ArabicNewSplits7_B_usingALLEssays_FineTuningAraBERT_run3_AugV5_k6_task5_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: 1.0794
  • Qwk: 0.2769
  • Mse: 1.0794
  • Rmse: 1.0389

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 0.0741 2 4.0254 0.0024 4.0254 2.0063
No log 0.1481 4 2.7057 -0.0310 2.7057 1.6449
No log 0.2222 6 2.7525 -0.0838 2.7525 1.6591
No log 0.2963 8 2.0904 0.0852 2.0904 1.4458
No log 0.3704 10 1.6324 0.0957 1.6324 1.2777
No log 0.4444 12 1.7281 0.1644 1.7281 1.3146
No log 0.5185 14 2.1127 0.0976 2.1127 1.4535
No log 0.5926 16 2.4789 0.0802 2.4789 1.5744
No log 0.6667 18 2.0321 0.1379 2.0321 1.4255
No log 0.7407 20 1.2849 0.2501 1.2849 1.1335
No log 0.8148 22 1.2558 0.2653 1.2558 1.1206
No log 0.8889 24 1.3784 0.2178 1.3784 1.1741
No log 0.9630 26 1.7659 0.2042 1.7659 1.3289
No log 1.0370 28 1.2739 0.3023 1.2739 1.1287
No log 1.1111 30 1.0461 0.3256 1.0461 1.0228
No log 1.1852 32 1.0763 0.3297 1.0763 1.0374
No log 1.2593 34 1.3299 0.2840 1.3299 1.1532
No log 1.3333 36 1.4380 0.3218 1.4380 1.1992
No log 1.4074 38 1.5100 0.3455 1.5100 1.2288
No log 1.4815 40 1.2438 0.2334 1.2438 1.1153
No log 1.5556 42 1.1295 0.3043 1.1295 1.0628
No log 1.6296 44 1.1387 0.3128 1.1387 1.0671
No log 1.7037 46 1.2973 0.2457 1.2973 1.1390
No log 1.7778 48 1.3163 0.2496 1.3163 1.1473
No log 1.8519 50 1.1564 0.2844 1.1564 1.0753
No log 1.9259 52 1.0816 0.2972 1.0816 1.0400
No log 2.0 54 1.1190 0.3380 1.1190 1.0578
No log 2.0741 56 1.0715 0.2829 1.0715 1.0351
No log 2.1481 58 1.4119 0.1778 1.4119 1.1882
No log 2.2222 60 1.6885 0.1386 1.6885 1.2994
No log 2.2963 62 1.6795 0.1386 1.6795 1.2959
No log 2.3704 64 1.2581 0.2110 1.2581 1.1216
No log 2.4444 66 1.0929 0.3352 1.0929 1.0454
No log 2.5185 68 1.0975 0.2965 1.0975 1.0476
No log 2.5926 70 1.1548 0.3421 1.1548 1.0746
No log 2.6667 72 1.0999 0.3363 1.0999 1.0488
No log 2.7407 74 1.0869 0.3218 1.0869 1.0425
No log 2.8148 76 1.1267 0.4297 1.1267 1.0614
No log 2.8889 78 1.1473 0.3875 1.1473 1.0711
No log 2.9630 80 1.2139 0.3554 1.2139 1.1018
No log 3.0370 82 1.2992 0.3174 1.2992 1.1398
No log 3.1111 84 1.2467 0.3340 1.2467 1.1166
No log 3.1852 86 1.1926 0.4147 1.1926 1.0921
No log 3.2593 88 1.1955 0.4898 1.1955 1.0934
No log 3.3333 90 1.1696 0.4342 1.1696 1.0815
No log 3.4074 92 1.1990 0.3568 1.1990 1.0950
No log 3.4815 94 1.1524 0.4511 1.1524 1.0735
No log 3.5556 96 1.1777 0.3480 1.1777 1.0852
No log 3.6296 98 1.1356 0.3962 1.1356 1.0657
No log 3.7037 100 1.1486 0.3237 1.1486 1.0717
No log 3.7778 102 1.2223 0.4298 1.2223 1.1056
No log 3.8519 104 1.2456 0.3990 1.2456 1.1161
No log 3.9259 106 1.2024 0.3394 1.2024 1.0965
No log 4.0 108 1.3498 0.2262 1.3498 1.1618
No log 4.0741 110 1.2523 0.2997 1.2523 1.1191
No log 4.1481 112 1.1616 0.3308 1.1616 1.0778
No log 4.2222 114 1.1880 0.3192 1.1880 1.0900
No log 4.2963 116 1.1942 0.3124 1.1942 1.0928
No log 4.3704 118 1.3255 0.2181 1.3255 1.1513
No log 4.4444 120 1.4126 0.1908 1.4126 1.1885
No log 4.5185 122 1.2129 0.3019 1.2129 1.1013
No log 4.5926 124 1.1533 0.3019 1.1533 1.0739
No log 4.6667 126 1.1490 0.2541 1.1490 1.0719
No log 4.7407 128 1.0965 0.2380 1.0965 1.0471
No log 4.8148 130 1.0982 0.2157 1.0982 1.0480
No log 4.8889 132 1.0176 0.3647 1.0176 1.0088
No log 4.9630 134 1.0536 0.2699 1.0536 1.0264
No log 5.0370 136 1.0177 0.3347 1.0177 1.0088
No log 5.1111 138 1.0380 0.3544 1.0380 1.0188
No log 5.1852 140 1.0340 0.3896 1.0340 1.0169
No log 5.2593 142 1.1063 0.2970 1.1063 1.0518
No log 5.3333 144 1.2243 0.2636 1.2243 1.1065
No log 5.4074 146 1.2790 0.2636 1.2790 1.1309
No log 5.4815 148 1.1950 0.3472 1.1950 1.0931
No log 5.5556 150 1.1558 0.3540 1.1558 1.0751
No log 5.6296 152 1.1858 0.3578 1.1858 1.0890
No log 5.7037 154 1.1997 0.2970 1.1997 1.0953
No log 5.7778 156 1.1492 0.2655 1.1492 1.0720
No log 5.8519 158 1.0794 0.2290 1.0794 1.0390
No log 5.9259 160 1.0784 0.2963 1.0784 1.0385
No log 6.0 162 1.0976 0.2514 1.0976 1.0476
No log 6.0741 164 1.1007 0.2738 1.1007 1.0492
No log 6.1481 166 1.0912 0.3113 1.0912 1.0446
No log 6.2222 168 1.1511 0.2694 1.1511 1.0729
No log 6.2963 170 1.2646 0.2036 1.2646 1.1245
No log 6.3704 172 1.1456 0.3342 1.1456 1.0703
No log 6.4444 174 1.1536 0.3483 1.1536 1.0741
No log 6.5185 176 1.1795 0.3045 1.1795 1.0860
No log 6.5926 178 1.1327 0.3502 1.1327 1.0643
No log 6.6667 180 1.1169 0.3768 1.1169 1.0568
No log 6.7407 182 1.0950 0.4537 1.0950 1.0464
No log 6.8148 184 1.1358 0.4023 1.1358 1.0657
No log 6.8889 186 1.1574 0.3472 1.1574 1.0758
No log 6.9630 188 1.1643 0.2748 1.1643 1.0790
No log 7.0370 190 1.0528 0.2908 1.0528 1.0261
No log 7.1111 192 0.9725 0.4010 0.9725 0.9862
No log 7.1852 194 0.9702 0.4010 0.9702 0.9850
No log 7.2593 196 1.0791 0.3042 1.0791 1.0388
No log 7.3333 198 1.1658 0.2907 1.1658 1.0797
No log 7.4074 200 1.1289 0.3756 1.1289 1.0625
No log 7.4815 202 1.1011 0.3880 1.1011 1.0493
No log 7.5556 204 1.0604 0.3330 1.0604 1.0297
No log 7.6296 206 1.1115 0.3472 1.1115 1.0543
No log 7.7037 208 1.1154 0.3491 1.1154 1.0561
No log 7.7778 210 1.0876 0.3011 1.0876 1.0429
No log 7.8519 212 1.1000 0.2721 1.1000 1.0488
No log 7.9259 214 1.1517 0.2792 1.1517 1.0732
No log 8.0 216 1.1962 0.2792 1.1962 1.0937
No log 8.0741 218 1.1897 0.2632 1.1897 1.0907
No log 8.1481 220 1.1308 0.1710 1.1308 1.0634
No log 8.2222 222 1.0714 0.3149 1.0714 1.0351
No log 8.2963 224 1.1000 0.2432 1.1000 1.0488
No log 8.3704 226 1.0766 0.2921 1.0766 1.0376
No log 8.4444 228 1.1387 0.2562 1.1387 1.0671
No log 8.5185 230 1.2167 0.2988 1.2167 1.1030
No log 8.5926 232 1.1396 0.3139 1.1396 1.0675
No log 8.6667 234 1.0379 0.3781 1.0379 1.0188
No log 8.7407 236 1.0686 0.2630 1.0686 1.0337
No log 8.8148 238 1.0620 0.3186 1.0620 1.0305
No log 8.8889 240 1.0639 0.3841 1.0639 1.0315
No log 8.9630 242 1.1881 0.3463 1.1881 1.0900
No log 9.0370 244 1.1677 0.3046 1.1677 1.0806
No log 9.1111 246 1.0421 0.2216 1.0421 1.0208
No log 9.1852 248 1.0217 0.2763 1.0217 1.0108
No log 9.2593 250 1.0287 0.1857 1.0287 1.0142
No log 9.3333 252 1.1701 0.1985 1.1701 1.0817
No log 9.4074 254 1.2389 0.3237 1.2389 1.1131
No log 9.4815 256 1.1347 0.2680 1.1347 1.0652
No log 9.5556 258 1.0148 0.2909 1.0148 1.0074
No log 9.6296 260 0.9906 0.3335 0.9906 0.9953
No log 9.7037 262 1.0093 0.3066 1.0093 1.0046
No log 9.7778 264 1.1676 0.3488 1.1676 1.0806
No log 9.8519 266 1.2519 0.3596 1.2519 1.1189
No log 9.9259 268 1.2605 0.3205 1.2605 1.1227
No log 10.0 270 1.1705 0.2907 1.1705 1.0819
No log 10.0741 272 1.1252 0.2610 1.1252 1.0607
No log 10.1481 274 1.1432 0.2907 1.1432 1.0692
No log 10.2222 276 1.1323 0.2907 1.1323 1.0641
No log 10.2963 278 1.1468 0.2836 1.1468 1.0709
No log 10.3704 280 1.1172 0.3626 1.1172 1.0570
No log 10.4444 282 1.1270 0.3154 1.1270 1.0616
No log 10.5185 284 1.1447 0.3154 1.1447 1.0699
No log 10.5926 286 1.2492 0.3453 1.2492 1.1177
No log 10.6667 288 1.3009 0.3461 1.3009 1.1406
No log 10.7407 290 1.1917 0.4032 1.1917 1.0916
No log 10.8148 292 1.0836 0.3932 1.0836 1.0409
No log 10.8889 294 1.1274 0.3450 1.1274 1.0618
No log 10.9630 296 1.0623 0.3781 1.0623 1.0307
No log 11.0370 298 1.0567 0.3029 1.0567 1.0280
No log 11.1111 300 1.1001 0.3542 1.1001 1.0489
No log 11.1852 302 1.1879 0.3243 1.1879 1.0899
No log 11.2593 304 1.1105 0.3026 1.1105 1.0538
No log 11.3333 306 0.9989 0.3474 0.9989 0.9994
No log 11.4074 308 0.9835 0.3435 0.9835 0.9917
No log 11.4815 310 0.9953 0.2432 0.9953 0.9977
No log 11.5556 312 1.0059 0.3474 1.0059 1.0029
No log 11.6296 314 1.0560 0.2951 1.0560 1.0276
No log 11.7037 316 1.1059 0.3029 1.1059 1.0516
No log 11.7778 318 1.1051 0.2991 1.1051 1.0512
No log 11.8519 320 1.1408 0.2919 1.1408 1.0681
No log 11.9259 322 1.1268 0.2679 1.1268 1.0615
No log 12.0 324 1.1046 0.3559 1.1046 1.0510
No log 12.0741 326 1.0967 0.2633 1.0967 1.0472
No log 12.1481 328 1.1203 0.3029 1.1203 1.0584
No log 12.2222 330 1.1866 0.3330 1.1866 1.0893
No log 12.2963 332 1.1779 0.3330 1.1779 1.0853
No log 12.3704 334 1.1149 0.2470 1.1149 1.0559
No log 12.4444 336 1.1011 0.2053 1.1011 1.0493
No log 12.5185 338 1.1098 0.2912 1.1098 1.0535
No log 12.5926 340 1.0727 0.3014 1.0727 1.0357
No log 12.6667 342 1.1494 0.3472 1.1494 1.0721
No log 12.7407 344 1.1591 0.2545 1.1591 1.0766
No log 12.8148 346 1.0746 0.2346 1.0746 1.0366
No log 12.8889 348 0.9990 0.3465 0.9990 0.9995
No log 12.9630 350 1.0530 0.2973 1.0530 1.0261
No log 13.0370 352 1.0598 0.2973 1.0598 1.0294
No log 13.1111 354 1.0046 0.3647 1.0046 1.0023
No log 13.1852 356 1.0528 0.3300 1.0528 1.0260
No log 13.2593 358 1.0931 0.3897 1.0931 1.0455
No log 13.3333 360 1.1502 0.3913 1.1502 1.0725
No log 13.4074 362 1.0946 0.3154 1.0946 1.0462
No log 13.4815 364 1.0433 0.3474 1.0433 1.0214
No log 13.5556 366 1.0679 0.3119 1.0679 1.0334
No log 13.6296 368 1.1348 0.2263 1.1348 1.0653
No log 13.7037 370 1.1541 0.2658 1.1541 1.0743
No log 13.7778 372 1.1372 0.3042 1.1372 1.0664
No log 13.8519 374 1.0955 0.2655 1.0955 1.0467
No log 13.9259 376 1.1222 0.2949 1.1222 1.0593
No log 14.0 378 1.1639 0.3210 1.1639 1.0789
No log 14.0741 380 1.1838 0.3275 1.1838 1.0880
No log 14.1481 382 1.1290 0.3542 1.1290 1.0625
No log 14.2222 384 1.0471 0.3144 1.0471 1.0233
No log 14.2963 386 1.0318 0.3276 1.0318 1.0158
No log 14.3704 388 1.0145 0.3243 1.0145 1.0072
No log 14.4444 390 1.0790 0.3139 1.0790 1.0388
No log 14.5185 392 1.1405 0.3418 1.1405 1.0679
No log 14.5926 394 1.1002 0.3281 1.1002 1.0489
No log 14.6667 396 1.0686 0.3243 1.0686 1.0337
No log 14.7407 398 1.0405 0.3263 1.0405 1.0201
No log 14.8148 400 1.0533 0.2942 1.0533 1.0263
No log 14.8889 402 1.0403 0.2974 1.0403 1.0199
No log 14.9630 404 1.0837 0.3560 1.0837 1.0410
No log 15.0370 406 1.1797 0.3654 1.1797 1.0861
No log 15.1111 408 1.2084 0.3514 1.2084 1.0993
No log 15.1852 410 1.1342 0.3134 1.1342 1.0650
No log 15.2593 412 1.0842 0.2677 1.0842 1.0413
No log 15.3333 414 1.0716 0.2456 1.0716 1.0352
No log 15.4074 416 1.1269 0.2988 1.1269 1.0615
No log 15.4815 418 1.1733 0.3323 1.1733 1.0832
No log 15.5556 420 1.1526 0.3262 1.1526 1.0736
No log 15.6296 422 1.1041 0.2651 1.1041 1.0508
No log 15.7037 424 1.0880 0.2651 1.0880 1.0431
No log 15.7778 426 1.0515 0.2336 1.0515 1.0254
No log 15.8519 428 1.0403 0.2336 1.0403 1.0199
No log 15.9259 430 1.0294 0.2336 1.0294 1.0146
No log 16.0 432 1.0252 0.2336 1.0252 1.0125
No log 16.0741 434 1.0192 0.2910 1.0192 1.0096
No log 16.1481 436 1.0191 0.3209 1.0191 1.0095
No log 16.2222 438 1.0260 0.2835 1.0260 1.0129
No log 16.2963 440 1.0317 0.3112 1.0317 1.0158
No log 16.3704 442 1.0176 0.2835 1.0176 1.0087
No log 16.4444 444 1.0793 0.3196 1.0793 1.0389
No log 16.5185 446 1.2605 0.3268 1.2605 1.1227
No log 16.5926 448 1.2528 0.3111 1.2528 1.1193
No log 16.6667 450 1.1221 0.2239 1.1221 1.0593
No log 16.7407 452 1.0047 0.2432 1.0047 1.0024
No log 16.8148 454 0.9841 0.2400 0.9841 0.9920
No log 16.8889 456 1.0037 0.2102 1.0037 1.0018
No log 16.9630 458 1.0726 0.1919 1.0726 1.0357
No log 17.0370 460 1.0773 0.2928 1.0773 1.0379
No log 17.1111 462 1.0179 0.3318 1.0179 1.0089
No log 17.1852 464 1.0202 0.3182 1.0202 1.0101
No log 17.2593 466 1.0959 0.2928 1.0959 1.0469
No log 17.3333 468 1.2080 0.2328 1.2080 1.0991
No log 17.4074 470 1.1782 0.1960 1.1782 1.0855
No log 17.4815 472 1.0535 0.2432 1.0535 1.0264
No log 17.5556 474 0.9786 0.2326 0.9786 0.9892
No log 17.6296 476 0.9741 0.3301 0.9741 0.9870
No log 17.7037 478 0.9709 0.2742 0.9709 0.9853
No log 17.7778 480 0.9936 0.2909 0.9936 0.9968
No log 17.8519 482 1.0121 0.2909 1.0121 1.0060
No log 17.9259 484 0.9975 0.3008 0.9975 0.9987
No log 18.0 486 1.0103 0.3306 1.0103 1.0051
No log 18.0741 488 1.0075 0.2504 1.0075 1.0038
No log 18.1481 490 0.9898 0.3052 0.9898 0.9949
No log 18.2222 492 0.9819 0.2667 0.9819 0.9909
No log 18.2963 494 0.9783 0.3033 0.9783 0.9891
No log 18.3704 496 1.0257 0.2887 1.0257 1.0128
No log 18.4444 498 1.0676 0.2723 1.0676 1.0332
0.2662 18.5185 500 1.0889 0.3024 1.0889 1.0435
0.2662 18.5926 502 1.0526 0.3182 1.0526 1.0260
0.2662 18.6667 504 0.9974 0.3030 0.9974 0.9987
0.2662 18.7407 506 0.9933 0.2976 0.9933 0.9966
0.2662 18.8148 508 0.9989 0.2976 0.9989 0.9995
0.2662 18.8889 510 1.0095 0.2954 1.0095 1.0047
0.2662 18.9630 512 1.0570 0.2769 1.0570 1.0281
0.2662 19.0370 514 1.0794 0.2769 1.0794 1.0389

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_k6_task5_organization

Finetuned
(4019)
this model