ArabicNewSplits7_usingWellWrittenEssays_FineTuningAraBERT_run2_AugV5_k11_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: 1.1494
  • Qwk: 0.2313
  • Mse: 1.1494
  • Rmse: 1.0721

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 0.0625 2 4.5646 -0.0132 4.5646 2.1365
No log 0.125 4 2.6677 -0.0474 2.6677 1.6333
No log 0.1875 6 1.8341 -0.0233 1.8341 1.3543
No log 0.25 8 1.4589 0.0182 1.4589 1.2079
No log 0.3125 10 1.7415 -0.1739 1.7415 1.3197
No log 0.375 12 1.5282 -0.1940 1.5282 1.2362
No log 0.4375 14 1.4982 -0.1452 1.4982 1.2240
No log 0.5 16 1.5714 -0.0921 1.5714 1.2536
No log 0.5625 18 1.5374 -0.0534 1.5374 1.2399
No log 0.625 20 1.3688 0.0688 1.3688 1.1699
No log 0.6875 22 1.2661 0.1200 1.2661 1.1252
No log 0.75 24 1.2010 0.1834 1.2010 1.0959
No log 0.8125 26 1.1585 0.2584 1.1585 1.0763
No log 0.875 28 1.3234 0.0488 1.3234 1.1504
No log 0.9375 30 1.4941 0.0 1.4941 1.2223
No log 1.0 32 1.3229 0.0811 1.3229 1.1502
No log 1.0625 34 1.1779 0.3041 1.1779 1.0853
No log 1.125 36 1.2733 0.1423 1.2733 1.1284
No log 1.1875 38 1.3423 0.1168 1.3423 1.1586
No log 1.25 40 1.3823 0.1379 1.3823 1.1757
No log 1.3125 42 1.4153 0.0865 1.4153 1.1897
No log 1.375 44 1.3253 0.1107 1.3253 1.1512
No log 1.4375 46 1.3456 0.0299 1.3456 1.1600
No log 1.5 48 1.3272 0.1300 1.3272 1.1521
No log 1.5625 50 1.3970 -0.0040 1.3970 1.1820
No log 1.625 52 1.5790 0.0600 1.5790 1.2566
No log 1.6875 54 1.7355 0.0321 1.7355 1.3174
No log 1.75 56 1.4999 0.0600 1.4999 1.2247
No log 1.8125 58 1.3044 0.0389 1.3044 1.1421
No log 1.875 60 1.2737 0.1468 1.2737 1.1286
No log 1.9375 62 1.2558 0.1016 1.2558 1.1206
No log 2.0 64 1.2853 0.1542 1.2853 1.1337
No log 2.0625 66 1.3538 0.0894 1.3538 1.1635
No log 2.125 68 1.3238 0.1507 1.3238 1.1506
No log 2.1875 70 1.2520 0.2025 1.2520 1.1189
No log 2.25 72 1.1948 0.1140 1.1948 1.0931
No log 2.3125 74 1.2090 0.1870 1.2090 1.0996
No log 2.375 76 1.1667 0.2001 1.1667 1.0801
No log 2.4375 78 1.1874 0.2230 1.1874 1.0897
No log 2.5 80 1.2141 0.3568 1.2141 1.1019
No log 2.5625 82 1.2142 0.2368 1.2142 1.1019
No log 2.625 84 1.2963 0.1974 1.2963 1.1386
No log 2.6875 86 1.2428 0.2785 1.2428 1.1148
No log 2.75 88 1.2538 0.3674 1.2538 1.1197
No log 2.8125 90 1.2765 0.3779 1.2765 1.1298
No log 2.875 92 1.2274 0.2660 1.2274 1.1079
No log 2.9375 94 1.2429 0.2098 1.2429 1.1149
No log 3.0 96 1.2761 0.1466 1.2761 1.1296
No log 3.0625 98 1.3423 0.2361 1.3423 1.1586
No log 3.125 100 1.2404 0.3498 1.2404 1.1137
No log 3.1875 102 1.3798 0.3058 1.3798 1.1747
No log 3.25 104 1.5985 0.2266 1.5985 1.2643
No log 3.3125 106 1.4148 0.2857 1.4148 1.1894
No log 3.375 108 1.1984 0.3606 1.1984 1.0947
No log 3.4375 110 1.1991 0.4114 1.1991 1.0951
No log 3.5 112 1.1808 0.4379 1.1808 1.0866
No log 3.5625 114 1.1413 0.4126 1.1413 1.0683
No log 3.625 116 1.1677 0.4066 1.1677 1.0806
No log 3.6875 118 1.2000 0.3673 1.2000 1.0955
No log 3.75 120 1.1292 0.3522 1.1292 1.0627
No log 3.8125 122 1.1346 0.3690 1.1346 1.0652
No log 3.875 124 1.1313 0.3152 1.1313 1.0636
No log 3.9375 126 1.1763 0.3086 1.1763 1.0846
No log 4.0 128 1.2360 0.3504 1.2360 1.1117
No log 4.0625 130 1.2805 0.3227 1.2805 1.1316
No log 4.125 132 1.2853 0.3144 1.2853 1.1337
No log 4.1875 134 1.2360 0.3485 1.2360 1.1118
No log 4.25 136 1.2503 0.2898 1.2503 1.1182
No log 4.3125 138 1.4044 0.2928 1.4044 1.1851
No log 4.375 140 1.4459 0.2948 1.4459 1.2025
No log 4.4375 142 1.3986 0.3192 1.3986 1.1826
No log 4.5 144 1.3045 0.3767 1.3045 1.1421
No log 4.5625 146 1.3107 0.3926 1.3107 1.1448
No log 4.625 148 1.4299 0.2661 1.4299 1.1958
No log 4.6875 150 1.4306 0.2430 1.4306 1.1961
No log 4.75 152 1.2847 0.3281 1.2847 1.1334
No log 4.8125 154 1.4641 0.1942 1.4641 1.2100
No log 4.875 156 1.5969 0.1130 1.5969 1.2637
No log 4.9375 158 1.3446 0.1379 1.3446 1.1596
No log 5.0 160 1.4281 0.2840 1.4281 1.1950
No log 5.0625 162 1.5725 0.1660 1.5725 1.2540
No log 5.125 164 1.4608 0.2733 1.4608 1.2086
No log 5.1875 166 1.3867 0.1043 1.3867 1.1776
No log 5.25 168 1.5724 0.1527 1.5724 1.2540
No log 5.3125 170 1.4629 0.1434 1.4629 1.2095
No log 5.375 172 1.3711 0.1912 1.3711 1.1710
No log 5.4375 174 1.4521 0.2237 1.4521 1.2050
No log 5.5 176 1.4823 0.2101 1.4823 1.2175
No log 5.5625 178 1.3850 0.2226 1.3850 1.1769
No log 5.625 180 1.2907 0.2624 1.2907 1.1361
No log 5.6875 182 1.2630 0.2812 1.2630 1.1238
No log 5.75 184 1.2525 0.2997 1.2525 1.1191
No log 5.8125 186 1.2580 0.2037 1.2580 1.1216
No log 5.875 188 1.2279 0.2686 1.2279 1.1081
No log 5.9375 190 1.2111 0.2313 1.2111 1.1005
No log 6.0 192 1.2116 0.2608 1.2116 1.1007
No log 6.0625 194 1.2687 0.2136 1.2687 1.1264
No log 6.125 196 1.3221 0.2411 1.3221 1.1498
No log 6.1875 198 1.3526 0.2461 1.3526 1.1630
No log 6.25 200 1.2673 0.2126 1.2673 1.1257
No log 6.3125 202 1.2470 0.2801 1.2470 1.1167
No log 6.375 204 1.2623 0.2714 1.2623 1.1235
No log 6.4375 206 1.3311 0.3377 1.3311 1.1537
No log 6.5 208 1.4821 0.2196 1.4821 1.2174
No log 6.5625 210 1.5859 0.2156 1.5859 1.2593
No log 6.625 212 1.4300 0.2401 1.4300 1.1958
No log 6.6875 214 1.2701 0.3151 1.2701 1.1270
No log 6.75 216 1.3020 0.3222 1.3020 1.1410
No log 6.8125 218 1.4340 0.2623 1.4340 1.1975
No log 6.875 220 1.5010 0.2172 1.5010 1.2252
No log 6.9375 222 1.4088 0.3504 1.4088 1.1869
No log 7.0 224 1.2557 0.4098 1.2557 1.1206
No log 7.0625 226 1.2283 0.3075 1.2283 1.1083
No log 7.125 228 1.2223 0.3579 1.2223 1.1056
No log 7.1875 230 1.3817 0.2470 1.3817 1.1754
No log 7.25 232 1.4177 0.2647 1.4177 1.1907
No log 7.3125 234 1.2744 0.3848 1.2744 1.1289
No log 7.375 236 1.1919 0.2820 1.1919 1.0917
No log 7.4375 238 1.2840 0.1206 1.2840 1.1332
No log 7.5 240 1.2598 0.2103 1.2598 1.1224
No log 7.5625 242 1.2547 0.3852 1.2547 1.1202
No log 7.625 244 1.5557 0.1753 1.5557 1.2473
No log 7.6875 246 1.7754 0.1793 1.7754 1.3325
No log 7.75 248 1.6577 0.1753 1.6577 1.2875
No log 7.8125 250 1.3789 0.2481 1.3789 1.1742
No log 7.875 252 1.2125 0.2315 1.2125 1.1012
No log 7.9375 254 1.2529 0.1468 1.2529 1.1193
No log 8.0 256 1.2144 0.1294 1.2144 1.1020
No log 8.0625 258 1.1852 0.3874 1.1852 1.0887
No log 8.125 260 1.1934 0.2782 1.1934 1.0924
No log 8.1875 262 1.2742 0.1995 1.2742 1.1288
No log 8.25 264 1.3436 0.2634 1.3436 1.1591
No log 8.3125 266 1.3319 0.2634 1.3319 1.1541
No log 8.375 268 1.2442 0.3111 1.2442 1.1154
No log 8.4375 270 1.2135 0.3089 1.2135 1.1016
No log 8.5 272 1.2313 0.3089 1.2313 1.1096
No log 8.5625 274 1.2446 0.2424 1.2446 1.1156
No log 8.625 276 1.3445 0.3044 1.3445 1.1595
No log 8.6875 278 1.4513 0.2339 1.4513 1.2047
No log 8.75 280 1.4798 0.2742 1.4798 1.2165
No log 8.8125 282 1.4250 0.2806 1.4250 1.1937
No log 8.875 284 1.4093 0.2784 1.4093 1.1872
No log 8.9375 286 1.4305 0.3021 1.4305 1.1960
No log 9.0 288 1.4255 0.3205 1.4255 1.1940
No log 9.0625 290 1.4384 0.2418 1.4384 1.1993
No log 9.125 292 1.5113 0.1967 1.5113 1.2294
No log 9.1875 294 1.4157 0.2564 1.4157 1.1899
No log 9.25 296 1.3453 0.2870 1.3453 1.1599
No log 9.3125 298 1.3928 0.2191 1.3928 1.1802
No log 9.375 300 1.3546 0.2072 1.3546 1.1639
No log 9.4375 302 1.2420 0.3632 1.2420 1.1145
No log 9.5 304 1.2297 0.3535 1.2297 1.1089
No log 9.5625 306 1.2443 0.3654 1.2443 1.1155
No log 9.625 308 1.2419 0.3310 1.2419 1.1144
No log 9.6875 310 1.2586 0.3518 1.2586 1.1219
No log 9.75 312 1.3112 0.3528 1.3112 1.1451
No log 9.8125 314 1.4139 0.2688 1.4139 1.1891
No log 9.875 316 1.3983 0.2863 1.3983 1.1825
No log 9.9375 318 1.2378 0.3954 1.2378 1.1126
No log 10.0 320 1.2044 0.2382 1.2044 1.0974
No log 10.0625 322 1.2044 0.1966 1.2044 1.0974
No log 10.125 324 1.1937 0.3970 1.1937 1.0926
No log 10.1875 326 1.2487 0.3151 1.2487 1.1175
No log 10.25 328 1.3068 0.3024 1.3068 1.1431
No log 10.3125 330 1.3432 0.2863 1.3432 1.1590
No log 10.375 332 1.2052 0.2547 1.2052 1.0978
No log 10.4375 334 1.1454 0.3361 1.1454 1.0702
No log 10.5 336 1.1637 0.3353 1.1637 1.0787
No log 10.5625 338 1.1642 0.3772 1.1642 1.0790
No log 10.625 340 1.2250 0.3962 1.2250 1.1068
No log 10.6875 342 1.3957 0.2885 1.3957 1.1814
No log 10.75 344 1.4013 0.2767 1.4013 1.1838
No log 10.8125 346 1.2601 0.3064 1.2601 1.1225
No log 10.875 348 1.1480 0.3209 1.1480 1.0714
No log 10.9375 350 1.1591 0.3811 1.1591 1.0766
No log 11.0 352 1.1771 0.3811 1.1771 1.0850
No log 11.0625 354 1.2064 0.3822 1.2064 1.0984
No log 11.125 356 1.3759 0.2130 1.3759 1.1730
No log 11.1875 358 1.4653 0.2478 1.4653 1.2105
No log 11.25 360 1.3997 0.2418 1.3997 1.1831
No log 11.3125 362 1.2920 0.2664 1.2920 1.1367
No log 11.375 364 1.1880 0.1951 1.1880 1.0900
No log 11.4375 366 1.1465 0.1543 1.1465 1.0708
No log 11.5 368 1.1602 0.1090 1.1602 1.0771
No log 11.5625 370 1.2032 0.1951 1.2032 1.0969
No log 11.625 372 1.2444 0.1951 1.2444 1.1155
No log 11.6875 374 1.2357 0.1951 1.2357 1.1116
No log 11.75 376 1.2250 0.2154 1.2250 1.1068
No log 11.8125 378 1.2793 0.2273 1.2793 1.1311
No log 11.875 380 1.3811 0.2191 1.3811 1.1752
No log 11.9375 382 1.3733 0.2350 1.3733 1.1719
No log 12.0 384 1.2655 0.3365 1.2655 1.1250
No log 12.0625 386 1.1688 0.3275 1.1688 1.0811
No log 12.125 388 1.1478 0.3019 1.1478 1.0714
No log 12.1875 390 1.1499 0.2446 1.1499 1.0723
No log 12.25 392 1.2118 0.2003 1.2118 1.1008
No log 12.3125 394 1.2463 0.3237 1.2463 1.1164
No log 12.375 396 1.2262 0.2782 1.2262 1.1074
No log 12.4375 398 1.2079 0.2273 1.2079 1.0990
No log 12.5 400 1.2036 0.2532 1.2036 1.0971
No log 12.5625 402 1.2531 0.3109 1.2531 1.1194
No log 12.625 404 1.2680 0.3109 1.2680 1.1260
No log 12.6875 406 1.3324 0.2399 1.3324 1.1543
No log 12.75 408 1.3233 0.2366 1.3233 1.1503
No log 12.8125 410 1.2235 0.2955 1.2235 1.1061
No log 12.875 412 1.1642 0.2686 1.1642 1.0790
No log 12.9375 414 1.1575 0.2313 1.1575 1.0759
No log 13.0 416 1.1783 0.2951 1.1783 1.0855
No log 13.0625 418 1.2772 0.2772 1.2772 1.1301
No log 13.125 420 1.4744 0.2701 1.4744 1.2142
No log 13.1875 422 1.5938 0.3209 1.5938 1.2625
No log 13.25 424 1.5587 0.2987 1.5587 1.2485
No log 13.3125 426 1.4008 0.2481 1.4008 1.1836
No log 13.375 428 1.2549 0.3383 1.2549 1.1202
No log 13.4375 430 1.2080 0.2735 1.2080 1.0991
No log 13.5 432 1.2194 0.2837 1.2194 1.1043
No log 13.5625 434 1.2795 0.2679 1.2795 1.1311
No log 13.625 436 1.3210 0.2549 1.3210 1.1494
No log 13.6875 438 1.2674 0.2679 1.2674 1.1258
No log 13.75 440 1.2318 0.3333 1.2318 1.1099
No log 13.8125 442 1.1965 0.3613 1.1965 1.0939
No log 13.875 444 1.1999 0.3232 1.1999 1.0954
No log 13.9375 446 1.1942 0.3232 1.1942 1.0928
No log 14.0 448 1.2120 0.3191 1.2120 1.1009
No log 14.0625 450 1.2671 0.2918 1.2671 1.1257
No log 14.125 452 1.2859 0.3003 1.2859 1.1340
No log 14.1875 454 1.2414 0.3068 1.2414 1.1142
No log 14.25 456 1.1398 0.2154 1.1398 1.0676
No log 14.3125 458 1.0750 0.2371 1.0750 1.0368
No log 14.375 460 1.0709 0.2371 1.0709 1.0348
No log 14.4375 462 1.1104 0.2810 1.1104 1.0538
No log 14.5 464 1.2507 0.3317 1.2507 1.1184
No log 14.5625 466 1.3613 0.3025 1.3613 1.1667
No log 14.625 468 1.3518 0.3210 1.3518 1.1627
No log 14.6875 470 1.2537 0.3088 1.2537 1.1197
No log 14.75 472 1.2060 0.2681 1.2060 1.0982
No log 14.8125 474 1.1454 0.2431 1.1454 1.0702
No log 14.875 476 1.1263 0.2591 1.1263 1.0613
No log 14.9375 478 1.1536 0.2955 1.1536 1.0740
No log 15.0 480 1.2320 0.3267 1.2320 1.1100
No log 15.0625 482 1.2350 0.3249 1.2350 1.1113
No log 15.125 484 1.2627 0.3590 1.2627 1.1237
No log 15.1875 486 1.2446 0.3528 1.2446 1.1156
No log 15.25 488 1.1887 0.3274 1.1887 1.0903
No log 15.3125 490 1.1062 0.3069 1.1062 1.0518
No log 15.375 492 1.0899 0.3548 1.0899 1.0440
No log 15.4375 494 1.0920 0.3548 1.0920 1.0450
No log 15.5 496 1.1436 0.2698 1.1436 1.0694
No log 15.5625 498 1.2740 0.2765 1.2740 1.1287
0.3664 15.625 500 1.3691 0.3416 1.3691 1.1701
0.3664 15.6875 502 1.3884 0.3047 1.3884 1.1783
0.3664 15.75 504 1.3110 0.1850 1.3110 1.1450
0.3664 15.8125 506 1.2443 0.1614 1.2443 1.1155
0.3664 15.875 508 1.1830 0.1562 1.1830 1.0876
0.3664 15.9375 510 1.1494 0.2313 1.1494 1.0721

Framework versions

  • Transformers 4.44.2
  • Pytorch 2.4.0+cu118
  • Datasets 2.21.0
  • Tokenizers 0.19.1
Downloads last month
2
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_usingWellWrittenEssays_FineTuningAraBERT_run2_AugV5_k11_task2_organization

Finetuned
(4019)
this model