ArabicNewSplits7_B_usingALLEssays_FineTuningAraBERT_run2_AugV5_k5_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: 1.2451
  • Qwk: 0.2302
  • Mse: 1.2451
  • Rmse: 1.1159

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 0.08 2 4.6119 0.0010 4.6119 2.1475
No log 0.16 4 2.5605 -0.0130 2.5605 1.6002
No log 0.24 6 1.7881 0.0062 1.7881 1.3372
No log 0.32 8 1.7678 0.0372 1.7678 1.3296
No log 0.4 10 1.3773 0.1315 1.3773 1.1736
No log 0.48 12 1.2003 0.1696 1.2003 1.0956
No log 0.56 14 1.3249 0.1371 1.3249 1.1510
No log 0.64 16 1.5401 0.0622 1.5401 1.2410
No log 0.72 18 1.4733 0.0898 1.4733 1.2138
No log 0.8 20 1.3406 0.0750 1.3406 1.1578
No log 0.88 22 1.1520 0.1904 1.1520 1.0733
No log 0.96 24 1.2774 0.1505 1.2774 1.1302
No log 1.04 26 1.8312 -0.0129 1.8312 1.3532
No log 1.12 28 1.7754 -0.0508 1.7754 1.3324
No log 1.2 30 1.3324 0.1112 1.3324 1.1543
No log 1.28 32 1.2793 0.1157 1.2793 1.1311
No log 1.3600 34 1.2705 0.1646 1.2705 1.1272
No log 1.44 36 1.3351 0.1050 1.3351 1.1555
No log 1.52 38 1.5431 0.0610 1.5431 1.2422
No log 1.6 40 1.8153 0.0568 1.8153 1.3473
No log 1.6800 42 1.7880 0.1525 1.7880 1.3372
No log 1.76 44 1.9967 0.1704 1.9967 1.4131
No log 1.8400 46 2.2902 0.0974 2.2902 1.5133
No log 1.92 48 2.3157 0.0974 2.3157 1.5217
No log 2.0 50 1.8623 0.1463 1.8623 1.3646
No log 2.08 52 1.5613 0.1150 1.5613 1.2495
No log 2.16 54 1.3132 0.2298 1.3132 1.1460
No log 2.24 56 1.2443 0.2081 1.2443 1.1155
No log 2.32 58 1.3114 0.1809 1.3114 1.1452
No log 2.4 60 1.2526 0.1638 1.2526 1.1192
No log 2.48 62 1.1939 0.1704 1.1939 1.0926
No log 2.56 64 1.1888 0.2092 1.1888 1.0903
No log 2.64 66 1.2196 0.3205 1.2196 1.1043
No log 2.7200 68 1.4090 0.0939 1.4090 1.1870
No log 2.8 70 1.5528 0.0624 1.5528 1.2461
No log 2.88 72 1.5294 0.1465 1.5294 1.2367
No log 2.96 74 1.3871 0.2795 1.3871 1.1777
No log 3.04 76 1.3630 0.2795 1.3630 1.1675
No log 3.12 78 1.3144 0.3186 1.3144 1.1465
No log 3.2 80 1.3074 0.2824 1.3074 1.1434
No log 3.2800 82 1.5252 0.1641 1.5252 1.2350
No log 3.36 84 1.9011 0.1066 1.9011 1.3788
No log 3.44 86 1.9794 0.1066 1.9794 1.4069
No log 3.52 88 1.6043 0.1657 1.6043 1.2666
No log 3.6 90 1.2942 0.1821 1.2942 1.1376
No log 3.68 92 1.2181 0.2527 1.2181 1.1037
No log 3.76 94 1.2498 0.2191 1.2498 1.1179
No log 3.84 96 1.3136 0.1347 1.3136 1.1461
No log 3.92 98 1.3677 0.1652 1.3677 1.1695
No log 4.0 100 1.3731 0.1865 1.3731 1.1718
No log 4.08 102 1.3475 0.2820 1.3475 1.1608
No log 4.16 104 1.4029 0.2353 1.4029 1.1844
No log 4.24 106 1.6060 0.1445 1.6060 1.2673
No log 4.32 108 1.5531 0.1471 1.5531 1.2463
No log 4.4 110 1.5259 0.1647 1.5259 1.2353
No log 4.48 112 1.3220 0.2845 1.3220 1.1498
No log 4.5600 114 1.3019 0.2629 1.3019 1.1410
No log 4.64 116 1.3314 0.2597 1.3314 1.1539
No log 4.72 118 1.3834 0.1831 1.3834 1.1762
No log 4.8 120 1.8363 0.1419 1.8363 1.3551
No log 4.88 122 1.8317 0.1276 1.8317 1.3534
No log 4.96 124 1.4694 0.0835 1.4694 1.2122
No log 5.04 126 1.4104 0.2488 1.4104 1.1876
No log 5.12 128 1.4849 0.2203 1.4849 1.2186
No log 5.2 130 1.7337 0.0676 1.7337 1.3167
No log 5.28 132 1.6440 0.0843 1.6440 1.2822
No log 5.36 134 1.5031 0.2528 1.5031 1.2260
No log 5.44 136 1.4733 0.1890 1.4733 1.2138
No log 5.52 138 1.4922 0.1315 1.4922 1.2216
No log 5.6 140 1.6283 0.1129 1.6283 1.2761
No log 5.68 142 1.5847 0.1129 1.5847 1.2588
No log 5.76 144 1.3523 0.2443 1.3523 1.1629
No log 5.84 146 1.2584 0.2700 1.2584 1.1218
No log 5.92 148 1.2657 0.2533 1.2657 1.1250
No log 6.0 150 1.3880 0.1781 1.3880 1.1782
No log 6.08 152 1.6214 0.1942 1.6214 1.2733
No log 6.16 154 1.7003 0.1297 1.7003 1.3040
No log 6.24 156 1.5446 0.2148 1.5446 1.2428
No log 6.32 158 1.3208 0.2150 1.3208 1.1493
No log 6.4 160 1.2662 0.2959 1.2662 1.1252
No log 6.48 162 1.2692 0.2616 1.2692 1.1266
No log 6.5600 164 1.4119 0.3105 1.4119 1.1882
No log 6.64 166 1.6137 0.1604 1.6137 1.2703
No log 6.72 168 1.5738 0.1718 1.5738 1.2545
No log 6.8 170 1.3712 0.2730 1.3712 1.1710
No log 6.88 172 1.3224 0.2996 1.3224 1.1500
No log 6.96 174 1.3550 0.2293 1.3550 1.1641
No log 7.04 176 1.3607 0.1588 1.3607 1.1665
No log 7.12 178 1.4113 0.1641 1.4113 1.1880
No log 7.2 180 1.3719 0.1849 1.3719 1.1713
No log 7.28 182 1.2276 0.2750 1.2276 1.1080
No log 7.36 184 1.1800 0.3303 1.1800 1.0863
No log 7.44 186 1.2159 0.3038 1.2159 1.1027
No log 7.52 188 1.3085 0.1620 1.3085 1.1439
No log 7.6 190 1.4611 0.2356 1.4611 1.2088
No log 7.68 192 1.4282 0.1986 1.4282 1.1951
No log 7.76 194 1.2716 0.3304 1.2716 1.1276
No log 7.84 196 1.2453 0.3304 1.2453 1.1159
No log 7.92 198 1.3462 0.1970 1.3462 1.1603
No log 8.0 200 1.3794 0.1507 1.3794 1.1745
No log 8.08 202 1.3728 0.1590 1.3728 1.1717
No log 8.16 204 1.4763 0.1578 1.4763 1.2150
No log 8.24 206 1.3076 0.1707 1.3076 1.1435
No log 8.32 208 1.1978 0.2972 1.1978 1.0945
No log 8.4 210 1.2091 0.2972 1.2091 1.0996
No log 8.48 212 1.4194 0.1525 1.4194 1.1914
No log 8.56 214 1.7081 0.1053 1.7081 1.3069
No log 8.64 216 1.5319 0.1024 1.5319 1.2377
No log 8.72 218 1.2221 0.1388 1.2221 1.1055
No log 8.8 220 1.1491 0.1732 1.1491 1.0719
No log 8.88 222 1.1435 0.2640 1.1435 1.0693
No log 8.96 224 1.2311 0.1210 1.2311 1.1095
No log 9.04 226 1.3653 0.2246 1.3653 1.1685
No log 9.12 228 1.3157 0.1972 1.3157 1.1471
No log 9.2 230 1.3121 0.1878 1.3121 1.1455
No log 9.28 232 1.2401 0.3103 1.2401 1.1136
No log 9.36 234 1.2447 0.2624 1.2447 1.1157
No log 9.44 236 1.2414 0.2747 1.2414 1.1142
No log 9.52 238 1.3194 0.1972 1.3194 1.1486
No log 9.6 240 1.3462 0.2331 1.3462 1.1603
No log 9.68 242 1.2283 0.2327 1.2283 1.1083
No log 9.76 244 1.1988 0.2647 1.1988 1.0949
No log 9.84 246 1.2290 0.2237 1.2290 1.1086
No log 9.92 248 1.2173 0.2556 1.2173 1.1033
No log 10.0 250 1.2522 0.2991 1.2522 1.1190
No log 10.08 252 1.3241 0.2544 1.3241 1.1507
No log 10.16 254 1.2466 0.2776 1.2466 1.1165
No log 10.24 256 1.1927 0.2526 1.1927 1.0921
No log 10.32 258 1.1947 0.2883 1.1947 1.0930
No log 10.4 260 1.1832 0.2995 1.1832 1.0878
No log 10.48 262 1.1799 0.2417 1.1799 1.0863
No log 10.56 264 1.1837 0.2851 1.1837 1.0880
No log 10.64 266 1.2301 0.3305 1.2301 1.1091
No log 10.72 268 1.1636 0.3133 1.1636 1.0787
No log 10.8 270 1.1336 0.2417 1.1336 1.0647
No log 10.88 272 1.1660 0.3191 1.1660 1.0798
No log 10.96 274 1.2234 0.3017 1.2234 1.1061
No log 11.04 276 1.3091 0.2891 1.3091 1.1442
No log 11.12 278 1.3194 0.2288 1.3194 1.1487
No log 11.2 280 1.2201 0.2803 1.2201 1.1046
No log 11.28 282 1.1696 0.3661 1.1696 1.0815
No log 11.36 284 1.1663 0.2417 1.1663 1.0800
No log 11.44 286 1.2655 0.2296 1.2655 1.1249
No log 11.52 288 1.3287 0.2162 1.3287 1.1527
No log 11.6 290 1.2539 0.2296 1.2539 1.1198
No log 11.68 292 1.2302 0.2249 1.2302 1.1092
No log 11.76 294 1.2088 0.2572 1.2088 1.0995
No log 11.84 296 1.1886 0.2927 1.1886 1.0902
No log 11.92 298 1.2337 0.2531 1.2337 1.1107
No log 12.0 300 1.2806 0.2069 1.2806 1.1316
No log 12.08 302 1.2920 0.2069 1.2920 1.1366
No log 12.16 304 1.2466 0.2225 1.2466 1.1165
No log 12.24 306 1.2098 0.2820 1.2098 1.0999
No log 12.32 308 1.2145 0.2820 1.2145 1.1020
No log 12.4 310 1.2759 0.2006 1.2759 1.1295
No log 12.48 312 1.3769 0.2378 1.3769 1.1734
No log 12.56 314 1.5487 0.1774 1.5487 1.2445
No log 12.64 316 1.5942 0.1673 1.5942 1.2626
No log 12.72 318 1.4996 0.2660 1.4996 1.2246
No log 12.8 320 1.3490 0.1988 1.3490 1.1615
No log 12.88 322 1.2276 0.2633 1.2276 1.1080
No log 12.96 324 1.2010 0.2523 1.2010 1.0959
No log 13.04 326 1.1887 0.2239 1.1887 1.0903
No log 13.12 328 1.1749 0.2694 1.1749 1.0839
No log 13.2 330 1.1833 0.2902 1.1833 1.0878
No log 13.28 332 1.1564 0.2694 1.1564 1.0754
No log 13.36 334 1.1204 0.2703 1.1204 1.0585
No log 13.44 336 1.1169 0.2950 1.1169 1.0568
No log 13.52 338 1.1350 0.2331 1.1350 1.0654
No log 13.6 340 1.2111 0.2458 1.2111 1.1005
No log 13.68 342 1.3303 0.2378 1.3303 1.1534
No log 13.76 344 1.4193 0.2304 1.4193 1.1913
No log 13.84 346 1.3500 0.2366 1.3500 1.1619
No log 13.92 348 1.2633 0.2952 1.2633 1.1240
No log 14.0 350 1.2569 0.2634 1.2569 1.1211
No log 14.08 352 1.2395 0.2198 1.2395 1.1134
No log 14.16 354 1.2368 0.2198 1.2368 1.1121
No log 14.24 356 1.2534 0.1928 1.2534 1.1195
No log 14.32 358 1.3055 0.2361 1.3055 1.1426
No log 14.4 360 1.4205 0.2807 1.4205 1.1919
No log 14.48 362 1.3996 0.2570 1.3996 1.1831
No log 14.56 364 1.2815 0.1885 1.2815 1.1320
No log 14.64 366 1.2079 0.3017 1.2079 1.0990
No log 14.72 368 1.2169 0.2684 1.2169 1.1031
No log 14.8 370 1.2202 0.2767 1.2202 1.1046
No log 14.88 372 1.2085 0.2931 1.2085 1.0993
No log 14.96 374 1.2181 0.2911 1.2181 1.1037
No log 15.04 376 1.2030 0.2995 1.2030 1.0968
No log 15.12 378 1.2203 0.2588 1.2203 1.1047
No log 15.2 380 1.2143 0.2877 1.2143 1.1020
No log 15.28 382 1.2224 0.2556 1.2224 1.1056
No log 15.36 384 1.1905 0.2012 1.1905 1.0911
No log 15.44 386 1.2236 0.2021 1.2236 1.1062
No log 15.52 388 1.2610 0.1751 1.2610 1.1229
No log 15.6 390 1.2285 0.2556 1.2285 1.1084
No log 15.68 392 1.2074 0.2618 1.2074 1.0988
No log 15.76 394 1.2376 0.2604 1.2376 1.1125
No log 15.84 396 1.2616 0.2710 1.2616 1.1232
No log 15.92 398 1.2463 0.2550 1.2463 1.1164
No log 16.0 400 1.1538 0.3353 1.1538 1.0742
No log 16.08 402 1.1376 0.2877 1.1376 1.0666
No log 16.16 404 1.1805 0.2395 1.1805 1.0865
No log 16.24 406 1.1893 0.2395 1.1893 1.0905
No log 16.32 408 1.1797 0.2664 1.1797 1.0861
No log 16.4 410 1.1771 0.2877 1.1771 1.0849
No log 16.48 412 1.2115 0.3014 1.2115 1.1007
No log 16.56 414 1.2322 0.3486 1.2322 1.1100
No log 16.64 416 1.2636 0.3486 1.2636 1.1241
No log 16.72 418 1.3086 0.2247 1.3086 1.1439
No log 16.8 420 1.3221 0.2169 1.3221 1.1498
No log 16.88 422 1.2680 0.1975 1.2680 1.1261
No log 16.96 424 1.2585 0.1824 1.2585 1.1218
No log 17.04 426 1.2774 0.2210 1.2774 1.1302
No log 17.12 428 1.2637 0.2108 1.2637 1.1242
No log 17.2 430 1.3012 0.2108 1.3012 1.1407
No log 17.28 432 1.3170 0.2389 1.3170 1.1476
No log 17.36 434 1.3071 0.2209 1.3071 1.1433
No log 17.44 436 1.2721 0.2340 1.2721 1.1279
No log 17.52 438 1.2554 0.2812 1.2554 1.1205
No log 17.6 440 1.2191 0.3186 1.2191 1.1041
No log 17.68 442 1.2108 0.2995 1.2108 1.1003
No log 17.76 444 1.2325 0.2485 1.2325 1.1102
No log 17.84 446 1.3251 0.2078 1.3251 1.1511
No log 17.92 448 1.3199 0.1891 1.3199 1.1489
No log 18.0 450 1.2982 0.2472 1.2982 1.1394
No log 18.08 452 1.3780 0.1716 1.3780 1.1739
No log 18.16 454 1.3496 0.2072 1.3496 1.1617
No log 18.24 456 1.3933 0.1986 1.3933 1.1804
No log 18.32 458 1.4208 0.1490 1.4208 1.1920
No log 18.4 460 1.3867 0.1578 1.3867 1.1776
No log 18.48 462 1.3238 0.1702 1.3238 1.1506
No log 18.56 464 1.3017 0.2249 1.3017 1.1409
No log 18.64 466 1.3014 0.2249 1.3014 1.1408
No log 18.72 468 1.2604 0.2239 1.2604 1.1227
No log 18.8 470 1.2373 0.1914 1.2373 1.1123
No log 18.88 472 1.2494 0.2006 1.2494 1.1178
No log 18.96 474 1.2437 0.2006 1.2437 1.1152
No log 19.04 476 1.3085 0.2198 1.3085 1.1439
No log 19.12 478 1.2517 0.2358 1.2517 1.1188
No log 19.2 480 1.1886 0.2995 1.1886 1.0902
No log 19.28 482 1.1657 0.2194 1.1657 1.0797
No log 19.36 484 1.1682 0.3418 1.1682 1.0808
No log 19.44 486 1.2594 0.2060 1.2594 1.1222
No log 19.52 488 1.3364 0.2293 1.3364 1.1560
No log 19.6 490 1.3200 0.2839 1.3200 1.1489
No log 19.68 492 1.2205 0.1966 1.2205 1.1048
No log 19.76 494 1.1481 0.3059 1.1481 1.0715
No log 19.84 496 1.1478 0.3059 1.1478 1.0714
No log 19.92 498 1.1888 0.2376 1.1888 1.0903
0.3213 20.0 500 1.2718 0.2654 1.2718 1.1277
0.3213 20.08 502 1.2925 0.2896 1.2925 1.1369
0.3213 20.16 504 1.2454 0.2851 1.2454 1.1160
0.3213 20.24 506 1.2032 0.2353 1.2032 1.0969
0.3213 20.32 508 1.1564 0.1637 1.1564 1.0753
0.3213 20.4 510 1.1518 0.2907 1.1518 1.0732
0.3213 20.48 512 1.1613 0.2516 1.1613 1.0777
0.3213 20.56 514 1.2483 0.2438 1.2483 1.1173
0.3213 20.64 516 1.4459 0.2468 1.4459 1.2025
0.3213 20.72 518 1.5142 0.2191 1.5142 1.2305
0.3213 20.8 520 1.3878 0.2772 1.3878 1.1780
0.3213 20.88 522 1.2209 0.2249 1.2209 1.1049
0.3213 20.96 524 1.1561 0.2731 1.1561 1.0752
0.3213 21.04 526 1.1629 0.2913 1.1629 1.0784
0.3213 21.12 528 1.1631 0.3001 1.1631 1.0785
0.3213 21.2 530 1.1291 0.3219 1.1291 1.0626
0.3213 21.28 532 1.1269 0.2157 1.1269 1.0616
0.3213 21.36 534 1.2085 0.2871 1.2085 1.0993
0.3213 21.44 536 1.2968 0.3031 1.2968 1.1388
0.3213 21.52 538 1.3067 0.3052 1.3067 1.1431
0.3213 21.6 540 1.2572 0.2446 1.2572 1.1212
0.3213 21.68 542 1.2084 0.1500 1.2084 1.0993
0.3213 21.76 544 1.1906 0.1498 1.1906 1.0912
0.3213 21.84 546 1.2029 0.1817 1.2029 1.0968
0.3213 21.92 548 1.2451 0.2302 1.2451 1.1159

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_run2_AugV5_k5_task2_organization

Finetuned
(4032)
this model