ArabicNewSplits7_B_usingALLEssays_FineTuningAraBERT_run2_AugV5_k12_task2_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: 1.0571
  • Qwk: 0.1982
  • Mse: 1.0571
  • Rmse: 1.0282

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 0.0333 2 4.5391 -0.0020 4.5391 2.1305
No log 0.0667 4 2.5711 0.0179 2.5711 1.6035
No log 0.1 6 1.8962 -0.0233 1.8962 1.3770
No log 0.1333 8 2.4609 -0.0660 2.4609 1.5687
No log 0.1667 10 1.8868 -0.0879 1.8868 1.3736
No log 0.2 12 1.3128 0.1081 1.3128 1.1458
No log 0.2333 14 1.4131 -0.0177 1.4131 1.1888
No log 0.2667 16 2.3459 -0.0114 2.3459 1.5316
No log 0.3 18 2.7943 -0.0320 2.7943 1.6716
No log 0.3333 20 1.9404 0.0733 1.9404 1.3930
No log 0.3667 22 1.4469 0.0969 1.4469 1.2029
No log 0.4 24 1.2916 0.0389 1.2916 1.1365
No log 0.4333 26 1.2664 0.0731 1.2664 1.1254
No log 0.4667 28 1.3065 0.0900 1.3065 1.1430
No log 0.5 30 1.3027 0.1289 1.3027 1.1414
No log 0.5333 32 1.5137 0.1553 1.5137 1.2303
No log 0.5667 34 1.6265 0.1723 1.6265 1.2753
No log 0.6 36 1.7599 0.1202 1.7599 1.3266
No log 0.6333 38 2.1100 0.1341 2.1100 1.4526
No log 0.6667 40 1.8864 0.1755 1.8864 1.3735
No log 0.7 42 1.2551 0.2181 1.2551 1.1203
No log 0.7333 44 1.1335 0.3337 1.1335 1.0647
No log 0.7667 46 1.2754 0.2550 1.2754 1.1293
No log 0.8 48 1.6920 0.2088 1.6920 1.3008
No log 0.8333 50 1.4775 0.2374 1.4775 1.2155
No log 0.8667 52 1.0848 0.3476 1.0848 1.0415
No log 0.9 54 1.0377 0.3014 1.0377 1.0187
No log 0.9333 56 1.0864 0.2785 1.0864 1.0423
No log 0.9667 58 1.1436 0.2191 1.1436 1.0694
No log 1.0 60 1.2472 0.1730 1.2472 1.1168
No log 1.0333 62 1.4320 0.1357 1.4320 1.1967
No log 1.0667 64 1.7577 0.1642 1.7577 1.3258
No log 1.1 66 1.6713 0.1819 1.6713 1.2928
No log 1.1333 68 1.3967 0.3022 1.3967 1.1818
No log 1.1667 70 1.2416 0.2900 1.2416 1.1143
No log 1.2 72 1.2168 0.3580 1.2168 1.1031
No log 1.2333 74 1.3329 0.3580 1.3329 1.1545
No log 1.2667 76 1.3742 0.3490 1.3742 1.1722
No log 1.3 78 1.3301 0.3145 1.3301 1.1533
No log 1.3333 80 1.0550 0.2963 1.0550 1.0271
No log 1.3667 82 1.0106 0.4203 1.0106 1.0053
No log 1.4 84 0.9950 0.4039 0.9950 0.9975
No log 1.4333 86 0.9812 0.4181 0.9812 0.9905
No log 1.4667 88 0.9594 0.4219 0.9594 0.9795
No log 1.5 90 0.9740 0.3637 0.9740 0.9869
No log 1.5333 92 1.4040 0.3243 1.4040 1.1849
No log 1.5667 94 1.7549 0.2598 1.7549 1.3247
No log 1.6 96 1.4800 0.3358 1.4800 1.2166
No log 1.6333 98 1.0181 0.5243 1.0181 1.0090
No log 1.6667 100 1.0095 0.4536 1.0095 1.0047
No log 1.7 102 1.0165 0.5243 1.0165 1.0082
No log 1.7333 104 1.2943 0.3339 1.2943 1.1377
No log 1.7667 106 1.4229 0.3437 1.4229 1.1928
No log 1.8 108 1.2105 0.4246 1.2105 1.1002
No log 1.8333 110 1.0725 0.4800 1.0725 1.0356
No log 1.8667 112 1.0711 0.4800 1.0711 1.0349
No log 1.9 114 1.1997 0.4155 1.1997 1.0953
No log 1.9333 116 1.0792 0.4810 1.0792 1.0388
No log 1.9667 118 1.0736 0.5248 1.0736 1.0361
No log 2.0 120 1.1291 0.5280 1.1291 1.0626
No log 2.0333 122 1.1851 0.4807 1.1851 1.0886
No log 2.0667 124 1.1112 0.4661 1.1112 1.0541
No log 2.1 126 1.1028 0.5076 1.1028 1.0501
No log 2.1333 128 1.2655 0.3379 1.2655 1.1250
No log 2.1667 130 1.5559 0.2635 1.5559 1.2474
No log 2.2 132 1.4038 0.2445 1.4038 1.1848
No log 2.2333 134 1.1472 0.2831 1.1472 1.0711
No log 2.2667 136 1.1348 0.2709 1.1348 1.0653
No log 2.3 138 1.1774 0.3939 1.1774 1.0851
No log 2.3333 140 1.2615 0.3763 1.2615 1.1232
No log 2.3667 142 1.3497 0.3040 1.3497 1.1618
No log 2.4 144 1.2972 0.3641 1.2972 1.1389
No log 2.4333 146 1.1521 0.2750 1.1521 1.0734
No log 2.4667 148 1.1630 0.2390 1.1630 1.0784
No log 2.5 150 1.1798 0.3401 1.1798 1.0862
No log 2.5333 152 1.3390 0.3004 1.3390 1.1572
No log 2.5667 154 1.3576 0.2944 1.3576 1.1651
No log 2.6 156 1.3002 0.3197 1.3002 1.1402
No log 2.6333 158 1.2449 0.3494 1.2449 1.1158
No log 2.6667 160 1.1684 0.2651 1.1684 1.0809
No log 2.7 162 1.1692 0.2461 1.1692 1.0813
No log 2.7333 164 1.3464 0.3453 1.3464 1.1604
No log 2.7667 166 1.4547 0.2495 1.4547 1.2061
No log 2.8 168 1.4578 0.2068 1.4578 1.2074
No log 2.8333 170 1.2651 0.3642 1.2651 1.1248
No log 2.8667 172 1.1612 0.3119 1.1612 1.0776
No log 2.9 174 1.1539 0.3629 1.1539 1.0742
No log 2.9333 176 1.1609 0.2682 1.1609 1.0775
No log 2.9667 178 1.1212 0.1856 1.1212 1.0589
No log 3.0 180 1.1298 0.1903 1.1298 1.0629
No log 3.0333 182 1.1730 0.1817 1.1730 1.0831
No log 3.0667 184 1.2173 0.1920 1.2173 1.1033
No log 3.1 186 1.3176 0.2384 1.3176 1.1479
No log 3.1333 188 1.4880 0.2412 1.4880 1.2198
No log 3.1667 190 1.8554 0.1815 1.8554 1.3621
No log 3.2 192 1.6554 0.2424 1.6554 1.2866
No log 3.2333 194 1.2734 0.2869 1.2734 1.1285
No log 3.2667 196 1.2274 0.3448 1.2274 1.1079
No log 3.3 198 1.2000 0.3532 1.2000 1.0954
No log 3.3333 200 1.1237 0.3849 1.1237 1.0600
No log 3.3667 202 1.4135 0.2328 1.4135 1.1889
No log 3.4 204 1.5580 0.2836 1.5580 1.2482
No log 3.4333 206 1.3208 0.2758 1.3208 1.1493
No log 3.4667 208 1.0608 0.2221 1.0608 1.0300
No log 3.5 210 1.0245 0.3363 1.0245 1.0122
No log 3.5333 212 1.0306 0.3516 1.0306 1.0152
No log 3.5667 214 1.0057 0.4444 1.0057 1.0028
No log 3.6 216 1.0085 0.4354 1.0085 1.0042
No log 3.6333 218 1.1262 0.3154 1.1262 1.0612
No log 3.6667 220 1.3469 0.3352 1.3469 1.1606
No log 3.7 222 1.3263 0.3352 1.3263 1.1516
No log 3.7333 224 1.1019 0.4592 1.1019 1.0497
No log 3.7667 226 1.1286 0.3319 1.1286 1.0624
No log 3.8 228 1.1583 0.3183 1.1583 1.0762
No log 3.8333 230 1.1084 0.3103 1.1084 1.0528
No log 3.8667 232 1.1118 0.2278 1.1118 1.0544
No log 3.9 234 1.1876 0.2128 1.1876 1.0898
No log 3.9333 236 1.2498 0.2687 1.2498 1.1179
No log 3.9667 238 1.2108 0.2044 1.2108 1.1004
No log 4.0 240 1.1776 0.2766 1.1776 1.0852
No log 4.0333 242 1.1872 0.2366 1.1872 1.0896
No log 4.0667 244 1.2878 0.3210 1.2878 1.1348
No log 4.1 246 1.4242 0.3180 1.4242 1.1934
No log 4.1333 248 1.4365 0.3119 1.4365 1.1985
No log 4.1667 250 1.2891 0.3548 1.2891 1.1354
No log 4.2 252 1.1474 0.4172 1.1474 1.0712
No log 4.2333 254 1.0241 0.3985 1.0241 1.0120
No log 4.2667 256 1.0214 0.375 1.0214 1.0106
No log 4.3 258 0.9994 0.4349 0.9994 0.9997
No log 4.3333 260 1.0200 0.3980 1.0200 1.0100
No log 4.3667 262 1.0343 0.3892 1.0343 1.0170
No log 4.4 264 0.9789 0.4082 0.9789 0.9894
No log 4.4333 266 0.9561 0.3827 0.9561 0.9778
No log 4.4667 268 0.9507 0.4301 0.9507 0.9750
No log 4.5 270 0.9562 0.4030 0.9562 0.9779
No log 4.5333 272 0.9276 0.4288 0.9276 0.9631
No log 4.5667 274 0.9269 0.4254 0.9269 0.9627
No log 4.6 276 0.9370 0.4050 0.9370 0.9680
No log 4.6333 278 0.9593 0.4176 0.9593 0.9794
No log 4.6667 280 1.0317 0.3494 1.0317 1.0157
No log 4.7 282 1.1004 0.3972 1.1004 1.0490
No log 4.7333 284 1.2322 0.3348 1.2322 1.1100
No log 4.7667 286 1.2432 0.3261 1.2432 1.1150
No log 4.8 288 1.1582 0.3471 1.1582 1.0762
No log 4.8333 290 1.0668 0.2651 1.0668 1.0329
No log 4.8667 292 1.0510 0.2505 1.0510 1.0252
No log 4.9 294 1.0637 0.2824 1.0637 1.0314
No log 4.9333 296 1.0609 0.3719 1.0609 1.0300
No log 4.9667 298 1.0227 0.3458 1.0227 1.0113
No log 5.0 300 1.0324 0.3869 1.0324 1.0161
No log 5.0333 302 1.1028 0.3307 1.1028 1.0502
No log 5.0667 304 1.0701 0.3444 1.0701 1.0344
No log 5.1 306 1.0144 0.4080 1.0144 1.0072
No log 5.1333 308 1.0280 0.3193 1.0280 1.0139
No log 5.1667 310 1.0841 0.3144 1.0841 1.0412
No log 5.2 312 1.0804 0.3237 1.0804 1.0394
No log 5.2333 314 1.0205 0.3480 1.0205 1.0102
No log 5.2667 316 0.9894 0.3826 0.9894 0.9947
No log 5.3 318 0.9975 0.4216 0.9975 0.9988
No log 5.3333 320 1.0079 0.4216 1.0079 1.0039
No log 5.3667 322 1.0363 0.3892 1.0363 1.0180
No log 5.4 324 1.0530 0.3318 1.0530 1.0261
No log 5.4333 326 1.0692 0.2871 1.0692 1.0340
No log 5.4667 328 1.0834 0.2726 1.0834 1.0409
No log 5.5 330 1.1067 0.2062 1.1067 1.0520
No log 5.5333 332 1.1498 0.2501 1.1498 1.0723
No log 5.5667 334 1.1222 0.2128 1.1222 1.0593
No log 5.6 336 1.1402 0.3052 1.1402 1.0678
No log 5.6333 338 1.0671 0.2759 1.0671 1.0330
No log 5.6667 340 1.0260 0.3363 1.0260 1.0129
No log 5.7 342 1.0236 0.4256 1.0236 1.0118
No log 5.7333 344 1.0640 0.2624 1.0640 1.0315
No log 5.7667 346 1.0884 0.3458 1.0884 1.0432
No log 5.8 348 1.0904 0.3622 1.0904 1.0442
No log 5.8333 350 1.0581 0.3573 1.0581 1.0286
No log 5.8667 352 0.9953 0.3397 0.9953 0.9976
No log 5.9 354 1.0436 0.3573 1.0436 1.0216
No log 5.9333 356 0.9948 0.3262 0.9948 0.9974
No log 5.9667 358 1.0258 0.2870 1.0258 1.0128
No log 6.0 360 1.1243 0.3267 1.1243 1.0603
No log 6.0333 362 1.1279 0.2657 1.1279 1.0620
No log 6.0667 364 1.0453 0.2669 1.0453 1.0224
No log 6.1 366 1.0220 0.2988 1.0220 1.0109
No log 6.1333 368 0.9958 0.2919 0.9958 0.9979
No log 6.1667 370 0.9783 0.3230 0.9783 0.9891
No log 6.2 372 0.9738 0.3608 0.9738 0.9868
No log 6.2333 374 0.9761 0.3415 0.9761 0.9880
No log 6.2667 376 1.0025 0.3584 1.0025 1.0012
No log 6.3 378 1.0936 0.2939 1.0936 1.0457
No log 6.3333 380 1.1651 0.3243 1.1651 1.0794
No log 6.3667 382 1.1202 0.3243 1.1202 1.0584
No log 6.4 384 0.9956 0.2702 0.9956 0.9978
No log 6.4333 386 0.9171 0.4100 0.9171 0.9577
No log 6.4667 388 0.9317 0.4295 0.9317 0.9652
No log 6.5 390 0.9440 0.3809 0.9440 0.9716
No log 6.5333 392 0.8836 0.4889 0.8836 0.9400
No log 6.5667 394 0.9152 0.4301 0.9152 0.9567
No log 6.6 396 1.0468 0.3952 1.0468 1.0231
No log 6.6333 398 1.0224 0.4238 1.0224 1.0111
No log 6.6667 400 0.9513 0.3897 0.9513 0.9753
No log 6.7 402 0.9510 0.3243 0.9510 0.9752
No log 6.7333 404 0.9528 0.3373 0.9528 0.9761
No log 6.7667 406 0.9923 0.3224 0.9923 0.9962
No log 6.8 408 0.9904 0.3082 0.9904 0.9952
No log 6.8333 410 0.9875 0.3626 0.9875 0.9937
No log 6.8667 412 1.0606 0.3663 1.0606 1.0299
No log 6.9 414 1.0979 0.3355 1.0979 1.0478
No log 6.9333 416 1.0064 0.3859 1.0064 1.0032
No log 6.9667 418 0.9658 0.3694 0.9658 0.9827
No log 7.0 420 1.0406 0.4223 1.0406 1.0201
No log 7.0333 422 1.0264 0.3764 1.0264 1.0131
No log 7.0667 424 0.9906 0.2944 0.9906 0.9953
No log 7.1 426 1.0772 0.2361 1.0772 1.0379
No log 7.1333 428 1.1008 0.2180 1.1008 1.0492
No log 7.1667 430 1.0286 0.1873 1.0286 1.0142
No log 7.2 432 1.0271 0.3117 1.0271 1.0135
No log 7.2333 434 1.0252 0.2970 1.0252 1.0125
No log 7.2667 436 0.9998 0.3552 0.9998 0.9999
No log 7.3 438 1.0067 0.3081 1.0067 1.0034
No log 7.3333 440 1.0796 0.2986 1.0796 1.0390
No log 7.3667 442 1.0876 0.2986 1.0876 1.0429
No log 7.4 444 1.0254 0.3231 1.0254 1.0126
No log 7.4333 446 0.9694 0.3881 0.9694 0.9846
No log 7.4667 448 0.9682 0.3836 0.9682 0.9840
No log 7.5 450 1.0154 0.3397 1.0154 1.0077
No log 7.5333 452 1.0967 0.3184 1.0967 1.0472
No log 7.5667 454 1.1306 0.2687 1.1306 1.0633
No log 7.6 456 1.1048 0.2687 1.1048 1.0511
No log 7.6333 458 1.0598 0.2467 1.0598 1.0295
No log 7.6667 460 1.1173 0.2687 1.1173 1.0570
No log 7.7 462 1.1248 0.2762 1.1248 1.0606
No log 7.7333 464 1.1273 0.2762 1.1273 1.0618
No log 7.7667 466 1.1110 0.2762 1.1110 1.0540
No log 7.8 468 1.0674 0.3330 1.0674 1.0331
No log 7.8333 470 1.0910 0.2919 1.0910 1.0445
No log 7.8667 472 1.1373 0.3179 1.1373 1.0665
No log 7.9 474 1.2094 0.2941 1.2094 1.0997
No log 7.9333 476 1.1088 0.3267 1.1088 1.0530
No log 7.9667 478 1.1154 0.3267 1.1154 1.0561
No log 8.0 480 1.0863 0.2919 1.0863 1.0422
No log 8.0333 482 1.0630 0.2417 1.0630 1.0310
No log 8.0667 484 1.1148 0.2962 1.1148 1.0558
No log 8.1 486 1.2446 0.2833 1.2446 1.1156
No log 8.1333 488 1.2228 0.2833 1.2228 1.1058
No log 8.1667 490 1.1333 0.3092 1.1333 1.0646
No log 8.2 492 1.0666 0.2361 1.0666 1.0328
No log 8.2333 494 1.0167 0.2939 1.0167 1.0083
No log 8.2667 496 0.9997 0.3448 0.9997 0.9998
No log 8.3 498 1.0376 0.3100 1.0376 1.0186
0.3248 8.3333 500 1.0506 0.2687 1.0506 1.0250
0.3248 8.3667 502 1.0570 0.2687 1.0570 1.0281
0.3248 8.4 504 0.9923 0.3269 0.9923 0.9962
0.3248 8.4333 506 0.9712 0.3406 0.9712 0.9855
0.3248 8.4667 508 0.9630 0.4485 0.9630 0.9813
0.3248 8.5 510 0.9901 0.3399 0.9901 0.9951
0.3248 8.5333 512 1.0486 0.2555 1.0486 1.0240
0.3248 8.5667 514 1.1499 0.2750 1.1499 1.0723
0.3248 8.6 516 1.2030 0.2554 1.2030 1.0968
0.3248 8.6333 518 1.1892 0.2554 1.1892 1.0905
0.3248 8.6667 520 1.1682 0.2417 1.1682 1.0808
0.3248 8.7 522 1.0987 0.2609 1.0987 1.0482
0.3248 8.7333 524 1.0571 0.1982 1.0571 1.0282

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_B_usingALLEssays_FineTuningAraBERT_run2_AugV5_k12_task2_organization

Finetuned
(4032)
this model