ArabicNewSplits7_FineTuningAraBERT_run2_AugV5_k11_task3_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: 1.0975
  • Qwk: -0.1246
  • Mse: 1.0975
  • Rmse: 1.0476

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 0.0645 2 3.6127 0.0183 3.6127 1.9007
No log 0.1290 4 2.0410 0.0431 2.0410 1.4286
No log 0.1935 6 1.5048 -0.0241 1.5048 1.2267
No log 0.2581 8 1.1919 0.0282 1.1919 1.0917
No log 0.3226 10 0.8281 -0.2167 0.8281 0.9100
No log 0.3871 12 0.8849 -0.0459 0.8849 0.9407
No log 0.4516 14 1.1748 -0.0178 1.1748 1.0839
No log 0.5161 16 1.7601 -0.0743 1.7601 1.3267
No log 0.5806 18 1.8014 -0.0743 1.8014 1.3422
No log 0.6452 20 1.2788 -0.0446 1.2788 1.1308
No log 0.7097 22 0.9766 0.0089 0.9766 0.9883
No log 0.7742 24 0.7768 -0.0215 0.7768 0.8813
No log 0.8387 26 1.0236 0.0260 1.0236 1.0117
No log 0.9032 28 1.8304 -0.0263 1.8304 1.3529
No log 0.9677 30 1.5121 -0.0215 1.5121 1.2297
No log 1.0323 32 0.8341 0.1502 0.8341 0.9133
No log 1.0968 34 0.7456 0.0807 0.7456 0.8635
No log 1.1613 36 0.8103 0.0316 0.8103 0.9002
No log 1.2258 38 1.1054 0.0358 1.1054 1.0514
No log 1.2903 40 1.4066 0.0279 1.4066 1.1860
No log 1.3548 42 1.1434 0.0196 1.1434 1.0693
No log 1.4194 44 0.8618 -0.1203 0.8618 0.9283
No log 1.4839 46 0.7913 -0.0427 0.7913 0.8896
No log 1.5484 48 0.7787 0.0496 0.7787 0.8824
No log 1.6129 50 0.8869 -0.1121 0.8869 0.9418
No log 1.6774 52 1.2379 -0.0610 1.2379 1.1126
No log 1.7419 54 1.5237 0.0130 1.5237 1.2344
No log 1.8065 56 1.9291 0.0175 1.9291 1.3889
No log 1.8710 58 1.3203 -0.0067 1.3203 1.1490
No log 1.9355 60 0.8098 -0.1121 0.8098 0.8999
No log 2.0 62 0.8247 -0.0385 0.8247 0.9081
No log 2.0645 64 0.8231 -0.0237 0.8231 0.9072
No log 2.1290 66 0.7717 0.0732 0.7717 0.8785
No log 2.1935 68 1.0267 0.0107 1.0267 1.0133
No log 2.2581 70 1.6840 0.0901 1.6840 1.2977
No log 2.3226 72 1.8955 0.0619 1.8955 1.3768
No log 2.3871 74 1.1375 0.0336 1.1375 1.0665
No log 2.4516 76 0.8334 0.1724 0.8334 0.9129
No log 2.5161 78 0.8641 0.0770 0.8641 0.9296
No log 2.5806 80 0.7643 -0.0473 0.7643 0.8742
No log 2.6452 82 0.7716 0.0956 0.7716 0.8784
No log 2.7097 84 1.5252 0.1432 1.5252 1.2350
No log 2.7742 86 1.7994 0.0168 1.7994 1.3414
No log 2.8387 88 1.5046 0.0130 1.5046 1.2266
No log 2.9032 90 1.1167 -0.0291 1.1167 1.0568
No log 2.9677 92 1.0853 0.0045 1.0853 1.0418
No log 3.0323 94 1.0783 0.0045 1.0783 1.0384
No log 3.0968 96 1.0773 0.0065 1.0773 1.0379
No log 3.1613 98 0.8811 -0.0076 0.8811 0.9387
No log 3.2258 100 0.7727 -0.0108 0.7727 0.8790
No log 3.2903 102 0.8553 0.0134 0.8553 0.9248
No log 3.3548 104 0.9739 0.0605 0.9739 0.9869
No log 3.4194 106 1.0171 0.0249 1.0171 1.0085
No log 3.4839 108 1.0769 -0.0066 1.0769 1.0378
No log 3.5484 110 1.3997 0.0279 1.3997 1.1831
No log 3.6129 112 1.5962 -0.0330 1.5962 1.2634
No log 3.6774 114 1.1910 0.0448 1.1910 1.0913
No log 3.7419 116 1.1723 0.0799 1.1723 1.0827
No log 3.8065 118 1.1995 0.0741 1.1995 1.0952
No log 3.8710 120 1.2603 0.0707 1.2603 1.1226
No log 3.9355 122 0.9792 -0.1444 0.9792 0.9895
No log 4.0 124 0.9183 -0.2138 0.9183 0.9583
No log 4.0645 126 0.9083 -0.0798 0.9083 0.9531
No log 4.1290 128 1.0443 -0.0746 1.0443 1.0219
No log 4.1935 130 1.4139 -0.1172 1.4139 1.1891
No log 4.2581 132 1.3395 -0.0274 1.3395 1.1574
No log 4.3226 134 0.9325 0.0118 0.9325 0.9657
No log 4.3871 136 0.8525 -0.0517 0.8525 0.9233
No log 4.4516 138 0.8707 -0.0200 0.8707 0.9331
No log 4.5161 140 1.1391 0.0778 1.1391 1.0673
No log 4.5806 142 1.5130 0.0153 1.5130 1.2300
No log 4.6452 144 1.3119 0.0287 1.3119 1.1454
No log 4.7097 146 0.9904 0.0224 0.9904 0.9952
No log 4.7742 148 0.8171 -0.0070 0.8171 0.9040
No log 4.8387 150 0.8212 0.0856 0.8212 0.9062
No log 4.9032 152 0.9358 -0.0076 0.9358 0.9673
No log 4.9677 154 1.1182 0.0481 1.1182 1.0574
No log 5.0323 156 0.9408 0.0392 0.9408 0.9700
No log 5.0968 158 0.7875 0.1131 0.7875 0.8874
No log 5.1613 160 0.7852 0.1130 0.7852 0.8861
No log 5.2258 162 0.8438 0.2048 0.8438 0.9186
No log 5.2903 164 1.0743 0.1228 1.0743 1.0365
No log 5.3548 166 1.1039 0.1189 1.1039 1.0507
No log 5.4194 168 0.8254 0.1239 0.8254 0.9085
No log 5.4839 170 0.7786 0.0081 0.7786 0.8824
No log 5.5484 172 0.8092 -0.1146 0.8092 0.8996
No log 5.6129 174 0.8005 0.0679 0.8005 0.8947
No log 5.6774 176 0.9018 0.1065 0.9018 0.9496
No log 5.7419 178 1.2352 -0.0348 1.2352 1.1114
No log 5.8065 180 1.2191 -0.0361 1.2191 1.1041
No log 5.8710 182 0.8414 0.1149 0.8414 0.9173
No log 5.9355 184 0.7744 -0.1678 0.7744 0.8800
No log 6.0 186 0.8401 -0.0040 0.8401 0.9166
No log 6.0645 188 0.7477 -0.0322 0.7477 0.8647
No log 6.1290 190 0.7654 0.1440 0.7654 0.8749
No log 6.1935 192 1.4970 0.1330 1.4970 1.2235
No log 6.2581 194 1.9447 0.0242 1.9447 1.3945
No log 6.3226 196 1.6526 0.0434 1.6526 1.2855
No log 6.3871 198 1.0448 0.0915 1.0448 1.0222
No log 6.4516 200 0.7884 0.0200 0.7884 0.8879
No log 6.5161 202 0.7471 0.0764 0.7471 0.8644
No log 6.5806 204 0.7944 0.2070 0.7944 0.8913
No log 6.6452 206 1.1712 0.0104 1.1712 1.0822
No log 6.7097 208 1.3872 -0.0647 1.3872 1.1778
No log 6.7742 210 1.1462 -0.0597 1.1462 1.0706
No log 6.8387 212 0.7587 0.1286 0.7587 0.8710
No log 6.9032 214 0.7053 0.2315 0.7053 0.8398
No log 6.9677 216 0.7410 0.1047 0.7410 0.8608
No log 7.0323 218 0.9176 0.1825 0.9176 0.9579
No log 7.0968 220 0.9738 0.1825 0.9738 0.9868
No log 7.1613 222 0.8383 0.1239 0.8383 0.9156
No log 7.2258 224 0.7434 0.2358 0.7434 0.8622
No log 7.2903 226 0.7517 0.1336 0.7517 0.8670
No log 7.3548 228 0.8030 0.1193 0.8030 0.8961
No log 7.4194 230 0.9508 0.0200 0.9508 0.9751
No log 7.4839 232 0.9193 0.0250 0.9193 0.9588
No log 7.5484 234 0.9525 -0.0157 0.9525 0.9760
No log 7.6129 236 1.0342 -0.0899 1.0342 1.0170
No log 7.6774 238 1.0258 -0.0551 1.0258 1.0128
No log 7.7419 240 0.8080 0.1149 0.8080 0.8989
No log 7.8065 242 0.7368 0.1659 0.7368 0.8584
No log 7.8710 244 0.7414 0.1304 0.7414 0.8611
No log 7.9355 246 0.7741 0.0783 0.7741 0.8798
No log 8.0 248 0.8896 0.0762 0.8896 0.9432
No log 8.0645 250 1.1999 -0.0597 1.1999 1.0954
No log 8.1290 252 1.3903 -0.0959 1.3903 1.1791
No log 8.1935 254 1.2196 -0.0925 1.2196 1.1043
No log 8.2581 256 0.8410 0.0490 0.8410 0.9170
No log 8.3226 258 0.8315 -0.1329 0.8315 0.9118
No log 8.3871 260 0.8764 -0.1647 0.8764 0.9361
No log 8.4516 262 0.7840 -0.0366 0.7840 0.8854
No log 8.5161 264 1.0334 0.0508 1.0334 1.0166
No log 8.5806 266 1.9377 -0.0046 1.9377 1.3920
No log 8.6452 268 2.1811 -0.0120 2.1811 1.4769
No log 8.7097 270 1.7844 -0.0190 1.7844 1.3358
No log 8.7742 272 1.1139 0.0147 1.1139 1.0554
No log 8.8387 274 0.9395 0.0587 0.9395 0.9693
No log 8.9032 276 0.8154 0.1095 0.8154 0.9030
No log 8.9677 278 0.7681 -0.0056 0.7681 0.8764
No log 9.0323 280 0.7737 0.0376 0.7737 0.8796
No log 9.0968 282 0.7818 0.0327 0.7818 0.8842
No log 9.1613 284 0.7956 0.0246 0.7956 0.8920
No log 9.2258 286 0.8442 0.0497 0.8442 0.9188
No log 9.2903 288 1.0212 0.0200 1.0212 1.0105
No log 9.3548 290 1.1304 0.0443 1.1304 1.0632
No log 9.4194 292 1.0972 0.0443 1.0972 1.0475
No log 9.4839 294 0.9889 0.0175 0.9889 0.9944
No log 9.5484 296 0.8190 0.0837 0.8190 0.9050
No log 9.6129 298 0.7854 -0.0912 0.7854 0.8862
No log 9.6774 300 0.8057 -0.0976 0.8057 0.8976
No log 9.7419 302 0.8960 0.0538 0.8960 0.9466
No log 9.8065 304 1.0693 -0.1232 1.0693 1.0341
No log 9.8710 306 1.1229 -0.0905 1.1229 1.0597
No log 9.9355 308 0.9882 -0.0408 0.9882 0.9941
No log 10.0 310 0.8900 0.0791 0.8900 0.9434
No log 10.0645 312 0.8877 0.0465 0.8877 0.9422
No log 10.1290 314 0.9243 -0.0271 0.9243 0.9614
No log 10.1935 316 1.0636 -0.0862 1.0636 1.0313
No log 10.2581 318 1.1321 -0.0905 1.1321 1.0640
No log 10.3226 320 1.0424 -0.0486 1.0424 1.0210
No log 10.3871 322 0.9453 0.0041 0.9453 0.9722
No log 10.4516 324 0.9316 0.0424 0.9316 0.9652
No log 10.5161 326 1.0273 -0.0138 1.0273 1.0135
No log 10.5806 328 1.2673 -0.0629 1.2673 1.1257
No log 10.6452 330 1.2990 -0.0353 1.2990 1.1397
No log 10.7097 332 1.0638 -0.0539 1.0638 1.0314
No log 10.7742 334 0.9457 -0.0138 0.9457 0.9725
No log 10.8387 336 0.9238 0.1239 0.9238 0.9611
No log 10.9032 338 0.8745 -0.0132 0.8745 0.9351
No log 10.9677 340 0.8669 -0.0462 0.8669 0.9311
No log 11.0323 342 0.8725 -0.0462 0.8725 0.9341
No log 11.0968 344 0.8962 0.0741 0.8962 0.9467
No log 11.1613 346 0.9856 0.0250 0.9856 0.9927
No log 11.2258 348 1.0187 -0.0513 1.0187 1.0093
No log 11.2903 350 0.9376 0.0651 0.9376 0.9683
No log 11.3548 352 0.8895 0.0684 0.8895 0.9432
No log 11.4194 354 0.8601 0.0684 0.8601 0.9274
No log 11.4839 356 0.8392 0.0871 0.8392 0.9161
No log 11.5484 358 0.8715 0.0304 0.8715 0.9335
No log 11.6129 360 0.8642 -0.0097 0.8642 0.9296
No log 11.6774 362 0.8238 0.1800 0.8238 0.9076
No log 11.7419 364 0.8237 0.1475 0.8237 0.9076
No log 11.8065 366 0.8777 0.0684 0.8777 0.9369
No log 11.8710 368 0.9986 -0.0157 0.9986 0.9993
No log 11.9355 370 0.9584 -0.0138 0.9584 0.9790
No log 12.0 372 0.8808 0.0684 0.8808 0.9385
No log 12.0645 374 0.8076 0.1758 0.8076 0.8987
No log 12.1290 376 0.8211 0.1646 0.8211 0.9061
No log 12.1935 378 0.9441 -0.0138 0.9441 0.9716
No log 12.2581 380 0.9433 -0.0138 0.9433 0.9712
No log 12.3226 382 0.9140 -0.0138 0.9140 0.9560
No log 12.3871 384 0.9188 -0.0138 0.9188 0.9585
No log 12.4516 386 1.0220 -0.0575 1.0220 1.0110
No log 12.5161 388 1.0598 -0.1245 1.0598 1.0295
No log 12.5806 390 0.9323 -0.0539 0.9323 0.9656
No log 12.6452 392 0.8725 0.0304 0.8725 0.9341
No log 12.7097 394 0.9472 -0.0551 0.9472 0.9732
No log 12.7742 396 1.0039 -0.0899 1.0039 1.0019
No log 12.8387 398 0.9761 -0.0551 0.9761 0.9880
No log 12.9032 400 0.8966 0.0587 0.8966 0.9469
No log 12.9677 402 0.8158 0.1599 0.8158 0.9032
No log 13.0323 404 0.8290 -0.2338 0.8290 0.9105
No log 13.0968 406 0.8378 -0.1411 0.8378 0.9153
No log 13.1613 408 0.8867 0.0551 0.8867 0.9417
No log 13.2258 410 1.1302 -0.0905 1.1302 1.0631
No log 13.2903 412 1.3570 -0.0947 1.3570 1.1649
No log 13.3548 414 1.2674 -0.1254 1.2674 1.1258
No log 13.4194 416 1.0452 -0.0912 1.0452 1.0224
No log 13.4839 418 0.9109 0.1025 0.9109 0.9544
No log 13.5484 420 0.8774 0.1106 0.8774 0.9367
No log 13.6129 422 0.9069 0.0651 0.9069 0.9523
No log 13.6774 424 1.0431 -0.0899 1.0431 1.0213
No log 13.7419 426 1.1266 -0.1243 1.1266 1.0614
No log 13.8065 428 1.0826 -0.0892 1.0826 1.0405
No log 13.8710 430 0.9214 0.0755 0.9214 0.9599
No log 13.9355 432 0.8576 -0.0326 0.8576 0.9261
No log 14.0 434 0.8618 -0.0024 0.8618 0.9283
No log 14.0645 436 0.9181 0.0769 0.9181 0.9582
No log 14.1290 438 0.9928 0.1065 0.9928 0.9964
No log 14.1935 440 1.0033 0.1025 1.0033 1.0016
No log 14.2581 442 0.9818 0.0277 0.9818 0.9909
No log 14.3226 444 0.9458 0.0684 0.9458 0.9725
No log 14.3871 446 0.9371 0.0651 0.9371 0.9681
No log 14.4516 448 0.9358 -0.0138 0.9358 0.9674
No log 14.5161 450 0.9247 -0.0526 0.9247 0.9616
No log 14.5806 452 0.8488 0.1593 0.8488 0.9213
No log 14.6452 454 0.8253 0.0956 0.8253 0.9084
No log 14.7097 456 0.8529 0.1593 0.8529 0.9235
No log 14.7742 458 1.0054 -0.0899 1.0054 1.0027
No log 14.8387 460 1.2321 0.0130 1.2321 1.1100
No log 14.9032 462 1.3853 0.0031 1.3853 1.1770
No log 14.9677 464 1.2537 -0.0145 1.2537 1.1197
No log 15.0323 466 1.0034 -0.0885 1.0034 1.0017
No log 15.0968 468 0.8897 0.1105 0.8897 0.9432
No log 15.1613 470 0.9185 0.0277 0.9185 0.9584
No log 15.2258 472 0.9690 -0.0526 0.9690 0.9844
No log 15.2903 474 0.9756 -0.0885 0.9756 0.9877
No log 15.3548 476 0.9316 -0.0138 0.9316 0.9652
No log 15.4194 478 0.9031 0.1149 0.9031 0.9503
No log 15.4839 480 0.9048 0.0333 0.9048 0.9512
No log 15.5484 482 0.9529 -0.0513 0.9529 0.9762
No log 15.6129 484 0.9899 -0.0877 0.9899 0.9950
No log 15.6774 486 0.9737 -0.0500 0.9737 0.9868
No log 15.7419 488 0.9536 -0.0486 0.9536 0.9765
No log 15.8065 490 0.9012 0.2054 0.9012 0.9493
No log 15.8710 492 0.8363 0.1001 0.8363 0.9145
No log 15.9355 494 0.8172 0.1001 0.8172 0.9040
No log 16.0 496 0.8342 0.1001 0.8342 0.9134
No log 16.0645 498 0.8814 0.1193 0.8814 0.9388
0.3098 16.1290 500 0.9759 -0.0500 0.9759 0.9879
0.3098 16.1935 502 0.9435 0.0719 0.9435 0.9713
0.3098 16.2581 504 0.9250 0.1542 0.9250 0.9618
0.3098 16.3226 506 0.9600 0.1809 0.9600 0.9798
0.3098 16.3871 508 0.9024 0.1484 0.9024 0.9499
0.3098 16.4516 510 0.8220 0.0188 0.8220 0.9067
0.3098 16.5161 512 0.7862 0.0359 0.7862 0.8867
0.3098 16.5806 514 0.7537 0.0791 0.7537 0.8681
0.3098 16.6452 516 0.7212 0.0323 0.7212 0.8493
0.3098 16.7097 518 0.7349 0.2034 0.7349 0.8572
0.3098 16.7742 520 0.7999 0.1716 0.7999 0.8944
0.3098 16.8387 522 0.8206 0.1286 0.8206 0.9058
0.3098 16.9032 524 0.7911 0.0709 0.7911 0.8894
0.3098 16.9677 526 0.8265 0.0408 0.8265 0.9091
0.3098 17.0323 528 0.8467 0.0 0.8467 0.9202
0.3098 17.0968 530 0.8554 0.1423 0.8554 0.9249
0.3098 17.1613 532 0.9625 0.0362 0.9625 0.9811
0.3098 17.2258 534 0.9829 -0.0076 0.9829 0.9914
0.3098 17.2903 536 0.9723 0.0277 0.9723 0.9861
0.3098 17.3548 538 0.9682 0.0250 0.9682 0.9840
0.3098 17.4194 540 0.8926 0.1542 0.8926 0.9448
0.3098 17.4839 542 0.9084 0.1542 0.9084 0.9531
0.3098 17.5484 544 0.8933 0.1542 0.8933 0.9452
0.3098 17.6129 546 0.8213 0.1003 0.8213 0.9063
0.3098 17.6774 548 0.8364 -0.0517 0.8364 0.9146
0.3098 17.7419 550 0.8461 -0.0533 0.8461 0.9198
0.3098 17.8065 552 0.9080 0.1862 0.9080 0.9529
0.3098 17.8710 554 1.0399 0.0881 1.0399 1.0197
0.3098 17.9355 556 1.1060 -0.0557 1.1060 1.0517
0.3098 18.0 558 1.0695 -0.0526 1.0695 1.0341
0.3098 18.0645 560 0.9505 0.1025 0.9505 0.9749
0.3098 18.1290 562 0.8637 0.1286 0.8637 0.9294
0.3098 18.1935 564 0.8616 0.1817 0.8616 0.9282
0.3098 18.2581 566 0.9803 0.0986 0.9803 0.9901
0.3098 18.3226 568 1.0636 -0.0526 1.0636 1.0313
0.3098 18.3871 570 1.0435 -0.0526 1.0435 1.0215
0.3098 18.4516 572 0.9923 0.0986 0.9923 0.9961
0.3098 18.5161 574 0.8948 0.0871 0.8948 0.9459
0.3098 18.5806 576 0.8299 0.1859 0.8299 0.9110
0.3098 18.6452 578 0.7925 0.1529 0.7925 0.8902
0.3098 18.7097 580 0.7851 0.1943 0.7851 0.8861
0.3098 18.7742 582 0.8061 0.1817 0.8061 0.8979
0.3098 18.8387 584 0.8552 0.1190 0.8552 0.9248
0.3098 18.9032 586 0.9171 0.1484 0.9171 0.9577
0.3098 18.9677 588 0.9327 0.1147 0.9327 0.9658
0.3098 19.0323 590 0.9133 0.2032 0.9133 0.9557
0.3098 19.0968 592 0.9178 0.1758 0.9178 0.9580
0.3098 19.1613 594 0.8968 0.1727 0.8968 0.9470
0.3098 19.2258 596 0.8584 0.1318 0.8584 0.9265
0.3098 19.2903 598 0.8452 0.1318 0.8452 0.9193
0.3098 19.3548 600 0.8833 0.1727 0.8833 0.9398
0.3098 19.4194 602 0.9765 -0.0471 0.9765 0.9882
0.3098 19.4839 604 1.0810 -0.1238 1.0810 1.0397
0.3098 19.5484 606 1.0831 -0.1238 1.0831 1.0407
0.3098 19.6129 608 0.9775 -0.0870 0.9775 0.9887
0.3098 19.6774 610 0.9304 -0.0118 0.9304 0.9646
0.3098 19.7419 612 0.9089 0.1542 0.9089 0.9534
0.3098 19.8065 614 0.9231 -0.0118 0.9231 0.9608
0.3098 19.8710 616 0.9663 -0.0877 0.9663 0.9830
0.3098 19.9355 618 1.0580 -0.1243 1.0580 1.0286
0.3098 20.0 620 1.1110 -0.1248 1.1110 1.0540
0.3098 20.0645 622 1.1221 -0.0953 1.1221 1.0593
0.3098 20.1290 624 1.0975 -0.1246 1.0975 1.0476

Framework versions

  • Transformers 4.44.2
  • Pytorch 2.4.0+cu118
  • Datasets 2.21.0
  • Tokenizers 0.19.1
Downloads last month
0
Safetensors
Model size
135M params
Tensor type
F32
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for MayBashendy/ArabicNewSplits7_FineTuningAraBERT_run2_AugV5_k11_task3_organization

Finetuned
(2730)
this model