ArabicNewSplits7_usingALLEssays_FineTuningAraBERT_run1_AugV5_k3_task1_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: 1.0648
  • Qwk: 0.6258
  • Mse: 1.0648
  • Rmse: 1.0319

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 0.1429 2 6.9592 0.0057 6.9592 2.6380
No log 0.2857 4 4.3777 0.0769 4.3777 2.0923
No log 0.4286 6 3.4871 -0.0219 3.4871 1.8674
No log 0.5714 8 4.3294 -0.0446 4.3294 2.0807
No log 0.7143 10 3.4130 0.0230 3.4130 1.8474
No log 0.8571 12 1.9777 0.1967 1.9777 1.4063
No log 1.0 14 1.7802 0.1964 1.7802 1.3343
No log 1.1429 16 1.9016 0.1869 1.9017 1.3790
No log 1.2857 18 2.0492 0.1667 2.0492 1.4315
No log 1.4286 20 2.0662 0.1579 2.0662 1.4374
No log 1.5714 22 1.8550 0.3478 1.8550 1.3620
No log 1.7143 24 1.8364 0.2812 1.8364 1.3551
No log 1.8571 26 2.3893 0.0800 2.3893 1.5457
No log 2.0 28 3.2795 0.0904 3.2795 1.8109
No log 2.1429 30 3.1371 0.0714 3.1371 1.7712
No log 2.2857 32 2.2938 0.1507 2.2938 1.5145
No log 2.4286 34 1.8159 0.3134 1.8159 1.3475
No log 2.5714 36 1.6783 0.3969 1.6783 1.2955
No log 2.7143 38 1.6546 0.3969 1.6546 1.2863
No log 2.8571 40 1.7143 0.3788 1.7143 1.3093
No log 3.0 42 1.7438 0.4 1.7438 1.3205
No log 3.1429 44 1.8790 0.3973 1.8790 1.3708
No log 3.2857 46 1.8447 0.4167 1.8447 1.3582
No log 3.4286 48 1.9321 0.4054 1.9321 1.3900
No log 3.5714 50 1.6508 0.4930 1.6508 1.2848
No log 3.7143 52 1.6480 0.4748 1.6480 1.2837
No log 3.8571 54 2.0997 0.3195 2.0997 1.4490
No log 4.0 56 2.5522 0.2378 2.5522 1.5976
No log 4.1429 58 2.5679 0.2378 2.5679 1.6025
No log 4.2857 60 2.0632 0.3333 2.0632 1.4364
No log 4.4286 62 1.7173 0.4265 1.7173 1.3105
No log 4.5714 64 1.4475 0.4062 1.4475 1.2031
No log 4.7143 66 1.3299 0.4127 1.3299 1.1532
No log 4.8571 68 1.2973 0.35 1.2973 1.1390
No log 5.0 70 1.3923 0.4252 1.3923 1.1800
No log 5.1429 72 1.4875 0.4341 1.4875 1.2196
No log 5.2857 74 1.6520 0.3676 1.6520 1.2853
No log 5.4286 76 1.6824 0.4203 1.6824 1.2971
No log 5.5714 78 1.7980 0.4400 1.7980 1.3409
No log 5.7143 80 2.3583 0.3575 2.3583 1.5357
No log 5.8571 82 3.0610 0.2262 3.0610 1.7496
No log 6.0 84 3.4665 0.2232 3.4665 1.8619
No log 6.1429 86 3.1253 0.2783 3.1253 1.7678
No log 6.2857 88 2.2052 0.3776 2.2052 1.4850
No log 6.4286 90 1.8787 0.4751 1.8787 1.3706
No log 6.5714 92 1.6927 0.5143 1.6927 1.3010
No log 6.7143 94 1.6865 0.5263 1.6865 1.2986
No log 6.8571 96 1.4975 0.5556 1.4975 1.2237
No log 7.0 98 1.4866 0.5595 1.4866 1.2193
No log 7.1429 100 1.5751 0.5795 1.5751 1.2550
No log 7.2857 102 1.5800 0.5876 1.5800 1.2570
No log 7.4286 104 1.3869 0.5848 1.3869 1.1777
No log 7.5714 106 1.2633 0.5926 1.2633 1.1240
No log 7.7143 108 1.2487 0.5912 1.2487 1.1175
No log 7.8571 110 1.0269 0.5075 1.0269 1.0134
No log 8.0 112 0.9174 0.5625 0.9174 0.9578
No log 8.1429 114 0.8812 0.5625 0.8812 0.9387
No log 8.2857 116 0.9221 0.5231 0.9221 0.9603
No log 8.4286 118 1.1558 0.5867 1.1558 1.0751
No log 8.5714 120 1.4122 0.5223 1.4122 1.1884
No log 8.7143 122 1.5506 0.4691 1.5506 1.2452
No log 8.8571 124 1.5197 0.475 1.5197 1.2328
No log 9.0 126 1.3013 0.5563 1.3013 1.1408
No log 9.1429 128 1.3223 0.5806 1.3223 1.1499
No log 9.2857 130 1.2562 0.5767 1.2562 1.1208
No log 9.4286 132 1.3200 0.6118 1.3200 1.1489
No log 9.5714 134 1.4151 0.6034 1.4151 1.1896
No log 9.7143 136 1.2342 0.6303 1.2342 1.1110
No log 9.8571 138 0.9421 0.6447 0.9421 0.9706
No log 10.0 140 0.7641 0.6901 0.7641 0.8741
No log 10.1429 142 0.7238 0.7101 0.7238 0.8508
No log 10.2857 144 0.7319 0.7361 0.7319 0.8555
No log 10.4286 146 0.8514 0.6467 0.8514 0.9227
No log 10.5714 148 1.2419 0.6316 1.2419 1.1144
No log 10.7143 150 1.5547 0.6054 1.5547 1.2469
No log 10.8571 152 1.3819 0.6067 1.3819 1.1755
No log 11.0 154 1.2266 0.5917 1.2266 1.1075
No log 11.1429 156 1.0931 0.6347 1.0931 1.0455
No log 11.2857 158 0.8612 0.6757 0.8612 0.9280
No log 11.4286 160 0.8539 0.6912 0.8539 0.9241
No log 11.5714 162 0.9255 0.6222 0.9255 0.9620
No log 11.7143 164 0.9931 0.6119 0.9931 0.9965
No log 11.8571 166 1.0491 0.5758 1.0491 1.0242
No log 12.0 168 1.1160 0.5797 1.1160 1.0564
No log 12.1429 170 1.1387 0.5655 1.1387 1.0671
No log 12.2857 172 1.0567 0.64 1.0567 1.0279
No log 12.4286 174 1.0238 0.6294 1.0238 1.0118
No log 12.5714 176 1.0443 0.5942 1.0443 1.0219
No log 12.7143 178 1.1322 0.5571 1.1322 1.0640
No log 12.8571 180 1.2131 0.5419 1.2131 1.1014
No log 13.0 182 1.2565 0.5610 1.2565 1.1209
No log 13.1429 184 1.2987 0.5455 1.2987 1.1396
No log 13.2857 186 1.3111 0.5325 1.3111 1.1451
No log 13.4286 188 1.1505 0.6049 1.1505 1.0726
No log 13.5714 190 1.0254 0.6076 1.0254 1.0126
No log 13.7143 192 1.0221 0.6194 1.0221 1.0110
No log 13.8571 194 1.0321 0.6582 1.0321 1.0159
No log 14.0 196 0.8913 0.6338 0.8913 0.9441
No log 14.1429 198 0.8247 0.6471 0.8247 0.9082
No log 14.2857 200 0.8042 0.6316 0.8042 0.8967
No log 14.4286 202 0.8410 0.6389 0.8410 0.9171
No log 14.5714 204 0.9347 0.6711 0.9347 0.9668
No log 14.7143 206 0.9004 0.6839 0.9004 0.9489
No log 14.8571 208 0.9104 0.675 0.9104 0.9541
No log 15.0 210 0.9001 0.6790 0.9001 0.9487
No log 15.1429 212 1.0426 0.6316 1.0426 1.0211
No log 15.2857 214 1.2578 0.5977 1.2578 1.1215
No log 15.4286 216 1.1943 0.6235 1.1943 1.0929
No log 15.5714 218 1.0820 0.6235 1.0820 1.0402
No log 15.7143 220 0.9637 0.6826 0.9637 0.9817
No log 15.8571 222 0.8297 0.6974 0.8297 0.9109
No log 16.0 224 0.7599 0.6525 0.7599 0.8717
No log 16.1429 226 0.7331 0.7050 0.7331 0.8562
No log 16.2857 228 0.7510 0.6950 0.7510 0.8666
No log 16.4286 230 0.8696 0.6974 0.8696 0.9325
No log 16.5714 232 1.0943 0.5802 1.0943 1.0461
No log 16.7143 234 1.1686 0.5882 1.1686 1.0810
No log 16.8571 236 1.0568 0.5926 1.0568 1.0280
No log 17.0 238 0.9093 0.6577 0.9093 0.9536
No log 17.1429 240 0.8854 0.6842 0.8854 0.9409
No log 17.2857 242 1.0258 0.6076 1.0258 1.0128
No log 17.4286 244 1.1537 0.5818 1.1537 1.0741
No log 17.5714 246 1.0645 0.5641 1.0645 1.0318
No log 17.7143 248 0.9515 0.6301 0.9515 0.9754
No log 17.8571 250 0.9066 0.6714 0.9066 0.9522
No log 18.0 252 0.8997 0.6763 0.8997 0.9485
No log 18.1429 254 0.9247 0.6809 0.9247 0.9616
No log 18.2857 256 1.0386 0.5612 1.0386 1.0191
No log 18.4286 258 1.1107 0.5986 1.1107 1.0539
No log 18.5714 260 1.0479 0.5793 1.0479 1.0236
No log 18.7143 262 0.9592 0.5778 0.9592 0.9794
No log 18.8571 264 0.8986 0.6619 0.8986 0.9480
No log 19.0 266 0.8964 0.6418 0.8964 0.9468
No log 19.1429 268 0.9224 0.6429 0.9224 0.9604
No log 19.2857 270 1.0821 0.5789 1.0821 1.0402
No log 19.4286 272 1.3603 0.5890 1.3603 1.1663
No log 19.5714 274 1.4611 0.5549 1.4611 1.2088
No log 19.7143 276 1.3517 0.5714 1.3517 1.1626
No log 19.8571 278 1.1194 0.6391 1.1194 1.0580
No log 20.0 280 1.0386 0.6548 1.0386 1.0191
No log 20.1429 282 1.0782 0.6279 1.0782 1.0383
No log 20.2857 284 1.1145 0.6108 1.1145 1.0557
No log 20.4286 286 1.1227 0.6087 1.1227 1.0596
No log 20.5714 288 0.9999 0.6626 0.9999 1.0000
No log 20.7143 290 0.9036 0.6667 0.9036 0.9506
No log 20.8571 292 0.9056 0.6667 0.9056 0.9516
No log 21.0 294 0.9063 0.6531 0.9063 0.9520
No log 21.1429 296 0.9478 0.6301 0.9478 0.9735
No log 21.2857 298 0.9991 0.6447 0.9991 0.9995
No log 21.4286 300 1.0042 0.6667 1.0042 1.0021
No log 21.5714 302 0.9724 0.6864 0.9724 0.9861
No log 21.7143 304 0.9614 0.7209 0.9614 0.9805
No log 21.8571 306 0.9610 0.6864 0.9610 0.9803
No log 22.0 308 1.0616 0.6509 1.0616 1.0303
No log 22.1429 310 1.2461 0.6353 1.2461 1.1163
No log 22.2857 312 1.2848 0.6092 1.2848 1.1335
No log 22.4286 314 1.1324 0.5988 1.1324 1.0641
No log 22.5714 316 0.9713 0.6203 0.9713 0.9855
No log 22.7143 318 0.9078 0.6338 0.9078 0.9528
No log 22.8571 320 0.9488 0.6338 0.9488 0.9741
No log 23.0 322 1.0204 0.6 1.0204 1.0102
No log 23.1429 324 1.0274 0.6 1.0274 1.0136
No log 23.2857 326 1.1213 0.5789 1.1213 1.0589
No log 23.4286 328 1.0646 0.5986 1.0646 1.0318
No log 23.5714 330 0.9998 0.6040 0.9998 0.9999
No log 23.7143 332 1.0673 0.5753 1.0673 1.0331
No log 23.8571 334 1.1085 0.6013 1.1085 1.0528
No log 24.0 336 1.2317 0.5535 1.2317 1.1098
No log 24.1429 338 1.3336 0.5316 1.3336 1.1548
No log 24.2857 340 1.1707 0.5963 1.1707 1.0820
No log 24.4286 342 0.9506 0.6842 0.9506 0.9750
No log 24.5714 344 0.8759 0.6803 0.8759 0.9359
No log 24.7143 346 0.8548 0.6714 0.8548 0.9246
No log 24.8571 348 0.8947 0.6222 0.8947 0.9459
No log 25.0 350 0.9236 0.5692 0.9236 0.9610
No log 25.1429 352 0.9212 0.5865 0.9212 0.9598
No log 25.2857 354 0.8777 0.6269 0.8777 0.9369
No log 25.4286 356 0.8595 0.6621 0.8595 0.9271
No log 25.5714 358 0.9603 0.6329 0.9603 0.9800
No log 25.7143 360 1.1110 0.6303 1.1110 1.0541
No log 25.8571 362 1.2046 0.5965 1.2046 1.0976
No log 26.0 364 1.1595 0.6554 1.1595 1.0768
No log 26.1429 366 0.9611 0.6905 0.9611 0.9803
No log 26.2857 368 0.8833 0.7108 0.8833 0.9398
No log 26.4286 370 0.9191 0.6871 0.9191 0.9587
No log 26.5714 372 0.9471 0.6790 0.9471 0.9732
No log 26.7143 374 0.9630 0.6909 0.9630 0.9813
No log 26.8571 376 0.9644 0.6667 0.9644 0.9820
No log 27.0 378 0.9852 0.6782 0.9852 0.9926
No log 27.1429 380 1.0400 0.6740 1.0400 1.0198
No log 27.2857 382 0.9848 0.6629 0.9848 0.9924
No log 27.4286 384 0.8955 0.7229 0.8955 0.9463
No log 27.5714 386 0.8636 0.7152 0.8636 0.9293
No log 27.7143 388 0.8842 0.6951 0.8842 0.9403
No log 27.8571 390 0.9489 0.6375 0.9489 0.9741
No log 28.0 392 0.9073 0.6541 0.9073 0.9525
No log 28.1429 394 0.8635 0.6712 0.8635 0.9293
No log 28.2857 396 0.8589 0.6806 0.8589 0.9268
No log 28.4286 398 0.8742 0.6806 0.8742 0.9350
No log 28.5714 400 0.8734 0.6809 0.8734 0.9346
No log 28.7143 402 0.8367 0.6763 0.8367 0.9147
No log 28.8571 404 0.8402 0.6901 0.8402 0.9166
No log 29.0 406 0.8426 0.6939 0.8426 0.9179
No log 29.1429 408 0.8801 0.6974 0.8801 0.9381
No log 29.2857 410 0.9176 0.6755 0.9176 0.9579
No log 29.4286 412 0.9001 0.6620 0.9001 0.9488
No log 29.5714 414 0.9281 0.6383 0.9281 0.9634
No log 29.7143 416 0.9367 0.6383 0.9367 0.9678
No log 29.8571 418 0.9264 0.6429 0.9264 0.9625
No log 30.0 420 0.8703 0.6475 0.8703 0.9329
No log 30.1429 422 0.8516 0.6475 0.8516 0.9228
No log 30.2857 424 0.8915 0.6475 0.8915 0.9442
No log 30.4286 426 0.9580 0.6479 0.9580 0.9788
No log 30.5714 428 1.0237 0.6174 1.0237 1.0118
No log 30.7143 430 0.9857 0.6443 0.9857 0.9928
No log 30.8571 432 0.9221 0.6621 0.9221 0.9602
No log 31.0 434 0.8954 0.6711 0.8954 0.9462
No log 31.1429 436 0.9092 0.6711 0.9092 0.9535
No log 31.2857 438 0.9171 0.6883 0.9171 0.9577
No log 31.4286 440 0.9399 0.6708 0.9399 0.9695
No log 31.5714 442 0.9159 0.6752 0.9159 0.9571
No log 31.7143 444 0.8727 0.6752 0.8727 0.9342
No log 31.8571 446 0.8589 0.6795 0.8589 0.9268
No log 32.0 448 0.8722 0.7081 0.8722 0.9339
No log 32.1429 450 0.9131 0.7143 0.9131 0.9556
No log 32.2857 452 1.0518 0.6588 1.0518 1.0256
No log 32.4286 454 1.2169 0.6102 1.2169 1.1031
No log 32.5714 456 1.0990 0.6550 1.0990 1.0483
No log 32.7143 458 0.8738 0.6795 0.8738 0.9348
No log 32.8571 460 0.7854 0.7092 0.7854 0.8862
No log 33.0 462 0.7673 0.7273 0.7673 0.8760
No log 33.1429 464 0.7531 0.7413 0.7531 0.8678
No log 33.2857 466 0.7569 0.7534 0.7569 0.8700
No log 33.4286 468 0.7876 0.6950 0.7876 0.8875
No log 33.5714 470 0.8278 0.6714 0.8278 0.9098
No log 33.7143 472 0.8370 0.6763 0.8370 0.9149
No log 33.8571 474 0.8691 0.6716 0.8691 0.9323
No log 34.0 476 0.9071 0.6165 0.9071 0.9524
No log 34.1429 478 0.9430 0.6212 0.9430 0.9711
No log 34.2857 480 0.9788 0.6232 0.9788 0.9893
No log 34.4286 482 1.0279 0.6216 1.0279 1.0138
No log 34.5714 484 1.0521 0.6626 1.0521 1.0257
No log 34.7143 486 1.0665 0.6744 1.0665 1.0327
No log 34.8571 488 1.0313 0.6780 1.0313 1.0155
No log 35.0 490 1.0141 0.6995 1.0141 1.0070
No log 35.1429 492 1.0082 0.6995 1.0082 1.0041
No log 35.2857 494 1.1048 0.6522 1.1048 1.0511
No log 35.4286 496 1.1094 0.6409 1.1094 1.0533
No log 35.5714 498 1.0360 0.6550 1.0360 1.0178
0.3325 35.7143 500 1.0095 0.6429 1.0095 1.0048
0.3325 35.8571 502 0.9981 0.6548 0.9981 0.9991
0.3325 36.0 504 0.9591 0.6585 0.9591 0.9794
0.3325 36.1429 506 0.8914 0.6623 0.8914 0.9441
0.3325 36.2857 508 0.8089 0.6939 0.8089 0.8994
0.3325 36.4286 510 0.7774 0.7 0.7774 0.8817
0.3325 36.5714 512 0.7750 0.7059 0.7750 0.8803
0.3325 36.7143 514 0.7752 0.7059 0.7752 0.8804
0.3325 36.8571 516 0.7762 0.6963 0.7762 0.8810
0.3325 37.0 518 0.7815 0.6715 0.7815 0.8840
0.3325 37.1429 520 0.7912 0.6809 0.7912 0.8895
0.3325 37.2857 522 0.8082 0.6809 0.8082 0.8990
0.3325 37.4286 524 0.8167 0.6803 0.8167 0.9037
0.3325 37.5714 526 0.7982 0.6803 0.7982 0.8934
0.3325 37.7143 528 0.7869 0.6803 0.7869 0.8871
0.3325 37.8571 530 0.8005 0.6757 0.8005 0.8947
0.3325 38.0 532 0.8060 0.6621 0.8060 0.8977
0.3325 38.1429 534 0.8339 0.6757 0.8339 0.9132
0.3325 38.2857 536 0.8658 0.6623 0.8658 0.9305
0.3325 38.4286 538 0.8931 0.6623 0.8931 0.9450
0.3325 38.5714 540 0.9096 0.6533 0.9096 0.9537
0.3325 38.7143 542 0.8593 0.6486 0.8593 0.9270
0.3325 38.8571 544 0.7804 0.6621 0.7804 0.8834
0.3325 39.0 546 0.7414 0.7133 0.7414 0.8610
0.3325 39.1429 548 0.7311 0.7376 0.7311 0.8550
0.3325 39.2857 550 0.7371 0.7143 0.7371 0.8585
0.3325 39.4286 552 0.7722 0.7114 0.7722 0.8787
0.3325 39.5714 554 0.8013 0.6846 0.8013 0.8952
0.3325 39.7143 556 0.7935 0.7075 0.7935 0.8908
0.3325 39.8571 558 0.7864 0.6809 0.7864 0.8868
0.3325 40.0 560 0.7649 0.7 0.7649 0.8746
0.3325 40.1429 562 0.7610 0.7429 0.7610 0.8723
0.3325 40.2857 564 0.7600 0.7746 0.7600 0.8718
0.3325 40.4286 566 0.7717 0.7391 0.7717 0.8785
0.3325 40.5714 568 0.7648 0.7518 0.7648 0.8745
0.3325 40.7143 570 0.7726 0.7194 0.7726 0.8790
0.3325 40.8571 572 0.7977 0.6763 0.7977 0.8932
0.3325 41.0 574 0.8320 0.6761 0.8320 0.9121
0.3325 41.1429 576 0.8320 0.6667 0.8320 0.9121
0.3325 41.2857 578 0.8328 0.6621 0.8328 0.9126
0.3325 41.4286 580 0.8395 0.6621 0.8395 0.9162
0.3325 41.5714 582 0.8416 0.6757 0.8416 0.9174
0.3325 41.7143 584 0.8619 0.6753 0.8619 0.9284
0.3325 41.8571 586 0.9079 0.6541 0.9079 0.9528
0.3325 42.0 588 0.9679 0.6708 0.9679 0.9838
0.3325 42.1429 590 1.0546 0.6587 1.0546 1.0269
0.3325 42.2857 592 1.1087 0.6391 1.1087 1.0530
0.3325 42.4286 594 1.1422 0.6279 1.1422 1.0688
0.3325 42.5714 596 1.1252 0.6279 1.1252 1.0607
0.3325 42.7143 598 1.1106 0.6391 1.1106 1.0539
0.3325 42.8571 600 1.0648 0.6258 1.0648 1.0319

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_run1_AugV5_k3_task1_organization

Finetuned
(4023)
this model