ArabicNewSplits7_B_usingALLEssays_FineTuningAraBERT_run3_AugV5_k20_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: 0.8044
  • Qwk: 0.6846
  • Mse: 0.8044
  • Rmse: 0.8969

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 0.0208 2 6.8461 0.0242 6.8461 2.6165
No log 0.0417 4 4.7364 0.0599 4.7364 2.1763
No log 0.0625 6 3.1045 0.0727 3.1045 1.7620
No log 0.0833 8 2.3184 0.1143 2.3184 1.5226
No log 0.1042 10 1.7255 0.2162 1.7255 1.3136
No log 0.125 12 2.2714 0.2158 2.2714 1.5071
No log 0.1458 14 2.4989 0.1184 2.4989 1.5808
No log 0.1667 16 2.0443 0.2576 2.0443 1.4298
No log 0.1875 18 2.3507 0.1447 2.3507 1.5332
No log 0.2083 20 2.8963 0.1243 2.8963 1.7018
No log 0.2292 22 3.2765 0.1451 3.2765 1.8101
No log 0.25 24 2.2504 0.2308 2.2504 1.5001
No log 0.2708 26 1.3248 0.4409 1.3248 1.1510
No log 0.2917 28 1.1687 0.4762 1.1687 1.0811
No log 0.3125 30 1.2751 0.3871 1.2751 1.1292
No log 0.3333 32 1.3390 0.3140 1.3390 1.1572
No log 0.3542 34 1.3149 0.4762 1.3149 1.1467
No log 0.375 36 2.0158 0.2895 2.0158 1.4198
No log 0.3958 38 3.1403 0.1818 3.1403 1.7721
No log 0.4167 40 3.2065 0.1951 3.2065 1.7907
No log 0.4375 42 2.6750 0.2081 2.6750 1.6355
No log 0.4583 44 1.9874 0.3401 1.9874 1.4098
No log 0.4792 46 1.7642 0.3380 1.7642 1.3283
No log 0.5 48 1.7791 0.3699 1.7791 1.3338
No log 0.5208 50 2.0184 0.3106 2.0184 1.4207
No log 0.5417 52 2.0712 0.3171 2.0712 1.4392
No log 0.5625 54 1.8166 0.3624 1.8166 1.3478
No log 0.5833 56 1.9282 0.3660 1.9282 1.3886
No log 0.6042 58 1.8562 0.3660 1.8562 1.3624
No log 0.625 60 1.8470 0.3733 1.8470 1.3590
No log 0.6458 62 1.8311 0.3916 1.8311 1.3532
No log 0.6667 64 1.8176 0.4 1.8176 1.3482
No log 0.6875 66 1.6956 0.4526 1.6956 1.3022
No log 0.7083 68 1.5053 0.4925 1.5053 1.2269
No log 0.7292 70 1.4959 0.4925 1.4959 1.2231
No log 0.75 72 1.4528 0.4741 1.4528 1.2053
No log 0.7708 74 1.3219 0.5 1.3219 1.1497
No log 0.7917 76 1.2264 0.5556 1.2264 1.1074
No log 0.8125 78 1.2894 0.5767 1.2894 1.1355
No log 0.8333 80 1.8759 0.5025 1.8759 1.3696
No log 0.8542 82 1.9705 0.4412 1.9705 1.4037
No log 0.875 84 1.4115 0.6051 1.4115 1.1881
No log 0.8958 86 0.8828 0.7349 0.8828 0.9396
No log 0.9167 88 0.7612 0.7453 0.7612 0.8724
No log 0.9375 90 0.7485 0.7758 0.7485 0.8651
No log 0.9583 92 0.8185 0.7368 0.8185 0.9047
No log 0.9792 94 0.9275 0.6667 0.9275 0.9631
No log 1.0 96 1.2954 0.6344 1.2954 1.1381
No log 1.0208 98 1.4003 0.5934 1.4003 1.1833
No log 1.0417 100 1.1064 0.6538 1.1064 1.0518
No log 1.0625 102 0.7945 0.7550 0.7945 0.8914
No log 1.0833 104 0.9382 0.6483 0.9382 0.9686
No log 1.1042 106 1.0647 0.5755 1.0647 1.0319
No log 1.125 108 1.0259 0.6014 1.0259 1.0128
No log 1.1458 110 1.0004 0.6471 1.0004 1.0002
No log 1.1667 112 1.1731 0.6526 1.1731 1.0831
No log 1.1875 114 1.1129 0.6667 1.1129 1.0549
No log 1.2083 116 0.8650 0.7486 0.8650 0.9301
No log 1.2292 118 0.7308 0.7953 0.7308 0.8549
No log 1.25 120 0.8163 0.7657 0.8163 0.9035
No log 1.2708 122 1.4192 0.5969 1.4192 1.1913
No log 1.2917 124 2.8517 0.3545 2.8517 1.6887
No log 1.3125 126 3.8841 0.2204 3.8841 1.9708
No log 1.3333 128 3.6497 0.2314 3.6497 1.9104
No log 1.3542 130 2.5894 0.3491 2.5894 1.6092
No log 1.375 132 1.3593 0.5375 1.3593 1.1659
No log 1.3958 134 0.8164 0.6993 0.8164 0.9036
No log 1.4167 136 0.6985 0.7619 0.6985 0.8358
No log 1.4375 138 0.7119 0.7703 0.7119 0.8438
No log 1.4583 140 0.7438 0.7733 0.7438 0.8624
No log 1.4792 142 0.8220 0.6883 0.8220 0.9067
No log 1.5 144 0.9031 0.6443 0.9031 0.9503
No log 1.5208 146 0.9579 0.6275 0.9579 0.9787
No log 1.5417 148 0.9114 0.6494 0.9114 0.9547
No log 1.5625 150 0.8929 0.6538 0.8929 0.9449
No log 1.5833 152 0.8502 0.6957 0.8502 0.9221
No log 1.6042 154 0.8193 0.7134 0.8193 0.9051
No log 1.625 156 1.0525 0.6395 1.0525 1.0259
No log 1.6458 158 1.4329 0.5604 1.4329 1.1970
No log 1.6667 160 1.5677 0.5745 1.5677 1.2521
No log 1.6875 162 1.1247 0.6429 1.1247 1.0605
No log 1.7083 164 0.8921 0.7073 0.8921 0.9445
No log 1.7292 166 0.7669 0.7468 0.7669 0.8757
No log 1.75 168 0.7062 0.7826 0.7062 0.8404
No log 1.7708 170 0.7105 0.8 0.7105 0.8429
No log 1.7917 172 0.8914 0.7191 0.8914 0.9441
No log 1.8125 174 1.0330 0.6704 1.0330 1.0164
No log 1.8333 176 0.7928 0.7251 0.7928 0.8904
No log 1.8542 178 0.7093 0.7742 0.7093 0.8422
No log 1.875 180 1.1604 0.5532 1.1604 1.0772
No log 1.8958 182 1.3899 0.4058 1.3899 1.1789
No log 1.9167 184 1.1310 0.5857 1.1310 1.0635
No log 1.9375 186 0.7724 0.7260 0.7724 0.8788
No log 1.9583 188 0.7203 0.75 0.7203 0.8487
No log 1.9792 190 0.7993 0.7170 0.7993 0.8940
No log 2.0 192 0.9043 0.7 0.9043 0.9510
No log 2.0208 194 0.8479 0.6928 0.8479 0.9208
No log 2.0417 196 0.7852 0.6986 0.7852 0.8861
No log 2.0625 198 0.8280 0.7226 0.8280 0.9099
No log 2.0833 200 0.9863 0.6748 0.9863 0.9931
No log 2.1042 202 0.8714 0.7160 0.8714 0.9335
No log 2.125 204 0.7279 0.7550 0.7279 0.8531
No log 2.1458 206 0.7229 0.7333 0.7229 0.8502
No log 2.1667 208 0.7809 0.7027 0.7809 0.8837
No log 2.1875 210 0.8946 0.6928 0.8946 0.9458
No log 2.2083 212 0.9256 0.6968 0.9256 0.9621
No log 2.2292 214 0.8207 0.7114 0.8207 0.9059
No log 2.25 216 0.7265 0.7285 0.7265 0.8524
No log 2.2708 218 0.7106 0.7517 0.7106 0.8430
No log 2.2917 220 0.7030 0.7651 0.7030 0.8385
No log 2.3125 222 0.7705 0.72 0.7705 0.8778
No log 2.3333 224 0.8089 0.7484 0.8089 0.8994
No log 2.3542 226 0.8527 0.7105 0.8527 0.9234
No log 2.375 228 0.8590 0.7073 0.8590 0.9268
No log 2.3958 230 0.8458 0.6941 0.8458 0.9197
No log 2.4167 232 0.7237 0.7879 0.7237 0.8507
No log 2.4375 234 0.7207 0.7712 0.7207 0.8489
No log 2.4583 236 0.7588 0.7517 0.7588 0.8711
No log 2.4792 238 0.7820 0.7190 0.7820 0.8843
No log 2.5 240 0.8165 0.7013 0.8165 0.9036
No log 2.5208 242 0.8864 0.6667 0.8864 0.9415
No log 2.5417 244 0.9422 0.6242 0.9422 0.9707
No log 2.5625 246 1.0304 0.6347 1.0304 1.0151
No log 2.5833 248 1.0151 0.6471 1.0151 1.0075
No log 2.6042 250 0.8551 0.7470 0.8551 0.9247
No log 2.625 252 0.7704 0.7320 0.7704 0.8778
No log 2.6458 254 0.7260 0.7550 0.7260 0.8520
No log 2.6667 256 0.7348 0.7532 0.7348 0.8572
No log 2.6875 258 0.8271 0.7683 0.8271 0.9095
No log 2.7083 260 0.8914 0.7066 0.8914 0.9441
No log 2.7292 262 0.7500 0.7758 0.7500 0.8660
No log 2.75 264 0.7085 0.7692 0.7085 0.8417
No log 2.7708 266 0.7895 0.7436 0.7895 0.8885
No log 2.7917 268 0.8296 0.6892 0.8296 0.9108
No log 2.8125 270 0.7945 0.6763 0.7945 0.8914
No log 2.8333 272 0.8756 0.6119 0.8756 0.9357
No log 2.8542 274 0.9518 0.5778 0.9518 0.9756
No log 2.875 276 1.1185 0.5455 1.1185 1.0576
No log 2.8958 278 1.1622 0.6 1.1622 1.0781
No log 2.9167 280 1.0805 0.6 1.0805 1.0395
No log 2.9375 282 0.8585 0.7191 0.8585 0.9266
No log 2.9583 284 0.6673 0.8171 0.6673 0.8169
No log 2.9792 286 0.6712 0.7421 0.6712 0.8193
No log 3.0 288 0.6853 0.7468 0.6853 0.8278
No log 3.0208 290 0.7468 0.75 0.7468 0.8642
No log 3.0417 292 0.8474 0.6939 0.8474 0.9205
No log 3.0625 294 0.8591 0.7050 0.8591 0.9269
No log 3.0833 296 0.7948 0.7 0.7948 0.8915
No log 3.1042 298 0.7300 0.7792 0.7300 0.8544
No log 3.125 300 0.7094 0.7453 0.7094 0.8423
No log 3.1458 302 0.6849 0.7711 0.6849 0.8276
No log 3.1667 304 0.6738 0.7711 0.6738 0.8208
No log 3.1875 306 0.8212 0.7191 0.8212 0.9062
No log 3.2083 308 1.0829 0.7016 1.0829 1.0406
No log 3.2292 310 1.3467 0.6533 1.3467 1.1605
No log 3.25 312 1.0905 0.6957 1.0905 1.0443
No log 3.2708 314 0.7401 0.7561 0.7401 0.8603
No log 3.2917 316 0.7258 0.7643 0.7258 0.8519
No log 3.3125 318 0.7590 0.7215 0.7590 0.8712
No log 3.3333 320 0.7918 0.7421 0.7918 0.8898
No log 3.3542 322 0.8433 0.7081 0.8433 0.9183
No log 3.375 324 0.8144 0.7226 0.8144 0.9024
No log 3.3958 326 0.7025 0.7843 0.7025 0.8381
No log 3.4167 328 0.6510 0.7821 0.6510 0.8069
No log 3.4375 330 0.6271 0.8077 0.6271 0.7919
No log 3.4583 332 0.6552 0.7975 0.6552 0.8095
No log 3.4792 334 0.6504 0.8050 0.6504 0.8065
No log 3.5 336 0.6807 0.8098 0.6807 0.8251
No log 3.5208 338 0.7507 0.7485 0.7507 0.8664
No log 3.5417 340 0.7047 0.8025 0.7047 0.8395
No log 3.5625 342 0.7261 0.8025 0.7261 0.8521
No log 3.5833 344 0.7270 0.8075 0.7270 0.8527
No log 3.6042 346 0.7364 0.8075 0.7364 0.8581
No log 3.625 348 0.8106 0.7375 0.8106 0.9004
No log 3.6458 350 0.8249 0.7176 0.8249 0.9082
No log 3.6667 352 0.7721 0.7630 0.7721 0.8787
No log 3.6875 354 0.6788 0.7955 0.6788 0.8239
No log 3.7083 356 0.6094 0.7952 0.6094 0.7806
No log 3.7292 358 0.6085 0.7952 0.6085 0.7801
No log 3.75 360 0.6055 0.7853 0.6055 0.7781
No log 3.7708 362 0.6416 0.8047 0.6416 0.8010
No log 3.7917 364 0.7630 0.7471 0.7630 0.8735
No log 3.8125 366 0.7723 0.7529 0.7723 0.8788
No log 3.8333 368 0.6921 0.7831 0.6921 0.8319
No log 3.8542 370 0.6365 0.7733 0.6365 0.7978
No log 3.875 372 0.7101 0.7 0.7101 0.8427
No log 3.8958 374 0.7882 0.6853 0.7882 0.8878
No log 3.9167 376 0.7619 0.7286 0.7619 0.8728
No log 3.9375 378 0.7796 0.7483 0.7796 0.8829
No log 3.9583 380 0.8953 0.6623 0.8953 0.9462
No log 3.9792 382 0.8718 0.6797 0.8718 0.9337
No log 4.0 384 0.7928 0.7308 0.7928 0.8904
No log 4.0208 386 0.6684 0.7582 0.6684 0.8175
No log 4.0417 388 0.6110 0.75 0.6110 0.7816
No log 4.0625 390 0.5932 0.7671 0.5932 0.7702
No log 4.0833 392 0.5771 0.7703 0.5771 0.7597
No log 4.1042 394 0.5885 0.7586 0.5885 0.7671
No log 4.125 396 0.5851 0.7703 0.5851 0.7649
No log 4.1458 398 0.6207 0.7742 0.6207 0.7879
No log 4.1667 400 0.7337 0.7342 0.7337 0.8566
No log 4.1875 402 0.8346 0.7097 0.8346 0.9136
No log 4.2083 404 0.8626 0.6395 0.8626 0.9288
No log 4.2292 406 0.8522 0.6531 0.8522 0.9232
No log 4.25 408 0.8312 0.6667 0.8312 0.9117
No log 4.2708 410 0.7993 0.6901 0.7993 0.8940
No log 4.2917 412 0.8695 0.6358 0.8695 0.9325
No log 4.3125 414 1.0479 0.6341 1.0479 1.0237
No log 4.3333 416 1.0928 0.6328 1.0928 1.0454
No log 4.3542 418 1.0523 0.6519 1.0523 1.0258
No log 4.375 420 0.7870 0.75 0.7870 0.8871
No log 4.3958 422 0.6946 0.7952 0.6946 0.8335
No log 4.4167 424 0.7424 0.7746 0.7424 0.8616
No log 4.4375 426 0.8504 0.7314 0.8504 0.9222
No log 4.4583 428 1.1081 0.6154 1.1081 1.0527
No log 4.4792 430 1.1134 0.6034 1.1134 1.0552
No log 4.5 432 0.9171 0.7191 0.9171 0.9576
No log 4.5208 434 0.7252 0.7654 0.7252 0.8516
No log 4.5417 436 0.6903 0.7662 0.6903 0.8309
No log 4.5625 438 0.7401 0.7152 0.7401 0.8603
No log 4.5833 440 0.8442 0.6490 0.8442 0.9188
No log 4.6042 442 0.8730 0.6358 0.8730 0.9344
No log 4.625 444 0.7659 0.7075 0.7659 0.8751
No log 4.6458 446 0.6879 0.7297 0.6879 0.8294
No log 4.6667 448 0.6760 0.7550 0.6760 0.8222
No log 4.6875 450 0.6850 0.7578 0.6850 0.8276
No log 4.7083 452 0.6843 0.7722 0.6843 0.8272
No log 4.7292 454 0.6755 0.7763 0.6755 0.8219
No log 4.75 456 0.6788 0.7682 0.6788 0.8239
No log 4.7708 458 0.7118 0.7534 0.7118 0.8437
No log 4.7917 460 0.7235 0.7273 0.7235 0.8506
No log 4.8125 462 0.7003 0.7361 0.7003 0.8368
No log 4.8333 464 0.7024 0.7297 0.7024 0.8381
No log 4.8542 466 0.6875 0.7297 0.6875 0.8292
No log 4.875 468 0.6497 0.7733 0.6497 0.8061
No log 4.8958 470 0.6390 0.7867 0.6390 0.7994
No log 4.9167 472 0.6380 0.7815 0.6380 0.7988
No log 4.9375 474 0.6223 0.7867 0.6223 0.7889
No log 4.9583 476 0.6307 0.7871 0.6307 0.7942
No log 4.9792 478 0.6826 0.7738 0.6826 0.8262
No log 5.0 480 0.6546 0.7879 0.6546 0.8091
No log 5.0208 482 0.6805 0.8144 0.6805 0.8249
No log 5.0417 484 0.7261 0.7738 0.7261 0.8521
No log 5.0625 486 0.6778 0.7826 0.6778 0.8233
No log 5.0833 488 0.6750 0.7432 0.6750 0.8216
No log 5.1042 490 0.7381 0.7027 0.7381 0.8591
No log 5.125 492 0.7280 0.7162 0.7280 0.8532
No log 5.1458 494 0.6996 0.7451 0.6996 0.8364
No log 5.1667 496 0.7655 0.7170 0.7655 0.8749
No log 5.1875 498 0.8928 0.6946 0.8928 0.9449
0.454 5.2083 500 0.8619 0.7143 0.8619 0.9284
0.454 5.2292 502 0.7112 0.7595 0.7112 0.8433
0.454 5.25 504 0.6870 0.7517 0.6870 0.8289
0.454 5.2708 506 0.7085 0.7432 0.7085 0.8417
0.454 5.2917 508 0.7167 0.7383 0.7167 0.8466
0.454 5.3125 510 0.7538 0.7034 0.7538 0.8682
0.454 5.3333 512 0.7660 0.7222 0.7660 0.8752
0.454 5.3542 514 0.7660 0.7083 0.7660 0.8752
0.454 5.375 516 0.8005 0.6667 0.8005 0.8947
0.454 5.3958 518 0.7506 0.7448 0.7506 0.8663
0.454 5.4167 520 0.6941 0.7183 0.6941 0.8331
0.454 5.4375 522 0.6567 0.7273 0.6567 0.8104
0.454 5.4583 524 0.6396 0.7785 0.6396 0.7997
0.454 5.4792 526 0.6536 0.7532 0.6536 0.8084
0.454 5.5 528 0.7461 0.7394 0.7461 0.8637
0.454 5.5208 530 0.8064 0.7305 0.8064 0.8980
0.454 5.5417 532 0.9114 0.6971 0.9114 0.9547
0.454 5.5625 534 0.8578 0.7356 0.8578 0.9262
0.454 5.5833 536 0.7188 0.7630 0.7188 0.8478
0.454 5.6042 538 0.6502 0.8098 0.6502 0.8063
0.454 5.625 540 0.6432 0.7595 0.6432 0.8020
0.454 5.6458 542 0.6522 0.7662 0.6522 0.8076
0.454 5.6667 544 0.6817 0.7662 0.6817 0.8257
0.454 5.6875 546 0.7478 0.7355 0.7478 0.8648
0.454 5.7083 548 0.7977 0.6883 0.7977 0.8931
0.454 5.7292 550 0.7232 0.7516 0.7232 0.8504
0.454 5.75 552 0.6630 0.8049 0.6630 0.8142
0.454 5.7708 554 0.6042 0.7922 0.6042 0.7773
0.454 5.7917 556 0.6108 0.7517 0.6108 0.7816
0.454 5.8125 558 0.5902 0.7517 0.5902 0.7683
0.454 5.8333 560 0.5957 0.7632 0.5957 0.7718
0.454 5.8542 562 0.5939 0.7843 0.5939 0.7706
0.454 5.875 564 0.6141 0.7974 0.6141 0.7837
0.454 5.8958 566 0.6564 0.7895 0.6564 0.8102
0.454 5.9167 568 0.7029 0.8105 0.7029 0.8384
0.454 5.9375 570 0.7336 0.7552 0.7336 0.8565
0.454 5.9583 572 0.7234 0.7324 0.7234 0.8505
0.454 5.9792 574 0.6897 0.7222 0.6897 0.8305
0.454 6.0 576 0.6278 0.7324 0.6278 0.7923
0.454 6.0208 578 0.6022 0.7671 0.6022 0.7760
0.454 6.0417 580 0.6150 0.7891 0.6150 0.7842
0.454 6.0625 582 0.6292 0.7891 0.6292 0.7932
0.454 6.0833 584 0.6446 0.7448 0.6446 0.8029
0.454 6.1042 586 0.6906 0.7286 0.6906 0.8310
0.454 6.125 588 0.7499 0.7234 0.7499 0.8659
0.454 6.1458 590 0.7551 0.7286 0.7551 0.8690
0.454 6.1667 592 0.7509 0.6906 0.7509 0.8665
0.454 6.1875 594 0.7621 0.7286 0.7621 0.8730
0.454 6.2083 596 0.8731 0.6763 0.8731 0.9344
0.454 6.2292 598 0.9007 0.6857 0.9007 0.9490
0.454 6.25 600 0.7823 0.7050 0.7823 0.8845
0.454 6.2708 602 0.6982 0.75 0.6982 0.8356
0.454 6.2917 604 0.7302 0.7590 0.7302 0.8545
0.454 6.3125 606 0.7518 0.7515 0.7518 0.8670
0.454 6.3333 608 0.7071 0.72 0.7071 0.8409
0.454 6.3542 610 0.7115 0.7234 0.7115 0.8435
0.454 6.375 612 0.7232 0.7143 0.7232 0.8504
0.454 6.3958 614 0.7358 0.6812 0.7358 0.8578
0.454 6.4167 616 0.7910 0.6846 0.7910 0.8894
0.454 6.4375 618 0.8352 0.6711 0.8352 0.9139
0.454 6.4583 620 0.8044 0.6846 0.8044 0.8969

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_k20_task1_organization

Finetuned
(4019)
this model