ArabicNewSplits7_B_usingALLEssays_FineTuningAraBERT_run3_AugV5_k5_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: 1.0728
  • Qwk: 0.2523
  • Mse: 1.0728
  • Rmse: 1.0358

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 0.08 2 4.6671 0.0010 4.6671 2.1603
No log 0.16 4 2.7485 -0.0278 2.7485 1.6579
No log 0.24 6 1.6754 0.0372 1.6754 1.2944
No log 0.32 8 1.4349 0.0372 1.4349 1.1979
No log 0.4 10 1.2382 0.0803 1.2382 1.1127
No log 0.48 12 1.1349 0.2268 1.1349 1.0653
No log 0.56 14 1.1539 0.1733 1.1539 1.0742
No log 0.64 16 1.3292 0.1076 1.3292 1.1529
No log 0.72 18 1.5269 0.0426 1.5269 1.2357
No log 0.8 20 1.5050 0.0426 1.5050 1.2268
No log 0.88 22 1.2760 0.2351 1.2760 1.1296
No log 0.96 24 1.0801 0.2478 1.0801 1.0393
No log 1.04 26 1.1293 0.1711 1.1293 1.0627
No log 1.12 28 1.0907 0.2440 1.0907 1.0444
No log 1.2 30 1.1308 0.2730 1.1308 1.0634
No log 1.28 32 1.3461 0.0898 1.3461 1.1602
No log 1.3600 34 1.4082 0.0898 1.4082 1.1867
No log 1.44 36 1.2992 0.1076 1.2992 1.1398
No log 1.52 38 1.3532 0.2071 1.3532 1.1633
No log 1.6 40 1.5980 0.1032 1.5980 1.2641
No log 1.6800 42 1.6291 0.1224 1.6291 1.2764
No log 1.76 44 1.8627 0.0668 1.8627 1.3648
No log 1.8400 46 2.0880 0.0904 2.0880 1.4450
No log 1.92 48 1.8223 0.0241 1.8223 1.3499
No log 2.0 50 1.3597 0.1461 1.3597 1.1661
No log 2.08 52 1.1096 0.2054 1.1096 1.0534
No log 2.16 54 1.0167 0.3263 1.0167 1.0083
No log 2.24 56 1.0354 0.3493 1.0354 1.0175
No log 2.32 58 1.0416 0.3337 1.0416 1.0206
No log 2.4 60 1.0772 0.3179 1.0772 1.0379
No log 2.48 62 1.1389 0.2560 1.1389 1.0672
No log 2.56 64 1.3289 0.1080 1.3289 1.1528
No log 2.64 66 1.3432 0.1604 1.3432 1.1590
No log 2.7200 68 1.2529 0.1493 1.2529 1.1193
No log 2.8 70 1.1217 0.2702 1.1217 1.0591
No log 2.88 72 1.1066 0.3224 1.1066 1.0520
No log 2.96 74 1.1726 0.2796 1.1726 1.0829
No log 3.04 76 1.2025 0.2896 1.2025 1.0966
No log 3.12 78 1.1052 0.3305 1.1052 1.0513
No log 3.2 80 1.0298 0.4016 1.0298 1.0148
No log 3.2800 82 1.0341 0.3356 1.0341 1.0169
No log 3.36 84 1.0395 0.3603 1.0395 1.0196
No log 3.44 86 1.1074 0.3218 1.1074 1.0523
No log 3.52 88 1.0706 0.3250 1.0706 1.0347
No log 3.6 90 0.9954 0.3558 0.9954 0.9977
No log 3.68 92 0.9491 0.3914 0.9491 0.9742
No log 3.76 94 0.9317 0.4235 0.9317 0.9653
No log 3.84 96 0.9025 0.4197 0.9025 0.9500
No log 3.92 98 0.8868 0.3478 0.8868 0.9417
No log 4.0 100 0.8788 0.3787 0.8788 0.9374
No log 4.08 102 0.8768 0.3695 0.8768 0.9364
No log 4.16 104 0.8802 0.4359 0.8802 0.9382
No log 4.24 106 0.9324 0.3985 0.9324 0.9656
No log 4.32 108 0.8941 0.4260 0.8941 0.9455
No log 4.4 110 0.8909 0.3552 0.8909 0.9438
No log 4.48 112 0.9630 0.3335 0.9630 0.9813
No log 4.5600 114 1.0022 0.4034 1.0022 1.0011
No log 4.64 116 1.0614 0.3686 1.0614 1.0302
No log 4.72 118 1.0021 0.3139 1.0021 1.0011
No log 4.8 120 0.9694 0.3695 0.9694 0.9846
No log 4.88 122 0.9884 0.3132 0.9884 0.9942
No log 4.96 124 0.9958 0.3468 0.9958 0.9979
No log 5.04 126 1.0089 0.3489 1.0089 1.0045
No log 5.12 128 1.1914 0.4077 1.1914 1.0915
No log 5.2 130 1.3940 0.3687 1.3940 1.1807
No log 5.28 132 1.2085 0.4016 1.2085 1.0993
No log 5.36 134 1.0963 0.3661 1.0963 1.0470
No log 5.44 136 1.1542 0.2833 1.1542 1.0743
No log 5.52 138 1.1908 0.3432 1.1908 1.0912
No log 5.6 140 1.0960 0.3635 1.0960 1.0469
No log 5.68 142 1.1008 0.3421 1.1008 1.0492
No log 5.76 144 1.0715 0.3105 1.0715 1.0351
No log 5.84 146 1.0738 0.3573 1.0738 1.0362
No log 5.92 148 1.1229 0.3418 1.1229 1.0597
No log 6.0 150 1.0529 0.4019 1.0529 1.0261
No log 6.08 152 1.0238 0.3949 1.0238 1.0118
No log 6.16 154 1.0095 0.3949 1.0095 1.0048
No log 6.24 156 0.9964 0.3908 0.9964 0.9982
No log 6.32 158 0.9891 0.4308 0.9891 0.9945
No log 6.4 160 0.9755 0.3897 0.9755 0.9877
No log 6.48 162 0.9668 0.3180 0.9668 0.9832
No log 6.5600 164 0.9617 0.3852 0.9617 0.9807
No log 6.64 166 0.9732 0.4313 0.9732 0.9865
No log 6.72 168 1.0161 0.4612 1.0161 1.0080
No log 6.8 170 1.0655 0.4321 1.0655 1.0322
No log 6.88 172 1.0619 0.4734 1.0619 1.0305
No log 6.96 174 1.0249 0.4110 1.0249 1.0124
No log 7.04 176 1.0124 0.4110 1.0124 1.0062
No log 7.12 178 1.0274 0.4110 1.0274 1.0136
No log 7.2 180 1.0312 0.4648 1.0312 1.0155
No log 7.28 182 0.9856 0.3861 0.9856 0.9928
No log 7.36 184 0.9916 0.2969 0.9916 0.9958
No log 7.44 186 1.0159 0.3037 1.0159 1.0079
No log 7.52 188 1.0351 0.3742 1.0351 1.0174
No log 7.6 190 1.1068 0.4082 1.1068 1.0520
No log 7.68 192 1.1209 0.3664 1.1209 1.0587
No log 7.76 194 1.0844 0.3129 1.0844 1.0414
No log 7.84 196 1.0822 0.3037 1.0822 1.0403
No log 7.92 198 1.0924 0.3081 1.0924 1.0452
No log 8.0 200 1.1071 0.3765 1.1071 1.0522
No log 8.08 202 1.1001 0.2966 1.1001 1.0488
No log 8.16 204 1.1141 0.2579 1.1141 1.0555
No log 8.24 206 1.1627 0.3465 1.1627 1.0783
No log 8.32 208 1.1420 0.3400 1.1420 1.0686
No log 8.4 210 1.1120 0.2396 1.1120 1.0545
No log 8.48 212 1.1304 0.2634 1.1304 1.0632
No log 8.56 214 1.1721 0.2901 1.1721 1.0826
No log 8.64 216 1.1149 0.2947 1.1149 1.0559
No log 8.72 218 1.0999 0.3584 1.0999 1.0488
No log 8.8 220 1.1370 0.2894 1.1370 1.0663
No log 8.88 222 1.1347 0.3068 1.1347 1.0652
No log 8.96 224 1.0941 0.3547 1.0941 1.0460
No log 9.04 226 1.1042 0.3415 1.1042 1.0508
No log 9.12 228 1.1172 0.3345 1.1172 1.0570
No log 9.2 230 1.1800 0.3353 1.1800 1.0863
No log 9.28 232 1.2462 0.3293 1.2462 1.1163
No log 9.36 234 1.2196 0.3434 1.2196 1.1043
No log 9.44 236 1.1295 0.3942 1.1295 1.0628
No log 9.52 238 1.1206 0.3557 1.1206 1.0586
No log 9.6 240 1.0966 0.3455 1.0966 1.0472
No log 9.68 242 1.0862 0.3296 1.0862 1.0422
No log 9.76 244 1.1866 0.3154 1.1866 1.0893
No log 9.84 246 1.2707 0.2298 1.2707 1.1273
No log 9.92 248 1.1411 0.2078 1.1411 1.0682
No log 10.0 250 1.0383 0.2920 1.0383 1.0190
No log 10.08 252 1.0482 0.2440 1.0482 1.0238
No log 10.16 254 1.0562 0.2921 1.0562 1.0277
No log 10.24 256 1.0352 0.2723 1.0352 1.0174
No log 10.32 258 1.0234 0.3168 1.0234 1.0116
No log 10.4 260 1.0395 0.3200 1.0395 1.0196
No log 10.48 262 1.0932 0.3401 1.0932 1.0456
No log 10.56 264 1.1255 0.3158 1.1255 1.0609
No log 10.64 266 1.0864 0.3804 1.0864 1.0423
No log 10.72 268 1.0951 0.2864 1.0951 1.0465
No log 10.8 270 1.1744 0.3243 1.1744 1.0837
No log 10.88 272 1.1879 0.3111 1.1879 1.0899
No log 10.96 274 1.1271 0.3243 1.1271 1.0616
No log 11.04 276 1.1039 0.3359 1.1039 1.0507
No log 11.12 278 1.1017 0.3707 1.1017 1.0496
No log 11.2 280 1.0918 0.3200 1.0918 1.0449
No log 11.28 282 1.1071 0.3635 1.1071 1.0522
No log 11.36 284 1.1105 0.3465 1.1105 1.0538
No log 11.44 286 1.0863 0.3343 1.0863 1.0423
No log 11.52 288 1.0891 0.3343 1.0891 1.0436
No log 11.6 290 1.0668 0.2772 1.0668 1.0329
No log 11.68 292 1.0471 0.2813 1.0471 1.0233
No log 11.76 294 1.0404 0.1903 1.0404 1.0200
No log 11.84 296 1.0322 0.2455 1.0322 1.0160
No log 11.92 298 1.0705 0.3113 1.0705 1.0346
No log 12.0 300 1.1760 0.3220 1.1760 1.0844
No log 12.08 302 1.1907 0.3667 1.1907 1.0912
No log 12.16 304 1.1446 0.3131 1.1446 1.0699
No log 12.24 306 1.0800 0.3065 1.0800 1.0392
No log 12.32 308 1.0688 0.3065 1.0688 1.0338
No log 12.4 310 1.0682 0.3282 1.0682 1.0335
No log 12.48 312 1.0690 0.3282 1.0690 1.0339
No log 12.56 314 1.0652 0.3282 1.0652 1.0321
No log 12.64 316 1.0721 0.3065 1.0721 1.0354
No log 12.72 318 1.0868 0.3160 1.0868 1.0425
No log 12.8 320 1.1186 0.2574 1.1186 1.0576
No log 12.88 322 1.1161 0.2481 1.1161 1.0565
No log 12.96 324 1.0987 0.2871 1.0987 1.0482
No log 13.04 326 1.0930 0.2972 1.0930 1.0455
No log 13.12 328 1.0828 0.2587 1.0828 1.0406
No log 13.2 330 1.0792 0.2995 1.0792 1.0389
No log 13.28 332 1.0725 0.3418 1.0725 1.0356
No log 13.36 334 1.0581 0.3164 1.0581 1.0287
No log 13.44 336 1.0643 0.3056 1.0643 1.0316
No log 13.52 338 1.0826 0.3299 1.0826 1.0405
No log 13.6 340 1.0809 0.3076 1.0809 1.0396
No log 13.68 342 1.1217 0.4019 1.1217 1.0591
No log 13.76 344 1.1450 0.3950 1.1450 1.0701
No log 13.84 346 1.1075 0.3716 1.1075 1.0524
No log 13.92 348 1.0415 0.3344 1.0415 1.0205
No log 14.0 350 1.0253 0.2993 1.0253 1.0126
No log 14.08 352 1.0151 0.3344 1.0151 1.0075
No log 14.16 354 1.0174 0.3200 1.0174 1.0087
No log 14.24 356 1.0642 0.3572 1.0642 1.0316
No log 14.32 358 1.0590 0.3268 1.0590 1.0291
No log 14.4 360 1.0209 0.3335 1.0209 1.0104
No log 14.48 362 1.0143 0.3376 1.0143 1.0071
No log 14.56 364 1.0277 0.3097 1.0277 1.0137
No log 14.64 366 1.0003 0.3208 1.0003 1.0001
No log 14.72 368 1.0026 0.3243 1.0026 1.0013
No log 14.8 370 1.0372 0.4110 1.0372 1.0184
No log 14.88 372 1.0272 0.3385 1.0272 1.0135
No log 14.96 374 0.9798 0.3548 0.9798 0.9898
No log 15.04 376 0.9563 0.3733 0.9563 0.9779
No log 15.12 378 0.9547 0.3733 0.9547 0.9771
No log 15.2 380 0.9639 0.3335 0.9639 0.9818
No log 15.28 382 0.9767 0.3043 0.9767 0.9883
No log 15.36 384 0.9774 0.3256 0.9774 0.9887
No log 15.44 386 0.9675 0.3463 0.9675 0.9836
No log 15.52 388 0.9711 0.3463 0.9711 0.9854
No log 15.6 390 0.9795 0.3720 0.9795 0.9897
No log 15.68 392 0.9916 0.3256 0.9916 0.9958
No log 15.76 394 0.9875 0.3256 0.9875 0.9937
No log 15.84 396 0.9840 0.3548 0.9840 0.9920
No log 15.92 398 0.9864 0.4277 0.9864 0.9932
No log 16.0 400 0.9969 0.3720 0.9969 0.9984
No log 16.08 402 1.0094 0.3578 1.0094 1.0047
No log 16.16 404 1.0236 0.3379 1.0236 1.0117
No log 16.24 406 1.0311 0.3319 1.0311 1.0154
No log 16.32 408 1.0338 0.3196 1.0338 1.0168
No log 16.4 410 1.0487 0.3677 1.0487 1.0241
No log 16.48 412 1.0447 0.3861 1.0447 1.0221
No log 16.56 414 1.0403 0.3482 1.0403 1.0200
No log 16.64 416 1.0437 0.3764 1.0437 1.0216
No log 16.72 418 1.0435 0.3424 1.0435 1.0215
No log 16.8 420 1.0437 0.3300 1.0437 1.0216
No log 16.88 422 1.0498 0.3088 1.0498 1.0246
No log 16.96 424 1.0766 0.3725 1.0766 1.0376
No log 17.04 426 1.0706 0.3545 1.0706 1.0347
No log 17.12 428 1.0428 0.3455 1.0428 1.0212
No log 17.2 430 1.0213 0.2995 1.0213 1.0106
No log 17.28 432 1.0084 0.3663 1.0084 1.0042
No log 17.36 434 0.9955 0.3987 0.9955 0.9978
No log 17.44 436 0.9877 0.3747 0.9877 0.9938
No log 17.52 438 0.9902 0.3804 0.9902 0.9951
No log 17.6 440 1.0189 0.3043 1.0189 1.0094
No log 17.68 442 1.0263 0.3820 1.0263 1.0131
No log 17.76 444 1.0088 0.3363 1.0088 1.0044
No log 17.84 446 0.9968 0.3094 0.9968 0.9984
No log 17.92 448 0.9992 0.3621 0.9992 0.9996
No log 18.0 450 1.0247 0.3720 1.0247 1.0123
No log 18.08 452 1.0327 0.3720 1.0327 1.0162
No log 18.16 454 1.0198 0.3621 1.0198 1.0098
No log 18.24 456 1.0095 0.2509 1.0095 1.0047
No log 18.32 458 1.0087 0.2509 1.0087 1.0044
No log 18.4 460 1.0012 0.2843 1.0012 1.0006
No log 18.48 462 0.9899 0.2967 0.9899 0.9949
No log 18.56 464 0.9997 0.3020 0.9997 0.9998
No log 18.64 466 1.0335 0.3735 1.0335 1.0166
No log 18.72 468 1.0452 0.3735 1.0452 1.0223
No log 18.8 470 1.0414 0.3735 1.0414 1.0205
No log 18.88 472 1.0249 0.3820 1.0249 1.0124
No log 18.96 474 1.0154 0.3196 1.0154 1.0077
No log 19.04 476 1.0218 0.3298 1.0218 1.0108
No log 19.12 478 1.0273 0.3020 1.0273 1.0136
No log 19.2 480 1.0381 0.3298 1.0381 1.0189
No log 19.28 482 1.0437 0.3298 1.0437 1.0216
No log 19.36 484 1.0592 0.3298 1.0592 1.0292
No log 19.44 486 1.0627 0.3298 1.0627 1.0309
No log 19.52 488 1.0585 0.3196 1.0585 1.0289
No log 19.6 490 1.0563 0.2967 1.0563 1.0278
No log 19.68 492 1.0581 0.2967 1.0581 1.0286
No log 19.76 494 1.0570 0.2967 1.0570 1.0281
No log 19.84 496 1.0590 0.3609 1.0590 1.0291
No log 19.92 498 1.0591 0.3577 1.0591 1.0291
0.3248 20.0 500 1.0526 0.3070 1.0526 1.0260
0.3248 20.08 502 1.0517 0.3070 1.0517 1.0255
0.3248 20.16 504 1.0522 0.2864 1.0522 1.0257
0.3248 20.24 506 1.0610 0.2157 1.0610 1.0300
0.3248 20.32 508 1.0691 0.2344 1.0691 1.0340
0.3248 20.4 510 1.0728 0.2523 1.0728 1.0358

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_run3_AugV5_k5_task2_organization

Finetuned
(4032)
this model