ArabicNewSplits7_B_usingALLEssays_FineTuningAraBERT_run3_AugV5_k12_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: 1.2536
  • Qwk: 0.2320
  • Mse: 1.2536
  • Rmse: 1.1197

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 0.0333 2 4.7559 -0.0132 4.7559 2.1808
No log 0.0667 4 2.9043 0.0140 2.9043 1.7042
No log 0.1 6 1.9972 -0.0298 1.9972 1.4132
No log 0.1333 8 2.6096 -0.0524 2.6096 1.6154
No log 0.1667 10 2.1341 -0.0885 2.1341 1.4609
No log 0.2 12 1.4183 0.0269 1.4183 1.1909
No log 0.2333 14 1.3033 0.0324 1.3033 1.1416
No log 0.2667 16 1.3811 0.0990 1.3811 1.1752
No log 0.3 18 2.1906 0.0627 2.1906 1.4801
No log 0.3333 20 2.4760 -0.0185 2.4760 1.5735
No log 0.3667 22 1.7796 0.0810 1.7796 1.3340
No log 0.4 24 1.3484 0.1921 1.3484 1.1612
No log 0.4333 26 1.1724 0.3210 1.1724 1.0828
No log 0.4667 28 1.1462 0.2815 1.1462 1.0706
No log 0.5 30 1.1432 0.1912 1.1432 1.0692
No log 0.5333 32 1.1784 0.2263 1.1784 1.0856
No log 0.5667 34 1.4175 0.2065 1.4175 1.1906
No log 0.6 36 1.9074 0.1722 1.9074 1.3811
No log 0.6333 38 2.5955 0.0648 2.5955 1.6110
No log 0.6667 40 2.6703 0.0862 2.6703 1.6341
No log 0.7 42 2.0575 0.0874 2.0575 1.4344
No log 0.7333 44 1.5032 0.2225 1.5032 1.2260
No log 0.7667 46 1.3598 0.2604 1.3598 1.1661
No log 0.8 48 1.3950 0.2773 1.3950 1.1811
No log 0.8333 50 1.4450 0.2272 1.4450 1.2021
No log 0.8667 52 1.4545 0.2191 1.4545 1.2060
No log 0.9 54 1.4235 0.2321 1.4235 1.1931
No log 0.9333 56 1.4961 0.2663 1.4961 1.2231
No log 0.9667 58 1.5016 0.2286 1.5016 1.2254
No log 1.0 60 1.4625 0.2015 1.4625 1.2093
No log 1.0333 62 1.4430 0.2329 1.4430 1.2013
No log 1.0667 64 1.5355 0.0821 1.5355 1.2392
No log 1.1 66 1.6691 0.1225 1.6691 1.2920
No log 1.1333 68 1.7083 0.1511 1.7083 1.3070
No log 1.1667 70 1.5738 0.2650 1.5738 1.2545
No log 1.2 72 1.5806 0.2576 1.5806 1.2572
No log 1.2333 74 1.7612 0.2312 1.7612 1.3271
No log 1.2667 76 2.0601 0.1416 2.0601 1.4353
No log 1.3 78 2.0520 0.1133 2.0520 1.4325
No log 1.3333 80 1.5173 0.2430 1.5173 1.2318
No log 1.3667 82 1.2303 0.1972 1.2303 1.1092
No log 1.4 84 1.2136 0.1693 1.2136 1.1016
No log 1.4333 86 1.2792 0.1898 1.2792 1.1310
No log 1.4667 88 1.4874 0.2317 1.4874 1.2196
No log 1.5 90 1.6291 0.2493 1.6291 1.2764
No log 1.5333 92 2.2571 0.1318 2.2571 1.5024
No log 1.5667 94 2.3780 0.1331 2.3780 1.5421
No log 1.6 96 1.8138 0.1983 1.8138 1.3468
No log 1.6333 98 1.2968 0.3314 1.2968 1.1388
No log 1.6667 100 1.2404 0.2576 1.2404 1.1137
No log 1.7 102 1.2777 0.3568 1.2777 1.1303
No log 1.7333 104 1.4227 0.2237 1.4227 1.1928
No log 1.7667 106 1.7647 0.1941 1.7647 1.3284
No log 1.8 108 1.8418 0.1672 1.8418 1.3571
No log 1.8333 110 1.6473 0.2150 1.6473 1.2835
No log 1.8667 112 1.4329 0.2822 1.4329 1.1970
No log 1.9 114 1.5487 0.2130 1.5487 1.2445
No log 1.9333 116 1.6653 0.2377 1.6653 1.2905
No log 1.9667 118 1.8522 0.1438 1.8522 1.3609
No log 2.0 120 1.7028 0.2138 1.7028 1.3049
No log 2.0333 122 1.5144 0.1288 1.5144 1.2306
No log 2.0667 124 1.3968 0.0494 1.3968 1.1819
No log 2.1 126 1.3653 0.0820 1.3653 1.1685
No log 2.1333 128 1.4885 0.1394 1.4885 1.2201
No log 2.1667 130 1.5901 0.1609 1.5901 1.2610
No log 2.2 132 1.4645 0.1394 1.4645 1.2102
No log 2.2333 134 1.4462 0.1460 1.4462 1.2026
No log 2.2667 136 1.4900 0.1539 1.4900 1.2207
No log 2.3 138 1.6623 0.2131 1.6623 1.2893
No log 2.3333 140 1.6020 0.1752 1.6020 1.2657
No log 2.3667 142 1.4022 0.1929 1.4022 1.1842
No log 2.4 144 1.3910 0.2472 1.3910 1.1794
No log 2.4333 146 1.3489 0.2015 1.3489 1.1614
No log 2.4667 148 1.3366 0.3126 1.3366 1.1561
No log 2.5 150 1.6796 0.1881 1.6796 1.2960
No log 2.5333 152 1.7377 0.1776 1.7377 1.3182
No log 2.5667 154 1.4069 0.1394 1.4069 1.1861
No log 2.6 156 1.2578 0.2404 1.2578 1.1215
No log 2.6333 158 1.2437 0.1533 1.2437 1.1152
No log 2.6667 160 1.3137 0.2501 1.3137 1.1462
No log 2.7 162 1.6118 0.1872 1.6118 1.2696
No log 2.7333 164 1.6542 0.2073 1.6542 1.2862
No log 2.7667 166 1.4342 0.1564 1.4342 1.1976
No log 2.8 168 1.2838 0.3441 1.2838 1.1331
No log 2.8333 170 1.2986 0.2845 1.2986 1.1396
No log 2.8667 172 1.3591 0.2480 1.3591 1.1658
No log 2.9 174 1.5319 0.1871 1.5319 1.2377
No log 2.9333 176 1.4792 0.1968 1.4792 1.2162
No log 2.9667 178 1.2755 0.3011 1.2755 1.1294
No log 3.0 180 1.2428 0.3080 1.2428 1.1148
No log 3.0333 182 1.3201 0.2515 1.3201 1.1489
No log 3.0667 184 1.4470 0.2295 1.4470 1.2029
No log 3.1 186 1.4686 0.2370 1.4686 1.2119
No log 3.1333 188 1.4254 0.3085 1.4254 1.1939
No log 3.1667 190 1.3984 0.3085 1.3984 1.1826
No log 3.2 192 1.3065 0.2812 1.3065 1.1430
No log 3.2333 194 1.3033 0.2991 1.3033 1.1416
No log 3.2667 196 1.3812 0.2685 1.3812 1.1752
No log 3.3 198 1.3690 0.3265 1.3690 1.1700
No log 3.3333 200 1.2397 0.3789 1.2397 1.1134
No log 3.3667 202 1.2129 0.3262 1.2129 1.1013
No log 3.4 204 1.3209 0.2570 1.3209 1.1493
No log 3.4333 206 1.2693 0.2640 1.2693 1.1266
No log 3.4667 208 1.2335 0.3056 1.2335 1.1106
No log 3.5 210 1.2382 0.3305 1.2382 1.1127
No log 3.5333 212 1.3019 0.3131 1.3019 1.1410
No log 3.5667 214 1.2820 0.3027 1.2820 1.1323
No log 3.6 216 1.3147 0.3889 1.3147 1.1466
No log 3.6333 218 1.5354 0.2241 1.5354 1.2391
No log 3.6667 220 1.5128 0.2900 1.5128 1.2299
No log 3.7 222 1.3110 0.3566 1.3110 1.1450
No log 3.7333 224 1.2291 0.3990 1.2291 1.1086
No log 3.7667 226 1.3192 0.3304 1.3192 1.1486
No log 3.8 228 1.6009 0.2475 1.6009 1.2653
No log 3.8333 230 1.5578 0.2396 1.5578 1.2481
No log 3.8667 232 1.2315 0.3009 1.2315 1.1097
No log 3.9 234 1.1325 0.3736 1.1325 1.0642
No log 3.9333 236 1.0965 0.2857 1.0965 1.0471
No log 3.9667 238 1.1035 0.3130 1.1035 1.0505
No log 4.0 240 1.2267 0.2946 1.2267 1.1076
No log 4.0333 242 1.4223 0.2663 1.4223 1.1926
No log 4.0667 244 1.4499 0.2663 1.4499 1.2041
No log 4.1 246 1.3372 0.3478 1.3372 1.1564
No log 4.1333 248 1.2399 0.3393 1.2399 1.1135
No log 4.1667 250 1.1816 0.3893 1.1816 1.0870
No log 4.2 252 1.1799 0.3505 1.1799 1.0862
No log 4.2333 254 1.2019 0.2857 1.2019 1.0963
No log 4.2667 256 1.1465 0.3490 1.1465 1.0708
No log 4.3 258 1.0992 0.3661 1.0992 1.0484
No log 4.3333 260 1.1007 0.3979 1.1007 1.0491
No log 4.3667 262 1.0779 0.3664 1.0779 1.0382
No log 4.4 264 1.0674 0.3311 1.0674 1.0331
No log 4.4333 266 1.2099 0.3243 1.2099 1.1000
No log 4.4667 268 1.3215 0.3243 1.3215 1.1496
No log 4.5 270 1.2037 0.2832 1.2037 1.0971
No log 4.5333 272 1.0924 0.3966 1.0924 1.0452
No log 4.5667 274 1.1373 0.3469 1.1373 1.0665
No log 4.6 276 1.1305 0.3289 1.1305 1.0632
No log 4.6333 278 1.1946 0.4276 1.1946 1.0930
No log 4.6667 280 1.4837 0.2614 1.4837 1.2181
No log 4.7 282 1.6051 0.2069 1.6051 1.2669
No log 4.7333 284 1.3875 0.2947 1.3875 1.1779
No log 4.7667 286 1.1669 0.3819 1.1669 1.0802
No log 4.8 288 1.1562 0.4084 1.1562 1.0752
No log 4.8333 290 1.1609 0.3480 1.1609 1.0775
No log 4.8667 292 1.1727 0.3119 1.1727 1.0829
No log 4.9 294 1.1766 0.2605 1.1766 1.0847
No log 4.9333 296 1.1302 0.2169 1.1302 1.0631
No log 4.9667 298 1.0736 0.3275 1.0736 1.0361
No log 5.0 300 1.0720 0.2898 1.0720 1.0354
No log 5.0333 302 1.1023 0.3062 1.1023 1.0499
No log 5.0667 304 1.1868 0.2876 1.1868 1.0894
No log 5.1 306 1.2582 0.2702 1.2582 1.1217
No log 5.1333 308 1.2996 0.2418 1.2996 1.1400
No log 5.1667 310 1.3115 0.2387 1.3115 1.1452
No log 5.2 312 1.1562 0.2624 1.1562 1.0753
No log 5.2333 314 1.0772 0.3180 1.0772 1.0379
No log 5.2667 316 1.1012 0.3648 1.1012 1.0494
No log 5.3 318 1.2440 0.3368 1.2440 1.1154
No log 5.3333 320 1.3085 0.3665 1.3085 1.1439
No log 5.3667 322 1.2151 0.2987 1.2151 1.1023
No log 5.4 324 1.2326 0.2881 1.2326 1.1102
No log 5.4333 326 1.3631 0.3318 1.3631 1.1675
No log 5.4667 328 1.3309 0.3765 1.3309 1.1536
No log 5.5 330 1.3124 0.3765 1.3124 1.1456
No log 5.5333 332 1.2493 0.3354 1.2493 1.1177
No log 5.5667 334 1.1440 0.3174 1.1440 1.0696
No log 5.6 336 1.1273 0.3174 1.1273 1.0618
No log 5.6333 338 1.1781 0.2593 1.1781 1.0854
No log 5.6667 340 1.3090 0.2899 1.3090 1.1441
No log 5.7 342 1.3379 0.2678 1.3379 1.1567
No log 5.7333 344 1.2263 0.3494 1.2263 1.1074
No log 5.7667 346 1.1949 0.3805 1.1949 1.0931
No log 5.8 348 1.2287 0.3494 1.2287 1.1085
No log 5.8333 350 1.3645 0.2836 1.3645 1.1681
No log 5.8667 352 1.4936 0.3074 1.4936 1.2221
No log 5.9 354 1.3700 0.2880 1.3700 1.1705
No log 5.9333 356 1.1671 0.3126 1.1671 1.0803
No log 5.9667 358 1.1076 0.3062 1.1076 1.0524
No log 6.0 360 1.1102 0.2871 1.1102 1.0537
No log 6.0333 362 1.1947 0.2374 1.1947 1.0930
No log 6.0667 364 1.3200 0.2191 1.3200 1.1489
No log 6.1 366 1.3502 0.2146 1.3502 1.1620
No log 6.1333 368 1.2258 0.3249 1.2258 1.1072
No log 6.1667 370 1.1761 0.2424 1.1761 1.0845
No log 6.2 372 1.1532 0.2198 1.1532 1.0739
No log 6.2333 374 1.1399 0.2616 1.1399 1.0677
No log 6.2667 376 1.1643 0.1920 1.1643 1.0790
No log 6.3 378 1.2736 0.1950 1.2736 1.1285
No log 6.3333 380 1.3138 0.2053 1.3138 1.1462
No log 6.3667 382 1.2179 0.1505 1.2179 1.1036
No log 6.4 384 1.1488 0.1630 1.1488 1.0718
No log 6.4333 386 1.1193 0.2629 1.1193 1.0580
No log 6.4667 388 1.1397 0.1866 1.1397 1.0676
No log 6.5 390 1.2100 0.2472 1.2100 1.1000
No log 6.5333 392 1.2947 0.2208 1.2947 1.1378
No log 6.5667 394 1.3248 0.2685 1.3248 1.1510
No log 6.6 396 1.2411 0.2431 1.2411 1.1141
No log 6.6333 398 1.1561 0.2803 1.1561 1.0752
No log 6.6667 400 1.1225 0.3412 1.1225 1.0595
No log 6.7 402 1.0979 0.2625 1.0979 1.0478
No log 6.7333 404 1.0822 0.1903 1.0822 1.0403
No log 6.7667 406 1.0924 0.1671 1.0924 1.0452
No log 6.8 408 1.1245 0.2572 1.1245 1.0604
No log 6.8333 410 1.1849 0.2501 1.1849 1.0885
No log 6.8667 412 1.2831 0.2498 1.2831 1.1327
No log 6.9 414 1.4214 0.2541 1.4214 1.1922
No log 6.9333 416 1.5694 0.2632 1.5694 1.2528
No log 6.9667 418 1.4187 0.2103 1.4187 1.1911
No log 7.0 420 1.2308 0.3189 1.2308 1.1094
No log 7.0333 422 1.1352 0.3174 1.1352 1.0655
No log 7.0667 424 1.0951 0.3174 1.0951 1.0465
No log 7.1 426 1.1152 0.1748 1.1152 1.0560
No log 7.1333 428 1.2060 0.2058 1.2060 1.0982
No log 7.1667 430 1.1746 0.2058 1.1746 1.0838
No log 7.2 432 1.0781 0.2261 1.0781 1.0383
No log 7.2333 434 1.0955 0.2667 1.0955 1.0466
No log 7.2667 436 1.1603 0.2451 1.1603 1.0772
No log 7.3 438 1.1561 0.2417 1.1561 1.0752
No log 7.3333 440 1.0396 0.3081 1.0396 1.0196
No log 7.3667 442 1.0066 0.3596 1.0066 1.0033
No log 7.4 444 1.0247 0.3406 1.0247 1.0123
No log 7.4333 446 1.1599 0.2565 1.1599 1.0770
No log 7.4667 448 1.2056 0.2062 1.2056 1.0980
No log 7.5 450 1.1531 0.2098 1.1531 1.0738
No log 7.5333 452 1.1070 0.2088 1.1070 1.0521
No log 7.5667 454 1.0529 0.3250 1.0529 1.0261
No log 7.6 456 1.0655 0.2824 1.0655 1.0322
No log 7.6333 458 1.1604 0.2673 1.1604 1.0772
No log 7.6667 460 1.2056 0.2941 1.2056 1.0980
No log 7.7 462 1.1376 0.3812 1.1376 1.0666
No log 7.7333 464 1.1002 0.4157 1.1002 1.0489
No log 7.7667 466 1.0673 0.4299 1.0673 1.0331
No log 7.8 468 1.0723 0.4123 1.0723 1.0355
No log 7.8333 470 1.1029 0.3768 1.1029 1.0502
No log 7.8667 472 1.1154 0.3856 1.1154 1.0561
No log 7.9 474 1.1645 0.3339 1.1645 1.0791
No log 7.9333 476 1.1372 0.3506 1.1372 1.0664
No log 7.9667 478 1.1072 0.3355 1.1072 1.0522
No log 8.0 480 1.0609 0.2918 1.0609 1.0300
No log 8.0333 482 1.0606 0.2410 1.0606 1.0299
No log 8.0667 484 1.0929 0.2075 1.0929 1.0454
No log 8.1 486 1.1543 0.2760 1.1543 1.0744
No log 8.1333 488 1.1674 0.3095 1.1674 1.0805
No log 8.1667 490 1.2413 0.3004 1.2413 1.1141
No log 8.2 492 1.3679 0.3238 1.3679 1.1696
No log 8.2333 494 1.3855 0.3340 1.3855 1.1771
No log 8.2667 496 1.3745 0.3024 1.3745 1.1724
No log 8.3 498 1.4096 0.3064 1.4096 1.1873
0.3367 8.3333 500 1.3148 0.3024 1.3148 1.1467
0.3367 8.3667 502 1.1513 0.2920 1.1513 1.0730
0.3367 8.4 504 1.0709 0.2897 1.0709 1.0348
0.3367 8.4333 506 1.0670 0.2850 1.0670 1.0330
0.3367 8.4667 508 1.0614 0.3039 1.0614 1.0302
0.3367 8.5 510 1.0733 0.2966 1.0733 1.0360
0.3367 8.5333 512 1.1442 0.3010 1.1442 1.0697
0.3367 8.5667 514 1.2944 0.2229 1.2944 1.1377
0.3367 8.6 516 1.3239 0.2277 1.3239 1.1506
0.3367 8.6333 518 1.2536 0.2320 1.2536 1.1197

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_k12_task2_organization

Finetuned
(4019)
this model