ArabicNewSplits7_usingALLEssays_FineTuningAraBERT_run3_AugV5_k15_task5_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: 1.1194
  • Qwk: 0.3281
  • Mse: 1.1194
  • Rmse: 1.0580

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 4.2053 -0.0087 4.2053 2.0507
No log 0.0833 4 2.3763 0.0540 2.3763 1.5415
No log 0.125 6 1.7816 0.0008 1.7816 1.3348
No log 0.1667 8 1.2240 0.1123 1.2240 1.1064
No log 0.2083 10 1.1562 0.1255 1.1562 1.0753
No log 0.25 12 1.4144 0.0925 1.4144 1.1893
No log 0.2917 14 2.5022 0.0848 2.5022 1.5818
No log 0.3333 16 2.1363 0.0890 2.1363 1.4616
No log 0.375 18 1.3953 -0.0690 1.3953 1.1812
No log 0.4167 20 1.2787 -0.0160 1.2787 1.1308
No log 0.4583 22 1.2952 -0.0096 1.2952 1.1381
No log 0.5 24 1.1531 0.2416 1.1531 1.0738
No log 0.5417 26 1.1123 0.2416 1.1123 1.0546
No log 0.5833 28 1.1398 0.1971 1.1398 1.0676
No log 0.625 30 1.1325 0.0454 1.1325 1.0642
No log 0.6667 32 1.1809 0.1285 1.1809 1.0867
No log 0.7083 34 1.2000 0.1285 1.2000 1.0955
No log 0.75 36 1.2008 0.1189 1.2008 1.0958
No log 0.7917 38 1.2600 0.1067 1.2600 1.1225
No log 0.8333 40 1.4563 0.2386 1.4563 1.2068
No log 0.875 42 1.4244 0.2076 1.4244 1.1935
No log 0.9167 44 1.2658 0.1523 1.2658 1.1251
No log 0.9583 46 1.1873 0.1482 1.1873 1.0896
No log 1.0 48 1.1669 0.1603 1.1669 1.0802
No log 1.0417 50 1.2022 0.2947 1.2022 1.0964
No log 1.0833 52 1.1870 0.2947 1.1870 1.0895
No log 1.125 54 1.1926 0.2330 1.1926 1.0921
No log 1.1667 56 1.0841 0.3127 1.0841 1.0412
No log 1.2083 58 1.0635 0.2416 1.0635 1.0313
No log 1.25 60 1.0327 0.1600 1.0327 1.0162
No log 1.2917 62 1.0714 0.2078 1.0714 1.0351
No log 1.3333 64 1.4336 0.2122 1.4336 1.1973
No log 1.375 66 1.7316 0.1502 1.7316 1.3159
No log 1.4167 68 1.5344 0.1863 1.5344 1.2387
No log 1.4583 70 1.1292 0.1631 1.1292 1.0626
No log 1.5 72 1.0842 0.2287 1.0842 1.0412
No log 1.5417 74 1.1615 0.2160 1.1615 1.0777
No log 1.5833 76 1.0605 0.2577 1.0605 1.0298
No log 1.625 78 1.0760 0.1379 1.0760 1.0373
No log 1.6667 80 1.1678 0.2195 1.1678 1.0806
No log 1.7083 82 1.0970 0.1557 1.0970 1.0474
No log 1.75 84 1.0984 0.2611 1.0984 1.0480
No log 1.7917 86 1.5000 0.1942 1.5000 1.2248
No log 1.8333 88 1.5696 0.1846 1.5696 1.2528
No log 1.875 90 1.3816 0.1161 1.3816 1.1754
No log 1.9167 92 1.1526 0.2183 1.1526 1.0736
No log 1.9583 94 1.1930 0.2217 1.1930 1.0922
No log 2.0 96 1.2349 0.1388 1.2349 1.1112
No log 2.0417 98 1.1642 0.1148 1.1642 1.0790
No log 2.0833 100 1.1251 0.0852 1.1251 1.0607
No log 2.125 102 1.1279 0.2391 1.1279 1.0620
No log 2.1667 104 1.1225 0.2794 1.1225 1.0595
No log 2.2083 106 1.1974 0.2287 1.1974 1.0943
No log 2.25 108 1.2281 0.2831 1.2281 1.1082
No log 2.2917 110 1.1856 0.3841 1.1856 1.0889
No log 2.3333 112 1.1980 0.3806 1.1980 1.0945
No log 2.375 114 1.2491 0.4282 1.2491 1.1176
No log 2.4167 116 1.3326 0.2244 1.3326 1.1544
No log 2.4583 118 1.3647 0.2244 1.3647 1.1682
No log 2.5 120 1.4020 0.1818 1.4020 1.1841
No log 2.5417 122 1.2786 0.3510 1.2786 1.1307
No log 2.5833 124 1.2540 0.3327 1.2540 1.1198
No log 2.625 126 1.2173 0.3162 1.2173 1.1033
No log 2.6667 128 1.1863 0.2047 1.1863 1.0892
No log 2.7083 130 1.1849 0.3768 1.1849 1.0885
No log 2.75 132 1.1403 0.2586 1.1403 1.0679
No log 2.7917 134 1.1357 0.2440 1.1357 1.0657
No log 2.8333 136 1.1380 0.2492 1.1380 1.0668
No log 2.875 138 1.1251 0.2347 1.1251 1.0607
No log 2.9167 140 1.1621 0.3225 1.1621 1.0780
No log 2.9583 142 1.2929 0.2650 1.2929 1.1371
No log 3.0 144 1.2760 0.2624 1.2760 1.1296
No log 3.0417 146 1.1596 0.2417 1.1596 1.0768
No log 3.0833 148 1.1395 0.3167 1.1395 1.0675
No log 3.125 150 1.1198 0.2625 1.1198 1.0582
No log 3.1667 152 1.0976 0.3209 1.0976 1.0477
No log 3.2083 154 1.0774 0.2932 1.0774 1.0380
No log 3.25 156 1.1538 0.1894 1.1538 1.0741
No log 3.2917 158 1.2813 0.2110 1.2813 1.1319
No log 3.3333 160 1.1644 0.3440 1.1644 1.0791
No log 3.375 162 1.1531 0.2766 1.1531 1.0738
No log 3.4167 164 1.1764 0.2616 1.1764 1.0846
No log 3.4583 166 1.1469 0.3014 1.1469 1.0709
No log 3.5 168 1.1476 0.3547 1.1476 1.0713
No log 3.5417 170 1.1644 0.3684 1.1644 1.0791
No log 3.5833 172 1.0741 0.2347 1.0741 1.0364
No log 3.625 174 1.0836 0.2370 1.0836 1.0410
No log 3.6667 176 1.0869 0.2347 1.0869 1.0426
No log 3.7083 178 1.0814 0.2347 1.0814 1.0399
No log 3.75 180 1.1124 0.3914 1.1124 1.0547
No log 3.7917 182 1.2116 0.2783 1.2116 1.1007
No log 3.8333 184 1.1939 0.3842 1.1939 1.0927
No log 3.875 186 1.1708 0.3000 1.1708 1.0820
No log 3.9167 188 1.1812 0.3631 1.1812 1.0868
No log 3.9583 190 1.3110 0.3228 1.3110 1.1450
No log 4.0 192 1.2855 0.2424 1.2855 1.1338
No log 4.0417 194 1.1154 0.2958 1.1154 1.0561
No log 4.0833 196 1.0918 0.3289 1.0918 1.0449
No log 4.125 198 1.0858 0.3011 1.0858 1.0420
No log 4.1667 200 1.0742 0.2556 1.0742 1.0364
No log 4.2083 202 1.0861 0.3316 1.0861 1.0422
No log 4.25 204 1.1254 0.2941 1.1254 1.0609
No log 4.2917 206 1.1108 0.3682 1.1108 1.0539
No log 4.3333 208 1.0850 0.3268 1.0850 1.0416
No log 4.375 210 1.0619 0.2972 1.0619 1.0305
No log 4.4167 212 1.0383 0.3087 1.0383 1.0190
No log 4.4583 214 0.9894 0.3209 0.9894 0.9947
No log 4.5 216 0.9916 0.3167 0.9916 0.9958
No log 4.5417 218 1.0118 0.3430 1.0118 1.0059
No log 4.5833 220 1.0293 0.3398 1.0293 1.0146
No log 4.625 222 1.0577 0.3521 1.0577 1.0285
No log 4.6667 224 1.1397 0.3607 1.1397 1.0675
No log 4.7083 226 1.0923 0.3596 1.0923 1.0451
No log 4.75 228 1.0485 0.3398 1.0485 1.0239
No log 4.7917 230 1.0811 0.3675 1.0811 1.0397
No log 4.8333 232 1.0862 0.2808 1.0862 1.0422
No log 4.875 234 1.0908 0.3169 1.0908 1.0444
No log 4.9167 236 1.1630 0.2999 1.1630 1.0784
No log 4.9583 238 1.2200 0.3197 1.2200 1.1046
No log 5.0 240 1.1683 0.3454 1.1683 1.0809
No log 5.0417 242 1.1316 0.3112 1.1316 1.0638
No log 5.0833 244 1.2341 0.2156 1.2341 1.1109
No log 5.125 246 1.2132 0.1717 1.2132 1.1015
No log 5.1667 248 1.1459 0.2579 1.1459 1.0705
No log 5.2083 250 1.1535 0.2416 1.1535 1.0740
No log 5.25 252 1.1172 0.2974 1.1172 1.0570
No log 5.2917 254 1.1180 0.3169 1.1180 1.0574
No log 5.3333 256 1.1361 0.3167 1.1361 1.0659
No log 5.375 258 1.1101 0.3554 1.1101 1.0536
No log 5.4167 260 1.0887 0.3430 1.0887 1.0434
No log 5.4583 262 1.0784 0.3908 1.0784 1.0385
No log 5.5 264 1.0938 0.3923 1.0938 1.0458
No log 5.5417 266 1.1280 0.3584 1.1280 1.0621
No log 5.5833 268 1.0710 0.4236 1.0710 1.0349
No log 5.625 270 1.0690 0.4165 1.0690 1.0339
No log 5.6667 272 1.0479 0.3787 1.0479 1.0237
No log 5.7083 274 1.0252 0.4110 1.0252 1.0125
No log 5.75 276 1.0295 0.4110 1.0295 1.0146
No log 5.7917 278 0.9808 0.3584 0.9808 0.9904
No log 5.8333 280 0.9536 0.3532 0.9536 0.9765
No log 5.875 282 0.9803 0.2577 0.9803 0.9901
No log 5.9167 284 1.0204 0.2714 1.0204 1.0102
No log 5.9583 286 1.0159 0.3965 1.0159 1.0079
No log 6.0 288 1.0648 0.4098 1.0648 1.0319
No log 6.0417 290 1.0887 0.4248 1.0887 1.0434
No log 6.0833 292 1.1880 0.3068 1.1880 1.0899
No log 6.125 294 1.2268 0.2539 1.2268 1.1076
No log 6.1667 296 1.0703 0.3152 1.0703 1.0346
No log 6.2083 298 1.0293 0.3224 1.0293 1.0145
No log 6.25 300 1.0617 0.2963 1.0617 1.0304
No log 6.2917 302 1.0473 0.3243 1.0473 1.0234
No log 6.3333 304 1.0109 0.3711 1.0109 1.0054
No log 6.375 306 1.0204 0.3243 1.0204 1.0102
No log 6.4167 308 1.1142 0.2893 1.1142 1.0555
No log 6.4583 310 1.0568 0.3603 1.0568 1.0280
No log 6.5 312 1.0102 0.3671 1.0102 1.0051
No log 6.5417 314 1.2463 0.3195 1.2463 1.1164
No log 6.5833 316 1.3050 0.3222 1.3050 1.1424
No log 6.625 318 1.1454 0.3421 1.1454 1.0702
No log 6.6667 320 1.1295 0.3682 1.1295 1.0628
No log 6.7083 322 1.3755 0.1780 1.3755 1.1728
No log 6.75 324 1.4479 0.1221 1.4479 1.2033
No log 6.7917 326 1.3028 0.2067 1.3028 1.1414
No log 6.8333 328 1.1033 0.3294 1.1033 1.0504
No log 6.875 330 1.0504 0.3540 1.0504 1.0249
No log 6.9167 332 1.0446 0.3493 1.0446 1.0221
No log 6.9583 334 1.0090 0.3398 1.0090 1.0045
No log 7.0 336 1.0343 0.3633 1.0343 1.0170
No log 7.0417 338 1.0816 0.4064 1.0816 1.0400
No log 7.0833 340 1.0314 0.3218 1.0314 1.0156
No log 7.125 342 1.1165 0.3907 1.1165 1.0566
No log 7.1667 344 1.2177 0.4 1.2177 1.1035
No log 7.2083 346 1.1369 0.3446 1.1369 1.0663
No log 7.25 348 1.0357 0.3455 1.0357 1.0177
No log 7.2917 350 1.0146 0.3398 1.0146 1.0073
No log 7.3333 352 1.0060 0.3263 1.0060 1.0030
No log 7.375 354 1.0166 0.2813 1.0166 1.0083
No log 7.4167 356 1.0233 0.2813 1.0233 1.0116
No log 7.4583 358 0.9977 0.3398 0.9977 0.9989
No log 7.5 360 1.0069 0.3532 1.0069 1.0034
No log 7.5417 362 1.0570 0.3231 1.0570 1.0281
No log 7.5833 364 1.0443 0.3840 1.0443 1.0219
No log 7.625 366 1.0357 0.3638 1.0357 1.0177
No log 7.6667 368 1.0401 0.3379 1.0401 1.0198
No log 7.7083 370 0.9889 0.3076 0.9889 0.9944
No log 7.75 372 0.9909 0.3398 0.9909 0.9954
No log 7.7917 374 1.0200 0.3144 1.0200 1.0100
No log 7.8333 376 0.9835 0.3112 0.9835 0.9917
No log 7.875 378 1.0064 0.2385 1.0064 1.0032
No log 7.9167 380 1.1160 0.2247 1.1160 1.0564
No log 7.9583 382 1.1073 0.2045 1.1073 1.0523
No log 8.0 384 1.0141 0.2268 1.0141 1.0070
No log 8.0417 386 1.0110 0.2767 1.0110 1.0055
No log 8.0833 388 1.0723 0.2470 1.0723 1.0355
No log 8.125 390 1.0547 0.2920 1.0547 1.0270
No log 8.1667 392 1.0477 0.3154 1.0477 1.0236
No log 8.2083 394 1.1195 0.2647 1.1195 1.0580
No log 8.25 396 1.1061 0.2302 1.1061 1.0517
No log 8.2917 398 1.0702 0.3602 1.0702 1.0345
No log 8.3333 400 1.0724 0.3375 1.0724 1.0356
No log 8.375 402 1.1531 0.3320 1.1531 1.0738
No log 8.4167 404 1.1483 0.3562 1.1483 1.0716
No log 8.4583 406 1.1248 0.3562 1.1248 1.0606
No log 8.5 408 1.0352 0.3750 1.0352 1.0175
No log 8.5417 410 1.0381 0.3985 1.0381 1.0189
No log 8.5833 412 1.0018 0.4105 1.0018 1.0009
No log 8.625 414 0.9817 0.3770 0.9817 0.9908
No log 8.6667 416 0.9731 0.4118 0.9731 0.9865
No log 8.7083 418 0.9742 0.4102 0.9742 0.9870
No log 8.75 420 1.0014 0.4227 1.0014 1.0007
No log 8.7917 422 0.9982 0.3980 0.9982 0.9991
No log 8.8333 424 1.0389 0.3876 1.0389 1.0193
No log 8.875 426 1.1157 0.3766 1.1157 1.0562
No log 8.9167 428 1.1207 0.4156 1.1207 1.0586
No log 8.9583 430 1.0792 0.3612 1.0792 1.0388
No log 9.0 432 1.0312 0.2360 1.0312 1.0155
No log 9.0417 434 1.0040 0.2766 1.0040 1.0020
No log 9.0833 436 0.9845 0.2952 0.9845 0.9922
No log 9.125 438 0.9916 0.2607 0.9916 0.9958
No log 9.1667 440 0.9981 0.2607 0.9981 0.9991
No log 9.2083 442 0.9916 0.3014 0.9916 0.9958
No log 9.25 444 0.9808 0.3398 0.9808 0.9904
No log 9.2917 446 1.0199 0.3490 1.0199 1.0099
No log 9.3333 448 1.0419 0.3395 1.0419 1.0207
No log 9.375 450 1.0041 0.4202 1.0041 1.0020
No log 9.4167 452 0.9971 0.4 0.9971 0.9986
No log 9.4583 454 1.0143 0.4261 1.0143 1.0071
No log 9.5 456 0.9926 0.4345 0.9926 0.9963
No log 9.5417 458 0.9866 0.4328 0.9866 0.9933
No log 9.5833 460 1.0043 0.4082 1.0043 1.0022
No log 9.625 462 0.9965 0.4202 0.9965 0.9982
No log 9.6667 464 0.9797 0.4434 0.9797 0.9898
No log 9.7083 466 0.9936 0.4434 0.9936 0.9968
No log 9.75 468 1.0160 0.4217 1.0160 1.0080
No log 9.7917 470 1.0466 0.3842 1.0466 1.0230
No log 9.8333 472 1.0353 0.3842 1.0353 1.0175
No log 9.875 474 0.9832 0.3675 0.9832 0.9916
No log 9.9167 476 0.9506 0.4014 0.9506 0.9750
No log 9.9583 478 0.9519 0.3878 0.9519 0.9756
No log 10.0 480 0.9706 0.3347 0.9706 0.9852
No log 10.0417 482 0.9713 0.3485 0.9713 0.9855
No log 10.0833 484 0.9761 0.3685 0.9761 0.9880
No log 10.125 486 1.0168 0.3818 1.0168 1.0083
No log 10.1667 488 1.0103 0.3818 1.0103 1.0051
No log 10.2083 490 1.0306 0.4321 1.0306 1.0152
No log 10.25 492 1.0497 0.4202 1.0497 1.0245
No log 10.2917 494 1.0288 0.4105 1.0288 1.0143
No log 10.3333 496 1.0581 0.3503 1.0581 1.0286
No log 10.375 498 1.0376 0.3855 1.0376 1.0186
0.3007 10.4167 500 1.0052 0.4093 1.0052 1.0026
0.3007 10.4583 502 1.0330 0.4082 1.0330 1.0164
0.3007 10.5 504 1.0277 0.3464 1.0277 1.0138
0.3007 10.5417 506 0.9604 0.3447 0.9604 0.9800
0.3007 10.5833 508 1.0298 0.3646 1.0298 1.0148
0.3007 10.625 510 1.1194 0.3281 1.1194 1.0580

Framework versions

  • Transformers 4.44.2
  • Pytorch 2.4.0+cu118
  • Datasets 2.21.0
  • Tokenizers 0.19.1
Downloads last month
1
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_usingALLEssays_FineTuningAraBERT_run3_AugV5_k15_task5_organization

Finetuned
(4033)
this model