ArabicNewSplits7_FineTuningAraBERT_run1_AugV5_k10_task2_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: 1.1932
  • Qwk: 0.2184
  • Mse: 1.1932
  • Rmse: 1.0923

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 0.0625 2 4.7139 0.0010 4.7139 2.1712
No log 0.125 4 2.8900 -0.0104 2.8900 1.7000
No log 0.1875 6 1.9753 0.0023 1.9753 1.4055
No log 0.25 8 1.5565 -0.0344 1.5565 1.2476
No log 0.3125 10 1.4300 0.0161 1.4300 1.1958
No log 0.375 12 1.3430 0.0462 1.3430 1.1589
No log 0.4375 14 1.2974 0.0522 1.2974 1.1390
No log 0.5 16 1.3392 -0.0506 1.3392 1.1572
No log 0.5625 18 1.3422 -0.0337 1.3422 1.1585
No log 0.625 20 1.3682 -0.0817 1.3682 1.1697
No log 0.6875 22 1.3660 -0.0304 1.3660 1.1687
No log 0.75 24 1.1839 0.2023 1.1839 1.0881
No log 0.8125 26 1.1867 0.1144 1.1867 1.0894
No log 0.875 28 1.2095 0.0700 1.2095 1.0998
No log 0.9375 30 1.2066 0.0872 1.2066 1.0985
No log 1.0 32 1.1784 0.1649 1.1784 1.0855
No log 1.0625 34 1.2612 0.0666 1.2612 1.1230
No log 1.125 36 1.3541 0.0865 1.3541 1.1637
No log 1.1875 38 1.3117 0.0776 1.3117 1.1453
No log 1.25 40 1.3342 0.0776 1.3342 1.1551
No log 1.3125 42 1.3027 0.0788 1.3027 1.1413
No log 1.375 44 1.3135 0.0300 1.3135 1.1461
No log 1.4375 46 1.2602 0.0878 1.2602 1.1226
No log 1.5 48 1.1534 0.0974 1.1534 1.0740
No log 1.5625 50 1.1132 0.2097 1.1132 1.0551
No log 1.625 52 1.1227 0.2574 1.1227 1.0596
No log 1.6875 54 1.1080 0.2574 1.1080 1.0526
No log 1.75 56 1.0880 0.2416 1.0880 1.0431
No log 1.8125 58 1.0919 0.2658 1.0919 1.0450
No log 1.875 60 1.1263 0.2155 1.1263 1.0613
No log 1.9375 62 1.1619 0.1532 1.1619 1.0779
No log 2.0 64 1.1376 0.1532 1.1376 1.0666
No log 2.0625 66 1.1440 0.1076 1.1440 1.0696
No log 2.125 68 1.1586 0.2936 1.1586 1.0764
No log 2.1875 70 1.1341 0.3038 1.1341 1.0649
No log 2.25 72 1.0713 0.2455 1.0713 1.0350
No log 2.3125 74 1.1205 0.1868 1.1205 1.0585
No log 2.375 76 1.3009 0.2132 1.3009 1.1406
No log 2.4375 78 1.3299 0.1906 1.3299 1.1532
No log 2.5 80 1.2716 0.1675 1.2716 1.1277
No log 2.5625 82 1.2689 0.3074 1.2689 1.1264
No log 2.625 84 1.1958 0.4449 1.1958 1.0935
No log 2.6875 86 1.1493 0.2609 1.1493 1.0720
No log 2.75 88 1.4899 0.1968 1.4899 1.2206
No log 2.8125 90 1.6000 0.1427 1.6000 1.2649
No log 2.875 92 1.5139 -0.0212 1.5139 1.2304
No log 2.9375 94 1.3728 0.0277 1.3728 1.1717
No log 3.0 96 1.2300 0.0711 1.2300 1.1090
No log 3.0625 98 1.0556 0.2782 1.0556 1.0274
No log 3.125 100 1.0151 0.3660 1.0151 1.0075
No log 3.1875 102 0.9699 0.3830 0.9699 0.9848
No log 3.25 104 0.9851 0.2721 0.9851 0.9925
No log 3.3125 106 1.2492 0.3392 1.2492 1.1177
No log 3.375 108 1.4202 0.2685 1.4202 1.1917
No log 3.4375 110 1.1910 0.2558 1.1910 1.0913
No log 3.5 112 0.9927 0.3345 0.9927 0.9963
No log 3.5625 114 1.0314 0.3714 1.0314 1.0156
No log 3.625 116 0.9776 0.4428 0.9776 0.9887
No log 3.6875 118 0.9447 0.4282 0.9447 0.9720
No log 3.75 120 0.9500 0.4423 0.9500 0.9747
No log 3.8125 122 0.9303 0.4240 0.9303 0.9645
No log 3.875 124 1.0360 0.3452 1.0360 1.0179
No log 3.9375 126 1.2083 0.3641 1.2083 1.0992
No log 4.0 128 1.0842 0.4186 1.0842 1.0412
No log 4.0625 130 0.9403 0.3196 0.9403 0.9697
No log 4.125 132 0.9267 0.3271 0.9267 0.9626
No log 4.1875 134 0.9419 0.3838 0.9419 0.9705
No log 4.25 136 0.9786 0.2313 0.9786 0.9893
No log 4.3125 138 0.9924 0.2704 0.9924 0.9962
No log 4.375 140 1.0047 0.3705 1.0047 1.0024
No log 4.4375 142 1.0333 0.3300 1.0333 1.0165
No log 4.5 144 1.1033 0.2933 1.1033 1.0504
No log 4.5625 146 1.1297 0.2933 1.1297 1.0629
No log 4.625 148 1.1737 0.3131 1.1737 1.0834
No log 4.6875 150 1.1405 0.3225 1.1405 1.0679
No log 4.75 152 1.0804 0.3268 1.0804 1.0394
No log 4.8125 154 1.0931 0.3359 1.0931 1.0455
No log 4.875 156 1.0402 0.2592 1.0402 1.0199
No log 4.9375 158 1.0393 0.2942 1.0393 1.0195
No log 5.0 160 1.0389 0.3925 1.0389 1.0193
No log 5.0625 162 1.0213 0.3185 1.0213 1.0106
No log 5.125 164 1.0677 0.2683 1.0677 1.0333
No log 5.1875 166 1.1239 0.2452 1.1239 1.0602
No log 5.25 168 1.0375 0.2909 1.0375 1.0186
No log 5.3125 170 0.9798 0.3668 0.9798 0.9899
No log 5.375 172 1.0402 0.3879 1.0402 1.0199
No log 5.4375 174 0.9406 0.4292 0.9406 0.9698
No log 5.5 176 1.0923 0.3151 1.0923 1.0451
No log 5.5625 178 1.2214 0.3648 1.2214 1.1052
No log 5.625 180 1.0723 0.3134 1.0723 1.0355
No log 5.6875 182 0.9497 0.3762 0.9497 0.9745
No log 5.75 184 0.9400 0.3902 0.9400 0.9695
No log 5.8125 186 0.9703 0.3654 0.9703 0.9850
No log 5.875 188 0.9991 0.3683 0.9991 0.9996
No log 5.9375 190 0.9498 0.3703 0.9498 0.9746
No log 6.0 192 0.9344 0.4050 0.9344 0.9667
No log 6.0625 194 0.9979 0.3568 0.9979 0.9990
No log 6.125 196 1.1160 0.3574 1.1160 1.0564
No log 6.1875 198 1.0585 0.2667 1.0585 1.0288
No log 6.25 200 1.0052 0.3786 1.0052 1.0026
No log 6.3125 202 0.9775 0.3147 0.9775 0.9887
No log 6.375 204 1.0150 0.3045 1.0150 1.0075
No log 6.4375 206 1.0002 0.3547 1.0002 1.0001
No log 6.5 208 0.9401 0.3191 0.9401 0.9696
No log 6.5625 210 0.9083 0.3720 0.9083 0.9530
No log 6.625 212 0.9923 0.2574 0.9923 0.9962
No log 6.6875 214 1.2130 0.3163 1.2130 1.1014
No log 6.75 216 1.1587 0.3265 1.1587 1.0764
No log 6.8125 218 1.0200 0.4252 1.0200 1.0100
No log 6.875 220 0.9781 0.4255 0.9781 0.9890
No log 6.9375 222 0.9546 0.4533 0.9546 0.9770
No log 7.0 224 1.0398 0.4048 1.0398 1.0197
No log 7.0625 226 1.0154 0.3716 1.0154 1.0077
No log 7.125 228 0.9436 0.3621 0.9436 0.9714
No log 7.1875 230 0.9423 0.3117 0.9423 0.9707
No log 7.25 232 1.0244 0.3786 1.0244 1.0122
No log 7.3125 234 1.0551 0.3530 1.0551 1.0272
No log 7.375 236 1.0865 0.3438 1.0865 1.0424
No log 7.4375 238 0.9594 0.3720 0.9594 0.9795
No log 7.5 240 0.9666 0.3773 0.9666 0.9832
No log 7.5625 242 0.9709 0.3908 0.9709 0.9854
No log 7.625 244 0.9312 0.3756 0.9312 0.9650
No log 7.6875 246 1.0629 0.3452 1.0629 1.0310
No log 7.75 248 1.0900 0.4099 1.0900 1.0440
No log 7.8125 250 0.9520 0.4505 0.9520 0.9757
No log 7.875 252 0.9677 0.4139 0.9677 0.9837
No log 7.9375 254 0.9737 0.3781 0.9737 0.9868
No log 8.0 256 0.9543 0.4278 0.9543 0.9769
No log 8.0625 258 1.0983 0.2978 1.0983 1.0480
No log 8.125 260 1.1171 0.2349 1.1171 1.0569
No log 8.1875 262 0.9997 0.3687 0.9997 0.9998
No log 8.25 264 0.9528 0.3437 0.9528 0.9761
No log 8.3125 266 0.9612 0.3437 0.9612 0.9804
No log 8.375 268 0.9801 0.3217 0.9801 0.9900
No log 8.4375 270 1.0668 0.2904 1.0668 1.0328
No log 8.5 272 1.0979 0.2381 1.0979 1.0478
No log 8.5625 274 1.0323 0.2904 1.0323 1.0160
No log 8.625 276 0.9636 0.3424 0.9636 0.9817
No log 8.6875 278 0.9692 0.4405 0.9692 0.9845
No log 8.75 280 1.0087 0.4238 1.0087 1.0044
No log 8.8125 282 0.9756 0.4145 0.9756 0.9877
No log 8.875 284 0.9371 0.3821 0.9371 0.9680
No log 8.9375 286 0.9597 0.3902 0.9597 0.9796
No log 9.0 288 0.9468 0.4292 0.9468 0.9730
No log 9.0625 290 0.9565 0.4609 0.9565 0.9780
No log 9.125 292 0.9611 0.4159 0.9611 0.9804
No log 9.1875 294 0.9801 0.3961 0.9801 0.9900
No log 9.25 296 1.0811 0.3390 1.0811 1.0397
No log 9.3125 298 1.1141 0.3043 1.1141 1.0555
No log 9.375 300 1.0285 0.4091 1.0285 1.0141
No log 9.4375 302 1.0298 0.4349 1.0298 1.0148
No log 9.5 304 1.0520 0.4089 1.0520 1.0257
No log 9.5625 306 1.1099 0.3595 1.1099 1.0535
No log 9.625 308 1.2588 0.2851 1.2588 1.1219
No log 9.6875 310 1.2141 0.2574 1.2141 1.1019
No log 9.75 312 1.0536 0.3045 1.0536 1.0264
No log 9.8125 314 0.9995 0.3443 0.9995 0.9998
No log 9.875 316 1.0061 0.3821 1.0061 1.0030
No log 9.9375 318 1.0046 0.3552 1.0046 1.0023
No log 10.0 320 1.0891 0.2668 1.0891 1.0436
No log 10.0625 322 1.1054 0.2799 1.1054 1.0514
No log 10.125 324 1.0160 0.2976 1.0160 1.0080
No log 10.1875 326 0.9600 0.3742 0.9600 0.9798
No log 10.25 328 0.9854 0.4025 0.9854 0.9927
No log 10.3125 330 1.0630 0.3936 1.0630 1.0310
No log 10.375 332 1.1771 0.3798 1.1771 1.0849
No log 10.4375 334 1.1019 0.3271 1.1019 1.0497
No log 10.5 336 0.9898 0.3300 0.9898 0.9949
No log 10.5625 338 0.9950 0.3042 0.9950 0.9975
No log 10.625 340 1.0259 0.2995 1.0259 1.0128
No log 10.6875 342 1.0849 0.3091 1.0849 1.0416
No log 10.75 344 1.0668 0.3200 1.0668 1.0329
No log 10.8125 346 1.0233 0.3361 1.0233 1.0116
No log 10.875 348 1.0579 0.3703 1.0579 1.0285
No log 10.9375 350 1.0923 0.3149 1.0923 1.0451
No log 11.0 352 1.1119 0.2838 1.1119 1.0545
No log 11.0625 354 1.1240 0.2623 1.1240 1.0602
No log 11.125 356 1.1298 0.2165 1.1298 1.0629
No log 11.1875 358 1.1122 0.2024 1.1122 1.0546
No log 11.25 360 1.0716 0.2967 1.0716 1.0352
No log 11.3125 362 1.0557 0.2794 1.0557 1.0275
No log 11.375 364 1.0512 0.3328 1.0512 1.0253
No log 11.4375 366 1.0212 0.3168 1.0212 1.0105
No log 11.5 368 1.0273 0.2822 1.0273 1.0135
No log 11.5625 370 1.0429 0.2951 1.0429 1.0212
No log 11.625 372 1.0291 0.3533 1.0291 1.0144
No log 11.6875 374 1.0155 0.4306 1.0155 1.0077
No log 11.75 376 1.0027 0.4340 1.0027 1.0013
No log 11.8125 378 1.0004 0.4125 1.0004 1.0002
No log 11.875 380 1.0515 0.3157 1.0515 1.0254
No log 11.9375 382 1.1136 0.2844 1.1136 1.0553
No log 12.0 384 1.0688 0.3225 1.0688 1.0338
No log 12.0625 386 1.0147 0.3159 1.0147 1.0073
No log 12.125 388 1.0424 0.2939 1.0424 1.0210
No log 12.1875 390 1.0077 0.3956 1.0077 1.0038
No log 12.25 392 0.9972 0.3802 0.9972 0.9986
No log 12.3125 394 1.1142 0.3197 1.1142 1.0556
No log 12.375 396 1.1032 0.2958 1.1032 1.0503
No log 12.4375 398 1.0066 0.3206 1.0066 1.0033
No log 12.5 400 0.9675 0.3115 0.9675 0.9836
No log 12.5625 402 0.9541 0.3608 0.9541 0.9768
No log 12.625 404 0.9721 0.3608 0.9721 0.9860
No log 12.6875 406 1.0143 0.2830 1.0143 1.0071
No log 12.75 408 1.0311 0.2668 1.0311 1.0154
No log 12.8125 410 1.0408 0.2930 1.0408 1.0202
No log 12.875 412 1.0621 0.2930 1.0621 1.0306
No log 12.9375 414 1.1259 0.2934 1.1259 1.0611
No log 13.0 416 1.1072 0.2619 1.1072 1.0522
No log 13.0625 418 1.0309 0.2317 1.0309 1.0153
No log 13.125 420 0.9956 0.2772 0.9956 0.9978
No log 13.1875 422 1.0111 0.2219 1.0111 1.0055
No log 13.25 424 1.1095 0.2417 1.1095 1.0533
No log 13.3125 426 1.1453 0.2681 1.1453 1.0702
No log 13.375 428 1.1111 0.2417 1.1111 1.0541
No log 13.4375 430 1.1235 0.2681 1.1235 1.0599
No log 13.5 432 1.0749 0.2590 1.0749 1.0368
No log 13.5625 434 0.9845 0.3861 0.9845 0.9922
No log 13.625 436 0.9618 0.3565 0.9618 0.9807
No log 13.6875 438 0.9717 0.4013 0.9717 0.9857
No log 13.75 440 1.0283 0.3043 1.0283 1.0140
No log 13.8125 442 1.1342 0.3466 1.1342 1.0650
No log 13.875 444 1.1302 0.3711 1.1302 1.0631
No log 13.9375 446 1.0953 0.3278 1.0953 1.0465
No log 14.0 448 1.0272 0.3892 1.0272 1.0135
No log 14.0625 450 0.9892 0.3550 0.9892 0.9946
No log 14.125 452 1.0126 0.4066 1.0126 1.0063
No log 14.1875 454 1.0191 0.4066 1.0191 1.0095
No log 14.25 456 1.0102 0.3344 1.0102 1.0051
No log 14.3125 458 1.0212 0.3261 1.0212 1.0105
No log 14.375 460 1.0258 0.2908 1.0258 1.0128
No log 14.4375 462 1.0087 0.3243 1.0087 1.0043
No log 14.5 464 0.9887 0.3953 0.9887 0.9943
No log 14.5625 466 0.9905 0.3953 0.9905 0.9953
No log 14.625 468 1.0241 0.3295 1.0241 1.0120
No log 14.6875 470 1.0436 0.3505 1.0436 1.0216
No log 14.75 472 1.0377 0.3343 1.0377 1.0187
No log 14.8125 474 1.0012 0.3729 1.0012 1.0006
No log 14.875 476 0.9742 0.3263 0.9742 0.9870
No log 14.9375 478 0.9913 0.3217 0.9913 0.9956
No log 15.0 480 1.0142 0.3926 1.0142 1.0071
No log 15.0625 482 1.0526 0.3182 1.0526 1.0260
No log 15.125 484 1.0089 0.3931 1.0089 1.0044
No log 15.1875 486 0.9708 0.3408 0.9708 0.9853
No log 15.25 488 0.9945 0.3829 0.9945 0.9973
No log 15.3125 490 1.0002 0.3066 1.0002 1.0001
No log 15.375 492 1.0819 0.2547 1.0819 1.0401
No log 15.4375 494 1.2911 0.2881 1.2911 1.1362
No log 15.5 496 1.3307 0.2632 1.3307 1.1535
No log 15.5625 498 1.3232 0.2309 1.3232 1.1503
0.3849 15.625 500 1.1949 0.2590 1.1949 1.0931
0.3849 15.6875 502 1.1535 0.2490 1.1535 1.0740
0.3849 15.75 504 1.1512 0.1959 1.1512 1.0729
0.3849 15.8125 506 1.1824 0.2791 1.1824 1.0874
0.3849 15.875 508 1.1749 0.2762 1.1749 1.0839
0.3849 15.9375 510 1.1501 0.2184 1.1501 1.0724
0.3849 16.0 512 1.1027 0.2997 1.1027 1.0501
0.3849 16.0625 514 1.0550 0.2574 1.0550 1.0271
0.3849 16.125 516 1.0370 0.2723 1.0370 1.0183
0.3849 16.1875 518 1.0515 0.2899 1.0515 1.0254
0.3849 16.25 520 1.0609 0.2604 1.0609 1.0300
0.3849 16.3125 522 1.0563 0.2604 1.0563 1.0277
0.3849 16.375 524 1.0503 0.2998 1.0503 1.0248
0.3849 16.4375 526 1.0320 0.2604 1.0320 1.0159
0.3849 16.5 528 1.0517 0.2702 1.0517 1.0255
0.3849 16.5625 530 1.1230 0.2909 1.1230 1.0597
0.3849 16.625 532 1.2592 0.2807 1.2592 1.1221
0.3849 16.6875 534 1.2716 0.2201 1.2716 1.1276
0.3849 16.75 536 1.1756 0.2460 1.1756 1.0843
0.3849 16.8125 538 1.0420 0.2470 1.0420 1.0208
0.3849 16.875 540 1.0136 0.2743 1.0136 1.0068
0.3849 16.9375 542 1.0140 0.2539 1.0140 1.0070
0.3849 17.0 544 1.0705 0.2516 1.0705 1.0346
0.3849 17.0625 546 1.1635 0.2184 1.1635 1.0787
0.3849 17.125 548 1.2326 0.2460 1.2326 1.1102
0.3849 17.1875 550 1.1932 0.2184 1.1932 1.0923

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/ArabicNewSplits7_FineTuningAraBERT_run1_AugV5_k10_task2_organization

Finetuned
(4023)
this model