ArabicNewSplits5_FineTuningAraBERT_run1_AugV5_k10_task3_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: 0.6598
  • Qwk: 0.2670
  • Mse: 0.6598
  • Rmse: 0.8123

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: 10

Training results

Training Loss Epoch Step Validation Loss Qwk Mse Rmse
No log 0.0333 2 3.3045 -0.0358 3.3045 1.8178
No log 0.0667 4 1.8137 -0.0070 1.8137 1.3467
No log 0.1 6 1.5427 0.0255 1.5427 1.2421
No log 0.1333 8 1.0439 -0.0268 1.0439 1.0217
No log 0.1667 10 0.8112 0.0047 0.8112 0.9007
No log 0.2 12 0.8386 -0.0833 0.8386 0.9158
No log 0.2333 14 1.2341 -0.0196 1.2341 1.1109
No log 0.2667 16 1.4843 -0.0268 1.4843 1.2183
No log 0.3 18 1.3336 -0.0268 1.3336 1.1548
No log 0.3333 20 1.1238 -0.0268 1.1238 1.0601
No log 0.3667 22 0.9468 -0.0268 0.9468 0.9730
No log 0.4 24 0.8142 -0.0543 0.8142 0.9023
No log 0.4333 26 0.7022 0.0222 0.7022 0.8380
No log 0.4667 28 0.6574 -0.0233 0.6574 0.8108
No log 0.5 30 0.7347 -0.1111 0.7347 0.8571
No log 0.5333 32 1.1812 -0.0407 1.1812 1.0868
No log 0.5667 34 2.0668 -0.0682 2.0668 1.4376
No log 0.6 36 1.9832 -0.0658 1.9832 1.4083
No log 0.6333 38 1.4577 0.0 1.4577 1.2074
No log 0.6667 40 1.3834 0.0 1.3834 1.1762
No log 0.7 42 1.4575 0.0 1.4575 1.2073
No log 0.7333 44 1.2138 0.0 1.2138 1.1017
No log 0.7667 46 0.8634 0.0333 0.8634 0.9292
No log 0.8 48 0.7820 0.0249 0.7820 0.8843
No log 0.8333 50 0.7725 0.0588 0.7725 0.8789
No log 0.8667 52 0.8943 0.0 0.8943 0.9457
No log 0.9 54 1.0550 0.0 1.0550 1.0271
No log 0.9333 56 1.0731 0.0 1.0731 1.0359
No log 0.9667 58 0.9758 0.0 0.9758 0.9878
No log 1.0 60 0.9011 0.0 0.9011 0.9493
No log 1.0333 62 0.7805 0.0918 0.7805 0.8835
No log 1.0667 64 0.6637 -0.0496 0.6637 0.8147
No log 1.1 66 0.7031 -0.1733 0.7031 0.8385
No log 1.1333 68 0.9814 -0.0133 0.9814 0.9906
No log 1.1667 70 1.4035 0.0 1.4035 1.1847
No log 1.2 72 1.6758 -0.0070 1.6758 1.2945
No log 1.2333 74 1.5756 -0.0036 1.5756 1.2552
No log 1.2667 76 1.2762 0.0 1.2762 1.1297
No log 1.3 78 0.8952 0.0476 0.8952 0.9462
No log 1.3333 80 0.7135 -0.1242 0.7135 0.8447
No log 1.3667 82 0.7146 -0.2346 0.7146 0.8453
No log 1.4 84 0.7831 -0.0273 0.7831 0.8849
No log 1.4333 86 0.9687 -0.0295 0.9687 0.9842
No log 1.4667 88 1.0246 0.0244 1.0246 1.0122
No log 1.5 90 1.1516 0.0078 1.1516 1.0731
No log 1.5333 92 1.1924 0.0114 1.1924 1.0920
No log 1.5667 94 1.0484 0.0741 1.0484 1.0239
No log 1.6 96 0.8024 -0.0169 0.8024 0.8957
No log 1.6333 98 0.6648 -0.0303 0.6648 0.8154
No log 1.6667 100 0.6302 -0.0159 0.6302 0.7939
No log 1.7 102 0.6348 -0.0612 0.6348 0.7967
No log 1.7333 104 0.8894 0.0685 0.8894 0.9431
No log 1.7667 106 1.4785 -0.0070 1.4785 1.2159
No log 1.8 108 1.7116 -0.0070 1.7116 1.3083
No log 1.8333 110 1.5119 -0.0036 1.5119 1.2296
No log 1.8667 112 1.1735 0.0 1.1735 1.0833
No log 1.9 114 0.9507 0.0345 0.9507 0.9751
No log 1.9333 116 0.8989 0.0345 0.8989 0.9481
No log 1.9667 118 0.8463 0.0698 0.8462 0.9199
No log 2.0 120 0.7706 0.1730 0.7706 0.8778
No log 2.0333 122 0.7498 0.2000 0.7498 0.8659
No log 2.0667 124 0.7278 0.1852 0.7278 0.8531
No log 2.1 126 0.7480 0.1852 0.7480 0.8649
No log 2.1333 128 0.6321 0.1590 0.6321 0.7950
No log 2.1667 130 0.5515 0.3580 0.5515 0.7426
No log 2.2 132 0.6387 0.2169 0.6387 0.7992
No log 2.2333 134 0.8357 0.2000 0.8357 0.9141
No log 2.2667 136 0.6266 0.2644 0.6266 0.7916
No log 2.3 138 0.6252 0.1141 0.6252 0.7907
No log 2.3333 140 0.6124 0.1053 0.6124 0.7825
No log 2.3667 142 0.6148 0.2093 0.6148 0.7841
No log 2.4 144 0.6169 0.3023 0.6169 0.7854
No log 2.4333 146 0.7425 0.1045 0.7425 0.8617
No log 2.4667 148 0.8395 0.0769 0.8395 0.9162
No log 2.5 150 0.6587 0.3054 0.6587 0.8116
No log 2.5333 152 0.5966 0.2994 0.5966 0.7724
No log 2.5667 154 0.6646 0.1919 0.6646 0.8152
No log 2.6 156 0.7390 0.1028 0.7390 0.8596
No log 2.6333 158 0.6086 0.3369 0.6086 0.7801
No log 2.6667 160 0.5880 0.3118 0.5880 0.7668
No log 2.7 162 0.6670 0.2990 0.6670 0.8167
No log 2.7333 164 0.6425 0.2990 0.6425 0.8015
No log 2.7667 166 0.5884 0.3725 0.5884 0.7671
No log 2.8 168 0.9112 0.1718 0.9112 0.9546
No log 2.8333 170 0.9066 0.1718 0.9066 0.9521
No log 2.8667 172 0.6049 0.3803 0.6049 0.7778
No log 2.9 174 0.6388 0.3706 0.6388 0.7992
No log 2.9333 176 0.6946 0.3367 0.6946 0.8334
No log 2.9667 178 0.5883 0.3200 0.5883 0.7670
No log 3.0 180 0.6126 0.3052 0.6126 0.7827
No log 3.0333 182 0.7804 0.1855 0.7804 0.8834
No log 3.0667 184 0.7136 0.3394 0.7136 0.8447
No log 3.1 186 0.6030 0.1832 0.6030 0.7765
No log 3.1333 188 0.6447 0.1579 0.6447 0.8029
No log 3.1667 190 0.6856 0.2308 0.6856 0.8280
No log 3.2 192 0.7174 0.3929 0.7174 0.8470
No log 3.2333 194 0.7536 0.3504 0.7536 0.8681
No log 3.2667 196 0.7188 0.2986 0.7188 0.8478
No log 3.3 198 0.7623 0.25 0.7623 0.8731
No log 3.3333 200 0.9443 0.2432 0.9443 0.9717
No log 3.3667 202 0.8255 0.2941 0.8255 0.9086
No log 3.4 204 0.6168 0.3628 0.6168 0.7854
No log 3.4333 206 0.5860 0.4233 0.5860 0.7655
No log 3.4667 208 0.6098 0.2780 0.6098 0.7809
No log 3.5 210 0.5857 0.3524 0.5857 0.7653
No log 3.5333 212 0.6915 0.2536 0.6915 0.8316
No log 3.5667 214 0.6809 0.2161 0.6809 0.8252
No log 3.6 216 0.6147 0.3367 0.6147 0.7840
No log 3.6333 218 0.6176 0.3299 0.6176 0.7859
No log 3.6667 220 0.6500 0.2709 0.6500 0.8062
No log 3.7 222 0.6281 0.3962 0.6281 0.7925
No log 3.7333 224 0.8733 0.1935 0.8733 0.9345
No log 3.7667 226 1.0361 0.1385 1.0361 1.0179
No log 3.8 228 0.8757 0.1613 0.8757 0.9358
No log 3.8333 230 0.6706 0.2661 0.6706 0.8189
No log 3.8667 232 0.7514 0.2744 0.7514 0.8669
No log 3.9 234 0.7817 0.2070 0.7817 0.8841
No log 3.9333 236 0.6288 0.3761 0.6288 0.7930
No log 3.9667 238 0.6971 0.3052 0.6971 0.8349
No log 4.0 240 1.0357 -0.0240 1.0357 1.0177
No log 4.0333 242 1.1182 -0.0612 1.1182 1.0575
No log 4.0667 244 1.0385 0.0041 1.0385 1.0191
No log 4.1 246 0.7438 0.2315 0.7438 0.8624
No log 4.1333 248 0.6640 0.2410 0.6640 0.8149
No log 4.1667 250 0.7191 0.1667 0.7191 0.8480
No log 4.2 252 0.6320 0.2086 0.6320 0.7950
No log 4.2333 254 0.6601 0.3407 0.6601 0.8125
No log 4.2667 256 0.8249 0.2000 0.8249 0.9082
No log 4.3 258 0.7962 0.2372 0.7962 0.8923
No log 4.3333 260 0.6955 0.2390 0.6955 0.8339
No log 4.3667 262 0.6927 0.2523 0.6927 0.8323
No log 4.4 264 0.7096 0.3028 0.7096 0.8424
No log 4.4333 266 0.7211 0.2500 0.7211 0.8492
No log 4.4667 268 0.7481 0.2356 0.7481 0.8649
No log 4.5 270 0.8199 0.2275 0.8199 0.9055
No log 4.5333 272 0.7609 0.2982 0.7609 0.8723
No log 4.5667 274 0.7132 0.2857 0.7132 0.8445
No log 4.6 276 0.7269 0.3527 0.7269 0.8526
No log 4.6333 278 0.7395 0.3496 0.7395 0.8600
No log 4.6667 280 0.7309 0.2423 0.7309 0.8549
No log 4.7 282 0.8379 0.2982 0.8379 0.9154
No log 4.7333 284 0.8444 0.3274 0.8444 0.9189
No log 4.7667 286 0.7219 0.2727 0.7219 0.8497
No log 4.8 288 0.7441 0.2432 0.7441 0.8626
No log 4.8333 290 0.9721 0.125 0.9721 0.9859
No log 4.8667 292 0.9473 0.125 0.9473 0.9733
No log 4.9 294 0.7417 0.3103 0.7417 0.8612
No log 4.9333 296 0.6903 0.1698 0.6903 0.8309
No log 4.9667 298 0.7307 0.2323 0.7307 0.8548
No log 5.0 300 0.7566 0.2239 0.7566 0.8698
No log 5.0333 302 0.7272 0.24 0.7272 0.8528
No log 5.0667 304 0.6997 0.1045 0.6997 0.8365
No log 5.1 306 0.7078 0.1068 0.7078 0.8413
No log 5.1333 308 0.7246 0.1388 0.7246 0.8512
No log 5.1667 310 0.7774 0.2692 0.7774 0.8817
No log 5.2 312 0.7569 0.2830 0.7569 0.8700
No log 5.2333 314 0.7279 0.1090 0.7279 0.8532
No log 5.2667 316 0.7529 0.1698 0.7529 0.8677
No log 5.3 318 0.7352 0.1416 0.7352 0.8574
No log 5.3333 320 0.7518 0.2780 0.7518 0.8670
No log 5.3667 322 0.8167 0.3455 0.8167 0.9037
No log 5.4 324 0.7731 0.2153 0.7731 0.8792
No log 5.4333 326 0.7480 0.2308 0.7480 0.8649
No log 5.4667 328 0.7438 0.1481 0.7438 0.8624
No log 5.5 330 0.7307 0.1469 0.7307 0.8548
No log 5.5333 332 0.7061 0.1469 0.7061 0.8403
No log 5.5667 334 0.6968 0.2300 0.6968 0.8347
No log 5.6 336 0.6852 0.1841 0.6852 0.8278
No log 5.6333 338 0.6770 0.1841 0.6770 0.8228
No log 5.6667 340 0.6852 0.2308 0.6852 0.8278
No log 5.7 342 0.7091 0.3131 0.7091 0.8421
No log 5.7333 344 0.6811 0.2475 0.6811 0.8253
No log 5.7667 346 0.6834 0.2563 0.6834 0.8267
No log 5.8 348 0.7532 0.3488 0.7532 0.8679
No log 5.8333 350 0.7576 0.3488 0.7576 0.8704
No log 5.8667 352 0.7161 0.2963 0.7161 0.8462
No log 5.9 354 0.7195 0.2217 0.7195 0.8482
No log 5.9333 356 0.7299 0.2372 0.7299 0.8543
No log 5.9667 358 0.8028 0.2405 0.8028 0.8960
No log 6.0 360 0.8565 0.2340 0.8565 0.9255
No log 6.0333 362 0.7870 0.2743 0.7870 0.8871
No log 6.0667 364 0.7230 0.2381 0.7230 0.8503
No log 6.1 366 0.7441 0.1683 0.7441 0.8626
No log 6.1333 368 0.7374 0.1683 0.7374 0.8587
No log 6.1667 370 0.7036 0.1527 0.7036 0.8388
No log 6.2 372 0.7247 0.2475 0.7247 0.8513
No log 6.2333 374 0.7461 0.2222 0.7461 0.8638
No log 6.2667 376 0.7561 0.2646 0.7561 0.8695
No log 6.3 378 0.7501 0.2294 0.7501 0.8661
No log 6.3333 380 0.7816 0.2146 0.7816 0.8841
No log 6.3667 382 0.7956 0.2143 0.7956 0.8920
No log 6.4 384 0.7425 0.2727 0.7425 0.8617
No log 6.4333 386 0.6486 0.1568 0.6486 0.8054
No log 6.4667 388 0.6297 0.1913 0.6297 0.7935
No log 6.5 390 0.6316 0.1568 0.6316 0.7948
No log 6.5333 392 0.6987 0.2621 0.6987 0.8359
No log 6.5667 394 0.8195 0.2364 0.8195 0.9053
No log 6.6 396 0.8090 0.2287 0.8090 0.8994
No log 6.6333 398 0.7770 0.2661 0.7770 0.8815
No log 6.6667 400 0.6955 0.2593 0.6955 0.8340
No log 6.7 402 0.6276 0.2000 0.6276 0.7922
No log 6.7333 404 0.6302 0.1429 0.6302 0.7938
No log 6.7667 406 0.6350 0.1429 0.6350 0.7969
No log 6.8 408 0.6297 0.2727 0.6297 0.7936
No log 6.8333 410 0.6964 0.3267 0.6964 0.8345
No log 6.8667 412 0.7804 0.2579 0.7804 0.8834
No log 6.9 414 0.7700 0.2579 0.7700 0.8775
No log 6.9333 416 0.7531 0.2593 0.7531 0.8678
No log 6.9667 418 0.6859 0.3398 0.6859 0.8282
No log 7.0 420 0.6722 0.28 0.6722 0.8199
No log 7.0333 422 0.6748 0.2075 0.6748 0.8215
No log 7.0667 424 0.6894 0.2941 0.6894 0.8303
No log 7.1 426 0.7076 0.2676 0.7076 0.8412
No log 7.1333 428 0.7430 0.2762 0.7430 0.8620
No log 7.1667 430 0.7613 0.2372 0.7613 0.8726
No log 7.2 432 0.7409 0.2762 0.7409 0.8607
No log 7.2333 434 0.6865 0.1781 0.6865 0.8285
No log 7.2667 436 0.6785 0.2676 0.6785 0.8237
No log 7.3 438 0.6819 0.1921 0.6819 0.8258
No log 7.3333 440 0.6774 0.1619 0.6774 0.8231
No log 7.3667 442 0.6889 0.2475 0.6889 0.8300
No log 7.4 444 0.7313 0.0955 0.7313 0.8552
No log 7.4333 446 0.7323 0.0955 0.7323 0.8557
No log 7.4667 448 0.7104 0.1919 0.7104 0.8429
No log 7.5 450 0.6849 0.2161 0.6849 0.8276
No log 7.5333 452 0.6845 0.2161 0.6845 0.8274
No log 7.5667 454 0.7042 0.2083 0.7042 0.8392
No log 7.6 456 0.7003 0.2083 0.7003 0.8368
No log 7.6333 458 0.6684 0.1746 0.6684 0.8175
No log 7.6667 460 0.6538 0.1568 0.6538 0.8086
No log 7.7 462 0.6565 0.1209 0.6565 0.8102
No log 7.7333 464 0.6648 0.2081 0.6648 0.8154
No log 7.7667 466 0.6851 0.1515 0.6851 0.8277
No log 7.8 468 0.6789 0.1753 0.6789 0.8240
No log 7.8333 470 0.6763 0.2081 0.6763 0.8224
No log 7.8667 472 0.6716 0.2081 0.6716 0.8195
No log 7.9 474 0.6584 0.2083 0.6584 0.8114
No log 7.9333 476 0.6486 0.2323 0.6486 0.8054
No log 7.9667 478 0.6452 0.2239 0.6452 0.8032
No log 8.0 480 0.6457 0.2239 0.6457 0.8036
No log 8.0333 482 0.6601 0.2475 0.6601 0.8125
No log 8.0667 484 0.6923 0.1848 0.6923 0.8321
No log 8.1 486 0.7117 0.2850 0.7117 0.8436
No log 8.1333 488 0.6931 0.2222 0.6931 0.8325
No log 8.1667 490 0.6776 0.1770 0.6776 0.8232
No log 8.2 492 0.6562 0.2315 0.6562 0.8100
No log 8.2333 494 0.6442 0.1287 0.6442 0.8026
No log 8.2667 496 0.6390 0.1287 0.6390 0.7994
No log 8.3 498 0.6295 0.1287 0.6295 0.7934
0.4898 8.3333 500 0.6199 0.1357 0.6199 0.7873
0.4898 8.3667 502 0.6137 0.2000 0.6137 0.7834
0.4898 8.4 504 0.6124 0.2000 0.6124 0.7826
0.4898 8.4333 506 0.6101 0.2086 0.6101 0.7811
0.4898 8.4667 508 0.6127 0.2609 0.6127 0.7827
0.4898 8.5 510 0.6102 0.2609 0.6102 0.7812
0.4898 8.5333 512 0.6122 0.2609 0.6122 0.7825
0.4898 8.5667 514 0.6106 0.1579 0.6106 0.7814
0.4898 8.6 516 0.6163 0.1357 0.6163 0.7851
0.4898 8.6333 518 0.6235 0.1503 0.6235 0.7896
0.4898 8.6667 520 0.6368 0.25 0.6368 0.7980
0.4898 8.7 522 0.6494 0.3061 0.6494 0.8059
0.4898 8.7333 524 0.6481 0.2563 0.6481 0.8051
0.4898 8.7667 526 0.6403 0.25 0.6403 0.8002
0.4898 8.8 528 0.6342 0.1579 0.6342 0.7964
0.4898 8.8333 530 0.6388 0.2086 0.6388 0.7993
0.4898 8.8667 532 0.6513 0.2577 0.6513 0.8070
0.4898 8.9 534 0.6523 0.2593 0.6523 0.8076
0.4898 8.9333 536 0.6548 0.2577 0.6548 0.8092
0.4898 8.9667 538 0.6582 0.3061 0.6582 0.8113
0.4898 9.0 540 0.6549 0.25 0.6549 0.8093
0.4898 9.0333 542 0.6604 0.3061 0.6604 0.8126
0.4898 9.0667 544 0.6635 0.3061 0.6635 0.8146
0.4898 9.1 546 0.6696 0.3061 0.6696 0.8183
0.4898 9.1333 548 0.6782 0.2637 0.6782 0.8235
0.4898 9.1667 550 0.6858 0.2000 0.6858 0.8281
0.4898 9.2 552 0.6829 0.2323 0.6829 0.8264
0.4898 9.2333 554 0.6800 0.2323 0.6800 0.8246
0.4898 9.2667 556 0.6761 0.2239 0.6761 0.8222
0.4898 9.3 558 0.6655 0.2990 0.6655 0.8158
0.4898 9.3333 560 0.6525 0.24 0.6525 0.8078
0.4898 9.3667 562 0.6445 0.2323 0.6445 0.8028
0.4898 9.4 564 0.6395 0.1429 0.6395 0.7997
0.4898 9.4333 566 0.6373 0.1429 0.6373 0.7983
0.4898 9.4667 568 0.6359 0.1357 0.6359 0.7974
0.4898 9.5 570 0.6341 0.1429 0.6341 0.7963
0.4898 9.5333 572 0.6332 0.1429 0.6332 0.7957
0.4898 9.5667 574 0.6349 0.1917 0.6349 0.7968
0.4898 9.6 576 0.6366 0.2410 0.6366 0.7979
0.4898 9.6333 578 0.6374 0.2410 0.6374 0.7984
0.4898 9.6667 580 0.6385 0.2410 0.6385 0.7991
0.4898 9.7 582 0.6393 0.2410 0.6393 0.7996
0.4898 9.7333 584 0.6413 0.2410 0.6413 0.8008
0.4898 9.7667 586 0.6436 0.25 0.6436 0.8022
0.4898 9.8 588 0.6472 0.2487 0.6472 0.8045
0.4898 9.8333 590 0.6515 0.2487 0.6515 0.8071
0.4898 9.8667 592 0.6547 0.2990 0.6547 0.8091
0.4898 9.9 594 0.6570 0.2990 0.6570 0.8105
0.4898 9.9333 596 0.6585 0.2670 0.6585 0.8114
0.4898 9.9667 598 0.6595 0.2670 0.6595 0.8121
0.4898 10.0 600 0.6598 0.2670 0.6598 0.8123

Framework versions

  • Transformers 4.44.2
  • Pytorch 2.4.0+cu118
  • Datasets 2.21.0
  • Tokenizers 0.19.1
Downloads last month
5
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/ArabicNewSplits5_FineTuningAraBERT_run1_AugV5_k10_task3_organization

Finetuned
(4041)
this model