ArabicNewSplits8_usingALLEssays_FineTuningAraBERT_run2_AugV5_k1_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: 1.3838
  • Qwk: 0.4391
  • Mse: 1.3838
  • Rmse: 1.1763

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 0.3333 2 5.0064 -0.0288 5.0064 2.2375
No log 0.6667 4 2.8805 0.1137 2.8805 1.6972
No log 1.0 6 1.6712 0.0329 1.6712 1.2928
No log 1.3333 8 1.1655 0.2833 1.1655 1.0796
No log 1.6667 10 1.1783 0.1898 1.1783 1.0855
No log 2.0 12 1.2806 0.1902 1.2806 1.1316
No log 2.3333 14 1.6689 0.2641 1.6689 1.2919
No log 2.6667 16 1.5236 0.1625 1.5236 1.2343
No log 3.0 18 1.5288 0.1696 1.5288 1.2364
No log 3.3333 20 1.6995 0.2576 1.6995 1.3036
No log 3.6667 22 1.5208 0.2105 1.5208 1.2332
No log 4.0 24 1.3840 0.1617 1.3840 1.1764
No log 4.3333 26 1.3296 0.1584 1.3296 1.1531
No log 4.6667 28 1.1652 0.3143 1.1652 1.0794
No log 5.0 30 1.1577 0.3444 1.1577 1.0760
No log 5.3333 32 1.1400 0.3602 1.1400 1.0677
No log 5.6667 34 1.2171 0.3711 1.2171 1.1032
No log 6.0 36 1.2376 0.3225 1.2376 1.1125
No log 6.3333 38 1.2606 0.3218 1.2606 1.1227
No log 6.6667 40 1.3379 0.3972 1.3379 1.1567
No log 7.0 42 1.2811 0.3571 1.2811 1.1319
No log 7.3333 44 1.1010 0.4422 1.1010 1.0493
No log 7.6667 46 1.0831 0.4167 1.0831 1.0407
No log 8.0 48 1.1790 0.3755 1.1790 1.0858
No log 8.3333 50 1.3216 0.4213 1.3216 1.1496
No log 8.6667 52 1.2362 0.4289 1.2362 1.1118
No log 9.0 54 1.0816 0.4136 1.0816 1.0400
No log 9.3333 56 1.0479 0.4644 1.0479 1.0237
No log 9.6667 58 1.1900 0.4682 1.1900 1.0909
No log 10.0 60 1.1977 0.4830 1.1977 1.0944
No log 10.3333 62 1.2709 0.4224 1.2709 1.1273
No log 10.6667 64 1.5131 0.3725 1.5131 1.2301
No log 11.0 66 1.5991 0.3601 1.5991 1.2646
No log 11.3333 68 1.4641 0.3689 1.4641 1.2100
No log 11.6667 70 1.2244 0.4645 1.2244 1.1065
No log 12.0 72 1.1152 0.4496 1.1152 1.0560
No log 12.3333 74 1.1951 0.4786 1.1951 1.0932
No log 12.6667 76 1.4430 0.4181 1.4430 1.2012
No log 13.0 78 1.4352 0.4328 1.4352 1.1980
No log 13.3333 80 1.2997 0.4771 1.2997 1.1400
No log 13.6667 82 1.0230 0.5073 1.0230 1.0114
No log 14.0 84 0.9252 0.5266 0.9252 0.9619
No log 14.3333 86 0.9372 0.4777 0.9372 0.9681
No log 14.6667 88 1.0705 0.5176 1.0705 1.0346
No log 15.0 90 1.2538 0.4538 1.2538 1.1197
No log 15.3333 92 1.3235 0.3890 1.3235 1.1504
No log 15.6667 94 1.3008 0.4065 1.3008 1.1405
No log 16.0 96 1.2594 0.4901 1.2594 1.1222
No log 16.3333 98 1.1236 0.5063 1.1236 1.0600
No log 16.6667 100 1.0593 0.4436 1.0593 1.0292
No log 17.0 102 1.0699 0.4768 1.0699 1.0343
No log 17.3333 104 1.1526 0.5031 1.1526 1.0736
No log 17.6667 106 1.1405 0.5067 1.1405 1.0680
No log 18.0 108 1.1118 0.5105 1.1118 1.0544
No log 18.3333 110 0.9786 0.5358 0.9786 0.9892
No log 18.6667 112 0.9411 0.5522 0.9411 0.9701
No log 19.0 114 0.9471 0.5094 0.9471 0.9732
No log 19.3333 116 0.9551 0.5129 0.9551 0.9773
No log 19.6667 118 1.0613 0.5023 1.0613 1.0302
No log 20.0 120 1.2853 0.4859 1.2853 1.1337
No log 20.3333 122 1.3344 0.4780 1.3344 1.1552
No log 20.6667 124 1.2798 0.4682 1.2798 1.1313
No log 21.0 126 1.2310 0.5002 1.2310 1.1095
No log 21.3333 128 1.1434 0.4986 1.1434 1.0693
No log 21.6667 130 1.1174 0.4986 1.1174 1.0571
No log 22.0 132 1.1369 0.4979 1.1369 1.0662
No log 22.3333 134 1.1183 0.5097 1.1183 1.0575
No log 22.6667 136 1.2014 0.5317 1.2014 1.0961
No log 23.0 138 1.3645 0.5031 1.3645 1.1681
No log 23.3333 140 1.4588 0.4704 1.4588 1.2078
No log 23.6667 142 1.3389 0.4836 1.3389 1.1571
No log 24.0 144 1.1275 0.5184 1.1275 1.0618
No log 24.3333 146 1.0638 0.4765 1.0638 1.0314
No log 24.6667 148 1.1573 0.4993 1.1573 1.0758
No log 25.0 150 1.3823 0.4264 1.3823 1.1757
No log 25.3333 152 1.5282 0.3969 1.5282 1.2362
No log 25.6667 154 1.4877 0.3967 1.4877 1.2197
No log 26.0 156 1.3148 0.4420 1.3148 1.1467
No log 26.3333 158 1.2587 0.4934 1.2587 1.1219
No log 26.6667 160 1.2962 0.4920 1.2962 1.1385
No log 27.0 162 1.4088 0.4178 1.4088 1.1869
No log 27.3333 164 1.4241 0.3934 1.4242 1.1934
No log 27.6667 166 1.4530 0.4315 1.4530 1.2054
No log 28.0 168 1.3536 0.4833 1.3536 1.1634
No log 28.3333 170 1.0812 0.5394 1.0812 1.0398
No log 28.6667 172 0.9696 0.5218 0.9696 0.9847
No log 29.0 174 0.9852 0.5006 0.9852 0.9926
No log 29.3333 176 1.1012 0.5181 1.1012 1.0494
No log 29.6667 178 1.3103 0.4717 1.3103 1.1447
No log 30.0 180 1.4238 0.4360 1.4238 1.1932
No log 30.3333 182 1.3167 0.4534 1.3167 1.1475
No log 30.6667 184 1.1422 0.5202 1.1422 1.0687
No log 31.0 186 1.1296 0.4991 1.1296 1.0628
No log 31.3333 188 1.2273 0.5032 1.2273 1.1078
No log 31.6667 190 1.4160 0.4134 1.4160 1.1900
No log 32.0 192 1.5000 0.4097 1.5000 1.2247
No log 32.3333 194 1.4749 0.4275 1.4749 1.2145
No log 32.6667 196 1.3144 0.4465 1.3144 1.1465
No log 33.0 198 1.1966 0.4910 1.1966 1.0939
No log 33.3333 200 1.0848 0.5202 1.0848 1.0415
No log 33.6667 202 1.0795 0.5285 1.0795 1.0390
No log 34.0 204 1.1939 0.5016 1.1939 1.0926
No log 34.3333 206 1.3644 0.4717 1.3644 1.1681
No log 34.6667 208 1.4299 0.4097 1.4299 1.1958
No log 35.0 210 1.4504 0.4049 1.4504 1.2043
No log 35.3333 212 1.3199 0.4909 1.3199 1.1489
No log 35.6667 214 1.1584 0.5076 1.1584 1.0763
No log 36.0 216 1.0004 0.4946 1.0004 1.0002
No log 36.3333 218 1.0097 0.5087 1.0097 1.0048
No log 36.6667 220 1.1242 0.4993 1.1242 1.0603
No log 37.0 222 1.3781 0.4668 1.3781 1.1739
No log 37.3333 224 1.4741 0.4314 1.4741 1.2141
No log 37.6667 226 1.3485 0.4861 1.3485 1.1612
No log 38.0 228 1.1389 0.5207 1.1389 1.0672
No log 38.3333 230 1.0830 0.5022 1.0830 1.0407
No log 38.6667 232 1.1540 0.5171 1.1540 1.0742
No log 39.0 234 1.3035 0.4856 1.3035 1.1417
No log 39.3333 236 1.3960 0.4426 1.3960 1.1815
No log 39.6667 238 1.3484 0.4032 1.3484 1.1612
No log 40.0 240 1.1908 0.4598 1.1908 1.0912
No log 40.3333 242 1.1354 0.5063 1.1354 1.0655
No log 40.6667 244 1.1893 0.5271 1.1893 1.0906
No log 41.0 246 1.2694 0.4805 1.2694 1.1267
No log 41.3333 248 1.2510 0.4681 1.2510 1.1185
No log 41.6667 250 1.1536 0.4758 1.1536 1.0741
No log 42.0 252 1.0389 0.5304 1.0389 1.0193
No log 42.3333 254 1.0470 0.5290 1.0470 1.0232
No log 42.6667 256 1.0916 0.5211 1.0916 1.0448
No log 43.0 258 1.1761 0.4883 1.1761 1.0845
No log 43.3333 260 1.2919 0.4585 1.2919 1.1366
No log 43.6667 262 1.3028 0.4269 1.3028 1.1414
No log 44.0 264 1.2959 0.4369 1.2959 1.1384
No log 44.3333 266 1.2578 0.4508 1.2578 1.1215
No log 44.6667 268 1.1944 0.4519 1.1944 1.0929
No log 45.0 270 1.1850 0.4125 1.1850 1.0886
No log 45.3333 272 1.2192 0.4468 1.2192 1.1042
No log 45.6667 274 1.3461 0.3979 1.3461 1.1602
No log 46.0 276 1.4354 0.4166 1.4354 1.1981
No log 46.3333 278 1.3777 0.4269 1.3777 1.1738
No log 46.6667 280 1.2126 0.4979 1.2126 1.1012
No log 47.0 282 1.1276 0.5171 1.1276 1.0619
No log 47.3333 284 1.1064 0.5125 1.1064 1.0518
No log 47.6667 286 1.1755 0.4907 1.1755 1.0842
No log 48.0 288 1.3394 0.4114 1.3394 1.1573
No log 48.3333 290 1.3922 0.4285 1.3922 1.1799
No log 48.6667 292 1.3392 0.4373 1.3392 1.1572
No log 49.0 294 1.2181 0.5017 1.2181 1.1037
No log 49.3333 296 1.0772 0.5359 1.0772 1.0379
No log 49.6667 298 1.0067 0.5144 1.0067 1.0033
No log 50.0 300 0.9780 0.4912 0.9780 0.9889
No log 50.3333 302 1.0085 0.5004 1.0085 1.0042
No log 50.6667 304 1.1104 0.5157 1.1104 1.0537
No log 51.0 306 1.2893 0.4666 1.2893 1.1355
No log 51.3333 308 1.4044 0.4343 1.4044 1.1851
No log 51.6667 310 1.4267 0.4204 1.4267 1.1944
No log 52.0 312 1.3496 0.4434 1.3496 1.1617
No log 52.3333 314 1.2148 0.4834 1.2148 1.1022
No log 52.6667 316 1.1145 0.5016 1.1145 1.0557
No log 53.0 318 1.0538 0.4759 1.0538 1.0266
No log 53.3333 320 1.0021 0.4794 1.0021 1.0010
No log 53.6667 322 1.0237 0.5078 1.0237 1.0118
No log 54.0 324 1.0371 0.5319 1.0371 1.0184
No log 54.3333 326 1.0873 0.5289 1.0873 1.0427
No log 54.6667 328 1.1317 0.5198 1.1317 1.0638
No log 55.0 330 1.1783 0.5259 1.1783 1.0855
No log 55.3333 332 1.1670 0.5139 1.1670 1.0803
No log 55.6667 334 1.1954 0.5235 1.1954 1.0933
No log 56.0 336 1.2156 0.5235 1.2156 1.1025
No log 56.3333 338 1.2514 0.4953 1.2514 1.1187
No log 56.6667 340 1.2392 0.5045 1.2392 1.1132
No log 57.0 342 1.2051 0.5139 1.2051 1.0978
No log 57.3333 344 1.1301 0.5332 1.1301 1.0631
No log 57.6667 346 1.1335 0.5332 1.1335 1.0647
No log 58.0 348 1.1769 0.5332 1.1769 1.0849
No log 58.3333 350 1.1523 0.5332 1.1523 1.0735
No log 58.6667 352 1.1817 0.5332 1.1817 1.0871
No log 59.0 354 1.1822 0.5332 1.1822 1.0873
No log 59.3333 356 1.1956 0.5332 1.1956 1.0934
No log 59.6667 358 1.1991 0.5235 1.1991 1.0950
No log 60.0 360 1.2216 0.4995 1.2216 1.1053
No log 60.3333 362 1.2740 0.4712 1.2740 1.1287
No log 60.6667 364 1.2589 0.5032 1.2589 1.1220
No log 61.0 366 1.2111 0.4972 1.2111 1.1005
No log 61.3333 368 1.1699 0.4986 1.1699 1.0816
No log 61.6667 370 1.2154 0.4979 1.2154 1.1025
No log 62.0 372 1.2333 0.4965 1.2333 1.1105
No log 62.3333 374 1.2576 0.4951 1.2576 1.1214
No log 62.6667 376 1.2481 0.4951 1.2481 1.1172
No log 63.0 378 1.1958 0.4965 1.1958 1.0935
No log 63.3333 380 1.1520 0.4986 1.1520 1.0733
No log 63.6667 382 1.1465 0.4986 1.1465 1.0707
No log 64.0 384 1.1796 0.4965 1.1796 1.0861
No log 64.3333 386 1.1948 0.4965 1.1948 1.0931
No log 64.6667 388 1.2305 0.4951 1.2305 1.1093
No log 65.0 390 1.2943 0.4748 1.2943 1.1377
No log 65.3333 392 1.3671 0.4531 1.3671 1.1692
No log 65.6667 394 1.3452 0.4531 1.3452 1.1598
No log 66.0 396 1.3483 0.4531 1.3483 1.1612
No log 66.3333 398 1.3738 0.4531 1.3738 1.1721
No log 66.6667 400 1.3770 0.4531 1.3770 1.1735
No log 67.0 402 1.3271 0.4748 1.3271 1.1520
No log 67.3333 404 1.2814 0.4763 1.2814 1.1320
No log 67.6667 406 1.2093 0.4939 1.2093 1.0997
No log 68.0 408 1.1426 0.4816 1.1426 1.0689
No log 68.3333 410 1.1301 0.4872 1.1301 1.0631
No log 68.6667 412 1.1683 0.4946 1.1683 1.0809
No log 69.0 414 1.2462 0.4869 1.2462 1.1163
No log 69.3333 416 1.3174 0.4753 1.3174 1.1478
No log 69.6667 418 1.3383 0.4753 1.3383 1.1569
No log 70.0 420 1.2797 0.4671 1.2797 1.1312
No log 70.3333 422 1.2043 0.4979 1.2043 1.0974
No log 70.6667 424 1.1606 0.5039 1.1606 1.0773
No log 71.0 426 1.1496 0.4986 1.1496 1.0722
No log 71.3333 428 1.1591 0.4986 1.1591 1.0766
No log 71.6667 430 1.2182 0.4972 1.2182 1.1037
No log 72.0 432 1.3040 0.4768 1.3040 1.1419
No log 72.3333 434 1.3829 0.4577 1.3829 1.1760
No log 72.6667 436 1.3949 0.4580 1.3949 1.1811
No log 73.0 438 1.3473 0.4856 1.3473 1.1607
No log 73.3333 440 1.2746 0.4965 1.2746 1.1290
No log 73.6667 442 1.2007 0.4979 1.2007 1.0958
No log 74.0 444 1.1544 0.4993 1.1544 1.0744
No log 74.3333 446 1.1260 0.5094 1.1260 1.0611
No log 74.6667 448 1.1272 0.5056 1.1272 1.0617
No log 75.0 450 1.1483 0.4986 1.1483 1.0716
No log 75.3333 452 1.1598 0.4939 1.1598 1.0769
No log 75.6667 454 1.1996 0.4939 1.1996 1.0953
No log 76.0 456 1.2416 0.4926 1.2416 1.1143
No log 76.3333 458 1.2859 0.4856 1.2859 1.1340
No log 76.6667 460 1.2975 0.4753 1.2975 1.1391
No log 77.0 462 1.3027 0.4621 1.3027 1.1413
No log 77.3333 464 1.3175 0.4483 1.3175 1.1478
No log 77.6667 466 1.3165 0.4574 1.3165 1.1474
No log 78.0 468 1.3104 0.4666 1.3104 1.1447
No log 78.3333 470 1.3034 0.4670 1.3034 1.1417
No log 78.6667 472 1.2999 0.4585 1.2999 1.1401
No log 79.0 474 1.2920 0.4589 1.2920 1.1367
No log 79.3333 476 1.2866 0.4781 1.2866 1.1343
No log 79.6667 478 1.2822 0.4781 1.2822 1.1323
No log 80.0 480 1.2944 0.4781 1.2944 1.1377
No log 80.3333 482 1.2835 0.4781 1.2835 1.1329
No log 80.6667 484 1.2651 0.4781 1.2651 1.1248
No log 81.0 486 1.2367 0.4781 1.2367 1.1121
No log 81.3333 488 1.1941 0.4786 1.1941 1.0928
No log 81.6667 490 1.1773 0.4932 1.1773 1.0850
No log 82.0 492 1.1796 0.4932 1.1796 1.0861
No log 82.3333 494 1.1742 0.4939 1.1742 1.0836
No log 82.6667 496 1.1945 0.4932 1.1945 1.0929
No log 83.0 498 1.2230 0.4727 1.2230 1.1059
0.2385 83.3333 500 1.2326 0.4727 1.2326 1.1102
0.2385 83.6667 502 1.2457 0.4727 1.2457 1.1161
0.2385 84.0 504 1.2337 0.4781 1.2337 1.1107
0.2385 84.3333 506 1.2064 0.4786 1.2064 1.0983
0.2385 84.6667 508 1.2087 0.4932 1.2087 1.0994
0.2385 85.0 510 1.2136 0.4926 1.2136 1.1016
0.2385 85.3333 512 1.2184 0.4926 1.2184 1.1038
0.2385 85.6667 514 1.2055 0.4932 1.2055 1.0979
0.2385 86.0 516 1.1907 0.4932 1.1907 1.0912
0.2385 86.3333 518 1.1820 0.4932 1.1820 1.0872
0.2385 86.6667 520 1.1996 0.4932 1.1996 1.0953
0.2385 87.0 522 1.2218 0.4926 1.2218 1.1054
0.2385 87.3333 524 1.2389 0.4926 1.2389 1.1131
0.2385 87.6667 526 1.2505 0.4926 1.2505 1.1183
0.2385 88.0 528 1.2686 0.4822 1.2686 1.1263
0.2385 88.3333 530 1.2896 0.4585 1.2896 1.1356
0.2385 88.6667 532 1.3255 0.4570 1.3255 1.1513
0.2385 89.0 534 1.3645 0.4480 1.3645 1.1681
0.2385 89.3333 536 1.3872 0.4480 1.3872 1.1778
0.2385 89.6667 538 1.3838 0.4391 1.3838 1.1763

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/ArabicNewSplits8_usingALLEssays_FineTuningAraBERT_run2_AugV5_k1_task1_organization

Finetuned
(4023)
this model