ArabicNewSplits7_B_usingALLEssays_FineTuningAraBERT_run1_AugV5_k15_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: 0.8591
  • Qwk: 0.3536
  • Mse: 0.8591
  • Rmse: 0.9269

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 0.0278 2 3.9144 -0.0151 3.9144 1.9785
No log 0.0556 4 2.2272 0.0372 2.2272 1.4924
No log 0.0833 6 1.5982 0.0465 1.5982 1.2642
No log 0.1111 8 1.1829 0.1160 1.1829 1.0876
No log 0.1389 10 1.3254 0.1426 1.3254 1.1513
No log 0.1667 12 2.0910 -0.0029 2.0910 1.4460
No log 0.1944 14 1.7901 0.0262 1.7901 1.3380
No log 0.2222 16 1.3761 -0.0245 1.3761 1.1731
No log 0.25 18 1.1977 0.1091 1.1977 1.0944
No log 0.2778 20 1.1812 0.0970 1.1812 1.0869
No log 0.3056 22 1.2745 0.0256 1.2745 1.1289
No log 0.3333 24 1.5396 -0.0032 1.5396 1.2408
No log 0.3611 26 1.5693 0.0116 1.5693 1.2527
No log 0.3889 28 1.4613 0.0116 1.4613 1.2088
No log 0.4167 30 1.2352 0.0436 1.2352 1.1114
No log 0.4444 32 1.0642 0.2217 1.0642 1.0316
No log 0.4722 34 1.0485 0.2788 1.0485 1.0240
No log 0.5 36 1.1372 0.1901 1.1372 1.0664
No log 0.5278 38 1.2181 0.1444 1.2181 1.1037
No log 0.5556 40 1.4195 0.1228 1.4195 1.1914
No log 0.5833 42 1.4071 0.1228 1.4071 1.1862
No log 0.6111 44 1.2289 0.1858 1.2289 1.1086
No log 0.6389 46 1.0580 0.2318 1.0580 1.0286
No log 0.6667 48 0.9902 0.3078 0.9902 0.9951
No log 0.6944 50 0.9768 0.4186 0.9768 0.9883
No log 0.7222 52 1.0003 0.2986 1.0003 1.0002
No log 0.75 54 1.1072 0.3049 1.1072 1.0522
No log 0.7778 56 1.0829 0.2864 1.0829 1.0406
No log 0.8056 58 1.0549 0.3243 1.0549 1.0271
No log 0.8333 60 0.9773 0.4252 0.9773 0.9886
No log 0.8611 62 0.9858 0.4252 0.9858 0.9929
No log 0.8889 64 0.9743 0.3983 0.9743 0.9871
No log 0.9167 66 0.9704 0.4345 0.9704 0.9851
No log 0.9444 68 0.9671 0.3198 0.9671 0.9834
No log 0.9722 70 0.9669 0.4164 0.9669 0.9833
No log 1.0 72 0.9920 0.4405 0.9920 0.9960
No log 1.0278 74 0.9638 0.4550 0.9638 0.9818
No log 1.0556 76 0.9561 0.4565 0.9561 0.9778
No log 1.0833 78 0.9502 0.3218 0.9502 0.9748
No log 1.1111 80 0.9540 0.4059 0.9540 0.9767
No log 1.1389 82 1.0046 0.3522 1.0046 1.0023
No log 1.1667 84 1.0646 0.2473 1.0646 1.0318
No log 1.1944 86 1.0081 0.4398 1.0081 1.0040
No log 1.2222 88 0.9848 0.4557 0.9848 0.9924
No log 1.25 90 0.9697 0.4321 0.9697 0.9847
No log 1.2778 92 0.9295 0.4305 0.9295 0.9641
No log 1.3056 94 0.9822 0.3350 0.9822 0.9911
No log 1.3333 96 0.9112 0.4053 0.9112 0.9546
No log 1.3611 98 0.8892 0.4229 0.8892 0.9430
No log 1.3889 100 0.9015 0.4203 0.9015 0.9495
No log 1.4167 102 0.9250 0.3821 0.9250 0.9617
No log 1.4444 104 0.9389 0.4045 0.9389 0.9690
No log 1.4722 106 1.0042 0.4019 1.0042 1.0021
No log 1.5 108 1.0968 0.3243 1.0968 1.0473
No log 1.5278 110 0.9747 0.4202 0.9747 0.9873
No log 1.5556 112 0.9725 0.4202 0.9725 0.9861
No log 1.5833 114 1.0177 0.4331 1.0177 1.0088
No log 1.6111 116 0.8935 0.4970 0.8935 0.9452
No log 1.6389 118 0.8874 0.4799 0.8874 0.9420
No log 1.6667 120 0.9047 0.4017 0.9047 0.9511
No log 1.6944 122 0.9258 0.4169 0.9258 0.9622
No log 1.7222 124 1.0541 0.3140 1.0541 1.0267
No log 1.75 126 1.1362 0.2748 1.1362 1.0659
No log 1.7778 128 1.1643 0.2773 1.1643 1.0790
No log 1.8056 130 1.1040 0.2175 1.1040 1.0507
No log 1.8333 132 1.0177 0.2909 1.0177 1.0088
No log 1.8611 134 0.9735 0.3559 0.9735 0.9867
No log 1.8889 136 0.9777 0.3326 0.9777 0.9888
No log 1.9167 138 1.0219 0.2408 1.0219 1.0109
No log 1.9444 140 1.1027 0.3081 1.1027 1.0501
No log 1.9722 142 1.0709 0.2505 1.0709 1.0348
No log 2.0 144 1.0081 0.2796 1.0081 1.0041
No log 2.0278 146 0.9939 0.2553 0.9939 0.9970
No log 2.0556 148 0.9686 0.3306 0.9686 0.9842
No log 2.0833 150 0.9393 0.3949 0.9393 0.9692
No log 2.1111 152 0.9385 0.3858 0.9385 0.9687
No log 2.1389 154 0.9463 0.3736 0.9463 0.9728
No log 2.1667 156 0.9137 0.4429 0.9137 0.9559
No log 2.1944 158 0.8704 0.4434 0.8704 0.9330
No log 2.2222 160 0.9234 0.4323 0.9234 0.9609
No log 2.25 162 0.9681 0.4233 0.9681 0.9839
No log 2.2778 164 0.8684 0.4147 0.8684 0.9319
No log 2.3056 166 0.8083 0.5074 0.8083 0.8990
No log 2.3333 168 0.9037 0.5138 0.9037 0.9506
No log 2.3611 170 1.0420 0.4114 1.0420 1.0208
No log 2.3889 172 1.0407 0.4234 1.0407 1.0202
No log 2.4167 174 0.9629 0.4327 0.9629 0.9813
No log 2.4444 176 0.8601 0.5462 0.8601 0.9274
No log 2.4722 178 0.7986 0.5226 0.7986 0.8937
No log 2.5 180 0.7951 0.4450 0.7951 0.8917
No log 2.5278 182 0.8229 0.3940 0.8229 0.9071
No log 2.5556 184 0.8961 0.4039 0.8961 0.9466
No log 2.5833 186 0.8645 0.3229 0.8645 0.9298
No log 2.6111 188 0.8113 0.4180 0.8113 0.9007
No log 2.6389 190 0.8027 0.4461 0.8027 0.8959
No log 2.6667 192 0.8047 0.5116 0.8047 0.8971
No log 2.6944 194 0.8743 0.4826 0.8743 0.9350
No log 2.7222 196 0.8907 0.4708 0.8907 0.9438
No log 2.75 198 0.8154 0.5121 0.8154 0.9030
No log 2.7778 200 0.8154 0.4852 0.8154 0.9030
No log 2.8056 202 0.9284 0.4700 0.9284 0.9635
No log 2.8333 204 1.2134 0.3564 1.2134 1.1015
No log 2.8611 206 1.1769 0.3525 1.1769 1.0849
No log 2.8889 208 0.9423 0.3976 0.9423 0.9707
No log 2.9167 210 0.9040 0.3218 0.9040 0.9508
No log 2.9444 212 0.9164 0.3218 0.9164 0.9573
No log 2.9722 214 0.9273 0.3708 0.9273 0.9630
No log 3.0 216 0.9704 0.3891 0.9704 0.9851
No log 3.0278 218 0.9529 0.3708 0.9529 0.9762
No log 3.0556 220 0.9684 0.2929 0.9684 0.9841
No log 3.0833 222 1.0614 0.3691 1.0614 1.0303
No log 3.1111 224 1.0264 0.3824 1.0264 1.0131
No log 3.1389 226 0.9423 0.3276 0.9423 0.9707
No log 3.1667 228 0.9253 0.3998 0.9253 0.9619
No log 3.1944 230 0.9018 0.3729 0.9018 0.9496
No log 3.2222 232 0.8968 0.3981 0.8968 0.9470
No log 3.25 234 0.9221 0.3256 0.9221 0.9603
No log 3.2778 236 0.8938 0.4042 0.8938 0.9454
No log 3.3056 238 0.8634 0.4802 0.8634 0.9292
No log 3.3333 240 1.0162 0.3993 1.0162 1.0081
No log 3.3611 242 1.1646 0.2690 1.1646 1.0792
No log 3.3889 244 1.0332 0.4144 1.0332 1.0165
No log 3.4167 246 0.8400 0.5163 0.8400 0.9165
No log 3.4444 248 0.8966 0.4840 0.8966 0.9469
No log 3.4722 250 0.9709 0.4496 0.9709 0.9853
No log 3.5 252 0.9467 0.5052 0.9467 0.9730
No log 3.5278 254 0.8715 0.4444 0.8715 0.9335
No log 3.5556 256 0.8957 0.4159 0.8957 0.9464
No log 3.5833 258 0.8897 0.3854 0.8897 0.9432
No log 3.6111 260 0.8683 0.4428 0.8683 0.9318
No log 3.6389 262 0.8643 0.3960 0.8643 0.9297
No log 3.6667 264 0.8907 0.3404 0.8907 0.9437
No log 3.6944 266 0.9344 0.4573 0.9344 0.9667
No log 3.7222 268 0.9205 0.4470 0.9205 0.9594
No log 3.75 270 0.8612 0.4471 0.8612 0.9280
No log 3.7778 272 0.8335 0.5235 0.8335 0.9130
No log 3.8056 274 0.8262 0.4770 0.8262 0.9090
No log 3.8333 276 0.8388 0.4368 0.8388 0.9159
No log 3.8611 278 0.8356 0.4385 0.8356 0.9141
No log 3.8889 280 0.8459 0.4499 0.8459 0.9198
No log 3.9167 282 0.8788 0.4615 0.8788 0.9374
No log 3.9444 284 0.8435 0.4782 0.8435 0.9184
No log 3.9722 286 0.8582 0.4972 0.8582 0.9264
No log 4.0 288 0.8891 0.4986 0.8891 0.9429
No log 4.0278 290 0.8736 0.5263 0.8736 0.9347
No log 4.0556 292 0.8535 0.5164 0.8535 0.9239
No log 4.0833 294 0.8553 0.4972 0.8553 0.9248
No log 4.1111 296 0.8264 0.4849 0.8264 0.9091
No log 4.1389 298 0.8380 0.4657 0.8380 0.9154
No log 4.1667 300 0.8128 0.4521 0.8128 0.9016
No log 4.1944 302 0.8110 0.4371 0.8110 0.9005
No log 4.2222 304 0.8321 0.4234 0.8321 0.9122
No log 4.25 306 0.8098 0.4151 0.8098 0.8999
No log 4.2778 308 0.8147 0.4113 0.8147 0.9026
No log 4.3056 310 0.8272 0.4113 0.8272 0.9095
No log 4.3333 312 0.8250 0.4676 0.8250 0.9083
No log 4.3611 314 0.8724 0.5084 0.8724 0.9340
No log 4.3889 316 0.9935 0.3787 0.9935 0.9968
No log 4.4167 318 1.0584 0.2961 1.0584 1.0288
No log 4.4444 320 1.0713 0.2820 1.0713 1.0350
No log 4.4722 322 1.0220 0.2961 1.0220 1.0109
No log 4.5 324 0.9373 0.3045 0.9373 0.9681
No log 4.5278 326 0.8799 0.4279 0.8799 0.9380
No log 4.5556 328 0.8647 0.4705 0.8647 0.9299
No log 4.5833 330 0.8805 0.4159 0.8805 0.9383
No log 4.6111 332 0.9266 0.4098 0.9266 0.9626
No log 4.6389 334 0.9672 0.3938 0.9672 0.9835
No log 4.6667 336 0.9066 0.4068 0.9066 0.9522
No log 4.6944 338 0.8159 0.3702 0.8159 0.9032
No log 4.7222 340 0.7935 0.3960 0.7935 0.8908
No log 4.75 342 0.7987 0.4490 0.7987 0.8937
No log 4.7778 344 0.8016 0.4490 0.8016 0.8953
No log 4.8056 346 0.8114 0.4223 0.8114 0.9008
No log 4.8333 348 0.8242 0.4097 0.8242 0.9078
No log 4.8611 350 0.8299 0.3959 0.8299 0.9110
No log 4.8889 352 0.8450 0.3959 0.8450 0.9193
No log 4.9167 354 0.8617 0.3682 0.8617 0.9283
No log 4.9444 356 0.8691 0.3673 0.8691 0.9323
No log 4.9722 358 0.8914 0.3258 0.8914 0.9441
No log 5.0 360 0.9229 0.2647 0.9229 0.9607
No log 5.0278 362 0.9558 0.2553 0.9558 0.9777
No log 5.0556 364 0.9791 0.2865 0.9791 0.9895
No log 5.0833 366 0.9637 0.2830 0.9637 0.9817
No log 5.1111 368 0.9044 0.3729 0.9044 0.9510
No log 5.1389 370 0.9095 0.4747 0.9095 0.9537
No log 5.1667 372 0.9098 0.4643 0.9098 0.9539
No log 5.1944 374 0.9048 0.3354 0.9048 0.9512
No log 5.2222 376 0.9863 0.2865 0.9863 0.9931
No log 5.25 378 1.0529 0.2723 1.0529 1.0261
No log 5.2778 380 1.0156 0.2408 1.0156 1.0077
No log 5.3056 382 0.9336 0.3306 0.9336 0.9662
No log 5.3333 384 0.9261 0.3382 0.9261 0.9624
No log 5.3611 386 0.9818 0.3779 0.9818 0.9909
No log 5.3889 388 0.9423 0.4112 0.9423 0.9707
No log 5.4167 390 0.8606 0.4471 0.8606 0.9277
No log 5.4444 392 0.9403 0.4920 0.9403 0.9697
No log 5.4722 394 1.0616 0.3753 1.0616 1.0304
No log 5.5 396 0.9973 0.3863 0.9973 0.9987
No log 5.5278 398 0.8636 0.4484 0.8636 0.9293
No log 5.5556 400 0.8413 0.4691 0.8413 0.9172
No log 5.5833 402 0.8531 0.4834 0.8531 0.9236
No log 5.6111 404 0.8452 0.4592 0.8452 0.9194
No log 5.6389 406 0.8300 0.4398 0.8300 0.9110
No log 5.6667 408 0.8568 0.3250 0.8568 0.9256
No log 5.6944 410 0.8833 0.3434 0.8833 0.9399
No log 5.7222 412 0.9099 0.3710 0.9099 0.9539
No log 5.75 414 0.9509 0.3972 0.9509 0.9752
No log 5.7778 416 0.9614 0.4234 0.9614 0.9805
No log 5.8056 418 0.8870 0.4202 0.8870 0.9418
No log 5.8333 420 0.8718 0.4543 0.8718 0.9337
No log 5.8611 422 0.8752 0.4056 0.8752 0.9355
No log 5.8889 424 0.8991 0.4586 0.8991 0.9482
No log 5.9167 426 0.9374 0.3424 0.9374 0.9682
No log 5.9444 428 0.9260 0.2582 0.9260 0.9623
No log 5.9722 430 0.8921 0.3424 0.8921 0.9445
No log 6.0 432 0.8532 0.4746 0.8532 0.9237
No log 6.0278 434 0.8525 0.3896 0.8525 0.9233
No log 6.0556 436 0.8540 0.4163 0.8540 0.9241
No log 6.0833 438 0.8548 0.4878 0.8548 0.9245
No log 6.1111 440 0.9145 0.3845 0.9145 0.9563
No log 6.1389 442 1.0035 0.3761 1.0035 1.0017
No log 6.1667 444 0.9963 0.3761 0.9963 0.9982
No log 6.1944 446 0.9308 0.3590 0.9308 0.9648
No log 6.2222 448 0.8603 0.4318 0.8603 0.9275
No log 6.25 450 0.8352 0.3590 0.8352 0.9139
No log 6.2778 452 0.8370 0.3467 0.8370 0.9149
No log 6.3056 454 0.8394 0.4105 0.8394 0.9162
No log 6.3333 456 0.8767 0.3902 0.8767 0.9363
No log 6.3611 458 0.9036 0.2200 0.9036 0.9506
No log 6.3889 460 0.8859 0.4214 0.8859 0.9412
No log 6.4167 462 0.8949 0.4595 0.8949 0.9460
No log 6.4444 464 0.8792 0.4595 0.8792 0.9377
No log 6.4722 466 0.8707 0.4823 0.8707 0.9331
No log 6.5 468 0.8674 0.4241 0.8674 0.9313
No log 6.5278 470 0.8190 0.4119 0.8190 0.9050
No log 6.5556 472 0.8168 0.4405 0.8168 0.9038
No log 6.5833 474 0.8219 0.4405 0.8219 0.9066
No log 6.6111 476 0.8393 0.3979 0.8393 0.9162
No log 6.6389 478 0.8480 0.4067 0.8480 0.9209
No log 6.6667 480 0.8383 0.4101 0.8383 0.9156
No log 6.6944 482 0.8298 0.4101 0.8298 0.9109
No log 6.7222 484 0.8159 0.3998 0.8159 0.9033
No log 6.75 486 0.8350 0.4639 0.8350 0.9138
No log 6.7778 488 0.8596 0.4782 0.8596 0.9271
No log 6.8056 490 0.8184 0.5239 0.8184 0.9047
No log 6.8333 492 0.8155 0.4067 0.8155 0.9030
No log 6.8611 494 0.8374 0.4593 0.8374 0.9151
No log 6.8889 496 0.8225 0.3922 0.8225 0.9069
No log 6.9167 498 0.7935 0.4119 0.7935 0.8908
0.2706 6.9444 500 0.8045 0.4585 0.8045 0.8969
0.2706 6.9722 502 0.8234 0.4585 0.8234 0.9074
0.2706 7.0 504 0.8111 0.4709 0.8111 0.9006
0.2706 7.0278 506 0.8001 0.4017 0.8001 0.8945
0.2706 7.0556 508 0.8451 0.4843 0.8451 0.9193
0.2706 7.0833 510 0.8827 0.3973 0.8827 0.9395
0.2706 7.1111 512 0.8490 0.4725 0.8490 0.9214
0.2706 7.1389 514 0.8272 0.4754 0.8272 0.9095
0.2706 7.1667 516 0.8113 0.4519 0.8113 0.9007
0.2706 7.1944 518 0.7836 0.5054 0.7836 0.8852
0.2706 7.2222 520 0.7883 0.4321 0.7883 0.8879
0.2706 7.25 522 0.7934 0.4422 0.7934 0.8907
0.2706 7.2778 524 0.7965 0.4676 0.7965 0.8925
0.2706 7.3056 526 0.7999 0.4776 0.7999 0.8944
0.2706 7.3333 528 0.8246 0.4613 0.8246 0.9081
0.2706 7.3611 530 0.8456 0.375 0.8456 0.9196
0.2706 7.3889 532 0.8422 0.4237 0.8422 0.9177
0.2706 7.4167 534 0.8418 0.4760 0.8418 0.9175
0.2706 7.4444 536 0.8650 0.3706 0.8650 0.9300
0.2706 7.4722 538 0.8783 0.3687 0.8783 0.9372
0.2706 7.5 540 0.8760 0.3687 0.8760 0.9359
0.2706 7.5278 542 0.8705 0.3682 0.8705 0.9330
0.2706 7.5556 544 0.8591 0.3536 0.8591 0.9269

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_k15_task5_organization

Finetuned
(4040)
this model