ArabicNewSplits7_B_usingWellWrittenEssays_FineTuningAraBERT_run2_AugV5_k10_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: 1.6207
  • Qwk: 0.3358
  • Mse: 1.6207
  • Rmse: 1.2731

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 0.0417 2 7.0639 0.0 7.0639 2.6578
No log 0.0833 4 4.8911 0.0803 4.8911 2.2116
No log 0.125 6 3.6801 -0.0212 3.6801 1.9184
No log 0.1667 8 3.3261 -0.0109 3.3261 1.8238
No log 0.2083 10 2.5607 0.0927 2.5607 1.6002
No log 0.25 12 2.0951 0.1705 2.0951 1.4474
No log 0.2917 14 1.8459 0.1026 1.8459 1.3586
No log 0.3333 16 1.7133 0.2222 1.7133 1.3089
No log 0.375 18 1.6451 0.2222 1.6451 1.2826
No log 0.4167 20 1.6826 0.2124 1.6826 1.2971
No log 0.4583 22 1.6520 0.1930 1.6520 1.2853
No log 0.5 24 1.8302 0.1488 1.8302 1.3528
No log 0.5417 26 1.7562 0.1404 1.7562 1.3252
No log 0.5833 28 1.5109 0.2301 1.5109 1.2292
No log 0.625 30 1.6580 0.3279 1.6580 1.2876
No log 0.6667 32 1.6611 0.3140 1.6611 1.2888
No log 0.7083 34 1.4168 0.3077 1.4168 1.1903
No log 0.75 36 1.4048 0.2783 1.4048 1.1853
No log 0.7917 38 1.4253 0.2906 1.4253 1.1939
No log 0.8333 40 1.4394 0.3697 1.4394 1.1997
No log 0.875 42 1.4617 0.3607 1.4617 1.2090
No log 0.9167 44 1.4291 0.4098 1.4291 1.1955
No log 0.9583 46 1.6763 0.3281 1.6763 1.2947
No log 1.0 48 1.6913 0.2969 1.6913 1.3005
No log 1.0417 50 1.4865 0.352 1.4865 1.2192
No log 1.0833 52 1.2575 0.3697 1.2575 1.1214
No log 1.125 54 1.3223 0.3968 1.3223 1.1499
No log 1.1667 56 1.2677 0.4320 1.2677 1.1259
No log 1.2083 58 1.1038 0.4706 1.1038 1.0506
No log 1.25 60 1.5513 0.3103 1.5513 1.2455
No log 1.2917 62 1.5006 0.3220 1.5006 1.2250
No log 1.3333 64 1.1729 0.5167 1.1729 1.0830
No log 1.375 66 1.1914 0.4786 1.1914 1.0915
No log 1.4167 68 1.1181 0.5042 1.1181 1.0574
No log 1.4583 70 1.0602 0.5691 1.0602 1.0297
No log 1.5 72 1.7898 0.2759 1.7898 1.3378
No log 1.5417 74 2.0719 0.0690 2.0719 1.4394
No log 1.5833 76 1.6980 0.3130 1.6980 1.3031
No log 1.625 78 1.2102 0.5455 1.2102 1.1001
No log 1.6667 80 0.9387 0.6565 0.9387 0.9688
No log 1.7083 82 0.9315 0.6412 0.9315 0.9651
No log 1.75 84 0.9899 0.6462 0.9899 0.9949
No log 1.7917 86 1.2965 0.4878 1.2965 1.1386
No log 1.8333 88 1.5524 0.3667 1.5524 1.2460
No log 1.875 90 1.4106 0.4426 1.4106 1.1877
No log 1.9167 92 1.1403 0.5738 1.1403 1.0678
No log 1.9583 94 1.0330 0.592 1.0330 1.0164
No log 2.0 96 1.1067 0.5760 1.1067 1.0520
No log 2.0417 98 1.3239 0.4651 1.3239 1.1506
No log 2.0833 100 1.7027 0.2791 1.7027 1.3049
No log 2.125 102 1.9053 0.2698 1.9053 1.3803
No log 2.1667 104 1.9125 0.2167 1.9125 1.3829
No log 2.2083 106 1.7160 0.3529 1.7160 1.3100
No log 2.25 108 1.3493 0.5042 1.3493 1.1616
No log 2.2917 110 1.2507 0.4957 1.2507 1.1183
No log 2.3333 112 1.3104 0.4386 1.3104 1.1447
No log 2.375 114 1.4886 0.3894 1.4886 1.2201
No log 2.4167 116 1.7637 0.1802 1.7637 1.3281
No log 2.4583 118 1.7067 0.3390 1.7067 1.3064
No log 2.5 120 1.6019 0.3636 1.6019 1.2656
No log 2.5417 122 1.5713 0.3492 1.5713 1.2535
No log 2.5833 124 1.4783 0.4252 1.4783 1.2158
No log 2.625 126 1.5077 0.3969 1.5077 1.2279
No log 2.6667 128 1.5349 0.3969 1.5349 1.2389
No log 2.7083 130 1.5075 0.3969 1.5075 1.2278
No log 2.75 132 1.5501 0.3664 1.5501 1.2450
No log 2.7917 134 1.5459 0.3788 1.5459 1.2433
No log 2.8333 136 1.4491 0.4580 1.4491 1.2038
No log 2.875 138 1.4362 0.4355 1.4362 1.1984
No log 2.9167 140 1.5241 0.4237 1.5241 1.2346
No log 2.9583 142 1.5480 0.3793 1.5480 1.2442
No log 3.0 144 1.4604 0.2727 1.4604 1.2085
No log 3.0417 146 1.3679 0.2727 1.3679 1.1696
No log 3.0833 148 1.2903 0.375 1.2903 1.1359
No log 3.125 150 1.2911 0.4746 1.2911 1.1363
No log 3.1667 152 1.4486 0.4355 1.4486 1.2036
No log 3.2083 154 1.8350 0.2059 1.8350 1.3546
No log 3.25 156 2.1437 0.1867 2.1437 1.4641
No log 3.2917 158 2.1822 0.2119 2.1822 1.4772
No log 3.3333 160 1.9996 0.2069 1.9996 1.4141
No log 3.375 162 1.5705 0.4088 1.5705 1.2532
No log 3.4167 164 1.2125 0.5 1.2125 1.1011
No log 3.4583 166 1.1526 0.5041 1.1526 1.0736
No log 3.5 168 1.2151 0.5469 1.2151 1.1023
No log 3.5417 170 1.3146 0.4885 1.3146 1.1466
No log 3.5833 172 1.2588 0.5649 1.2588 1.1220
No log 3.625 174 1.2464 0.5649 1.2464 1.1164
No log 3.6667 176 1.3580 0.4776 1.3580 1.1653
No log 3.7083 178 1.3806 0.4812 1.3806 1.1750
No log 3.75 180 1.2897 0.5645 1.2897 1.1357
No log 3.7917 182 1.1744 0.5645 1.1744 1.0837
No log 3.8333 184 1.1282 0.5167 1.1282 1.0622
No log 3.875 186 1.1518 0.4874 1.1518 1.0732
No log 3.9167 188 1.2333 0.5645 1.2333 1.1106
No log 3.9583 190 1.2362 0.5873 1.2362 1.1118
No log 4.0 192 1.3376 0.5113 1.3376 1.1565
No log 4.0417 194 1.5541 0.3529 1.5541 1.2466
No log 4.0833 196 1.6164 0.3235 1.6164 1.2714
No log 4.125 198 1.5155 0.4 1.5155 1.2311
No log 4.1667 200 1.2800 0.5692 1.2800 1.1314
No log 4.2083 202 1.1527 0.56 1.1527 1.0736
No log 4.25 204 1.1685 0.5366 1.1685 1.0810
No log 4.2917 206 1.2465 0.5692 1.2465 1.1165
No log 4.3333 208 1.2989 0.4962 1.2989 1.1397
No log 4.375 210 1.3660 0.4559 1.3660 1.1688
No log 4.4167 212 1.3983 0.4526 1.3983 1.1825
No log 4.4583 214 1.3770 0.4559 1.3770 1.1735
No log 4.5 216 1.3239 0.5113 1.3239 1.1506
No log 4.5417 218 1.2029 0.4538 1.2029 1.0968
No log 4.5833 220 1.1707 0.3717 1.1707 1.0820
No log 4.625 222 1.1198 0.4667 1.1198 1.0582
No log 4.6667 224 1.1992 0.5736 1.1992 1.0951
No log 4.7083 226 1.3477 0.5113 1.3477 1.1609
No log 4.75 228 1.2799 0.5649 1.2799 1.1313
No log 4.7917 230 1.0439 0.6047 1.0439 1.0217
No log 4.8333 232 0.8979 0.6357 0.8979 0.9476
No log 4.875 234 0.8683 0.6357 0.8683 0.9318
No log 4.9167 236 0.9274 0.6094 0.9274 0.9630
No log 4.9583 238 1.1620 0.5802 1.1620 1.0780
No log 5.0 240 1.5913 0.3796 1.5913 1.2615
No log 5.0417 242 1.8024 0.3111 1.8024 1.3425
No log 5.0833 244 1.8000 0.2857 1.8000 1.3416
No log 5.125 246 1.5903 0.4030 1.5903 1.2611
No log 5.1667 248 1.4279 0.4651 1.4279 1.1950
No log 5.2083 250 1.3836 0.5000 1.3836 1.1762
No log 5.25 252 1.4510 0.4444 1.4510 1.2046
No log 5.2917 254 1.5573 0.3817 1.5573 1.2479
No log 5.3333 256 1.6319 0.3582 1.6319 1.2775
No log 5.375 258 1.6513 0.3358 1.6513 1.2850
No log 5.4167 260 1.4891 0.3910 1.4891 1.2203
No log 5.4583 262 1.2430 0.5312 1.2430 1.1149
No log 5.5 264 1.1681 0.5827 1.1681 1.0808
No log 5.5417 266 1.2171 0.5116 1.2171 1.1032
No log 5.5833 268 1.3972 0.4148 1.3972 1.1820
No log 5.625 270 1.5490 0.3768 1.5490 1.2446
No log 5.6667 272 1.5115 0.3881 1.5115 1.2294
No log 5.7083 274 1.3288 0.4496 1.3288 1.1528
No log 5.75 276 1.2140 0.5484 1.2140 1.1018
No log 5.7917 278 1.2135 0.4915 1.2135 1.1016
No log 5.8333 280 1.2599 0.4918 1.2599 1.1224
No log 5.875 282 1.3653 0.4496 1.3653 1.1685
No log 5.9167 284 1.5618 0.3704 1.5618 1.2497
No log 5.9583 286 1.6734 0.3529 1.6734 1.2936
No log 6.0 288 1.5873 0.3796 1.5873 1.2599
No log 6.0417 290 1.5366 0.3796 1.5366 1.2396
No log 6.0833 292 1.4348 0.4179 1.4348 1.1978
No log 6.125 294 1.4012 0.4275 1.4012 1.1837
No log 6.1667 296 1.3024 0.5 1.3024 1.1412
No log 6.2083 298 1.2724 0.5 1.2724 1.1280
No log 6.25 300 1.3332 0.4580 1.3332 1.1546
No log 6.2917 302 1.5246 0.3529 1.5246 1.2347
No log 6.3333 304 1.6191 0.3529 1.6191 1.2725
No log 6.375 306 1.6117 0.3529 1.6117 1.2695
No log 6.4167 308 1.4846 0.3731 1.4846 1.2184
No log 6.4583 310 1.3492 0.4733 1.3492 1.1616
No log 6.5 312 1.1972 0.5156 1.1972 1.0942
No log 6.5417 314 1.1552 0.5397 1.1552 1.0748
No log 6.5833 316 1.2030 0.4882 1.2030 1.0968
No log 6.625 318 1.3551 0.4496 1.3551 1.1641
No log 6.6667 320 1.4640 0.4091 1.4640 1.2100
No log 6.7083 322 1.4277 0.4394 1.4277 1.1949
No log 6.75 324 1.3648 0.4651 1.3648 1.1683
No log 6.7917 326 1.3337 0.5426 1.3337 1.1549
No log 6.8333 328 1.3966 0.5116 1.3966 1.1818
No log 6.875 330 1.5033 0.4 1.5033 1.2261
No log 6.9167 332 1.6293 0.3885 1.6293 1.2764
No log 6.9583 334 1.7625 0.3380 1.7625 1.3276
No log 7.0 336 1.7347 0.3380 1.7347 1.3171
No log 7.0417 338 1.6819 0.3857 1.6819 1.2969
No log 7.0833 340 1.5545 0.4234 1.5545 1.2468
No log 7.125 342 1.3745 0.4885 1.3745 1.1724
No log 7.1667 344 1.3388 0.5426 1.3388 1.1570
No log 7.2083 346 1.4026 0.4925 1.4026 1.1843
No log 7.25 348 1.4569 0.4412 1.4569 1.2070
No log 7.2917 350 1.3547 0.5185 1.3547 1.1639
No log 7.3333 352 1.3218 0.5185 1.3218 1.1497
No log 7.375 354 1.2044 0.5075 1.2044 1.0975
No log 7.4167 356 1.1198 0.5271 1.1198 1.0582
No log 7.4583 358 1.1934 0.5113 1.1934 1.0924
No log 7.5 360 1.3887 0.4662 1.3887 1.1784
No log 7.5417 362 1.5322 0.3704 1.5322 1.2378
No log 7.5833 364 1.5724 0.3704 1.5724 1.2540
No log 7.625 366 1.4454 0.4234 1.4454 1.2023
No log 7.6667 368 1.3707 0.4853 1.3707 1.1708
No log 7.7083 370 1.3487 0.4853 1.3487 1.1613
No log 7.75 372 1.4184 0.4741 1.4184 1.1909
No log 7.7917 374 1.4566 0.4741 1.4566 1.2069
No log 7.8333 376 1.4119 0.4853 1.4119 1.1882
No log 7.875 378 1.2990 0.5075 1.2990 1.1397
No log 7.9167 380 1.2320 0.5038 1.2320 1.1100
No log 7.9583 382 1.1972 0.5323 1.1972 1.0942
No log 8.0 384 1.2446 0.5 1.2446 1.1156
No log 8.0417 386 1.2820 0.4733 1.2820 1.1322
No log 8.0833 388 1.3063 0.4812 1.3063 1.1429
No log 8.125 390 1.3045 0.4741 1.3045 1.1422
No log 8.1667 392 1.3805 0.4460 1.3805 1.1749
No log 8.2083 394 1.4336 0.4412 1.4336 1.1973
No log 8.25 396 1.4770 0.4493 1.4770 1.2153
No log 8.2917 398 1.4302 0.4493 1.4302 1.1959
No log 8.3333 400 1.4445 0.4493 1.4445 1.2019
No log 8.375 402 1.3289 0.5271 1.3289 1.1528
No log 8.4167 404 1.3192 0.5469 1.3192 1.1486
No log 8.4583 406 1.4105 0.4627 1.4105 1.1876
No log 8.5 408 1.6009 0.3971 1.6009 1.2653
No log 8.5417 410 1.7966 0.3143 1.7966 1.3404
No log 8.5833 412 1.8161 0.3143 1.8161 1.3476
No log 8.625 414 1.7376 0.3404 1.7376 1.3182
No log 8.6667 416 1.7277 0.3404 1.7277 1.3144
No log 8.7083 418 1.8001 0.3143 1.8001 1.3417
No log 8.75 420 1.8288 0.3143 1.8288 1.3523
No log 8.7917 422 1.7018 0.3623 1.7018 1.3045
No log 8.8333 424 1.5675 0.4148 1.5675 1.2520
No log 8.875 426 1.4402 0.4724 1.4402 1.2001
No log 8.9167 428 1.4231 0.4733 1.4231 1.1929
No log 8.9583 430 1.3880 0.4697 1.3880 1.1781
No log 9.0 432 1.4110 0.4593 1.4110 1.1878
No log 9.0417 434 1.4605 0.4412 1.4605 1.2085
No log 9.0833 436 1.5684 0.4118 1.5684 1.2524
No log 9.125 438 1.4726 0.4118 1.4726 1.2135
No log 9.1667 440 1.2294 0.5303 1.2294 1.1088
No log 9.2083 442 1.1960 0.5303 1.1960 1.0936
No log 9.25 444 1.2334 0.5303 1.2334 1.1106
No log 9.2917 446 1.2703 0.5303 1.2703 1.1271
No log 9.3333 448 1.2469 0.5303 1.2469 1.1166
No log 9.375 450 1.2054 0.5271 1.2054 1.0979
No log 9.4167 452 1.2003 0.5469 1.2003 1.0956
No log 9.4583 454 1.2949 0.5 1.2949 1.1380
No log 9.5 456 1.4336 0.4361 1.4336 1.1973
No log 9.5417 458 1.5047 0.4179 1.5047 1.2267
No log 9.5833 460 1.4648 0.4060 1.4648 1.2103
No log 9.625 462 1.3695 0.5 1.3695 1.1703
No log 9.6667 464 1.2776 0.5116 1.2776 1.1303
No log 9.7083 466 1.2466 0.5116 1.2466 1.1165
No log 9.75 468 1.3132 0.5 1.3132 1.1460
No log 9.7917 470 1.5527 0.4148 1.5527 1.2461
No log 9.8333 472 1.7807 0.3309 1.7807 1.3344
No log 9.875 474 1.8083 0.3188 1.8083 1.3447
No log 9.9167 476 1.7122 0.3704 1.7122 1.3085
No log 9.9583 478 1.6446 0.3881 1.6446 1.2824
No log 10.0 480 1.5857 0.4328 1.5857 1.2593
No log 10.0417 482 1.5592 0.4060 1.5592 1.2487
No log 10.0833 484 1.5458 0.4179 1.5458 1.2433
No log 10.125 486 1.6025 0.3910 1.6025 1.2659
No log 10.1667 488 1.5425 0.3817 1.5425 1.2420
No log 10.2083 490 1.4512 0.4062 1.4512 1.2046
No log 10.25 492 1.4319 0.4531 1.4319 1.1966
No log 10.2917 494 1.4426 0.4341 1.4426 1.2011
No log 10.3333 496 1.5255 0.3817 1.5255 1.2351
No log 10.375 498 1.5930 0.3881 1.5930 1.2621
0.374 10.4167 500 1.5281 0.3881 1.5281 1.2362
0.374 10.4583 502 1.5004 0.3817 1.5004 1.2249
0.374 10.5 504 1.5185 0.3881 1.5185 1.2323
0.374 10.5417 506 1.6266 0.3529 1.6266 1.2754
0.374 10.5833 508 1.5934 0.3529 1.5934 1.2623
0.374 10.625 510 1.6207 0.3358 1.6207 1.2731

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_usingWellWrittenEssays_FineTuningAraBERT_run2_AugV5_k10_task1_organization

Finetuned
(4019)
this model