ArabicNewSplits7_usingWellWrittenEssays_FineTuningAraBERT_run3_AugV5_k4_task7_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: 0.7460
  • Qwk: 0.2007
  • Mse: 0.7460
  • Rmse: 0.8637

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 0.2 2 2.4280 -0.0646 2.4280 1.5582
No log 0.4 4 1.0881 0.2875 1.0881 1.0431
No log 0.6 6 1.0474 -0.1517 1.0474 1.0234
No log 0.8 8 1.3691 -0.1706 1.3691 1.1701
No log 1.0 10 1.2737 -0.1706 1.2737 1.1286
No log 1.2 12 1.0007 0.0283 1.0007 1.0003
No log 1.4 14 0.9275 0.1183 0.9275 0.9631
No log 1.6 16 0.8221 0.0428 0.8221 0.9067
No log 1.8 18 0.8087 0.0 0.8087 0.8993
No log 2.0 20 0.7870 0.0 0.7870 0.8871
No log 2.2 22 0.7671 0.0 0.7671 0.8758
No log 2.4 24 0.7781 0.0 0.7781 0.8821
No log 2.6 26 0.8770 -0.0320 0.8770 0.9365
No log 2.8 28 1.0144 -0.0076 1.0144 1.0072
No log 3.0 30 0.8925 -0.0700 0.8925 0.9447
No log 3.2 32 0.7964 0.0481 0.7964 0.8924
No log 3.4 34 0.7693 0.1674 0.7693 0.8771
No log 3.6 36 0.8324 0.2285 0.8324 0.9124
No log 3.8 38 0.8668 0.2319 0.8668 0.9310
No log 4.0 40 0.9179 -0.0045 0.9179 0.9581
No log 4.2 42 1.2134 0.0367 1.2134 1.1015
No log 4.4 44 1.0908 -0.0033 1.0908 1.0444
No log 4.6 46 0.8646 0.2063 0.8646 0.9298
No log 4.8 48 0.8583 0.1550 0.8583 0.9264
No log 5.0 50 0.8892 0.1815 0.8892 0.9430
No log 5.2 52 0.8956 0.1766 0.8956 0.9463
No log 5.4 54 0.8394 0.1699 0.8394 0.9162
No log 5.6 56 0.8778 0.0410 0.8778 0.9369
No log 5.8 58 1.0232 0.0974 1.0232 1.0115
No log 6.0 60 1.0125 0.1259 1.0125 1.0062
No log 6.2 62 0.8948 0.1498 0.8948 0.9459
No log 6.4 64 0.8853 0.1541 0.8853 0.9409
No log 6.6 66 0.8866 0.1587 0.8866 0.9416
No log 6.8 68 0.8985 0.0930 0.8985 0.9479
No log 7.0 70 0.8920 0.1760 0.8920 0.9444
No log 7.2 72 0.9077 0.1815 0.9077 0.9528
No log 7.4 74 1.0511 0.1271 1.0511 1.0252
No log 7.6 76 0.9777 0.1712 0.9777 0.9888
No log 7.8 78 0.8505 0.1303 0.8505 0.9222
No log 8.0 80 0.8537 0.1379 0.8537 0.9240
No log 8.2 82 0.8646 0.1531 0.8646 0.9298
No log 8.4 84 0.8664 0.2202 0.8664 0.9308
No log 8.6 86 0.8772 0.2987 0.8772 0.9366
No log 8.8 88 0.9030 0.2328 0.9030 0.9502
No log 9.0 90 0.8730 0.2888 0.8730 0.9344
No log 9.2 92 0.8736 0.2256 0.8736 0.9347
No log 9.4 94 0.8433 0.2936 0.8433 0.9183
No log 9.6 96 0.8252 0.3296 0.8252 0.9084
No log 9.8 98 0.8418 0.3060 0.8418 0.9175
No log 10.0 100 0.8461 0.3060 0.8461 0.9198
No log 10.2 102 0.8368 0.3478 0.8368 0.9148
No log 10.4 104 0.9080 0.1018 0.9080 0.9529
No log 10.6 106 0.8953 0.0702 0.8953 0.9462
No log 10.8 108 0.8388 0.1379 0.8388 0.9158
No log 11.0 110 0.8305 0.2475 0.8305 0.9113
No log 11.2 112 0.8178 0.2360 0.8178 0.9043
No log 11.4 114 0.8298 0.1797 0.8298 0.9109
No log 11.6 116 0.8452 0.1179 0.8452 0.9194
No log 11.8 118 0.8094 0.1179 0.8094 0.8997
No log 12.0 120 0.7902 0.2360 0.7902 0.8889
No log 12.2 122 0.7951 0.2973 0.7951 0.8917
No log 12.4 124 0.8498 0.2633 0.8498 0.9218
No log 12.6 126 0.8424 0.2633 0.8424 0.9178
No log 12.8 128 0.8301 0.2561 0.8301 0.9111
No log 13.0 130 0.8169 0.1471 0.8169 0.9038
No log 13.2 132 0.8238 0.1331 0.8238 0.9077
No log 13.4 134 0.9034 0.2633 0.9034 0.9505
No log 13.6 136 1.0901 0.1439 1.0901 1.0441
No log 13.8 138 1.0790 0.1743 1.0790 1.0387
No log 14.0 140 0.9223 0.2495 0.9223 0.9604
No log 14.2 142 0.8429 0.2072 0.8429 0.9181
No log 14.4 144 0.9117 0.1156 0.9117 0.9548
No log 14.6 146 0.8728 0.1162 0.8728 0.9343
No log 14.8 148 0.8074 0.1432 0.8074 0.8986
No log 15.0 150 0.8247 0.2261 0.8247 0.9081
No log 15.2 152 0.8430 0.1740 0.8430 0.9181
No log 15.4 154 0.8124 0.2590 0.8124 0.9013
No log 15.6 156 0.8154 0.1768 0.8154 0.9030
No log 15.8 158 0.8283 0.1870 0.8283 0.9101
No log 16.0 160 0.7892 0.1509 0.7892 0.8884
No log 16.2 162 0.7765 0.1353 0.7765 0.8812
No log 16.4 164 0.8255 0.2995 0.8255 0.9086
No log 16.6 166 0.8558 0.2521 0.8558 0.9251
No log 16.8 168 0.8069 0.2558 0.8069 0.8983
No log 17.0 170 0.7459 0.1010 0.7459 0.8636
No log 17.2 172 0.7710 0.1170 0.7710 0.8781
No log 17.4 174 0.7844 0.2283 0.7844 0.8856
No log 17.6 176 0.7267 0.1224 0.7267 0.8525
No log 17.8 178 0.6903 0.1094 0.6903 0.8308
No log 18.0 180 0.6972 0.2206 0.6972 0.8350
No log 18.2 182 0.7135 0.2685 0.7135 0.8447
No log 18.4 184 0.7196 0.2621 0.7196 0.8483
No log 18.6 186 0.7269 0.2279 0.7269 0.8526
No log 18.8 188 0.7438 0.2867 0.7438 0.8624
No log 19.0 190 0.7609 0.3069 0.7609 0.8723
No log 19.2 192 0.7642 0.2152 0.7642 0.8742
No log 19.4 194 0.7544 0.2102 0.7544 0.8685
No log 19.6 196 0.7471 0.2371 0.7471 0.8644
No log 19.8 198 0.7661 0.2414 0.7661 0.8753
No log 20.0 200 0.8426 0.3918 0.8426 0.9179
No log 20.2 202 0.8463 0.3918 0.8463 0.9199
No log 20.4 204 0.8038 0.3662 0.8038 0.8966
No log 20.6 206 0.7569 0.3518 0.7569 0.8700
No log 20.8 208 0.7127 0.2621 0.7127 0.8442
No log 21.0 210 0.7430 0.1857 0.7430 0.8620
No log 21.2 212 0.8000 0.1775 0.8000 0.8944
No log 21.4 214 0.7829 0.2911 0.7829 0.8848
No log 21.6 216 0.7883 0.3172 0.7883 0.8879
No log 21.8 218 0.8993 0.3586 0.8993 0.9483
No log 22.0 220 0.9577 0.3417 0.9577 0.9786
No log 22.2 222 0.8709 0.3653 0.8709 0.9332
No log 22.4 224 0.7573 0.2784 0.7573 0.8702
No log 22.6 226 0.7719 0.1528 0.7719 0.8786
No log 22.8 228 0.9097 0.3137 0.9097 0.9538
No log 23.0 230 0.9308 0.3105 0.9308 0.9648
No log 23.2 232 0.8329 0.1775 0.8329 0.9127
No log 23.4 234 0.7509 0.1649 0.7509 0.8666
No log 23.6 236 0.8036 0.3221 0.8036 0.8965
No log 23.8 238 0.9176 0.3710 0.9176 0.9579
No log 24.0 240 0.9428 0.3710 0.9428 0.9710
No log 24.2 242 0.8633 0.3723 0.8633 0.9291
No log 24.4 244 0.7685 0.3471 0.7685 0.8767
No log 24.6 246 0.7358 0.2563 0.7358 0.8578
No log 24.8 248 0.7595 0.2398 0.7595 0.8715
No log 25.0 250 0.7789 0.2098 0.7789 0.8826
No log 25.2 252 0.7605 0.2072 0.7605 0.8720
No log 25.4 254 0.7409 0.1935 0.7409 0.8608
No log 25.6 256 0.7553 0.2847 0.7553 0.8691
No log 25.8 258 0.8000 0.3471 0.8000 0.8944
No log 26.0 260 0.8252 0.3737 0.8252 0.9084
No log 26.2 262 0.7965 0.3471 0.7965 0.8925
No log 26.4 264 0.7400 0.2843 0.7400 0.8602
No log 26.6 266 0.7358 0.2113 0.7358 0.8578
No log 26.8 268 0.7479 0.1471 0.7479 0.8648
No log 27.0 270 0.7491 0.3239 0.7491 0.8655
No log 27.2 272 0.7487 0.3239 0.7487 0.8653
No log 27.4 274 0.7528 0.2294 0.7528 0.8676
No log 27.6 276 0.7528 0.2379 0.7528 0.8676
No log 27.8 278 0.7679 0.2913 0.7679 0.8763
No log 28.0 280 0.7699 0.3341 0.7699 0.8774
No log 28.2 282 0.7613 0.1988 0.7613 0.8725
No log 28.4 284 0.7630 0.1988 0.7630 0.8735
No log 28.6 286 0.7587 0.2327 0.7587 0.8710
No log 28.8 288 0.7566 0.2965 0.7566 0.8698
No log 29.0 290 0.7491 0.2965 0.7491 0.8655
No log 29.2 292 0.7664 0.3138 0.7664 0.8755
No log 29.4 294 0.7425 0.2622 0.7425 0.8617
No log 29.6 296 0.7144 0.2327 0.7144 0.8452
No log 29.8 298 0.7345 0.3155 0.7345 0.8570
No log 30.0 300 0.7783 0.3399 0.7783 0.8822
No log 30.2 302 0.7695 0.3399 0.7695 0.8772
No log 30.4 304 0.7412 0.2294 0.7412 0.8609
No log 30.6 306 0.7692 0.2895 0.7692 0.8770
No log 30.8 308 0.8228 0.2544 0.8228 0.9071
No log 31.0 310 0.8495 0.2428 0.8495 0.9217
No log 31.2 312 0.8644 0.2684 0.8644 0.9297
No log 31.4 314 0.8180 0.2911 0.8180 0.9044
No log 31.6 316 0.7732 0.2652 0.7732 0.8793
No log 31.8 318 0.7761 0.2471 0.7761 0.8810
No log 32.0 320 0.7988 0.2283 0.7988 0.8938
No log 32.2 322 0.7854 0.2414 0.7854 0.8862
No log 32.4 324 0.7524 0.2023 0.7524 0.8674
No log 32.6 326 0.7463 0.1051 0.7463 0.8639
No log 32.8 328 0.7862 0.1795 0.7862 0.8867
No log 33.0 330 0.7880 0.1693 0.7880 0.8877
No log 33.2 332 0.7675 0.2038 0.7675 0.8761
No log 33.4 334 0.7659 0.2360 0.7659 0.8752
No log 33.6 336 0.7677 0.2327 0.7677 0.8762
No log 33.8 338 0.7660 0.2294 0.7660 0.8752
No log 34.0 340 0.7580 0.1988 0.7580 0.8706
No log 34.2 342 0.7540 0.1624 0.7540 0.8683
No log 34.4 344 0.7432 0.1624 0.7432 0.8621
No log 34.6 346 0.7423 0.1303 0.7423 0.8616
No log 34.8 348 0.7532 0.2294 0.7532 0.8679
No log 35.0 350 0.7859 0.2691 0.7859 0.8865
No log 35.2 352 0.7941 0.3471 0.7941 0.8911
No log 35.4 354 0.7814 0.2847 0.7814 0.8840
No log 35.6 356 0.7683 0.2471 0.7683 0.8766
No log 35.8 358 0.7432 0.1219 0.7432 0.8621
No log 36.0 360 0.7387 0.1219 0.7387 0.8595
No log 36.2 362 0.7414 0.1303 0.7414 0.8611
No log 36.4 364 0.7518 0.0896 0.7518 0.8671
No log 36.6 366 0.7636 0.2161 0.7636 0.8738
No log 36.8 368 0.7679 0.2475 0.7679 0.8763
No log 37.0 370 0.7583 0.2652 0.7583 0.8708
No log 37.2 372 0.7592 0.2936 0.7592 0.8713
No log 37.4 374 0.7616 0.3239 0.7616 0.8727
No log 37.6 376 0.7638 0.3530 0.7638 0.8740
No log 37.8 378 0.7632 0.3530 0.7632 0.8736
No log 38.0 380 0.7583 0.2936 0.7583 0.8708
No log 38.2 382 0.7621 0.2843 0.7621 0.8730
No log 38.4 384 0.7528 0.3452 0.7528 0.8676
No log 38.6 386 0.7454 0.3452 0.7454 0.8634
No log 38.8 388 0.7291 0.2973 0.7291 0.8538
No log 39.0 390 0.7287 0.2099 0.7287 0.8536
No log 39.2 392 0.7421 0.3155 0.7421 0.8614
No log 39.4 394 0.7486 0.3155 0.7486 0.8652
No log 39.6 396 0.7497 0.3253 0.7497 0.8658
No log 39.8 398 0.7517 0.3253 0.7517 0.8670
No log 40.0 400 0.7482 0.2936 0.7482 0.8650
No log 40.2 402 0.7459 0.2936 0.7459 0.8637
No log 40.4 404 0.7462 0.3551 0.7462 0.8638
No log 40.6 406 0.7561 0.2943 0.7561 0.8695
No log 40.8 408 0.7810 0.2414 0.7810 0.8837
No log 41.0 410 0.7931 0.3287 0.7931 0.8906
No log 41.2 412 0.7810 0.3060 0.7810 0.8838
No log 41.4 414 0.7654 0.3060 0.7654 0.8748
No log 41.6 416 0.7488 0.3127 0.7488 0.8653
No log 41.8 418 0.7291 0.3341 0.7291 0.8539
No log 42.0 420 0.7240 0.2145 0.7240 0.8509
No log 42.2 422 0.7253 0.1407 0.7253 0.8516
No log 42.4 424 0.7191 0.1407 0.7191 0.8480
No log 42.6 426 0.7111 0.2145 0.7111 0.8433
No log 42.8 428 0.7098 0.3341 0.7098 0.8425
No log 43.0 430 0.7144 0.3341 0.7144 0.8452
No log 43.2 432 0.7134 0.3341 0.7134 0.8446
No log 43.4 434 0.7224 0.3622 0.7224 0.8499
No log 43.6 436 0.7193 0.3622 0.7193 0.8481
No log 43.8 438 0.7039 0.2294 0.7039 0.8390
No log 44.0 440 0.6929 0.2621 0.6929 0.8324
No log 44.2 442 0.6962 0.2360 0.6962 0.8344
No log 44.4 444 0.7013 0.2936 0.7013 0.8375
No log 44.6 446 0.7053 0.2936 0.7053 0.8398
No log 44.8 448 0.7159 0.3224 0.7159 0.8461
No log 45.0 450 0.7224 0.3196 0.7224 0.8500
No log 45.2 452 0.7192 0.3196 0.7192 0.8480
No log 45.4 454 0.7104 0.3196 0.7104 0.8428
No log 45.6 456 0.7006 0.3196 0.7006 0.8370
No log 45.8 458 0.6922 0.2943 0.6922 0.8320
No log 46.0 460 0.6886 0.3369 0.6886 0.8298
No log 46.2 462 0.6871 0.2717 0.6871 0.8289
No log 46.4 464 0.6863 0.2099 0.6863 0.8284
No log 46.6 466 0.6873 0.2099 0.6873 0.8290
No log 46.8 468 0.7027 0.2621 0.7027 0.8383
No log 47.0 470 0.7412 0.3471 0.7412 0.8609
No log 47.2 472 0.7877 0.3996 0.7877 0.8875
No log 47.4 474 0.8105 0.4247 0.8105 0.9003
No log 47.6 476 0.7979 0.4247 0.7979 0.8933
No log 47.8 478 0.7737 0.3996 0.7737 0.8796
No log 48.0 480 0.7672 0.3329 0.7672 0.8759
No log 48.2 482 0.7591 0.3399 0.7591 0.8713
No log 48.4 484 0.7503 0.3127 0.7503 0.8662
No log 48.6 486 0.7399 0.3127 0.7399 0.8602
No log 48.8 488 0.7324 0.2471 0.7324 0.8558
No log 49.0 490 0.7325 0.2685 0.7325 0.8558
No log 49.2 492 0.7452 0.2498 0.7452 0.8632
No log 49.4 494 0.7578 0.2751 0.7578 0.8705
No log 49.6 496 0.7655 0.2751 0.7655 0.8749
No log 49.8 498 0.7721 0.2751 0.7721 0.8787
0.2568 50.0 500 0.7658 0.2751 0.7658 0.8751
0.2568 50.2 502 0.7611 0.2294 0.7611 0.8724
0.2568 50.4 504 0.7613 0.1661 0.7613 0.8725
0.2568 50.6 506 0.7577 0.1393 0.7577 0.8705
0.2568 50.8 508 0.7472 0.1009 0.7472 0.8644
0.2568 51.0 510 0.7460 0.2007 0.7460 0.8637

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_usingWellWrittenEssays_FineTuningAraBERT_run3_AugV5_k4_task7_organization

Finetuned
(4019)
this model