.8821
No log 25.0588 426 0.9200 0.2578 0.9200 0.9592
No log 25.1765 428 1.0892 0.3273 1.0892 1.0437
No log 25.2941 430 1.1873 0.3541 1.1873 1.0896
No log 25.4118 432 1.1145 0.3557 1.1145 1.0557
No log 25.5294 434 0.9873 0.3936 0.9873 0.9936
No log 25.6471 436 0.8466 0.3424 0.8466 0.9201
No log 25.7647 438 0.7454 0.4263 0.7454 0.8634
No log 25.8824 440 0.7024 0.4013 0.7024 0.8381
No log 26.0 442 0.6954 0.3504 0.6954 0.8339
No log 26.1176 444 0.7044 0.3504 0.7044 0.8393
No log 26.2353 446 0.7238 0.3078 0.7238 0.8508
No log 26.3529 448 0.7341 0.3078 0.7341 0.8568
No log 26.4706 450 0.7577 0.3820 0.7577 0.8705
No log 26.5882 452 0.8260 0.2905 0.8260 0.9088
No log 26.7059 454 0.9116 0.3074 0.9116 0.9548
No log 26.8235 456 1.0230 0.2921 1.0230 1.0114
No log 26.9412 458 1.2075 0.2601 1.2075 1.0988
No log 27.0588 460 1.3118 0.2928 1.3118 1.1453
No log 27.1765 462 1.3052 0.3142 1.3052 1.1425
No log 27.2941 464 1.2559 0.2601 1.2559 1.1207
No log 27.4118 466 1.1044 0.2278 1.1044 1.0509
No log 27.5294 468 0.9884 0.2958 0.9884 0.9942
No log 27.6471 470 0.9145 0.2516 0.9145 0.9563
No log 27.7647 472 0.8596 0.2805 0.8596 0.9272
No log 27.8824 474 0.8144 0.2523 0.8144 0.9024
No log 28.0 476 0.7989 0.2521 0.7989 0.8938
No log 28.1176 478 0.7984 0.2724 0.7984 0.8935
No log 28.2353 480 0.8129 0.3159 0.8129 0.9016
No log 28.3529 482 0.8975 0.2964 0.8975 0.9473
No log 28.4706 484 0.9907 0.3074 0.9907 0.9954
No log 28.5882 486 1.0228 0.3357 1.0228 1.0113
No log 28.7059 488 0.9472 0.3431 0.9472 0.9732
No log 28.8235 490 0.8254 0.3867 0.8254 0.9085
No log 28.9412 492 0.7523 0.4038 0.7523 0.8673
No log 29.0588 494 0.6974 0.4684 0.6974 0.8351
No log 29.1765 496 0.6882 0.4764 0.6882 0.8296
No log 29.2941 498 0.7176 0.4684 0.7176 0.8471
0.3337 29.4118 500 0.7451 0.4334 0.7451 0.8632
0.3337 29.5294 502 0.7823 0.3973 0.7823 0.8845
0.3337 29.6471 504 0.7687 0.4334 0.7687 0.8768
0.3337 29.7647 506 0.7375 0.4979 0.7375 0.8588
0.3337 29.8824 508 0.7668 0.4173 0.7668 0.8756
0.3337 30.0 510 0.8392 0.3867 0.8392 0.9161
0.3337 30.1176 512 0.9017 0.3867 0.9017 0.9496
0.3337 30.2353 514 0.9147 0.3867 0.9147 0.9564
0.3337 30.3529 516 0.8725 0.3867 0.8725 0.9341

Framework versions

  • Transformers 4.44.2
  • Pytorch 2.4.0+cu118
  • Datasets 2.21.0
  • Tokenizers 0.19.1
Downloads last month
8
Safetensors
Model size
135M params
Tensor type
F32
·
Inference Providers NEW
This model is not currently available via any of the supported third-party Inference Providers, and the model is not deployed on the HF Inference API.

Model tree for MayBashendy/ArabicNewSplits7_FineTuningAraBERT_run1_AugV5_k6_task7_organization

Finetuned
(4223)
this model