ArabicNewSplits7_B_usingALLEssays_FineTuningAraBERT_run1_AugV5_k8_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: 0.8286
  • Qwk: 0.4802
  • Mse: 0.8286
  • Rmse: 0.9103

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 0.0556 2 4.1120 0.0078 4.1120 2.0278
No log 0.1111 4 2.4977 -0.0687 2.4977 1.5804
No log 0.1667 6 2.6222 -0.0130 2.6222 1.6193
No log 0.2222 8 1.7028 -0.0244 1.7028 1.3049
No log 0.2778 10 1.2321 0.0574 1.2321 1.1100
No log 0.3333 12 1.3470 -0.0091 1.3470 1.1606
No log 0.3889 14 1.3552 0.0234 1.3552 1.1641
No log 0.4444 16 1.4589 0.0217 1.4589 1.2078
No log 0.5 18 1.3444 0.0274 1.3444 1.1595
No log 0.5556 20 1.2476 0.0325 1.2476 1.1169
No log 0.6111 22 1.1694 0.0792 1.1694 1.0814
No log 0.6667 24 1.1814 0.1698 1.1814 1.0869
No log 0.7222 26 1.4262 0.1838 1.4262 1.1943
No log 0.7778 28 1.3601 0.2459 1.3601 1.1662
No log 0.8333 30 1.0516 0.3988 1.0516 1.0255
No log 0.8889 32 0.9069 0.3795 0.9069 0.9523
No log 0.9444 34 0.9086 0.3265 0.9086 0.9532
No log 1.0 36 1.0762 0.2969 1.0762 1.0374
No log 1.0556 38 1.1284 0.2547 1.1284 1.0623
No log 1.1111 40 1.0022 0.2567 1.0022 1.0011
No log 1.1667 42 0.8823 0.3583 0.8823 0.9393
No log 1.2222 44 0.8902 0.3626 0.8902 0.9435
No log 1.2778 46 1.0366 0.2897 1.0366 1.0181
No log 1.3333 48 1.0447 0.2897 1.0447 1.0221
No log 1.3889 50 0.9120 0.3804 0.9120 0.9550
No log 1.4444 52 0.9452 0.2923 0.9452 0.9722
No log 1.5 54 1.1527 0.3126 1.1527 1.0736
No log 1.5556 56 1.1116 0.3180 1.1116 1.0543
No log 1.6111 58 0.9895 0.3392 0.9895 0.9947
No log 1.6667 60 1.0267 0.2147 1.0267 1.0133
No log 1.7222 62 1.0792 0.1859 1.0792 1.0389
No log 1.7778 64 1.0894 0.2521 1.0894 1.0437
No log 1.8333 66 1.2588 0.3409 1.2588 1.1219
No log 1.8889 68 1.3049 0.2925 1.3049 1.1423
No log 1.9444 70 1.1248 0.3340 1.1248 1.0606
No log 2.0 72 1.0768 0.2408 1.0768 1.0377
No log 2.0556 74 1.2053 0.1189 1.2053 1.0978
No log 2.1111 76 1.1246 0.2510 1.1246 1.0605
No log 2.1667 78 0.9507 0.4428 0.9507 0.9750
No log 2.2222 80 0.9176 0.3095 0.9176 0.9579
No log 2.2778 82 1.2219 0.3646 1.2219 1.1054
No log 2.3333 84 1.3634 0.3375 1.3634 1.1676
No log 2.3889 86 1.1347 0.3951 1.1347 1.0652
No log 2.4444 88 0.9088 0.3448 0.9088 0.9533
No log 2.5 90 0.8523 0.4234 0.8523 0.9232
No log 2.5556 92 0.8279 0.4610 0.8279 0.9099
No log 2.6111 94 0.8124 0.4345 0.8124 0.9014
No log 2.6667 96 0.8006 0.4764 0.8006 0.8947
No log 2.7222 98 0.8068 0.5171 0.8068 0.8982
No log 2.7778 100 0.8254 0.5171 0.8254 0.9085
No log 2.8333 102 0.8546 0.4304 0.8546 0.9244
No log 2.8889 104 0.8725 0.4097 0.8725 0.9341
No log 2.9444 106 1.0143 0.3717 1.0143 1.0071
No log 3.0 108 1.0979 0.3488 1.0979 1.0478
No log 3.0556 110 0.9755 0.3897 0.9755 0.9877
No log 3.1111 112 0.8822 0.4304 0.8822 0.9392
No log 3.1667 114 1.0355 0.4511 1.0355 1.0176
No log 3.2222 116 0.9954 0.4726 0.9954 0.9977
No log 3.2778 118 0.8737 0.4592 0.8737 0.9347
No log 3.3333 120 0.8423 0.4507 0.8423 0.9178
No log 3.3889 122 0.8685 0.3804 0.8685 0.9319
No log 3.4444 124 0.8450 0.4336 0.8450 0.9192
No log 3.5 126 0.8549 0.3656 0.8549 0.9246
No log 3.5556 128 0.9698 0.3277 0.9698 0.9848
No log 3.6111 130 1.1000 0.3545 1.1000 1.0488
No log 3.6667 132 1.0278 0.4296 1.0278 1.0138
No log 3.7222 134 0.8618 0.4932 0.8618 0.9283
No log 3.7778 136 0.9190 0.3725 0.9190 0.9586
No log 3.8333 138 0.9844 0.4085 0.9844 0.9922
No log 3.8889 140 0.9001 0.3725 0.9001 0.9488
No log 3.9444 142 0.9205 0.4775 0.9205 0.9595
No log 4.0 144 1.1441 0.3782 1.1441 1.0696
No log 4.0556 146 1.2383 0.3780 1.2383 1.1128
No log 4.1111 148 1.0834 0.3212 1.0834 1.0409
No log 4.1667 150 0.8842 0.3544 0.8842 0.9403
No log 4.2222 152 0.9005 0.4562 0.9005 0.9490
No log 4.2778 154 1.0035 0.3913 1.0035 1.0018
No log 4.3333 156 0.9715 0.3913 0.9715 0.9856
No log 4.3889 158 0.8515 0.4450 0.8515 0.9228
No log 4.4444 160 0.7986 0.4388 0.7986 0.8936
No log 4.5 162 0.8233 0.4573 0.8233 0.9074
No log 4.5556 164 0.8274 0.5074 0.8274 0.9096
No log 4.6111 166 0.8074 0.5402 0.8074 0.8986
No log 4.6667 168 0.8550 0.4359 0.8550 0.9246
No log 4.7222 170 0.8863 0.4115 0.8863 0.9414
No log 4.7778 172 0.8384 0.4630 0.8384 0.9156
No log 4.8333 174 0.8161 0.4883 0.8161 0.9034
No log 4.8889 176 0.8113 0.5131 0.8113 0.9007
No log 4.9444 178 0.8052 0.5131 0.8052 0.8973
No log 5.0 180 0.8178 0.4873 0.8178 0.9043
No log 5.0556 182 0.8231 0.4759 0.8231 0.9072
No log 5.1111 184 0.8340 0.4759 0.8340 0.9132
No log 5.1667 186 0.8585 0.4743 0.8585 0.9265
No log 5.2222 188 0.8673 0.4743 0.8673 0.9313
No log 5.2778 190 0.8583 0.4175 0.8583 0.9264
No log 5.3333 192 0.8612 0.4534 0.8612 0.9280
No log 5.3889 194 0.8594 0.4757 0.8594 0.9271
No log 5.4444 196 0.8478 0.4630 0.8478 0.9208
No log 5.5 198 0.8437 0.4483 0.8437 0.9185
No log 5.5556 200 0.8273 0.3702 0.8273 0.9096
No log 5.6111 202 0.8083 0.4251 0.8083 0.8990
No log 5.6667 204 0.8077 0.4269 0.8077 0.8987
No log 5.7222 206 0.8007 0.4269 0.8007 0.8948
No log 5.7778 208 0.8045 0.4405 0.8045 0.8970
No log 5.8333 210 0.8239 0.4499 0.8239 0.9077
No log 5.8889 212 0.8377 0.4499 0.8377 0.9152
No log 5.9444 214 0.8345 0.4629 0.8345 0.9135
No log 6.0 216 0.8926 0.3988 0.8926 0.9448
No log 6.0556 218 1.0754 0.3486 1.0754 1.0370
No log 6.1111 220 1.0448 0.3505 1.0448 1.0221
No log 6.1667 222 0.9034 0.3408 0.9034 0.9505
No log 6.2222 224 0.9236 0.4491 0.9236 0.9610
No log 6.2778 226 0.9157 0.3992 0.9157 0.9569
No log 6.3333 228 0.9033 0.3915 0.9033 0.9504
No log 6.3889 230 0.9029 0.3685 0.9029 0.9502
No log 6.4444 232 0.9093 0.4974 0.9093 0.9535
No log 6.5 234 0.9274 0.4491 0.9274 0.9630
No log 6.5556 236 0.9227 0.3790 0.9227 0.9606
No log 6.6111 238 0.9088 0.4006 0.9088 0.9533
No log 6.6667 240 0.8898 0.4378 0.8898 0.9433
No log 6.7222 242 0.9022 0.4110 0.9022 0.9498
No log 6.7778 244 0.9209 0.3404 0.9209 0.9596
No log 6.8333 246 0.9457 0.3229 0.9457 0.9725
No log 6.8889 248 0.9323 0.3107 0.9323 0.9656
No log 6.9444 250 0.8983 0.3250 0.8983 0.9478
No log 7.0 252 0.8945 0.3250 0.8945 0.9458
No log 7.0556 254 0.8876 0.3445 0.8876 0.9421
No log 7.1111 256 0.8968 0.4030 0.8968 0.9470
No log 7.1667 258 0.9448 0.3933 0.9448 0.9720
No log 7.2222 260 0.9183 0.4198 0.9183 0.9583
No log 7.2778 262 0.8974 0.3818 0.8974 0.9473
No log 7.3333 264 0.8930 0.3552 0.8930 0.9450
No log 7.3889 266 0.9008 0.3860 0.9008 0.9491
No log 7.4444 268 0.9749 0.4071 0.9749 0.9873
No log 7.5 270 1.0265 0.4334 1.0265 1.0132
No log 7.5556 272 0.9696 0.4085 0.9696 0.9847
No log 7.6111 274 0.9833 0.4085 0.9833 0.9916
No log 7.6667 276 0.9320 0.4071 0.9320 0.9654
No log 7.7222 278 0.8606 0.3821 0.8606 0.9277
No log 7.7778 280 0.8576 0.3902 0.8576 0.9261
No log 7.8333 282 0.8548 0.3902 0.8548 0.9246
No log 7.8889 284 0.8601 0.3637 0.8601 0.9274
No log 7.9444 286 0.9077 0.4071 0.9077 0.9527
No log 8.0 288 0.9290 0.3671 0.9290 0.9638
No log 8.0556 290 0.8822 0.4379 0.8822 0.9392
No log 8.1111 292 0.8578 0.4429 0.8578 0.9262
No log 8.1667 294 0.8501 0.4534 0.8501 0.9220
No log 8.2222 296 0.8573 0.4313 0.8573 0.9259
No log 8.2778 298 0.8689 0.4186 0.8689 0.9321
No log 8.3333 300 0.8515 0.4405 0.8515 0.9228
No log 8.3889 302 0.8713 0.3940 0.8713 0.9335
No log 8.4444 304 0.9026 0.3330 0.9026 0.9501
No log 8.5 306 0.9075 0.3973 0.9075 0.9526
No log 8.5556 308 0.8599 0.4280 0.8599 0.9273
No log 8.6111 310 0.8790 0.4285 0.8790 0.9376
No log 8.6667 312 0.8590 0.4245 0.8590 0.9268
No log 8.7222 314 0.8431 0.5112 0.8431 0.9182
No log 8.7778 316 0.8495 0.4273 0.8495 0.9217
No log 8.8333 318 0.8891 0.3921 0.8891 0.9429
No log 8.8889 320 0.9714 0.3883 0.9714 0.9856
No log 8.9444 322 0.9772 0.3883 0.9772 0.9885
No log 9.0 324 0.9357 0.4421 0.9357 0.9673
No log 9.0556 326 0.9236 0.4476 0.9236 0.9611
No log 9.1111 328 0.9292 0.4143 0.9292 0.9640
No log 9.1667 330 0.9262 0.4143 0.9262 0.9624
No log 9.2222 332 0.9902 0.3794 0.9902 0.9951
No log 9.2778 334 1.0358 0.3636 1.0358 1.0178
No log 9.3333 336 0.9859 0.4180 0.9859 0.9929
No log 9.3889 338 0.9144 0.4335 0.9144 0.9563
No log 9.4444 340 0.8772 0.3236 0.8772 0.9366
No log 9.5 342 0.8693 0.3236 0.8693 0.9323
No log 9.5556 344 0.8885 0.4220 0.8885 0.9426
No log 9.6111 346 0.9527 0.4465 0.9527 0.9761
No log 9.6667 348 1.0063 0.4666 1.0063 1.0031
No log 9.7222 350 0.9968 0.4666 0.9968 0.9984
No log 9.7778 352 1.0222 0.4310 1.0222 1.0110
No log 9.8333 354 1.0682 0.4310 1.0682 1.0335
No log 9.8889 356 1.0074 0.4036 1.0074 1.0037
No log 9.9444 358 0.9354 0.4318 0.9354 0.9672
No log 10.0 360 0.8618 0.3272 0.8618 0.9283
No log 10.0556 362 0.8541 0.3272 0.8541 0.9242
No log 10.1111 364 0.8787 0.3780 0.8787 0.9374
No log 10.1667 366 0.8959 0.3760 0.8959 0.9465
No log 10.2222 368 0.8628 0.3393 0.8628 0.9289
No log 10.2778 370 0.8304 0.3414 0.8304 0.9113
No log 10.3333 372 0.7999 0.4151 0.7999 0.8944
No log 10.3889 374 0.7913 0.4411 0.7913 0.8895
No log 10.4444 376 0.8317 0.4159 0.8317 0.9120
No log 10.5 378 0.8518 0.3826 0.8518 0.9229
No log 10.5556 380 0.8349 0.4507 0.8349 0.9138
No log 10.6111 382 0.8570 0.4257 0.8570 0.9257
No log 10.6667 384 0.8851 0.4075 0.8851 0.9408
No log 10.7222 386 0.8657 0.3563 0.8657 0.9304
No log 10.7778 388 0.8627 0.3583 0.8627 0.9288
No log 10.8333 390 0.8582 0.3721 0.8582 0.9264
No log 10.8889 392 0.8531 0.3721 0.8531 0.9237
No log 10.9444 394 0.8580 0.3702 0.8580 0.9263
No log 11.0 396 0.8827 0.3424 0.8827 0.9395
No log 11.0556 398 0.9064 0.4310 0.9064 0.9520
No log 11.1111 400 0.9074 0.4335 0.9074 0.9526
No log 11.1667 402 0.8877 0.3974 0.8877 0.9422
No log 11.2222 404 0.8809 0.3861 0.8809 0.9386
No log 11.2778 406 0.8852 0.4023 0.8852 0.9409
No log 11.3333 408 0.8995 0.4023 0.8995 0.9484
No log 11.3889 410 0.9268 0.4250 0.9268 0.9627
No log 11.4444 412 0.9223 0.4343 0.9223 0.9603
No log 11.5 414 0.8802 0.4220 0.8802 0.9382
No log 11.5556 416 0.8513 0.4227 0.8513 0.9227
No log 11.6111 418 0.8577 0.4843 0.8577 0.9261
No log 11.6667 420 0.8967 0.4250 0.8967 0.9469
No log 11.7222 422 0.9496 0.4326 0.9496 0.9745
No log 11.7778 424 0.9349 0.4326 0.9349 0.9669
No log 11.8333 426 0.8409 0.5580 0.8409 0.9170
No log 11.8889 428 0.8167 0.4524 0.8167 0.9037
No log 11.9444 430 0.8265 0.4304 0.8265 0.9091
No log 12.0 432 0.8188 0.4675 0.8188 0.9049
No log 12.0556 434 0.8178 0.4659 0.8178 0.9043
No log 12.1111 436 0.8218 0.4914 0.8218 0.9065
No log 12.1667 438 0.8197 0.4893 0.8197 0.9054
No log 12.2222 440 0.8154 0.4893 0.8154 0.9030
No log 12.2778 442 0.8147 0.4422 0.8147 0.9026
No log 12.3333 444 0.8096 0.4156 0.8096 0.8998
No log 12.3889 446 0.8027 0.4659 0.8027 0.8960
No log 12.4444 448 0.8046 0.4345 0.8046 0.8970
No log 12.5 450 0.8074 0.4625 0.8074 0.8986
No log 12.5556 452 0.8122 0.5003 0.8122 0.9012
No log 12.6111 454 0.8196 0.4882 0.8196 0.9053
No log 12.6667 456 0.8183 0.4503 0.8183 0.9046
No log 12.7222 458 0.8176 0.4363 0.8176 0.9042
No log 12.7778 460 0.8360 0.4450 0.8360 0.9144
No log 12.8333 462 0.8534 0.3902 0.8534 0.9238
No log 12.8889 464 0.8220 0.4082 0.8220 0.9066
No log 12.9444 466 0.7985 0.4503 0.7985 0.8936
No log 13.0 468 0.7883 0.4381 0.7883 0.8878
No log 13.0556 470 0.7836 0.4381 0.7836 0.8852
No log 13.1111 472 0.7994 0.4439 0.7994 0.8941
No log 13.1667 474 0.7872 0.4259 0.7872 0.8872
No log 13.2222 476 0.7801 0.4503 0.7801 0.8832
No log 13.2778 478 0.7975 0.4223 0.7975 0.8930
No log 13.3333 480 0.8367 0.4952 0.8367 0.9147
No log 13.3889 482 0.8832 0.4681 0.8832 0.9398
No log 13.4444 484 0.8703 0.4581 0.8703 0.9329
No log 13.5 486 0.8262 0.4478 0.8262 0.9090
No log 13.5556 488 0.7914 0.4251 0.7914 0.8896
No log 13.6111 490 0.7814 0.4251 0.7814 0.8840
No log 13.6667 492 0.7798 0.4251 0.7798 0.8831
No log 13.7222 494 0.7801 0.4251 0.7801 0.8832
No log 13.7778 496 0.8026 0.4995 0.8026 0.8959
No log 13.8333 498 0.8031 0.5127 0.8031 0.8962
0.2727 13.8889 500 0.8060 0.5017 0.8060 0.8978
0.2727 13.9444 502 0.8157 0.5131 0.8157 0.9032
0.2727 14.0 504 0.8140 0.5274 0.8140 0.9022
0.2727 14.0556 506 0.8219 0.4576 0.8219 0.9066
0.2727 14.1111 508 0.8463 0.4338 0.8463 0.9199
0.2727 14.1667 510 0.8414 0.4338 0.8414 0.9173
0.2727 14.2222 512 0.8251 0.4444 0.8251 0.9084
0.2727 14.2778 514 0.8286 0.4802 0.8286 0.9103

Framework versions

  • Transformers 4.44.2
  • Pytorch 2.4.0+cu118
  • Datasets 2.21.0
  • Tokenizers 0.19.1
Downloads last month
3
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_B_usingALLEssays_FineTuningAraBERT_run1_AugV5_k8_task5_organization

Finetuned
(4034)
this model