ArabicNewSplits8_usingALLEssays_FineTuningAraBERT_run1_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: 1.6486
  • Qwk: 0.2433
  • Mse: 1.6486
  • Rmse: 1.2840

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 8.3066 0.0050 8.3066 2.8821
No log 0.6667 4 5.1206 0.0115 5.1206 2.2629
No log 1.0 6 2.4864 0.0960 2.4864 1.5768
No log 1.3333 8 1.5159 0.1355 1.5159 1.2312
No log 1.6667 10 1.2288 0.1771 1.2288 1.1085
No log 2.0 12 1.4402 0.1475 1.4402 1.2001
No log 2.3333 14 1.7516 0.1808 1.7516 1.3235
No log 2.6667 16 1.8846 0.1728 1.8846 1.3728
No log 3.0 18 1.6326 0.0330 1.6326 1.2777
No log 3.3333 20 1.6284 0.1504 1.6284 1.2761
No log 3.6667 22 2.1309 0.1780 2.1309 1.4598
No log 4.0 24 1.8962 0.1066 1.8962 1.3770
No log 4.3333 26 1.8451 0.1920 1.8451 1.3583
No log 4.6667 28 1.6229 0.2375 1.6229 1.2739
No log 5.0 30 1.3973 0.1792 1.3973 1.1821
No log 5.3333 32 1.4129 0.1083 1.4129 1.1887
No log 5.6667 34 1.4759 0.1867 1.4759 1.2149
No log 6.0 36 1.6011 0.3023 1.6011 1.2654
No log 6.3333 38 1.5178 0.2936 1.5178 1.2320
No log 6.6667 40 1.4251 0.2603 1.4251 1.1938
No log 7.0 42 1.2616 0.2777 1.2616 1.1232
No log 7.3333 44 1.2925 0.2556 1.2925 1.1369
No log 7.6667 46 1.2834 0.2917 1.2834 1.1329
No log 8.0 48 1.3280 0.2683 1.3280 1.1524
No log 8.3333 50 1.3269 0.2518 1.3269 1.1519
No log 8.6667 52 1.4256 0.2370 1.4256 1.1940
No log 9.0 54 1.6870 0.3085 1.6870 1.2989
No log 9.3333 56 1.8969 0.2327 1.8969 1.3773
No log 9.6667 58 1.8830 0.2665 1.8830 1.3722
No log 10.0 60 1.9572 0.2665 1.9572 1.3990
No log 10.3333 62 2.1038 0.2584 2.1038 1.4505
No log 10.6667 64 1.8760 0.2406 1.8760 1.3697
No log 11.0 66 1.5453 0.2458 1.5453 1.2431
No log 11.3333 68 1.5914 0.2346 1.5914 1.2615
No log 11.6667 70 1.8175 0.3016 1.8175 1.3482
No log 12.0 72 1.7932 0.2991 1.7932 1.3391
No log 12.3333 74 1.6931 0.2272 1.6931 1.3012
No log 12.6667 76 1.4352 0.2226 1.4352 1.1980
No log 13.0 78 1.4628 0.2586 1.4628 1.2095
No log 13.3333 80 1.7513 0.2976 1.7513 1.3234
No log 13.6667 82 1.8024 0.2687 1.8024 1.3425
No log 14.0 84 1.6799 0.3296 1.6799 1.2961
No log 14.3333 86 1.5620 0.3245 1.5620 1.2498
No log 14.6667 88 1.6688 0.2930 1.6688 1.2918
No log 15.0 90 1.7903 0.2742 1.7903 1.3380
No log 15.3333 92 1.7862 0.2586 1.7862 1.3365
No log 15.6667 94 1.6999 0.2466 1.6999 1.3038
No log 16.0 96 1.5324 0.2409 1.5324 1.2379
No log 16.3333 98 1.5735 0.2283 1.5735 1.2544
No log 16.6667 100 1.8382 0.2742 1.8382 1.3558
No log 17.0 102 1.9215 0.2719 1.9215 1.3862
No log 17.3333 104 1.7492 0.2701 1.7492 1.3226
No log 17.6667 106 1.8052 0.2939 1.8052 1.3436
No log 18.0 108 1.6735 0.2607 1.6735 1.2936
No log 18.3333 110 1.6761 0.2681 1.6761 1.2947
No log 18.6667 112 1.5923 0.2833 1.5923 1.2618
No log 19.0 114 1.4100 0.2803 1.4100 1.1874
No log 19.3333 116 1.4769 0.2755 1.4769 1.2153
No log 19.6667 118 1.6079 0.2541 1.6079 1.2680
No log 20.0 120 1.6602 0.2681 1.6602 1.2885
No log 20.3333 122 1.6270 0.2711 1.6270 1.2756
No log 20.6667 124 1.9001 0.2824 1.9001 1.3784
No log 21.0 126 2.0512 0.2916 2.0512 1.4322
No log 21.3333 128 1.7339 0.2691 1.7339 1.3168
No log 21.6667 130 1.6267 0.2291 1.6267 1.2754
No log 22.0 132 1.8455 0.2585 1.8455 1.3585
No log 22.3333 134 2.0715 0.2573 2.0715 1.4393
No log 22.6667 136 1.9094 0.2814 1.9094 1.3818
No log 23.0 138 1.7350 0.2954 1.7350 1.3172
No log 23.3333 140 1.5170 0.3032 1.5170 1.2317
No log 23.6667 142 1.4387 0.3067 1.4387 1.1995
No log 24.0 144 1.4775 0.3168 1.4775 1.2155
No log 24.3333 146 1.7120 0.2955 1.7120 1.3084
No log 24.6667 148 1.7991 0.2756 1.7991 1.3413
No log 25.0 150 1.6629 0.2478 1.6629 1.2895
No log 25.3333 152 1.5602 0.2543 1.5602 1.2491
No log 25.6667 154 1.4712 0.3220 1.4712 1.2129
No log 26.0 156 1.5588 0.2598 1.5588 1.2485
No log 26.3333 158 1.8259 0.2870 1.8259 1.3512
No log 26.6667 160 2.1772 0.2828 2.1772 1.4755
No log 27.0 162 2.3033 0.2646 2.3033 1.5177
No log 27.3333 164 1.9980 0.2834 1.9980 1.4135
No log 27.6667 166 1.8518 0.3024 1.8518 1.3608
No log 28.0 168 1.6472 0.2801 1.6472 1.2834
No log 28.3333 170 1.5543 0.2888 1.5543 1.2467
No log 28.6667 172 1.5965 0.2947 1.5965 1.2635
No log 29.0 174 1.5220 0.3088 1.5220 1.2337
No log 29.3333 176 1.5327 0.3088 1.5327 1.2380
No log 29.6667 178 1.6623 0.2800 1.6623 1.2893
No log 30.0 180 1.7859 0.2887 1.7859 1.3364
No log 30.3333 182 1.8394 0.2887 1.8394 1.3562
No log 30.6667 184 1.7612 0.2943 1.7612 1.3271
No log 31.0 186 1.5039 0.2887 1.5039 1.2263
No log 31.3333 188 1.4680 0.2945 1.4680 1.2116
No log 31.6667 190 1.5725 0.2823 1.5725 1.2540
No log 32.0 192 1.8773 0.2615 1.8773 1.3702
No log 32.3333 194 1.9694 0.2653 1.9694 1.4033
No log 32.6667 196 1.8818 0.2687 1.8818 1.3718
No log 33.0 198 1.5406 0.2795 1.5406 1.2412
No log 33.3333 200 1.4208 0.1984 1.4208 1.1920
No log 33.6667 202 1.5414 0.2608 1.5414 1.2415
No log 34.0 204 1.7955 0.2820 1.7955 1.3400
No log 34.3333 206 1.7538 0.2854 1.7538 1.3243
No log 34.6667 208 1.5949 0.2819 1.5949 1.2629
No log 35.0 210 1.5903 0.2819 1.5903 1.2611
No log 35.3333 212 1.6833 0.3129 1.6833 1.2974
No log 35.6667 214 1.6878 0.3027 1.6878 1.2991
No log 36.0 216 1.6082 0.2678 1.6082 1.2681
No log 36.3333 218 1.5972 0.2729 1.5972 1.2638
No log 36.6667 220 1.6235 0.2668 1.6235 1.2742
No log 37.0 222 1.7679 0.2820 1.7679 1.3296
No log 37.3333 224 1.9214 0.2868 1.9214 1.3862
No log 37.6667 226 1.9145 0.2719 1.9145 1.3837
No log 38.0 228 1.8709 0.2533 1.8709 1.3678
No log 38.3333 230 1.7610 0.2479 1.7610 1.3270
No log 38.6667 232 1.8468 0.2502 1.8468 1.3590
No log 39.0 234 1.8804 0.2574 1.8804 1.3713
No log 39.3333 236 1.9901 0.2751 1.9901 1.4107
No log 39.6667 238 1.8206 0.2563 1.8206 1.3493
No log 40.0 240 1.6502 0.2813 1.6502 1.2846
No log 40.3333 242 1.5953 0.3008 1.5953 1.2631
No log 40.6667 244 1.4161 0.3171 1.4161 1.1900
No log 41.0 246 1.3913 0.3399 1.3913 1.1795
No log 41.3333 248 1.4457 0.3744 1.4457 1.2024
No log 41.6667 250 1.5366 0.3510 1.5366 1.2396
No log 42.0 252 1.6273 0.2658 1.6273 1.2757
No log 42.3333 254 1.6352 0.2724 1.6352 1.2787
No log 42.6667 256 1.7976 0.2542 1.7976 1.3408
No log 43.0 258 1.8490 0.2553 1.8490 1.3598
No log 43.3333 260 1.9417 0.2594 1.9417 1.3934
No log 43.6667 262 2.1321 0.2651 2.1321 1.4602
No log 44.0 264 2.0651 0.2653 2.0651 1.4371
No log 44.3333 266 1.9550 0.2715 1.9550 1.3982
No log 44.6667 268 1.8619 0.2710 1.8619 1.3645
No log 45.0 270 1.7243 0.2457 1.7243 1.3131
No log 45.3333 272 1.7584 0.2457 1.7584 1.3260
No log 45.6667 274 1.9902 0.2535 1.9902 1.4108
No log 46.0 276 2.1083 0.2383 2.1083 1.4520
No log 46.3333 278 2.0373 0.2223 2.0373 1.4274
No log 46.6667 280 1.8889 0.2248 1.8889 1.3744
No log 47.0 282 1.8250 0.2398 1.8250 1.3509
No log 47.3333 284 1.8958 0.2398 1.8958 1.3769
No log 47.6667 286 2.0289 0.2321 2.0289 1.4244
No log 48.0 288 1.9803 0.2634 1.9803 1.4072
No log 48.3333 290 1.8383 0.2427 1.8383 1.3558
No log 48.6667 292 1.8334 0.2510 1.8334 1.3540
No log 49.0 294 1.9237 0.2472 1.9237 1.3870
No log 49.3333 296 2.0165 0.2445 2.0165 1.4200
No log 49.6667 298 1.8854 0.2544 1.8854 1.3731
No log 50.0 300 1.7211 0.2563 1.7211 1.3119
No log 50.3333 302 1.5119 0.2034 1.5119 1.2296
No log 50.6667 304 1.4693 0.1897 1.4693 1.2122
No log 51.0 306 1.5887 0.2364 1.5887 1.2604
No log 51.3333 308 1.8839 0.2902 1.8839 1.3726
No log 51.6667 310 2.0447 0.2555 2.0447 1.4299
No log 52.0 312 2.0284 0.2420 2.0284 1.4242
No log 52.3333 314 1.8541 0.2687 1.8541 1.3617
No log 52.6667 316 1.6217 0.2574 1.6217 1.2735
No log 53.0 318 1.4884 0.2625 1.4884 1.2200
No log 53.3333 320 1.4987 0.2625 1.4987 1.2242
No log 53.6667 322 1.6112 0.2564 1.6112 1.2693
No log 54.0 324 1.7607 0.2553 1.7607 1.3269
No log 54.3333 326 1.7603 0.2457 1.7603 1.3268
No log 54.6667 328 1.7458 0.2684 1.7458 1.3213
No log 55.0 330 1.7096 0.2575 1.7096 1.3075
No log 55.3333 332 1.5970 0.2540 1.5970 1.2637
No log 55.6667 334 1.6557 0.2599 1.6557 1.2867
No log 56.0 336 1.8047 0.2457 1.8047 1.3434
No log 56.3333 338 1.9436 0.2401 1.9436 1.3941
No log 56.6667 340 1.9812 0.2493 1.9812 1.4075
No log 57.0 342 1.9667 0.2493 1.9667 1.4024
No log 57.3333 344 1.8620 0.2614 1.8620 1.3646
No log 57.6667 346 1.7167 0.2743 1.7167 1.3102
No log 58.0 348 1.6558 0.2587 1.6558 1.2868
No log 58.3333 350 1.7176 0.2621 1.7176 1.3106
No log 58.6667 352 1.8213 0.2165 1.8213 1.3495
No log 59.0 354 1.8434 0.2165 1.8434 1.3577
No log 59.3333 356 1.8233 0.2165 1.8233 1.3503
No log 59.6667 358 1.8176 0.2178 1.8176 1.3482
No log 60.0 360 1.7729 0.2531 1.7729 1.3315
No log 60.3333 362 1.8220 0.2710 1.8220 1.3498
No log 60.6667 364 1.7318 0.2691 1.7318 1.3160
No log 61.0 366 1.6557 0.2638 1.6557 1.2868
No log 61.3333 368 1.7170 0.2678 1.7170 1.3104
No log 61.6667 370 1.6750 0.2521 1.6750 1.2942
No log 62.0 372 1.6496 0.2521 1.6496 1.2844
No log 62.3333 374 1.6157 0.2520 1.6157 1.2711
No log 62.6667 376 1.6574 0.2478 1.6574 1.2874
No log 63.0 378 1.7904 0.2636 1.7904 1.3381
No log 63.3333 380 1.9101 0.2564 1.9101 1.3820
No log 63.6667 382 1.9234 0.2634 1.9234 1.3869
No log 64.0 384 1.7898 0.2616 1.7898 1.3378
No log 64.3333 386 1.6434 0.2564 1.6434 1.2820
No log 64.6667 388 1.6106 0.2529 1.6106 1.2691
No log 65.0 390 1.7062 0.2767 1.7062 1.3062
No log 65.3333 392 1.8404 0.2769 1.8404 1.3566
No log 65.6667 394 1.8903 0.2787 1.8903 1.3749
No log 66.0 396 1.8681 0.2656 1.8681 1.3668
No log 66.3333 398 1.7970 0.2687 1.7970 1.3405
No log 66.6667 400 1.6764 0.2628 1.6764 1.2947
No log 67.0 402 1.5700 0.2518 1.5700 1.2530
No log 67.3333 404 1.4877 0.2803 1.4877 1.2197
No log 67.6667 406 1.4710 0.2696 1.4710 1.2128
No log 68.0 408 1.5367 0.2634 1.5367 1.2396
No log 68.3333 410 1.6994 0.2767 1.6994 1.3036
No log 68.6667 412 1.8453 0.2724 1.8453 1.3584
No log 69.0 414 1.9117 0.2613 1.9117 1.3826
No log 69.3333 416 1.8360 0.2678 1.8360 1.3550
No log 69.6667 418 1.6949 0.2607 1.6949 1.3019
No log 70.0 420 1.5850 0.2887 1.5850 1.2590
No log 70.3333 422 1.5025 0.2651 1.5025 1.2258
No log 70.6667 424 1.4792 0.2590 1.4792 1.2162
No log 71.0 426 1.5391 0.2868 1.5391 1.2406
No log 71.3333 428 1.6514 0.2441 1.6514 1.2851
No log 71.6667 430 1.7346 0.2391 1.7346 1.3170
No log 72.0 432 1.8762 0.2636 1.8762 1.3698
No log 72.3333 434 1.9515 0.2724 1.9515 1.3970
No log 72.6667 436 1.9109 0.2634 1.9109 1.3824
No log 73.0 438 1.8087 0.2574 1.8087 1.3449
No log 73.3333 440 1.6730 0.2586 1.6730 1.2934
No log 73.6667 442 1.5862 0.2413 1.5862 1.2595
No log 74.0 444 1.5963 0.2346 1.5963 1.2635
No log 74.3333 446 1.6152 0.2346 1.6152 1.2709
No log 74.6667 448 1.6606 0.2498 1.6606 1.2886
No log 75.0 450 1.6801 0.2498 1.6801 1.2962
No log 75.3333 452 1.7543 0.2455 1.7543 1.3245
No log 75.6667 454 1.7977 0.2318 1.7977 1.3408
No log 76.0 456 1.8477 0.2511 1.8477 1.3593
No log 76.3333 458 1.8738 0.2544 1.8738 1.3689
No log 76.6667 460 1.8227 0.2511 1.8227 1.3501
No log 77.0 462 1.7613 0.2238 1.7613 1.3271
No log 77.3333 464 1.7206 0.2312 1.7206 1.3117
No log 77.6667 466 1.7514 0.2338 1.7514 1.3234
No log 78.0 468 1.7939 0.2436 1.7939 1.3394
No log 78.3333 470 1.7725 0.2415 1.7725 1.3313
No log 78.6667 472 1.7547 0.2415 1.7547 1.3247
No log 79.0 474 1.7527 0.2415 1.7527 1.3239
No log 79.3333 476 1.7502 0.2553 1.7502 1.3230
No log 79.6667 478 1.7177 0.2597 1.7177 1.3106
No log 80.0 480 1.6610 0.2653 1.6610 1.2888
No log 80.3333 482 1.6237 0.2702 1.6237 1.2743
No log 80.6667 484 1.6450 0.2621 1.6450 1.2826
No log 81.0 486 1.6657 0.2640 1.6657 1.2906
No log 81.3333 488 1.6978 0.2661 1.6979 1.3030
No log 81.6667 490 1.7072 0.2738 1.7072 1.3066
No log 82.0 492 1.7587 0.2785 1.7587 1.3261
No log 82.3333 494 1.7686 0.2785 1.7686 1.3299
No log 82.6667 496 1.7495 0.2785 1.7495 1.3227
No log 83.0 498 1.7069 0.2691 1.7069 1.3065
0.2815 83.3333 500 1.6663 0.2509 1.6663 1.2908
0.2815 83.6667 502 1.6705 0.2531 1.6705 1.2925
0.2815 84.0 504 1.7152 0.2691 1.7152 1.3097
0.2815 84.3333 506 1.7878 0.2710 1.7878 1.3371
0.2815 84.6667 508 1.8342 0.2678 1.8342 1.3543
0.2815 85.0 510 1.8349 0.2678 1.8349 1.3546
0.2815 85.3333 512 1.7893 0.2574 1.7893 1.3377
0.2815 85.6667 514 1.7178 0.2531 1.7178 1.3106
0.2815 86.0 516 1.6329 0.2586 1.6329 1.2779
0.2815 86.3333 518 1.6033 0.2713 1.6033 1.2662
0.2815 86.6667 520 1.6164 0.2733 1.6164 1.2714
0.2815 87.0 522 1.6436 0.2653 1.6436 1.2820
0.2815 87.3333 524 1.6718 0.2520 1.6718 1.2930
0.2815 87.6667 526 1.7010 0.2443 1.7010 1.3042
0.2815 88.0 528 1.7385 0.2391 1.7385 1.3185
0.2815 88.3333 530 1.7668 0.2479 1.7668 1.3292
0.2815 88.6667 532 1.7834 0.2574 1.7834 1.3354
0.2815 89.0 534 1.7766 0.2479 1.7766 1.3329
0.2815 89.3333 536 1.7653 0.2479 1.7653 1.3286
0.2815 89.6667 538 1.7303 0.2691 1.7303 1.3154
0.2815 90.0 540 1.6891 0.2664 1.6891 1.2997
0.2815 90.3333 542 1.6787 0.2664 1.6787 1.2957
0.2815 90.6667 544 1.6601 0.2664 1.6601 1.2884
0.2815 91.0 546 1.6604 0.2664 1.6604 1.2886
0.2815 91.3333 548 1.6602 0.2664 1.6602 1.2885
0.2815 91.6667 550 1.6646 0.2664 1.6646 1.2902
0.2815 92.0 552 1.6805 0.2509 1.6805 1.2963
0.2815 92.3333 554 1.6844 0.2671 1.6844 1.2978
0.2815 92.6667 556 1.6896 0.2691 1.6896 1.2998
0.2815 93.0 558 1.6857 0.2671 1.6857 1.2983
0.2815 93.3333 560 1.6877 0.2691 1.6877 1.2991
0.2815 93.6667 562 1.6937 0.2691 1.6937 1.3014
0.2815 94.0 564 1.7020 0.2691 1.7020 1.3046
0.2815 94.3333 566 1.7042 0.2691 1.7042 1.3055
0.2815 94.6667 568 1.7074 0.2691 1.7074 1.3067
0.2815 95.0 570 1.7005 0.2691 1.7005 1.3040
0.2815 95.3333 572 1.6954 0.2691 1.6954 1.3021
0.2815 95.6667 574 1.6942 0.2691 1.6942 1.3016
0.2815 96.0 576 1.6832 0.2691 1.6832 1.2974
0.2815 96.3333 578 1.6711 0.2531 1.6711 1.2927
0.2815 96.6667 580 1.6654 0.2531 1.6654 1.2905
0.2815 97.0 582 1.6631 0.2531 1.6631 1.2896
0.2815 97.3333 584 1.6591 0.2531 1.6591 1.2881
0.2815 97.6667 586 1.6588 0.2531 1.6588 1.2880
0.2815 98.0 588 1.6562 0.2531 1.6562 1.2869
0.2815 98.3333 590 1.6519 0.2433 1.6519 1.2853
0.2815 98.6667 592 1.6489 0.2433 1.6489 1.2841
0.2815 99.0 594 1.6480 0.2433 1.6480 1.2838
0.2815 99.3333 596 1.6482 0.2433 1.6482 1.2838
0.2815 99.6667 598 1.6486 0.2433 1.6486 1.2840

Framework versions

  • Transformers 4.44.2
  • Pytorch 2.4.0+cu118
  • Datasets 2.21.0
  • Tokenizers 0.19.1
Downloads last month
6
Safetensors
Model size
135M params
Tensor type
F32
·
Inference Providers NEW
This model is not currently available via any of the supported third-party Inference Providers, and the model is not deployed on the HF Inference API.

Model tree for MayBashendy/ArabicNewSplits8_usingALLEssays_FineTuningAraBERT_run1_AugV5_k1_task1_organization

Finetuned
(4222)
this model