ArabicNewSplits7_FineTuningAraBERT_run2_AugV5_k12_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: 0.7560
  • Qwk: 0.4440
  • Mse: 0.7560
  • Rmse: 0.8695

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 3.8998 0.0124 3.8998 1.9748
No log 0.125 4 1.8693 0.0318 1.8693 1.3672
No log 0.1875 6 1.1996 -0.0627 1.1996 1.0953
No log 0.25 8 1.0795 0.2441 1.0795 1.0390
No log 0.3125 10 1.0976 0.1418 1.0976 1.0476
No log 0.375 12 1.2351 0.0249 1.2351 1.1114
No log 0.4375 14 1.4945 -0.0858 1.4945 1.2225
No log 0.5 16 1.6856 -0.0411 1.6856 1.2983
No log 0.5625 18 1.5115 -0.0560 1.5115 1.2294
No log 0.625 20 1.2983 -0.0328 1.2983 1.1394
No log 0.6875 22 1.1399 0.1268 1.1399 1.0676
No log 0.75 24 1.0546 0.2416 1.0546 1.0270
No log 0.8125 26 1.0514 0.0762 1.0514 1.0254
No log 0.875 28 1.0289 0.1076 1.0289 1.0143
No log 0.9375 30 1.0153 0.4051 1.0153 1.0076
No log 1.0 32 1.0239 0.2343 1.0239 1.0119
No log 1.0625 34 1.1216 0.1142 1.1216 1.0591
No log 1.125 36 1.1869 0.0 1.1869 1.0894
No log 1.1875 38 1.1328 0.0996 1.1328 1.0643
No log 1.25 40 0.9713 0.4167 0.9713 0.9855
No log 1.3125 42 0.9117 0.4031 0.9117 0.9548
No log 1.375 44 0.9185 0.4218 0.9185 0.9584
No log 1.4375 46 0.9131 0.4512 0.9131 0.9556
No log 1.5 48 0.9881 0.3790 0.9881 0.9940
No log 1.5625 50 1.1039 0.2513 1.1039 1.0507
No log 1.625 52 1.1056 0.2850 1.1056 1.0515
No log 1.6875 54 0.9419 0.375 0.9419 0.9705
No log 1.75 56 0.9125 0.2314 0.9125 0.9553
No log 1.8125 58 1.0117 0.1799 1.0117 1.0058
No log 1.875 60 1.0029 0.1545 1.0029 1.0014
No log 1.9375 62 0.9630 0.1783 0.9630 0.9813
No log 2.0 64 0.9759 0.3310 0.9759 0.9879
No log 2.0625 66 0.9466 0.4167 0.9466 0.9729
No log 2.125 68 0.8062 0.3435 0.8062 0.8979
No log 2.1875 70 0.7767 0.3652 0.7767 0.8813
No log 2.25 72 0.8180 0.3164 0.8180 0.9044
No log 2.3125 74 0.7902 0.3603 0.7902 0.8889
No log 2.375 76 0.7129 0.4831 0.7129 0.8444
No log 2.4375 78 0.7098 0.5763 0.7098 0.8425
No log 2.5 80 0.7035 0.5559 0.7035 0.8387
No log 2.5625 82 0.6607 0.5153 0.6607 0.8128
No log 2.625 84 0.6674 0.5562 0.6674 0.8170
No log 2.6875 86 0.6472 0.6272 0.6472 0.8045
No log 2.75 88 0.6978 0.6015 0.6978 0.8353
No log 2.8125 90 0.8253 0.5614 0.8253 0.9085
No log 2.875 92 1.0172 0.3942 1.0172 1.0086
No log 2.9375 94 1.0333 0.4073 1.0333 1.0165
No log 3.0 96 0.9521 0.4668 0.9521 0.9758
No log 3.0625 98 0.8172 0.6035 0.8172 0.9040
No log 3.125 100 0.7584 0.5902 0.7584 0.8709
No log 3.1875 102 0.7435 0.5675 0.7435 0.8622
No log 3.25 104 0.7553 0.5521 0.7553 0.8691
No log 3.3125 106 0.6618 0.6071 0.6618 0.8135
No log 3.375 108 0.6580 0.6445 0.6580 0.8112
No log 3.4375 110 0.7096 0.6529 0.7096 0.8424
No log 3.5 112 0.7748 0.5275 0.7748 0.8802
No log 3.5625 114 0.8174 0.5485 0.8174 0.9041
No log 3.625 116 0.7901 0.5239 0.7901 0.8889
No log 3.6875 118 0.8013 0.5968 0.8013 0.8952
No log 3.75 120 0.8091 0.6141 0.8091 0.8995
No log 3.8125 122 0.7102 0.6147 0.7102 0.8428
No log 3.875 124 0.6779 0.5495 0.6779 0.8233
No log 3.9375 126 0.6320 0.5603 0.6320 0.7950
No log 4.0 128 0.6061 0.5934 0.6061 0.7785
No log 4.0625 130 0.5691 0.6886 0.5691 0.7544
No log 4.125 132 0.5830 0.6719 0.5830 0.7635
No log 4.1875 134 0.5386 0.6878 0.5386 0.7339
No log 4.25 136 0.4913 0.7231 0.4913 0.7009
No log 4.3125 138 0.4835 0.7182 0.4835 0.6954
No log 4.375 140 0.5287 0.7483 0.5287 0.7271
No log 4.4375 142 0.6172 0.7469 0.6172 0.7856
No log 4.5 144 0.5426 0.7437 0.5426 0.7366
No log 4.5625 146 0.4731 0.7544 0.4731 0.6878
No log 4.625 148 0.4849 0.7449 0.4849 0.6963
No log 4.6875 150 0.5305 0.7437 0.5305 0.7284
No log 4.75 152 0.6914 0.6653 0.6914 0.8315
No log 4.8125 154 0.7118 0.6061 0.7118 0.8437
No log 4.875 156 0.6310 0.6053 0.6310 0.7944
No log 4.9375 158 0.6175 0.6301 0.6175 0.7858
No log 5.0 160 0.6002 0.6311 0.6002 0.7747
No log 5.0625 162 0.5984 0.5798 0.5984 0.7735
No log 5.125 164 0.6966 0.6170 0.6966 0.8346
No log 5.1875 166 0.9324 0.4854 0.9324 0.9656
No log 5.25 168 0.9354 0.5404 0.9354 0.9672
No log 5.3125 170 0.7437 0.6190 0.7437 0.8624
No log 5.375 172 0.6694 0.6573 0.6694 0.8182
No log 5.4375 174 0.7013 0.6019 0.7013 0.8375
No log 5.5 176 0.7319 0.5705 0.7319 0.8555
No log 5.5625 178 0.6687 0.6434 0.6687 0.8178
No log 5.625 180 0.5748 0.6482 0.5748 0.7582
No log 5.6875 182 0.5266 0.6606 0.5266 0.7257
No log 5.75 184 0.5267 0.6687 0.5267 0.7257
No log 5.8125 186 0.6056 0.6190 0.6056 0.7782
No log 5.875 188 0.6552 0.6079 0.6552 0.8095
No log 5.9375 190 0.6352 0.6368 0.6352 0.7970
No log 6.0 192 0.5864 0.6944 0.5864 0.7658
No log 6.0625 194 0.5718 0.7347 0.5718 0.7562
No log 6.125 196 0.5726 0.7347 0.5726 0.7567
No log 6.1875 198 0.5587 0.7332 0.5587 0.7475
No log 6.25 200 0.6915 0.6720 0.6915 0.8316
No log 6.3125 202 0.7058 0.6466 0.7058 0.8401
No log 6.375 204 0.5542 0.7368 0.5542 0.7444
No log 6.4375 206 0.4300 0.6962 0.4300 0.6558
No log 6.5 208 0.5444 0.6835 0.5444 0.7379
No log 6.5625 210 0.5802 0.6624 0.5802 0.7617
No log 6.625 212 0.5209 0.5692 0.5209 0.7217
No log 6.6875 214 0.5517 0.5972 0.5517 0.7428
No log 6.75 216 0.6253 0.5446 0.6253 0.7907
No log 6.8125 218 0.6190 0.5380 0.6190 0.7867
No log 6.875 220 0.6175 0.4858 0.6175 0.7858
No log 6.9375 222 0.6445 0.4960 0.6445 0.8028
No log 7.0 224 0.7368 0.5867 0.7368 0.8584
No log 7.0625 226 0.8773 0.5721 0.8773 0.9366
No log 7.125 228 0.8689 0.5853 0.8689 0.9322
No log 7.1875 230 0.7890 0.5229 0.7890 0.8882
No log 7.25 232 0.7873 0.4286 0.7873 0.8873
No log 7.3125 234 0.7380 0.4650 0.7380 0.8590
No log 7.375 236 0.7063 0.4908 0.7063 0.8404
No log 7.4375 238 0.7720 0.5216 0.7720 0.8786
No log 7.5 240 0.7993 0.5380 0.7993 0.8940
No log 7.5625 242 0.7259 0.5769 0.7259 0.8520
No log 7.625 244 0.6000 0.6731 0.6000 0.7746
No log 7.6875 246 0.5574 0.6908 0.5574 0.7466
No log 7.75 248 0.5472 0.6908 0.5472 0.7398
No log 7.8125 250 0.6178 0.6089 0.6178 0.7860
No log 7.875 252 0.6512 0.6505 0.6512 0.8070
No log 7.9375 254 0.5591 0.7385 0.5591 0.7477
No log 8.0 256 0.4820 0.7122 0.4820 0.6942
No log 8.0625 258 0.5081 0.7244 0.5081 0.7128
No log 8.125 260 0.4893 0.7336 0.4893 0.6995
No log 8.1875 262 0.4691 0.6962 0.4691 0.6849
No log 8.25 264 0.5690 0.6413 0.5690 0.7543
No log 8.3125 266 0.6692 0.5994 0.6692 0.8181
No log 8.375 268 0.6799 0.5968 0.6799 0.8245
No log 8.4375 270 0.6835 0.5777 0.6835 0.8267
No log 8.5 272 0.6978 0.5356 0.6978 0.8353
No log 8.5625 274 0.6765 0.6109 0.6765 0.8225
No log 8.625 276 0.6295 0.6167 0.6295 0.7934
No log 8.6875 278 0.6101 0.6092 0.6101 0.7811
No log 8.75 280 0.6465 0.5822 0.6465 0.8040
No log 8.8125 282 0.6460 0.6032 0.6460 0.8037
No log 8.875 284 0.6505 0.5675 0.6505 0.8065
No log 8.9375 286 0.6312 0.6190 0.6312 0.7945
No log 9.0 288 0.6638 0.5867 0.6638 0.8148
No log 9.0625 290 0.5962 0.7099 0.5962 0.7722
No log 9.125 292 0.5631 0.7099 0.5631 0.7504
No log 9.1875 294 0.5977 0.6773 0.5977 0.7731
No log 9.25 296 0.6734 0.6105 0.6734 0.8206
No log 9.3125 298 0.6412 0.6105 0.6412 0.8007
No log 9.375 300 0.5985 0.6791 0.5985 0.7736
No log 9.4375 302 0.5227 0.6985 0.5227 0.7230
No log 9.5 304 0.5295 0.6869 0.5295 0.7277
No log 9.5625 306 0.5467 0.7099 0.5467 0.7394
No log 9.625 308 0.6263 0.6622 0.6263 0.7914
No log 9.6875 310 0.7117 0.6377 0.7117 0.8436
No log 9.75 312 0.6974 0.6128 0.6974 0.8351
No log 9.8125 314 0.6268 0.7073 0.6268 0.7917
No log 9.875 316 0.5489 0.6932 0.5489 0.7408
No log 9.9375 318 0.6171 0.6035 0.6171 0.7856
No log 10.0 320 0.6128 0.6215 0.6128 0.7828
No log 10.0625 322 0.5536 0.6690 0.5536 0.7440
No log 10.125 324 0.5736 0.6938 0.5736 0.7574
No log 10.1875 326 0.7468 0.5962 0.7468 0.8642
No log 10.25 328 0.8142 0.6208 0.8142 0.9023
No log 10.3125 330 0.7140 0.6056 0.7140 0.8450
No log 10.375 332 0.6026 0.7246 0.6026 0.7763
No log 10.4375 334 0.5851 0.6306 0.5851 0.7649
No log 10.5 336 0.5747 0.6641 0.5747 0.7581
No log 10.5625 338 0.5958 0.6578 0.5958 0.7719
No log 10.625 340 0.6373 0.5728 0.6373 0.7983
No log 10.6875 342 0.5897 0.5894 0.5897 0.7679
No log 10.75 344 0.5630 0.6673 0.5630 0.7504
No log 10.8125 346 0.5720 0.6491 0.5720 0.7563
No log 10.875 348 0.5610 0.6632 0.5610 0.7490
No log 10.9375 350 0.6350 0.5948 0.6350 0.7968
No log 11.0 352 0.7919 0.5990 0.7919 0.8899
No log 11.0625 354 0.7848 0.5205 0.7848 0.8859
No log 11.125 356 0.6847 0.4908 0.6847 0.8275
No log 11.1875 358 0.6262 0.4943 0.6262 0.7913
No log 11.25 360 0.6201 0.5217 0.6201 0.7874
No log 11.3125 362 0.6309 0.5292 0.6309 0.7943
No log 11.375 364 0.7419 0.5320 0.7419 0.8613
No log 11.4375 366 0.8898 0.5165 0.8898 0.9433
No log 11.5 368 0.8830 0.5165 0.8830 0.9397
No log 11.5625 370 0.7584 0.5734 0.7584 0.8708
No log 11.625 372 0.6327 0.5751 0.6327 0.7954
No log 11.6875 374 0.5660 0.6276 0.5660 0.7523
No log 11.75 376 0.5348 0.6759 0.5348 0.7313
No log 11.8125 378 0.5333 0.6327 0.5333 0.7303
No log 11.875 380 0.5230 0.6419 0.5230 0.7232
No log 11.9375 382 0.5147 0.7074 0.5147 0.7174
No log 12.0 384 0.5848 0.6727 0.5848 0.7647
No log 12.0625 386 0.6495 0.6455 0.6495 0.8059
No log 12.125 388 0.6019 0.6698 0.6019 0.7758
No log 12.1875 390 0.5492 0.6555 0.5492 0.7411
No log 12.25 392 0.5687 0.6419 0.5687 0.7541
No log 12.3125 394 0.5854 0.6251 0.5854 0.7651
No log 12.375 396 0.5695 0.6276 0.5695 0.7546
No log 12.4375 398 0.5629 0.6445 0.5629 0.7503
No log 12.5 400 0.5743 0.5442 0.5743 0.7578
No log 12.5625 402 0.5864 0.5622 0.5864 0.7657
No log 12.625 404 0.5745 0.5729 0.5745 0.7580
No log 12.6875 406 0.5647 0.7246 0.5647 0.7515
No log 12.75 408 0.5819 0.7292 0.5819 0.7628
No log 12.8125 410 0.5646 0.6872 0.5646 0.7514
No log 12.875 412 0.5690 0.6925 0.5690 0.7543
No log 12.9375 414 0.5731 0.6043 0.5731 0.7570
No log 13.0 416 0.5892 0.6578 0.5892 0.7676
No log 13.0625 418 0.5751 0.6154 0.5751 0.7584
No log 13.125 420 0.5748 0.6578 0.5748 0.7582
No log 13.1875 422 0.5830 0.6340 0.5830 0.7636
No log 13.25 424 0.5967 0.6042 0.5967 0.7724
No log 13.3125 426 0.5790 0.6482 0.5790 0.7609
No log 13.375 428 0.6126 0.5928 0.6126 0.7827
No log 13.4375 430 0.6010 0.6311 0.6010 0.7753
No log 13.5 432 0.5859 0.6189 0.5859 0.7655
No log 13.5625 434 0.6226 0.6230 0.6226 0.7890
No log 13.625 436 0.6231 0.5728 0.6231 0.7894
No log 13.6875 438 0.5963 0.6450 0.5963 0.7722
No log 13.75 440 0.5498 0.6450 0.5498 0.7415
No log 13.8125 442 0.5049 0.6993 0.5049 0.7106
No log 13.875 444 0.4937 0.6753 0.4937 0.7026
No log 13.9375 446 0.5012 0.6796 0.5012 0.7080
No log 14.0 448 0.4896 0.6990 0.4896 0.6997
No log 14.0625 450 0.5558 0.7375 0.5558 0.7455
No log 14.125 452 0.5615 0.7124 0.5615 0.7493
No log 14.1875 454 0.5034 0.7164 0.5034 0.7095
No log 14.25 456 0.4819 0.7459 0.4819 0.6942
No log 14.3125 458 0.4940 0.7573 0.4940 0.7029
No log 14.375 460 0.5015 0.7566 0.5015 0.7082
No log 14.4375 462 0.5137 0.7101 0.5137 0.7167
No log 14.5 464 0.4859 0.7277 0.4859 0.6971
No log 14.5625 466 0.4559 0.7389 0.4559 0.6752
No log 14.625 468 0.4644 0.7438 0.4644 0.6815
No log 14.6875 470 0.5176 0.7479 0.5176 0.7195
No log 14.75 472 0.5603 0.7241 0.5603 0.7485
No log 14.8125 474 0.6374 0.6481 0.6374 0.7984
No log 14.875 476 0.6278 0.6417 0.6278 0.7923
No log 14.9375 478 0.6339 0.5902 0.6339 0.7962
No log 15.0 480 0.6255 0.5953 0.6255 0.7909
No log 15.0625 482 0.5935 0.6021 0.5935 0.7704
No log 15.125 484 0.5863 0.6450 0.5863 0.7657
No log 15.1875 486 0.5808 0.6099 0.5808 0.7621
No log 15.25 488 0.5784 0.6521 0.5784 0.7605
No log 15.3125 490 0.5295 0.6926 0.5295 0.7277
No log 15.375 492 0.4747 0.7544 0.4747 0.6890
No log 15.4375 494 0.4709 0.7398 0.4709 0.6862
No log 15.5 496 0.4986 0.7114 0.4986 0.7061
No log 15.5625 498 0.5604 0.6305 0.5604 0.7486
0.2972 15.625 500 0.5939 0.6188 0.5939 0.7706
0.2972 15.6875 502 0.6094 0.5835 0.6094 0.7806
0.2972 15.75 504 0.5711 0.6188 0.5711 0.7557
0.2972 15.8125 506 0.5063 0.6762 0.5063 0.7116
0.2972 15.875 508 0.4674 0.7331 0.4674 0.6837
0.2972 15.9375 510 0.4721 0.7331 0.4721 0.6871
0.2972 16.0 512 0.5230 0.6491 0.5230 0.7232
0.2972 16.0625 514 0.6400 0.5714 0.6400 0.8000
0.2972 16.125 516 0.7345 0.6110 0.7345 0.8570
0.2972 16.1875 518 0.6962 0.6280 0.6962 0.8344
0.2972 16.25 520 0.5850 0.6114 0.5850 0.7648
0.2972 16.3125 522 0.4743 0.7277 0.4743 0.6887
0.2972 16.375 524 0.4591 0.7625 0.4591 0.6775
0.2972 16.4375 526 0.4848 0.7064 0.4848 0.6963
0.2972 16.5 528 0.4775 0.7056 0.4775 0.6910
0.2972 16.5625 530 0.4855 0.7277 0.4855 0.6968
0.2972 16.625 532 0.5974 0.6035 0.5974 0.7729
0.2972 16.6875 534 0.7159 0.5261 0.7159 0.8461
0.2972 16.75 536 0.7766 0.4759 0.7766 0.8813
0.2972 16.8125 538 0.7906 0.4550 0.7906 0.8892
0.2972 16.875 540 0.7560 0.4440 0.7560 0.8695

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_run2_AugV5_k12_task5_organization

Finetuned
(4023)
this model