ArabicNewSplits7_usingWellWrittenEssays_FineTuningAraBERT_run2_AugV5_k5_task3_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: 0.8931
  • Qwk: -0.0138
  • Mse: 0.8931
  • Rmse: 0.9451

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 0.1538 2 3.8664 0.0017 3.8664 1.9663
No log 0.3077 4 2.0204 0.0672 2.0204 1.4214
No log 0.4615 6 2.5026 -0.0150 2.5026 1.5820
No log 0.6154 8 1.7223 0.0194 1.7223 1.3124
No log 0.7692 10 1.6980 -0.0996 1.6980 1.3031
No log 0.9231 12 0.9377 0.0134 0.9377 0.9683
No log 1.0769 14 1.0291 0.0651 1.0291 1.0145
No log 1.2308 16 1.7916 -0.0712 1.7916 1.3385
No log 1.3846 18 1.3110 -0.0712 1.3110 1.1450
No log 1.5385 20 0.7653 -0.0695 0.7653 0.8748
No log 1.6923 22 0.7318 -0.0551 0.7318 0.8555
No log 1.8462 24 0.8383 0.1107 0.8383 0.9156
No log 2.0 26 1.1859 -0.0457 1.1859 1.0890
No log 2.1538 28 1.3996 -0.0490 1.3996 1.1830
No log 2.3077 30 1.0437 -0.0411 1.0437 1.0216
No log 2.4615 32 0.8414 -0.0408 0.8414 0.9173
No log 2.6154 34 0.8846 0.0287 0.8846 0.9405
No log 2.7692 36 0.9781 0.0458 0.9781 0.9890
No log 2.9231 38 1.3263 -0.0468 1.3263 1.1516
No log 3.0769 40 1.2289 -0.0446 1.2289 1.1086
No log 3.2308 42 0.8090 -0.0331 0.8090 0.8994
No log 3.3846 44 0.7235 0.0460 0.7235 0.8506
No log 3.5385 46 0.8072 -0.1249 0.8072 0.8984
No log 3.6923 48 1.7579 0.0059 1.7579 1.3259
No log 3.8462 50 2.1972 -0.0474 2.1972 1.4823
No log 4.0 52 1.4783 -0.0098 1.4783 1.2159
No log 4.1538 54 0.8533 -0.1994 0.8533 0.9237
No log 4.3077 56 0.8381 -0.1527 0.8381 0.9155
No log 4.4615 58 1.0014 -0.0468 1.0014 1.0007
No log 4.6154 60 1.4287 0.0231 1.4287 1.1953
No log 4.7692 62 1.4642 -0.0387 1.4642 1.2100
No log 4.9231 64 0.9552 -0.0757 0.9552 0.9774
No log 5.0769 66 0.8319 -0.1916 0.8319 0.9121
No log 5.2308 68 0.9402 -0.0694 0.9402 0.9697
No log 5.3846 70 1.6269 -0.0399 1.6269 1.2755
No log 5.5385 72 1.8716 -0.0890 1.8716 1.3681
No log 5.6923 74 1.2521 0.0086 1.2521 1.1190
No log 5.8462 76 0.8574 -0.1116 0.8574 0.9259
No log 6.0 78 0.8172 -0.1468 0.8172 0.9040
No log 6.1538 80 0.8945 -0.1184 0.8945 0.9458
No log 6.3077 82 1.0372 -0.1214 1.0372 1.0184
No log 6.4615 84 0.9859 -0.0391 0.9859 0.9929
No log 6.6154 86 0.8213 -0.1088 0.8213 0.9063
No log 6.7692 88 0.8082 -0.1081 0.8082 0.8990
No log 6.9231 90 0.9699 -0.0837 0.9699 0.9848
No log 7.0769 92 1.0628 -0.0500 1.0628 1.0309
No log 7.2308 94 0.8615 -0.1521 0.8615 0.9282
No log 7.3846 96 0.8601 -0.1531 0.8601 0.9274
No log 7.5385 98 0.9974 -0.1111 0.9974 0.9987
No log 7.6923 100 1.1405 -0.0466 1.1405 1.0679
No log 7.8462 102 0.9336 -0.1093 0.9336 0.9662
No log 8.0 104 0.9810 -0.1501 0.9810 0.9905
No log 8.1538 106 1.0432 -0.1127 1.0432 1.0214
No log 8.3077 108 0.8584 -0.0669 0.8584 0.9265
No log 8.4615 110 0.8732 -0.0283 0.8732 0.9344
No log 8.6154 112 1.0085 -0.0097 1.0085 1.0042
No log 8.7692 114 1.0846 -0.0194 1.0846 1.0415
No log 8.9231 116 0.9281 -0.1140 0.9281 0.9634
No log 9.0769 118 0.9213 -0.1093 0.9213 0.9599
No log 9.2308 120 1.1421 -0.1566 1.1421 1.0687
No log 9.3846 122 1.2531 -0.0948 1.2531 1.1194
No log 9.5385 124 0.9502 -0.0809 0.9502 0.9748
No log 9.6923 126 0.8125 -0.0062 0.8125 0.9014
No log 9.8462 128 0.8166 0.0375 0.8166 0.9037
No log 10.0 130 0.8936 -0.0355 0.8936 0.9453
No log 10.1538 132 1.1092 -0.0966 1.1092 1.0532
No log 10.3077 134 1.1552 -0.1875 1.1552 1.0748
No log 10.4615 136 0.9405 0.0152 0.9405 0.9698
No log 10.6154 138 0.8573 -0.0118 0.8573 0.9259
No log 10.7692 140 0.9007 0.0183 0.9007 0.9490
No log 10.9231 142 0.9137 0.0095 0.9137 0.9559
No log 11.0769 144 0.8730 0.0183 0.8730 0.9343
No log 11.2308 146 1.0382 -0.0837 1.0382 1.0189
No log 11.3846 148 1.0970 -0.1172 1.0970 1.0474
No log 11.5385 150 0.9539 -0.1083 0.9539 0.9767
No log 11.6923 152 0.8769 -0.0407 0.8769 0.9364
No log 11.8462 154 0.8369 0.0030 0.8369 0.9148
No log 12.0 156 0.8866 -0.1191 0.8866 0.9416
No log 12.1538 158 1.1599 -0.0575 1.1599 1.0770
No log 12.3077 160 1.1204 -0.0563 1.1204 1.0585
No log 12.4615 162 1.0565 -0.0885 1.0565 1.0279
No log 12.6154 164 0.8838 -0.0295 0.8838 0.9401
No log 12.7692 166 0.9002 -0.1506 0.9002 0.9488
No log 12.9231 168 0.9042 -0.1083 0.9042 0.9509
No log 13.0769 170 0.8463 -0.1060 0.8463 0.9199
No log 13.2308 172 0.8215 -0.0578 0.8215 0.9064
No log 13.3846 174 0.9449 -0.0799 0.9449 0.9721
No log 13.5385 176 1.1164 -0.0563 1.1164 1.0566
No log 13.6923 178 0.9974 -0.0828 0.9974 0.9987
No log 13.8462 180 0.8554 -0.0488 0.8554 0.9249
No log 14.0 182 0.8528 -0.0678 0.8528 0.9235
No log 14.1538 184 0.8022 0.0099 0.8022 0.8956
No log 14.3077 186 0.8184 -0.1524 0.8184 0.9047
No log 14.4615 188 1.3905 -0.0925 1.3905 1.1792
No log 14.6154 190 1.9470 -0.0975 1.9470 1.3953
No log 14.7692 192 1.8743 -0.0996 1.8743 1.3691
No log 14.9231 194 1.3683 -0.0657 1.3683 1.1697
No log 15.0769 196 0.9800 -0.1219 0.9800 0.9900
No log 15.2308 198 0.9053 -0.0391 0.9053 0.9515
No log 15.3846 200 0.8995 0.0068 0.8995 0.9484
No log 15.5385 202 1.0041 -0.1582 1.0041 1.0021
No log 15.6923 204 1.1688 -0.0720 1.1688 1.0811
No log 15.8462 206 1.2063 -0.0720 1.2063 1.0983
No log 16.0 208 1.0817 -0.0925 1.0817 1.0401
No log 16.1538 210 0.9407 -0.0694 0.9407 0.9699
No log 16.3077 212 0.9080 -0.1093 0.9080 0.9529
No log 16.4615 214 0.9696 -0.0828 0.9696 0.9847
No log 16.6154 216 1.0814 -0.0964 1.0814 1.0399
No log 16.7692 218 1.0849 -0.0712 1.0849 1.0416
No log 16.9231 220 0.9522 -0.0905 0.9522 0.9758
No log 17.0769 222 0.8078 0.0355 0.8078 0.8988
No log 17.2308 224 0.8056 -0.0532 0.8056 0.8976
No log 17.3846 226 0.8412 -0.0118 0.8412 0.9172
No log 17.5385 228 0.9676 -0.1209 0.9676 0.9836
No log 17.6923 230 1.1473 -0.0563 1.1473 1.0711
No log 17.8462 232 1.1020 -0.0526 1.1020 1.0497
No log 18.0 234 0.9567 -0.1997 0.9567 0.9781
No log 18.1538 236 0.8773 -0.0488 0.8773 0.9366
No log 18.3077 238 0.8778 -0.0550 0.8778 0.9369
No log 18.4615 240 0.9469 -0.1623 0.9469 0.9731
No log 18.6154 242 1.1880 -0.0586 1.1880 1.0900
No log 18.7692 244 1.3360 -0.1256 1.3360 1.1559
No log 18.9231 246 1.2501 -0.0974 1.2501 1.1181
No log 19.0769 248 1.0523 -0.0953 1.0523 1.0258
No log 19.2308 250 0.9344 0.0152 0.9344 0.9667
No log 19.3846 252 0.9464 -0.0252 0.9464 0.9728
No log 19.5385 254 1.0028 -0.2392 1.0028 1.0014
No log 19.6923 256 1.0136 -0.1609 1.0136 1.0068
No log 19.8462 258 0.9143 -0.0295 0.9143 0.9562
No log 20.0 260 0.9019 -0.1206 0.9019 0.9497
No log 20.1538 262 1.0037 -0.0586 1.0037 1.0018
No log 20.3077 264 1.1132 0.0238 1.1132 1.0551
No log 20.4615 266 1.0809 0.0006 1.0809 1.0397
No log 20.6154 268 1.0230 0.0111 1.0230 1.0114
No log 20.7692 270 1.0740 0.0067 1.0740 1.0364
No log 20.9231 272 1.1588 0.0282 1.1588 1.0765
No log 21.0769 274 1.0929 -0.0211 1.0929 1.0454
No log 21.2308 276 1.0003 -0.1601 1.0003 1.0002
No log 21.3846 278 0.9425 -0.0723 0.9425 0.9708
No log 21.5385 280 0.9619 -0.1557 0.9619 0.9808
No log 21.6923 282 0.9952 -0.1605 0.9952 0.9976
No log 21.8462 284 1.1563 -0.0306 1.1563 1.0753
No log 22.0 286 1.1916 -0.0385 1.1916 1.0916
No log 22.1538 288 1.0083 -0.0583 1.0083 1.0041
No log 22.3077 290 0.8539 -0.0686 0.8539 0.9240
No log 22.4615 292 0.8170 -0.0170 0.8170 0.9039
No log 22.6154 294 0.8243 -0.0170 0.8243 0.9079
No log 22.7692 296 0.8676 -0.0408 0.8676 0.9315
No log 22.9231 298 0.9507 -0.1277 0.9507 0.9750
No log 23.0769 300 0.9245 -0.0916 0.9245 0.9615
No log 23.2308 302 0.8560 -0.0778 0.8560 0.9252
No log 23.3846 304 0.8174 -0.0179 0.8174 0.9041
No log 23.5385 306 0.8127 -0.0118 0.8127 0.9015
No log 23.6923 308 0.8152 -0.1180 0.8152 0.9029
No log 23.8462 310 0.8801 -0.0101 0.8801 0.9381
No log 24.0 312 0.9498 -0.0558 0.9498 0.9746
No log 24.1538 314 0.8871 -0.0182 0.8871 0.9418
No log 24.3077 316 0.8086 -0.0704 0.8086 0.8992
No log 24.4615 318 0.7964 0.0395 0.7964 0.8924
No log 24.6154 320 0.8182 0.0723 0.8182 0.9046
No log 24.7692 322 0.8523 -0.0788 0.8523 0.9232
No log 24.9231 324 0.9280 -0.0513 0.9280 0.9633
No log 25.0769 326 1.0846 -0.0677 1.0846 1.0414
No log 25.2308 328 1.0686 -0.0563 1.0686 1.0337
No log 25.3846 330 1.0496 -0.0885 1.0496 1.0245
No log 25.5385 332 0.9358 -0.0408 0.9358 0.9674
No log 25.6923 334 0.8740 -0.0056 0.8740 0.9349
No log 25.8462 336 0.8580 -0.0029 0.8580 0.9263
No log 26.0 338 0.8900 0.0146 0.8900 0.9434
No log 26.1538 340 0.9837 -0.0563 0.9837 0.9918
No log 26.3077 342 1.0635 -0.0712 1.0635 1.0312
No log 26.4615 344 1.0830 -0.1006 1.0830 1.0407
No log 26.6154 346 1.0332 -0.0385 1.0332 1.0165
No log 26.7692 348 0.9500 -0.1228 0.9500 0.9747
No log 26.9231 350 0.8966 -0.0486 0.8966 0.9469
No log 27.0769 352 0.9134 -0.0157 0.9134 0.9557
No log 27.2308 354 0.9816 0.0772 0.9816 0.9907
No log 27.3846 356 0.9572 0.0772 0.9572 0.9783
No log 27.5385 358 0.8710 0.0207 0.8710 0.9332
No log 27.6923 360 0.7987 -0.0743 0.7987 0.8937
No log 27.8462 362 0.7962 -0.0743 0.7962 0.8923
No log 28.0 364 0.8024 -0.0252 0.8024 0.8958
No log 28.1538 366 0.8408 0.0016 0.8408 0.9169
No log 28.3077 368 0.8511 0.1001 0.8511 0.9225
No log 28.4615 370 0.9046 -0.0828 0.9046 0.9511
No log 28.6154 372 0.9983 -0.0972 0.9983 0.9992
No log 28.7692 374 0.9928 -0.0638 0.9928 0.9964
No log 28.9231 376 0.8900 -0.1212 0.8900 0.9434
No log 29.0769 378 0.8308 0.0821 0.8308 0.9115
No log 29.2308 380 0.8309 0.0357 0.8309 0.9115
No log 29.3846 382 0.8351 0.0821 0.8351 0.9138
No log 29.5385 384 0.9014 -0.0854 0.9014 0.9494
No log 29.6923 386 0.9656 -0.0236 0.9656 0.9826
No log 29.8462 388 0.9617 -0.0551 0.9617 0.9807
No log 30.0 390 0.9654 -0.0551 0.9654 0.9825
No log 30.1538 392 0.9090 -0.1214 0.9090 0.9534
No log 30.3077 394 0.9096 -0.1209 0.9096 0.9537
No log 30.4615 396 0.8908 -0.1191 0.8908 0.9438
No log 30.6154 398 0.8989 -0.1572 0.8989 0.9481
No log 30.7692 400 0.9551 -0.0809 0.9551 0.9773
No log 30.9231 402 0.9984 -0.0837 0.9984 0.9992
No log 31.0769 404 1.1189 -0.0586 1.1189 1.0578
No log 31.2308 406 1.1224 -0.0918 1.1224 1.0594
No log 31.3846 408 1.0822 -0.1558 1.0822 1.0403
No log 31.5385 410 0.9910 -0.0551 0.9910 0.9955
No log 31.6923 412 0.8736 -0.0316 0.8736 0.9347
No log 31.8462 414 0.8360 -0.0118 0.8360 0.9143
No log 32.0 416 0.8329 0.0814 0.8329 0.9126
No log 32.1538 418 0.8755 -0.0336 0.8755 0.9357
No log 32.3077 420 1.0141 -0.0245 1.0141 1.0070
No log 32.4615 422 1.0934 -0.1287 1.0934 1.0457
No log 32.6154 424 1.0594 -0.1599 1.0594 1.0293
No log 32.7692 426 0.9554 -0.0870 0.9554 0.9774
No log 32.9231 428 0.8489 0.0123 0.8489 0.9213
No log 33.0769 430 0.8171 -0.0059 0.8171 0.9039
No log 33.2308 432 0.8178 -0.0493 0.8178 0.9043
No log 33.3846 434 0.8243 -0.0567 0.8243 0.9079
No log 33.5385 436 0.9676 -0.0456 0.9676 0.9837
No log 33.6923 438 1.1456 -0.1550 1.1456 1.0703
No log 33.8462 440 1.1691 -0.1581 1.1691 1.0812
No log 34.0 442 1.1061 -0.1245 1.1061 1.0517
No log 34.1538 444 1.0010 -0.0539 1.0010 1.0005
No log 34.3077 446 0.8983 0.0095 0.8983 0.9478
No log 34.4615 448 0.8859 0.0562 0.8859 0.9412
No log 34.6154 450 0.8777 0.0095 0.8777 0.9368
No log 34.7692 452 0.8719 0.0095 0.8719 0.9338
No log 34.9231 454 0.9193 -0.1212 0.9193 0.9588
No log 35.0769 456 0.9410 -0.0138 0.9410 0.9701
No log 35.2308 458 1.0078 0.0067 1.0078 1.0039
No log 35.3846 460 1.0449 -0.0359 1.0449 1.0222
No log 35.5385 462 0.9971 0.0067 0.9971 0.9985
No log 35.6923 464 0.8888 -0.0425 0.8888 0.9428
No log 35.8462 466 0.8792 -0.1206 0.8792 0.9377
No log 36.0 468 0.8501 -0.1191 0.8501 0.9220
No log 36.1538 470 0.8514 0.0289 0.8514 0.9227
No log 36.3077 472 0.8574 -0.1077 0.8574 0.9259
No log 36.4615 474 0.8862 -0.1200 0.8862 0.9414
No log 36.6154 476 0.9421 -0.1226 0.9421 0.9706
No log 36.7692 478 0.9434 -0.0877 0.9434 0.9713
No log 36.9231 480 0.9296 -0.0157 0.9296 0.9642
No log 37.0769 482 0.9522 -0.0571 0.9522 0.9758
No log 37.2308 484 1.0374 -0.0031 1.0374 1.0185
No log 37.3846 486 1.0374 -0.0385 1.0374 1.0185
No log 37.5385 488 0.9395 -0.0617 0.9395 0.9693
No log 37.6923 490 0.8696 -0.0845 0.8696 0.9325
No log 37.8462 492 0.8336 -0.0391 0.8336 0.9130
No log 38.0 494 0.8397 -0.0391 0.8397 0.9163
No log 38.1538 496 0.8935 0.0250 0.8935 0.9453
No log 38.3077 498 1.0374 -0.0899 1.0374 1.0185
0.216 38.4615 500 1.1717 -0.0049 1.1717 1.0825
0.216 38.6154 502 1.2088 -0.0695 1.2088 1.0995
0.216 38.7692 504 1.1775 -0.0712 1.1775 1.0851
0.216 38.9231 506 1.1018 -0.0704 1.1018 1.0497
0.216 39.0769 508 0.9879 0.0305 0.9879 0.9939
0.216 39.2308 510 0.9314 0.0089 0.9314 0.9651
0.216 39.3846 512 0.9537 0.0329 0.9537 0.9766
0.216 39.5385 514 0.9800 0.0329 0.9800 0.9900
0.216 39.6923 516 1.0030 0.1007 1.0030 1.0015
0.216 39.8462 518 1.0681 0.0305 1.0681 1.0335
0.216 40.0 520 1.0577 -0.0031 1.0577 1.0285
0.216 40.1538 522 0.9510 0.0089 0.9510 0.9752
0.216 40.3077 524 0.9106 0.0157 0.9106 0.9542
0.216 40.4615 526 0.8841 -0.0138 0.8841 0.9403
0.216 40.6154 528 0.8548 -0.0818 0.8548 0.9245
0.216 40.7692 530 0.8398 0.0456 0.8398 0.9164
0.216 40.9231 532 0.8457 0.0525 0.8457 0.9196
0.216 41.0769 534 0.8511 -0.0373 0.8511 0.9225
0.216 41.2308 536 0.8793 -0.0425 0.8793 0.9377
0.216 41.3846 538 0.8808 -0.0425 0.8808 0.9385
0.216 41.5385 540 0.8989 -0.1217 0.8989 0.9481
0.216 41.6923 542 0.8931 -0.0138 0.8931 0.9451

Framework versions

  • Transformers 4.44.2
  • Pytorch 2.4.0+cu118
  • Datasets 2.21.0
  • Tokenizers 0.19.1
Downloads last month
2
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_run2_AugV5_k5_task3_organization

Finetuned
(4019)
this model